pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2025-10-04 23:38:38 +09:00
Code Issues Projects Releases Wiki Activity

Merge pull request #32950 from ytdl-org/master

Browse Source 
Merge from master
This commit is contained in:
dirkf
2024-10-14 14:09:51 +01:00
committed by GitHub
parent f3cf092584 c5098961b0
commit 49093c09c0
136 changed files with 17041 additions and 3547 deletions
Download Patch File Download Diff File Expand all files Collapse all files

456
youtube_dl/YoutubeDL.py
View File

@@ -4,11 +4,10 @@
from __future__ import absolute_import, unicode_literals
import collections
import contextlib
import copy
import datetime
import errno
import fileinput
import functools
import io
import itertools
import json
@@ -26,25 +25,39 @@ import tokenize
import traceback
import random
try:
from ssl import OPENSSL_VERSION
except ImportError:
# Must be Python 2.6, should be built against 1.0.2
OPENSSL_VERSION = 'OpenSSL 1.0.2(?)'
from string import ascii_letters
from .compat import (
compat_basestring,
compat_cookiejar,
compat_collections_chain_map as ChainMap,
compat_filter as filter,
compat_get_terminal_size,
compat_http_client,
compat_http_cookiejar_Cookie,
compat_http_cookies_SimpleCookie,
compat_integer_types,
compat_kwargs,
compat_map as map,
compat_numeric_types,
compat_open as open,
compat_os_name,
compat_str,
compat_tokenize_tokenize,
compat_urllib_error,
compat_urllib_parse,
compat_urllib_request,
compat_urllib_request_DataHandler,
)
from .utils import (
_UnsafeExtensionError,
age_restricted,
args_to_str,
bug_reports_message,
ContentTooShortError,
date_from_str,
DateRange,
@@ -62,7 +75,9 @@ from .utils import (
GeoRestrictedError,
int_or_none,
ISO3166Utils,
join_nonempty,
locked_file,
LazyList,
make_HTTPS_handler,
MaxDownloadsReached,
orderedSet,
@@ -73,6 +88,7 @@ from .utils import (
PostProcessingError,
preferredencoding,
prepend_extension,
process_communicate_or_kill,
register_socks_protocols,
render_table,
replace_extension,
@@ -84,6 +100,7 @@ from .utils import (
std_headers,
str_or_none,
subtitles_filename,
traverse_obj,
UnavailableVideoError,
url_basename,
version_tuple,
@@ -93,6 +110,7 @@ from .utils import (
YoutubeDLCookieProcessor,
YoutubeDLHandler,
YoutubeDLRedirectHandler,
ytdl_is_updateable,
)
from .cache import Cache
from .extractor import get_info_extractor, gen_extractor_classes, _LAZY_LOADER
@@ -113,6 +131,20 @@ if compat_os_name == 'nt':
import ctypes
def _catch_unsafe_file_extension(func):
@functools.wraps(func)
def wrapper(self, *args, **kwargs):
try:
return func(self, *args, **kwargs)
except _UnsafeExtensionError as error:
self.report_error(
'{0} found; to avoid damaging your system, this value is disallowed.'
' If you believe this is an error{1}'.format(
error_to_compat_str(error), bug_reports_message(',')))
return wrapper
class YoutubeDL(object):
"""YoutubeDL class.
@@ -362,6 +394,9 @@ class YoutubeDL(object):
self.params.update(params)
self.cache = Cache(self)
self._header_cookies = []
self._load_cookies_from_headers(self.params.get('http_headers'))
def check_deprecated(param, option, suggestion):
if self.params.get(param) is not None:
self.report_warning(
@@ -568,7 +603,7 @@ class YoutubeDL(object):
if self.params.get('cookiefile') is not None:
self.cookiejar.save(ignore_discard=True, ignore_expires=True)
def trouble(self, message=None, tb=None):
def trouble(self, *args, **kwargs):
"""Determine action to take when a download problem appears.
Depending on if the downloader has been configured to ignore
@@ -577,6 +612,11 @@ class YoutubeDL(object):
tb, if given, is additional traceback information.
"""
# message=None, tb=None, is_error=True
message = args[0] if len(args) > 0 else kwargs.get('message', None)
tb = args[1] if len(args) > 1 else kwargs.get('tb', None)
is_error = args[2] if len(args) > 2 else kwargs.get('is_error', True)
if message is not None:
self.to_stderr(message)
if self.params.get('verbose'):
@@ -589,7 +629,10 @@ class YoutubeDL(object):
else:
tb_data = traceback.format_list(traceback.extract_stack())
tb = ''.join(tb_data)
self.to_stderr(tb)
if tb:
self.to_stderr(tb)
if not is_error:
return
if not self.params.get('ignoreerrors', False):
if sys.exc_info()[0] and hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]:
exc_info = sys.exc_info()[1].exc_info
@@ -598,11 +641,18 @@ class YoutubeDL(object):
raise DownloadError(message, exc_info)
self._download_retcode = 1
def report_warning(self, message):
def report_warning(self, message, only_once=False, _cache={}):
'''
Print the message to stderr, it will be prefixed with 'WARNING:'
If stderr is a tty file the 'WARNING:' will be colored
'''
if only_once:
m_hash = hash((self, message))
m_cnt = _cache.setdefault(m_hash, 0)
_cache[m_hash] = m_cnt + 1
if m_cnt > 0:
return
if self.params.get('logger') is not None:
self.params['logger'].warning(message)
else:
@@ -615,7 +665,7 @@ class YoutubeDL(object):
warning_message = '%s %s' % (_msg_header, message)
self.to_stderr(warning_message)
def report_error(self, message, tb=None):
def report_error(self, message, *args, **kwargs):
'''
Do the same as trouble, but prefixes the message with 'ERROR:', colored
in red if stderr is a tty file.
@@ -624,8 +674,18 @@ class YoutubeDL(object):
_msg_header = '\033[0;31mERROR:\033[0m'
else:
_msg_header = 'ERROR:'
error_message = '%s %s' % (_msg_header, message)
self.trouble(error_message, tb)
kwargs['message'] = '%s %s' % (_msg_header, message)
self.trouble(*args, **kwargs)
def report_unscoped_cookies(self, *args, **kwargs):
# message=None, tb=False, is_error=False
if len(args) <= 2:
kwargs.setdefault('is_error', False)
if len(args) <= 0:
kwargs.setdefault(
'message',
'Unscoped cookies are not allowed: please specify some sort of scoping')
self.report_error(*args, **kwargs)
def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded."""
@@ -720,7 +780,7 @@ class YoutubeDL(object):
filename = encodeFilename(filename, True).decode(preferredencoding())
return sanitize_path(filename)
except ValueError as err:
self.report_error('Error in output template: ' + str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
self.report_error('Error in output template: ' + error_to_compat_str(err) + ' (encoding: ' + repr(preferredencoding()) + ')')
return None
def _match_entry(self, info_dict, incomplete):
@@ -821,7 +881,7 @@ class YoutubeDL(object):
msg += '\nYou might want to use a VPN or a proxy server (with --proxy) to workaround.'
self.report_error(msg)
except ExtractorError as e: # An error we somewhat expected
self.report_error(compat_str(e), e.format_traceback())
self.report_error(compat_str(e), tb=e.format_traceback())
except MaxDownloadsReached:
raise
except Exception as e:
@@ -831,8 +891,83 @@ class YoutubeDL(object):
raise
return wrapper
def _remove_cookie_header(self, http_headers):
"""Filters out `Cookie` header from an `http_headers` dict
The `Cookie` header is removed to prevent leaks as a result of unscoped cookies.
See: https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-v8mc-9377-rwjj
@param http_headers An `http_headers` dict from which any `Cookie` header
should be removed, or None
"""
return dict(filter(lambda pair: pair[0].lower() != 'cookie', (http_headers or {}).items()))
def _load_cookies(self, data, **kwargs):
"""Loads cookies from a `Cookie` header
This tries to work around the security vulnerability of passing cookies to every domain.
@param data The Cookie header as a string to load the cookies from
@param autoscope If `False`, scope cookies using Set-Cookie syntax and error for cookie without domains
If `True`, save cookies for later to be stored in the jar with a limited scope
If a URL, save cookies in the jar with the domain of the URL
"""
# autoscope=True (kw-only)
autoscope = kwargs.get('autoscope', True)
for cookie in compat_http_cookies_SimpleCookie(data).values() if data else []:
if autoscope and any(cookie.values()):
raise ValueError('Invalid syntax in Cookie Header')
domain = cookie.get('domain') or ''
expiry = cookie.get('expires')
if expiry == '': # 0 is valid so we check for `''` explicitly
expiry = None
prepared_cookie = compat_http_cookiejar_Cookie(
cookie.get('version') or 0, cookie.key, cookie.value, None, False,
domain, True, True, cookie.get('path') or '', bool(cookie.get('path')),
bool(cookie.get('secure')), expiry, False, None, None, {})
if domain:
self.cookiejar.set_cookie(prepared_cookie)
elif autoscope is True:
self.report_warning(
'Passing cookies as a header is a potential security risk; '
'they will be scoped to the domain of the downloaded urls. '
'Please consider loading cookies from a file or browser instead.',
only_once=True)
self._header_cookies.append(prepared_cookie)
elif autoscope:
self.report_warning(
'The extractor result contains an unscoped cookie as an HTTP header. '
'If you are specifying an input URL, ' + bug_reports_message(),
only_once=True)
self._apply_header_cookies(autoscope, [prepared_cookie])
else:
self.report_unscoped_cookies()
def _load_cookies_from_headers(self, headers):
self._load_cookies(traverse_obj(headers, 'cookie', casesense=False))
def _apply_header_cookies(self, url, cookies=None):
"""This method applies stray header cookies to the provided url
This loads header cookies and scopes them to the domain provided in `url`.
While this is not ideal, it helps reduce the risk of them being sent to
an unintended destination.
"""
parsed = compat_urllib_parse.urlparse(url)
if not parsed.hostname:
return
for cookie in map(copy.copy, cookies or self._header_cookies):
cookie.domain = '.' + parsed.hostname
self.cookiejar.set_cookie(cookie)
@__handle_extraction_exceptions
def __extract_info(self, url, ie, download, extra_info, process):
# Compat with passing cookies in http headers
self._apply_header_cookies(url)
ie_result = ie.extract(url)
if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here)
return
@@ -858,7 +993,7 @@ class YoutubeDL(object):
def process_ie_result(self, ie_result, download=True, extra_info={}):
"""
Take the result of the ie(may be modified) and resolve all unresolved
Take the result of the ie (may be modified) and resolve all unresolved
references (URLs, playlist items).
It will also download the videos if 'download'.
@@ -920,8 +1055,8 @@ class YoutubeDL(object):
elif result_type in ('playlist', 'multi_video'):
# Protect from infinite recursion due to recursively nested playlists
# (see https://github.com/ytdl-org/youtube-dl/issues/27833)
webpage_url = ie_result['webpage_url']
if webpage_url in self._playlist_urls:
webpage_url = ie_result.get('webpage_url') # not all pl/mv have this
if webpage_url and webpage_url in self._playlist_urls:
self.to_screen(
'[download] Skipping already downloaded playlist: %s'
% ie_result.get('title') or ie_result.get('id'))
@@ -929,6 +1064,10 @@ class YoutubeDL(object):
self._playlist_level += 1
self._playlist_urls.add(webpage_url)
new_result = dict((k, v) for k, v in extra_info.items() if k not in ie_result)
if new_result:
new_result.update(ie_result)
ie_result = new_result
try:
return self.__process_playlist(ie_result, download)
finally:
@@ -1385,17 +1524,16 @@ class YoutubeDL(object):
'abr': formats_info[1].get('abr'),
'ext': output_ext,
}
video_selector, audio_selector = map(_build_selector_function, selector.selector)
def selector_function(ctx):
for pair in itertools.product(
video_selector(copy.deepcopy(ctx)), audio_selector(copy.deepcopy(ctx))):
selector_fn = lambda x: _build_selector_function(x)(ctx)
for pair in itertools.product(*map(selector_fn, selector.selector)):
yield _merge(pair)
filters = [self._build_format_filter(f) for f in selector.filters]
def final_selector(ctx):
ctx_copy = copy.deepcopy(ctx)
ctx_copy = dict(ctx)
for _filter in filters:
ctx_copy['formats'] = list(filter(_filter, ctx_copy['formats']))
return selector_function(ctx_copy)
@@ -1430,29 +1568,73 @@ class YoutubeDL(object):
parsed_selector = _parse_format_selection(iter(TokenIterator(tokens)))
return _build_selector_function(parsed_selector)
def _calc_headers(self, info_dict):
res = std_headers.copy()
def _calc_headers(self, info_dict, load_cookies=False):
if load_cookies: # For --load-info-json
# load cookies from http_headers in legacy info.json
self._load_cookies(traverse_obj(info_dict, ('http_headers', 'Cookie'), casesense=False),
autoscope=info_dict['url'])
# load scoped cookies from info.json
self._load_cookies(info_dict.get('cookies'), autoscope=False)
add_headers = info_dict.get('http_headers')
if add_headers:
res.update(add_headers)
cookies = self._calc_cookies(info_dict)
cookies = self.cookiejar.get_cookies_for_url(info_dict['url'])
if cookies:
res['Cookie'] = cookies
# Make a string like name1=val1; attr1=a_val1; ...name2=val2; ...
# By convention a cookie name can't be a well-known attribute name
# so this syntax is unambiguous and can be parsed by (eg) SimpleCookie
encoder = compat_http_cookies_SimpleCookie()
values = []
attributes = (('Domain', '='), ('Path', '='), ('Secure',), ('Expires', '='), ('Version', '='))
attributes = tuple([x[0].lower()] + list(x) for x in attributes)
for cookie in cookies:
_, value = encoder.value_encode(cookie.value)
# Py 2 '' --> '', Py 3 '' --> '""'
if value == '':
value = '""'
values.append('='.join((cookie.name, value)))
for attr in attributes:
value = getattr(cookie, attr[0], None)
if value:
values.append('%s%s' % (''.join(attr[1:]), value if len(attr) == 3 else ''))
info_dict['cookies'] = '; '.join(values)
res = std_headers.copy()
res.update(info_dict.get('http_headers') or {})
res = self._remove_cookie_header(res)
if 'X-Forwarded-For' not in res:
x_forwarded_for_ip = info_dict.get('__x_forwarded_for_ip')
if x_forwarded_for_ip:
res['X-Forwarded-For'] = x_forwarded_for_ip
return res
return res or None
def _calc_cookies(self, info_dict):
pr = sanitized_Request(info_dict['url'])
self.cookiejar.add_cookie_header(pr)
return pr.get_header('Cookie')
def _fill_common_fields(self, info_dict, final=True):
for ts_key, date_key in (
('timestamp', 'upload_date'),
('release_timestamp', 'release_date'),
):
if info_dict.get(date_key) is None and info_dict.get(ts_key) is not None:
# Working around out-of-range timestamp values (e.g. negative ones on Windows,
# see http://bugs.python.org/issue1646728)
try:
upload_date = datetime.datetime.utcfromtimestamp(info_dict[ts_key])
info_dict[date_key] = compat_str(upload_date.strftime('%Y%m%d'))
except (ValueError, OverflowError, OSError):
pass
# Auto generate title fields corresponding to the *_number fields when missing
# in order to always have clean titles. This is very common for TV series.
if final:
for field in ('chapter', 'season', 'episode'):
if info_dict.get('%s_number' % field) is not None and not info_dict.get(field):
info_dict[field] = '%s %d' % (field.capitalize(), info_dict['%s_number' % field])
def process_video_result(self, info_dict, download=True):
assert info_dict.get('_type', 'video') == 'video'
@@ -1520,24 +1702,7 @@ class YoutubeDL(object):
if 'display_id' not in info_dict and 'id' in info_dict:
info_dict['display_id'] = info_dict['id']
for ts_key, date_key in (
('timestamp', 'upload_date'),
('release_timestamp', 'release_date'),
):
if info_dict.get(date_key) is None and info_dict.get(ts_key) is not None:
# Working around out-of-range timestamp values (e.g. negative ones on Windows,
# see http://bugs.python.org/issue1646728)
try:
upload_date = datetime.datetime.utcfromtimestamp(info_dict[ts_key])
info_dict[date_key] = upload_date.strftime('%Y%m%d')
except (ValueError, OverflowError, OSError):
pass
# Auto generate title fields corresponding to the *_number fields when missing
# in order to always have clean titles. This is very common for TV series.
for field in ('chapter', 'season', 'episode'):
if info_dict.get('%s_number' % field) is not None and not info_dict.get(field):
info_dict[field] = '%s %d' % (field.capitalize(), info_dict['%s_number' % field])
self._fill_common_fields(info_dict)
for cc_kind in ('subtitles', 'automatic_captions'):
cc = info_dict.get(cc_kind)
@@ -1569,9 +1734,6 @@ class YoutubeDL(object):
else:
formats = info_dict['formats']
if not formats:
raise ExtractorError('No video formats found!')
def is_wellformed(f):
url = f.get('url')
if not url:
@@ -1584,7 +1746,10 @@ class YoutubeDL(object):
return True
# Filter out malformed formats for better extraction robustness
formats = list(filter(is_wellformed, formats))
formats = list(filter(is_wellformed, formats or []))
if not formats:
raise ExtractorError('No video formats found!')
formats_dict = {}
@@ -1625,10 +1790,13 @@ class YoutubeDL(object):
format['protocol'] = determine_protocol(format)
# Add HTTP headers, so that external programs can use them from the
# json output
full_format_info = info_dict.copy()
full_format_info.update(format)
format['http_headers'] = self._calc_headers(full_format_info)
# Remove private housekeeping stuff
format['http_headers'] = self._calc_headers(ChainMap(format, info_dict), load_cookies=True)
# Safeguard against old/insecure infojson when using --load-info-json
info_dict['http_headers'] = self._remove_cookie_header(
info_dict.get('http_headers') or {}) or None
# Remove private housekeeping stuff (copied to http_headers in _calc_headers())
if '__x_forwarded_for_ip' in info_dict:
del info_dict['__x_forwarded_for_ip']
@@ -1771,17 +1939,17 @@ class YoutubeDL(object):
self.to_stdout(formatSeconds(info_dict['duration']))
print_mandatory('format')
if self.params.get('forcejson', False):
self.to_stdout(json.dumps(info_dict))
self.to_stdout(json.dumps(self.sanitize_info(info_dict)))
@_catch_unsafe_file_extension
def process_info(self, info_dict):
"""Process a single resolved IE result."""
assert info_dict.get('_type', 'video') == 'video'
max_downloads = self.params.get('max_downloads')
if max_downloads is not None:
if self._num_downloads >= int(max_downloads):
raise MaxDownloadsReached()
max_downloads = int_or_none(self.params.get('max_downloads')) or float('inf')
if self._num_downloads >= max_downloads:
raise MaxDownloadsReached()
# TODO: backward compatibility, to be removed
info_dict['fulltitle'] = info_dict['title']
@@ -1832,7 +2000,7 @@ class YoutubeDL(object):
else:
try:
self.to_screen('[info] Writing video description to: ' + descfn)
with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
with open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
descfile.write(info_dict['description'])
except (OSError, IOError):
self.report_error('Cannot write description file ' + descfn)
@@ -1847,7 +2015,7 @@ class YoutubeDL(object):
else:
try:
self.to_screen('[info] Writing video annotations to: ' + annofn)
with io.open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile:
with open(encodeFilename(annofn), 'w', encoding='utf-8') as annofile:
annofile.write(info_dict['annotations'])
except (KeyError, TypeError):
self.report_warning('There are no annotations to write.')
@@ -1874,7 +2042,7 @@ class YoutubeDL(object):
try:
# Use newline='' to prevent conversion of newline characters
# See https://github.com/ytdl-org/youtube-dl/issues/10268
with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8', newline='') as subfile:
with open(encodeFilename(sub_filename), 'w', encoding='utf-8', newline='') as subfile:
subfile.write(sub_info['data'])
except (OSError, IOError):
self.report_error('Cannot write subtitles file ' + sub_filename)
@@ -1883,36 +2051,41 @@ class YoutubeDL(object):
try:
sub_data = ie._request_webpage(
sub_info['url'], info_dict['id'], note=False).read()
with io.open(encodeFilename(sub_filename), 'wb') as subfile:
with open(encodeFilename(sub_filename), 'wb') as subfile:
subfile.write(sub_data)
except (ExtractorError, IOError, OSError, ValueError) as err:
self.report_warning('Unable to download subtitle for "%s": %s' %
(sub_lang, error_to_compat_str(err)))
continue
if self.params.get('writeinfojson', False):
infofn = replace_extension(filename, 'info.json', info_dict.get('ext'))
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(infofn)):
self.to_screen('[info] Video description metadata is already present')
else:
self.to_screen('[info] Writing video description metadata as JSON to: ' + infofn)
try:
write_json_file(self.filter_requested_info(info_dict), infofn)
except (OSError, IOError):
self.report_error('Cannot write metadata to JSON file ' + infofn)
return
self._write_info_json(
'video description', info_dict,
replace_extension(filename, 'info.json', info_dict.get('ext')))
self._write_thumbnails(info_dict, filename)
if not self.params.get('skip_download', False):
try:
def checked_get_suitable_downloader(info_dict, params):
ed_args = params.get('external_downloader_args')
dler = get_suitable_downloader(info_dict, params)
if ed_args and not params.get('external_downloader_args'):
# external_downloader_args was cleared because external_downloader was rejected
self.report_warning('Requested external downloader cannot be used: '
'ignoring --external-downloader-args.')
return dler
def dl(name, info):
fd = get_suitable_downloader(info, self.params)(self, self.params)
fd = checked_get_suitable_downloader(info, self.params)(self, self.params)
for ph in self._progress_hooks:
fd.add_progress_hook(ph)
if self.params.get('verbose'):
self.to_screen('[debug] Invoking downloader on %r' % info.get('url'))
return fd.download(name, info)
new_info = dict((k, v) for k, v in info.items() if not k.startswith('__p'))
new_info['http_headers'] = self._calc_headers(new_info)
return fd.download(name, new_info)
if info_dict.get('requested_formats') is not None:
downloaded = []
@@ -1941,18 +2114,26 @@ class YoutubeDL(object):
# TODO: Check acodec/vcodec
return False
filename_real_ext = os.path.splitext(filename)[1][1:]
filename_wo_ext = (
os.path.splitext(filename)[0]
if filename_real_ext == info_dict['ext']
else filename)
exts = [info_dict['ext']]
requested_formats = info_dict['requested_formats']
if self.params.get('merge_output_format') is None and not compatible_formats(requested_formats):
info_dict['ext'] = 'mkv'
self.report_warning(
'Requested formats are incompatible for merge and will be merged into mkv.')
exts.append(info_dict['ext'])
# Ensure filename always has a correct extension for successful merge
filename = '%s.%s' % (filename_wo_ext, info_dict['ext'])
def correct_ext(filename, ext=exts[1]):
if filename == '-':
return filename
f_name, f_real_ext = os.path.splitext(filename)
f_real_ext = f_real_ext[1:]
filename_wo_ext = f_name if f_real_ext in exts else filename
if ext is None:
ext = f_real_ext or None
return join_nonempty(filename_wo_ext, ext, delim='.')
filename = correct_ext(filename)
if os.path.exists(encodeFilename(filename)):
self.to_screen(
'[download] %s has already been downloaded and '
@@ -1962,8 +2143,9 @@ class YoutubeDL(object):
new_info = dict(info_dict)
new_info.update(f)
fname = prepend_extension(
self.prepare_filename(new_info),
'f%s' % f['format_id'], new_info['ext'])
correct_ext(
self.prepare_filename(new_info), new_info['ext']),
'f%s' % (f['format_id'],), new_info['ext'])
if not ensure_dir_exists(fname):
return
downloaded.append(fname)
@@ -2049,9 +2231,12 @@ class YoutubeDL(object):
try:
self.post_process(filename, info_dict)
except (PostProcessingError) as err:
self.report_error('postprocessing: %s' % str(err))
self.report_error('postprocessing: %s' % error_to_compat_str(err))
return
self.record_download_archive(info_dict)
# avoid possible nugatory search for further items (PR #26638)
if self._num_downloads >= max_downloads:
raise MaxDownloadsReached()
def download(self, url_list):
"""Download a given list of URLs."""
@@ -2074,16 +2259,13 @@ class YoutubeDL(object):
raise
else:
if self.params.get('dump_single_json', False):
self.to_stdout(json.dumps(res))
self.to_stdout(json.dumps(self.sanitize_info(res)))
return self._download_retcode
def download_with_info_file(self, info_filename):
with contextlib.closing(fileinput.FileInput(
[info_filename], mode='r',
openhook=fileinput.hook_encoded('utf-8'))) as f:
# FileInput doesn't have a read method, we can't call json.load
info = self.filter_requested_info(json.loads('\n'.join(f)))
with open(info_filename, encoding='utf-8') as f:
info = self.filter_requested_info(json.load(f))
try:
self.process_ie_result(info, download=True)
except DownloadError:
@@ -2096,10 +2278,36 @@ class YoutubeDL(object):
return self._download_retcode
@staticmethod
def filter_requested_info(info_dict):
return dict(
(k, v) for k, v in info_dict.items()
if k not in ['requested_formats', 'requested_subtitles'])
def sanitize_info(info_dict, remove_private_keys=False):
''' Sanitize the infodict for converting to json '''
if info_dict is None:
return info_dict
if remove_private_keys:
reject = lambda k, v: (v is None
or k.startswith('__')
or k in ('requested_formats',
'requested_subtitles'))
else:
reject = lambda k, v: False
def filter_fn(obj):
if isinstance(obj, dict):
return dict((k, filter_fn(v)) for k, v in obj.items() if not reject(k, v))
elif isinstance(obj, (list, tuple, set, LazyList)):
return list(map(filter_fn, obj))
elif obj is None or any(isinstance(obj, c)
for c in (compat_integer_types,
(compat_str, float, bool))):
return obj
else:
return repr(obj)
return filter_fn(info_dict)
@classmethod
def filter_requested_info(cls, info_dict):
return cls.sanitize_info(info_dict, True)
def post_process(self, filename, ie_info):
"""Run all the postprocessors on the given file."""
@@ -2306,18 +2514,21 @@ class YoutubeDL(object):
self.get_encoding()))
write_string(encoding_str, encoding=None)
self._write_string('[debug] youtube-dl version ' + __version__ + '\n')
writeln_debug = lambda *s: self._write_string('[debug] %s\n' % (''.join(s), ))
writeln_debug('youtube-dl version ', __version__)
if _LAZY_LOADER:
self._write_string('[debug] Lazy loading extractors enabled' + '\n')
writeln_debug('Lazy loading extractors enabled')
if ytdl_is_updateable():
writeln_debug('Single file build')
try:
sp = subprocess.Popen(
['git', 'rev-parse', '--short', 'HEAD'],
stdout=subprocess.PIPE, stderr=subprocess.PIPE,
cwd=os.path.dirname(os.path.abspath(__file__)))
out, err = sp.communicate()
out, err = process_communicate_or_kill(sp)
out = out.decode().strip()
if re.match('[0-9a-f]+', out):
self._write_string('[debug] Git HEAD: ' + out + '\n')
writeln_debug('Git HEAD: ', out)
except Exception:
try:
sys.exc_clear()
@@ -2330,9 +2541,22 @@ class YoutubeDL(object):
return impl_name + ' version %d.%d.%d' % sys.pypy_version_info[:3]
return impl_name
self._write_string('[debug] Python version %s (%s) - %s\n' % (
platform.python_version(), python_implementation(),
platform_name()))
def libc_ver():
try:
return platform.libc_ver()
except OSError: # We may not have access to the executable
return []
libc = join_nonempty(*libc_ver(), delim=' ')
writeln_debug('Python %s (%s %s %s) - %s - %s%s' % (
platform.python_version(),
python_implementation(),
platform.machine(),
platform.architecture()[0],
platform_name(),
OPENSSL_VERSION,
(' - %s' % (libc, )) if libc else ''
))
exe_versions = FFmpegPostProcessor.get_versions(self)
exe_versions['rtmpdump'] = rtmpdump_version()
@@ -2344,17 +2568,17 @@ class YoutubeDL(object):
)
if not exe_str:
exe_str = 'none'
self._write_string('[debug] exe versions: %s\n' % exe_str)
writeln_debug('exe versions: %s' % (exe_str, ))
proxy_map = {}
for handler in self._opener.handlers:
if hasattr(handler, 'proxies'):
proxy_map.update(handler.proxies)
self._write_string('[debug] Proxy map: ' + compat_str(proxy_map) + '\n')
writeln_debug('Proxy map: ', compat_str(proxy_map))
if self.params.get('call_home', False):
ipaddr = self.urlopen('https://yt-dl.org/ip').read().decode('utf-8')
self._write_string('[debug] Public IP address: %s\n' % ipaddr)
writeln_debug('Public IP address: %s' % (ipaddr, ))
latest_version = self.urlopen(
'https://yt-dl.org/latest/version').read().decode('utf-8')
if version_tuple(latest_version) > version_tuple(__version__):
@@ -2371,7 +2595,7 @@ class YoutubeDL(object):
opts_proxy = self.params.get('proxy')
if opts_cookiefile is None:
self.cookiejar = compat_cookiejar.CookieJar()
self.cookiejar = YoutubeDLCookieJar()
else:
opts_cookiefile = expand_path(opts_cookiefile)
self.cookiejar = YoutubeDLCookieJar(opts_cookiefile)
@@ -2432,6 +2656,28 @@ class YoutubeDL(object):
encoding = preferredencoding()
return encoding
def _write_info_json(self, label, info_dict, infofn, overwrite=None):
if not self.params.get('writeinfojson', False):
return False
def msg(fmt, lbl):
return fmt % (lbl + ' metadata',)
if overwrite is None:
overwrite = not self.params.get('nooverwrites', False)
if not overwrite and os.path.exists(encodeFilename(infofn)):
self.to_screen(msg('[info] %s is already present', label.title()))
return 'exists'
else:
self.to_screen(msg('[info] Writing %s as JSON to: ', label) + infofn)
try:
write_json_file(self.filter_requested_info(info_dict), infofn)
return True
except (OSError, IOError):
self.report_error(msg('Cannot write %s to JSON file ', label) + infofn)
return
def _write_thumbnails(self, info_dict, filename):
if self.params.get('writethumbnail', False):
thumbnails = info_dict.get('thumbnails')

12
youtube_dl/__init__.py
View File

@@ -5,7 +5,6 @@ from __future__ import unicode_literals
__license__ = 'Public Domain'
import codecs
import io
import os
import random
@@ -17,10 +16,12 @@ from .options import (
)
from .compat import (
compat_getpass,
compat_register_utf8,
compat_shlex_split,
workaround_optparse_bug9161,
)
from .utils import (
_UnsafeExtensionError,
DateRange,
decodeOption,
DEFAULT_OUTTMPL,
@@ -46,10 +47,8 @@ from .YoutubeDL import YoutubeDL
def _real_main(argv=None):
# Compatibility fixes for Windows
if sys.platform == 'win32':
# https://github.com/ytdl-org/youtube-dl/issues/820
codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
# Compatibility fix for Windows
compat_register_utf8()
workaround_optparse_bug9161()
@@ -175,6 +174,9 @@ def _real_main(argv=None):
if opts.ap_mso and opts.ap_mso not in MSO_INFO:
parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
if opts.no_check_extensions:
_UnsafeExtensionError.lenient = True
def parse_retries(retries):
if retries in ('inf', 'infinite'):
parsed_retries = float('inf')

39
youtube_dl/aes.py
View File

@@ -8,6 +8,18 @@ from .utils import bytes_to_intlist, intlist_to_bytes
BLOCK_SIZE_BYTES = 16
def pkcs7_padding(data):
"""
PKCS#7 padding
@param {int[]} data cleartext
@returns {int[]} padding data
"""
remaining_length = BLOCK_SIZE_BYTES - len(data) % BLOCK_SIZE_BYTES
return data + [remaining_length] * remaining_length
def aes_ctr_decrypt(data, key, counter):
"""
Decrypt with aes in counter mode
@@ -76,8 +88,7 @@ def aes_cbc_encrypt(data, key, iv):
previous_cipher_block = iv
for i in range(block_count):
block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
remaining_length = BLOCK_SIZE_BYTES - len(block)
block += [remaining_length] * remaining_length
block = pkcs7_padding(block)
mixed_block = xor(block, previous_cipher_block)
encrypted_block = aes_encrypt(mixed_block, expanded_key)
@@ -88,6 +99,28 @@ def aes_cbc_encrypt(data, key, iv):
return encrypted_data
def aes_ecb_encrypt(data, key):
"""
Encrypt with aes in ECB mode. Using PKCS#7 padding
@param {int[]} data cleartext
@param {int[]} key 16/24/32-Byte cipher key
@returns {int[]} encrypted data
"""
expanded_key = key_expansion(key)
block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
encrypted_data = []
for i in range(block_count):
block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
block = pkcs7_padding(block)
encrypted_block = aes_encrypt(block, expanded_key)
encrypted_data += encrypted_block
return encrypted_data
def key_expansion(data):
"""
Generate key schedule
@@ -303,7 +336,7 @@ def xor(data1, data2):
def rijndael_mul(a, b):
if(a == 0 or b == 0):
if (a == 0 or b == 0):
return 0
return RIJNDAEL_EXP_TABLE[(RIJNDAEL_LOG_TABLE[a] + RIJNDAEL_LOG_TABLE[b]) % 0xFF]

36
youtube_dl/cache.py
View File

@@ -1,21 +1,32 @@
from __future__ import unicode_literals
import errno
import io
import json
import os
import re
import shutil
import traceback
from .compat import compat_getenv
from .compat import (
compat_getenv,
compat_open as open,
)
from .utils import (
error_to_compat_str,
expand_path,
is_outdated_version,
try_get,
write_json_file,
)
from .version import __version__
class Cache(object):
_YTDL_DIR = 'youtube-dl'
_VERSION_KEY = _YTDL_DIR + '_version'
_DEFAULT_VERSION = '2021.12.17'
def __init__(self, ydl):
self._ydl = ydl
@@ -23,7 +34,7 @@ class Cache(object):
res = self._ydl.params.get('cachedir')
if res is None:
cache_root = compat_getenv('XDG_CACHE_HOME', '~/.cache')
res = os.path.join(cache_root, 'youtube-dl')
res = os.path.join(cache_root, self._YTDL_DIR)
return expand_path(res)
def _get_cache_fn(self, section, key, dtype):
@@ -50,13 +61,22 @@ class Cache(object):
except OSError as ose:
if ose.errno != errno.EEXIST:
raise
write_json_file(data, fn)
write_json_file({self._VERSION_KEY: __version__, 'data': data}, fn)
except Exception:
tb = traceback.format_exc()
self._ydl.report_warning(
'Writing cache to %r failed: %s' % (fn, tb))
def load(self, section, key, dtype='json', default=None):
def _validate(self, data, min_ver):
version = try_get(data, lambda x: x[self._VERSION_KEY])
if not version: # Backward compatibility
data, version = {'data': data}, self._DEFAULT_VERSION
if not is_outdated_version(version, min_ver or '0', assume_new=False):
return data['data']
self._ydl.to_screen(
'Discarding old cache from version {version} (needs {min_ver})'.format(**locals()))
def load(self, section, key, dtype='json', default=None, min_ver=None):
assert dtype in ('json',)
if not self.enabled:
@@ -65,13 +85,13 @@ class Cache(object):
cache_fn = self._get_cache_fn(section, key, dtype)
try:
try:
with io.open(cache_fn, 'r', encoding='utf-8') as cachef:
return json.load(cachef)
with open(cache_fn, 'r', encoding='utf-8') as cachef:
return self._validate(json.load(cachef), min_ver)
except ValueError:
try:
file_size = os.path.getsize(cache_fn)
except (OSError, IOError) as oe:
file_size = str(oe)
file_size = error_to_compat_str(oe)
self._ydl.report_warning(
'Cache retrieval from %s failed (%s)' % (cache_fn, file_size))
except IOError:

1667
youtube_dl/casefold.py Normal file
View File

File diff suppressed because it is too large Load Diff

720
youtube_dl/compat.py
View File

@@ -1,10 +1,12 @@
# coding: utf-8
from __future__ import unicode_literals
from __future__ import division
import base64
import binascii
import collections
import ctypes
import datetime
import email
import getpass
import io
@@ -19,8 +21,31 @@ import socket
import struct
import subprocess
import sys
import types
import xml.etree.ElementTree
# naming convention
# 'compat_' + Python3_name.replace('.', '_')
# other aliases exist for convenience and/or legacy
# deal with critical unicode/str things first
try:
# Python 2
compat_str, compat_basestring, compat_chr = (
unicode, basestring, unichr
)
except NameError:
compat_str, compat_basestring, compat_chr = (
str, (str, bytes), chr
)
# casefold
try:
compat_str.casefold
compat_casefold = lambda s: s.casefold()
except AttributeError:
from .casefold import casefold as compat_casefold
try:
import collections.abc as compat_collections_abc
except ImportError:
@@ -31,6 +56,29 @@ try:
except ImportError: # Python 2
import urllib2 as compat_urllib_request
# Also fix up lack of method arg in old Pythons
try:
type(compat_urllib_request.Request('http://127.0.0.1', method='GET'))
except TypeError:
def _add_init_method_arg(cls):
init = cls.__init__
def wrapped_init(self, *args, **kwargs):
method = kwargs.pop('method', 'GET')
init(self, *args, **kwargs)
if any(callable(x.__dict__.get('get_method')) for x in (self.__class__, self) if x != cls):
# allow instance or its subclass to override get_method()
return
if self.has_data() and method == 'GET':
method = 'POST'
self.get_method = types.MethodType(lambda _: method, self)
cls.__init__ = wrapped_init
_add_init_method_arg(compat_urllib_request.Request)
del _add_init_method_arg
try:
import urllib.error as compat_urllib_error
except ImportError: # Python 2
@@ -40,26 +88,32 @@ try:
import urllib.parse as compat_urllib_parse
except ImportError: # Python 2
import urllib as compat_urllib_parse
import urlparse as _urlparse
for a in dir(_urlparse):
if not hasattr(compat_urllib_parse, a):
setattr(compat_urllib_parse, a, getattr(_urlparse, a))
del _urlparse
try:
from urllib.parse import urlparse as compat_urllib_parse_urlparse
except ImportError: # Python 2
from urlparse import urlparse as compat_urllib_parse_urlparse
try:
import urllib.parse as compat_urlparse
except ImportError: # Python 2
import urlparse as compat_urlparse
# unfavoured aliases
compat_urlparse = compat_urllib_parse
compat_urllib_parse_urlparse = compat_urllib_parse.urlparse
try:
import urllib.response as compat_urllib_response
except ImportError: # Python 2
import urllib as compat_urllib_response
try:
compat_urllib_response.addinfourl.status
except AttributeError:
# .getcode() is deprecated in Py 3.
compat_urllib_response.addinfourl.status = property(lambda self: self.getcode())
try:
import http.cookiejar as compat_cookiejar
except ImportError: # Python 2
import cookielib as compat_cookiejar
compat_http_cookiejar = compat_cookiejar
if sys.version_info[0] == 2:
class compat_cookiejar_Cookie(compat_cookiejar.Cookie):
@@ -71,20 +125,35 @@ if sys.version_info[0] == 2:
compat_cookiejar.Cookie.__init__(self, version, name, value, *args, **kwargs)
else:
compat_cookiejar_Cookie = compat_cookiejar.Cookie
compat_http_cookiejar_Cookie = compat_cookiejar_Cookie
try:
import http.cookies as compat_cookies
except ImportError: # Python 2
import Cookie as compat_cookies
compat_http_cookies = compat_cookies
if sys.version_info[0] == 2:
if sys.version_info[0] == 2 or sys.version_info < (3, 3):
class compat_cookies_SimpleCookie(compat_cookies.SimpleCookie):
def load(self, rawdata):
if isinstance(rawdata, compat_str):
rawdata = str(rawdata)
return super(compat_cookies_SimpleCookie, self).load(rawdata)
must_have_value = 0
if not isinstance(rawdata, dict):
if sys.version_info[:2] != (2, 7) or sys.platform.startswith('java'):
# attribute must have value for parsing
rawdata, must_have_value = re.subn(
r'(?i)(;\s*)(secure|httponly)(\s*(?:;|$))', r'\1\2=\2\3', rawdata)
if sys.version_info[0] == 2:
if isinstance(rawdata, compat_str):
rawdata = str(rawdata)
super(compat_cookies_SimpleCookie, self).load(rawdata)
if must_have_value > 0:
for morsel in self.values():
for attr in ('secure', 'httponly'):
if morsel.get(attr):
morsel[attr] = True
else:
compat_cookies_SimpleCookie = compat_cookies.SimpleCookie
compat_http_cookies_SimpleCookie = compat_cookies_SimpleCookie
try:
import html.entities as compat_html_entities
@@ -2333,39 +2402,45 @@ try:
import http.client as compat_http_client
except ImportError: # Python 2
import httplib as compat_http_client
try:
compat_http_client.HTTPResponse.getcode
except AttributeError:
# Py < 3.1
compat_http_client.HTTPResponse.getcode = lambda self: self.status
try:
from urllib.error import HTTPError as compat_HTTPError
except ImportError: # Python 2
from urllib2 import HTTPError as compat_HTTPError
compat_urllib_HTTPError = compat_HTTPError
try:
from urllib.request import urlretrieve as compat_urlretrieve
except ImportError: # Python 2
from urllib import urlretrieve as compat_urlretrieve
compat_urllib_request_urlretrieve = compat_urlretrieve
try:
from HTMLParser import (
HTMLParser as compat_HTMLParser,
HTMLParseError as compat_HTMLParseError)
except ImportError: # Python 3
from html.parser import HTMLParser as compat_HTMLParser
except ImportError: # Python 2
from HTMLParser import HTMLParser as compat_HTMLParser
try: # Python 2
from HTMLParser import HTMLParseError as compat_HTMLParseError
except ImportError: # Python <3.4
try:
from html.parser import HTMLParseError as compat_HTMLParseError
except ImportError: # Python >3.4
# HTMLParseError has been deprecated in Python 3.3 and removed in
# HTMLParseError was deprecated in Python 3.3 and removed in
# Python 3.5. Introducing dummy exception for Python >3.5 for compatible
# and uniform cross-version exception handling
class compat_HTMLParseError(Exception):
pass
compat_html_parser_HTMLParser = compat_HTMLParser
compat_html_parser_HTMLParseError = compat_HTMLParseError
try:
from subprocess import DEVNULL
compat_subprocess_get_DEVNULL = lambda: DEVNULL
except ImportError:
_DEVNULL = subprocess.DEVNULL
compat_subprocess_get_DEVNULL = lambda: _DEVNULL
except AttributeError:
compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')
try:
@@ -2373,15 +2448,12 @@ try:
except ImportError:
import BaseHTTPServer as compat_http_server
try:
compat_str = unicode # Python 2
except NameError:
compat_str = str
try:
from urllib.parse import unquote_to_bytes as compat_urllib_parse_unquote_to_bytes
from urllib.parse import unquote as compat_urllib_parse_unquote
from urllib.parse import unquote_plus as compat_urllib_parse_unquote_plus
from urllib.parse import urlencode as compat_urllib_parse_urlencode
from urllib.parse import parse_qs as compat_parse_qs
except ImportError: # Python 2
_asciire = (compat_urllib_parse._asciire if hasattr(compat_urllib_parse, '_asciire')
else re.compile(r'([\x00-\x7f]+)'))
@@ -2448,9 +2520,6 @@ except ImportError: # Python 2
string = string.replace('+', ' ')
return compat_urllib_parse_unquote(string, encoding, errors)
try:
from urllib.parse import urlencode as compat_urllib_parse_urlencode
except ImportError: # Python 2
# Python 2 will choke in urlencode on mixture of byte and unicode strings.
# Possible solutions are to either port it from python 3 with all
# the friends or manually ensure input query contains only byte strings.
@@ -2472,7 +2541,62 @@ except ImportError: # Python 2
def encode_list(l):
return [encode_elem(e) for e in l]
return compat_urllib_parse.urlencode(encode_elem(query), doseq=doseq)
return compat_urllib_parse._urlencode(encode_elem(query), doseq=doseq)
# HACK: The following is the correct parse_qs implementation from cpython 3's stdlib.
# Python 2's version is apparently totally broken
def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
encoding='utf-8', errors='replace'):
qs, _coerce_result = qs, compat_str
pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
r = []
for name_value in pairs:
if not name_value and not strict_parsing:
continue
nv = name_value.split('=', 1)
if len(nv) != 2:
if strict_parsing:
raise ValueError('bad query field: %r' % (name_value,))
# Handle case of a control-name with no equal sign
if keep_blank_values:
nv.append('')
else:
continue
if len(nv[1]) or keep_blank_values:
name = nv[0].replace('+', ' ')
name = compat_urllib_parse_unquote(
name, encoding=encoding, errors=errors)
name = _coerce_result(name)
value = nv[1].replace('+', ' ')
value = compat_urllib_parse_unquote(
value, encoding=encoding, errors=errors)
value = _coerce_result(value)
r.append((name, value))
return r
def compat_parse_qs(qs, keep_blank_values=False, strict_parsing=False,
encoding='utf-8', errors='replace'):
parsed_result = {}
pairs = _parse_qsl(qs, keep_blank_values, strict_parsing,
encoding=encoding, errors=errors)
for name, value in pairs:
if name in parsed_result:
parsed_result[name].append(value)
else:
parsed_result[name] = [value]
return parsed_result
setattr(compat_urllib_parse, '_urlencode',
getattr(compat_urllib_parse, 'urlencode'))
for name, fix in (
('unquote_to_bytes', compat_urllib_parse_unquote_to_bytes),
('parse_unquote', compat_urllib_parse_unquote),
('unquote_plus', compat_urllib_parse_unquote_plus),
('urlencode', compat_urllib_parse_urlencode),
('parse_qs', compat_parse_qs)):
setattr(compat_urllib_parse, name, fix)
compat_urllib_parse_parse_qs = compat_parse_qs
try:
from urllib.request import DataHandler as compat_urllib_request_DataHandler
@@ -2508,21 +2632,11 @@ except ImportError: # Python < 3.4
return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url)
try:
compat_basestring = basestring # Python 2
except NameError:
compat_basestring = str
try:
compat_chr = unichr # Python 2
except NameError:
compat_chr = chr
try:
from xml.etree.ElementTree import ParseError as compat_xml_parse_error
except ImportError: # Python 2.6
from xml.parsers.expat import ExpatError as compat_xml_parse_error
compat_xml_etree_ElementTree_ParseError = compat_xml_parse_error
etree = xml.etree.ElementTree
@@ -2536,10 +2650,11 @@ try:
# xml.etree.ElementTree.Element is a method in Python <=2.6 and
# the following will crash with:
# TypeError: isinstance() arg 2 must be a class, type, or tuple of classes and types
isinstance(None, xml.etree.ElementTree.Element)
isinstance(None, etree.Element)
from xml.etree.ElementTree import Element as compat_etree_Element
except TypeError: # Python <=2.6
from xml.etree.ElementTree import _ElementInterface as compat_etree_Element
compat_xml_etree_ElementTree_Element = compat_etree_Element
if sys.version_info[0] >= 3:
def compat_etree_fromstring(text):
@@ -2595,6 +2710,7 @@ else:
if k == uri or v == prefix:
del etree._namespace_map[k]
etree._namespace_map[uri] = prefix
compat_xml_etree_register_namespace = compat_etree_register_namespace
if sys.version_info < (2, 7):
# Here comes the crazy part: In 2.6, if the xpath is a unicode,
@@ -2603,55 +2719,222 @@ if sys.version_info < (2, 7):
if isinstance(xpath, compat_str):
xpath = xpath.encode('ascii')
return xpath
# further code below based on CPython 2.7 source
import functools
_xpath_tokenizer_re = re.compile(r'''(?x)
( # (1)
'[^']*'|"[^"]*"| # quoted strings, or
::|//?|\.\.|\(\)|[/.*:[\]()@=] # navigation specials
)| # or (2)
((?:\{[^}]+\})?[^/[\]()@=\s]+)| # token: optional {ns}, no specials
\s+ # or white space
''')
def _xpath_tokenizer(pattern, namespaces=None):
for token in _xpath_tokenizer_re.findall(pattern):
tag = token[1]
if tag and tag[0] != "{" and ":" in tag:
try:
if not namespaces:
raise KeyError
prefix, uri = tag.split(":", 1)
yield token[0], "{%s}%s" % (namespaces[prefix], uri)
except KeyError:
raise SyntaxError("prefix %r not found in prefix map" % prefix)
else:
yield token
def _get_parent_map(context):
parent_map = context.parent_map
if parent_map is None:
context.parent_map = parent_map = {}
for p in context.root.getiterator():
for e in p:
parent_map[e] = p
return parent_map
def _select(context, result, filter_fn=lambda *_: True):
for elem in result:
for e in elem:
if filter_fn(e, elem):
yield e
def _prepare_child(next_, token):
tag = token[1]
return functools.partial(_select, filter_fn=lambda e, _: e.tag == tag)
def _prepare_star(next_, token):
return _select
def _prepare_self(next_, token):
return lambda _, result: (e for e in result)
def _prepare_descendant(next_, token):
token = next(next_)
if token[0] == "*":
tag = "*"
elif not token[0]:
tag = token[1]
else:
raise SyntaxError("invalid descendant")
def select(context, result):
for elem in result:
for e in elem.getiterator(tag):
if e is not elem:
yield e
return select
def _prepare_parent(next_, token):
def select(context, result):
# FIXME: raise error if .. is applied at toplevel?
parent_map = _get_parent_map(context)
result_map = {}
for elem in result:
if elem in parent_map:
parent = parent_map[elem]
if parent not in result_map:
result_map[parent] = None
yield parent
return select
def _prepare_predicate(next_, token):
signature = []
predicate = []
for token in next_:
if token[0] == "]":
break
if token[0] and token[0][:1] in "'\"":
token = "'", token[0][1:-1]
signature.append(token[0] or "-")
predicate.append(token[1])
def select(context, result, filter_fn=lambda _: True):
for elem in result:
if filter_fn(elem):
yield elem
signature = "".join(signature)
# use signature to determine predicate type
if signature == "@-":
# [@attribute] predicate
key = predicate[1]
return functools.partial(
select, filter_fn=lambda el: el.get(key) is not None)
if signature == "@-='":
# [@attribute='value']
key = predicate[1]
value = predicate[-1]
return functools.partial(
select, filter_fn=lambda el: el.get(key) == value)
if signature == "-" and not re.match(r"\d+$", predicate[0]):
# [tag]
tag = predicate[0]
return functools.partial(
select, filter_fn=lambda el: el.find(tag) is not None)
if signature == "-='" and not re.match(r"\d+$", predicate[0]):
# [tag='value']
tag = predicate[0]
value = predicate[-1]
def itertext(el):
for e in el.getiterator():
e = e.text
if e:
yield e
def select(context, result):
for elem in result:
for e in elem.findall(tag):
if "".join(itertext(e)) == value:
yield elem
break
return select
if signature == "-" or signature == "-()" or signature == "-()-":
# [index] or [last()] or [last()-index]
if signature == "-":
index = int(predicate[0]) - 1
else:
if predicate[0] != "last":
raise SyntaxError("unsupported function")
if signature == "-()-":
try:
index = int(predicate[2]) - 1
except ValueError:
raise SyntaxError("unsupported expression")
else:
index = -1
def select(context, result):
parent_map = _get_parent_map(context)
for elem in result:
try:
parent = parent_map[elem]
# FIXME: what if the selector is "*" ?
elems = list(parent.findall(elem.tag))
if elems[index] is elem:
yield elem
except (IndexError, KeyError):
pass
return select
raise SyntaxError("invalid predicate")
ops = {
"": _prepare_child,
"*": _prepare_star,
".": _prepare_self,
"..": _prepare_parent,
"//": _prepare_descendant,
"[": _prepare_predicate,
}
_cache = {}
class _SelectorContext:
parent_map = None
def __init__(self, root):
self.root = root
##
# Generate all matching objects.
def compat_etree_iterfind(elem, path, namespaces=None):
# compile selector pattern
if path[-1:] == "/":
path = path + "*" # implicit all (FIXME: keep this?)
try:
selector = _cache[path]
except KeyError:
if len(_cache) > 100:
_cache.clear()
if path[:1] == "/":
raise SyntaxError("cannot use absolute path on element")
tokens = _xpath_tokenizer(path, namespaces)
selector = []
for token in tokens:
if token[0] == "/":
continue
try:
selector.append(ops[token[0]](tokens, token))
except StopIteration:
raise SyntaxError("invalid path")
_cache[path] = selector
# execute selector pattern
result = [elem]
context = _SelectorContext(elem)
for select in selector:
result = select(context, result)
return result
# end of code based on CPython 2.7 source
else:
compat_xpath = lambda xpath: xpath
try:
from urllib.parse import parse_qs as compat_parse_qs
except ImportError: # Python 2
# HACK: The following is the correct parse_qs implementation from cpython 3's stdlib.
# Python 2's version is apparently totally broken
def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
encoding='utf-8', errors='replace'):
qs, _coerce_result = qs, compat_str
pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
r = []
for name_value in pairs:
if not name_value and not strict_parsing:
continue
nv = name_value.split('=', 1)
if len(nv) != 2:
if strict_parsing:
raise ValueError('bad query field: %r' % (name_value,))
# Handle case of a control-name with no equal sign
if keep_blank_values:
nv.append('')
else:
continue
if len(nv[1]) or keep_blank_values:
name = nv[0].replace('+', ' ')
name = compat_urllib_parse_unquote(
name, encoding=encoding, errors=errors)
name = _coerce_result(name)
value = nv[1].replace('+', ' ')
value = compat_urllib_parse_unquote(
value, encoding=encoding, errors=errors)
value = _coerce_result(value)
r.append((name, value))
return r
def compat_parse_qs(qs, keep_blank_values=False, strict_parsing=False,
encoding='utf-8', errors='replace'):
parsed_result = {}
pairs = _parse_qsl(qs, keep_blank_values, strict_parsing,
encoding=encoding, errors=errors)
for name, value in pairs:
if name in parsed_result:
parsed_result[name].append(value)
else:
parsed_result[name] = [value]
return parsed_result
compat_etree_iterfind = lambda element, match: element.iterfind(match)
compat_os_name = os._name if os.name == 'java' else os.name
@@ -2687,7 +2970,7 @@ except (AssertionError, UnicodeEncodeError):
def compat_ord(c):
if type(c) is int:
if isinstance(c, int):
return c
else:
return ord(c)
@@ -2777,6 +3060,8 @@ else:
else:
compat_expanduser = os.path.expanduser
compat_os_path_expanduser = compat_expanduser
if compat_os_name == 'nt' and sys.version_info < (3, 8):
# os.path.realpath on Windows does not follow symbolic links
@@ -2788,6 +3073,8 @@ if compat_os_name == 'nt' and sys.version_info < (3, 8):
else:
compat_realpath = os.path.realpath
compat_os_path_realpath = compat_realpath
if sys.version_info < (3, 0):
def compat_print(s):
@@ -2808,11 +3095,15 @@ if sys.version_info < (3, 0) and sys.platform == 'win32':
else:
compat_getpass = getpass.getpass
compat_getpass_getpass = compat_getpass
try:
compat_input = raw_input
except NameError: # Python 3
compat_input = input
# Python < 2.6.5 require kwargs to be bytes
try:
def _testfunc(x):
@@ -2863,6 +3154,51 @@ else:
compat_socket_create_connection = socket.create_connection
try:
from contextlib import suppress as compat_contextlib_suppress
except ImportError:
class compat_contextlib_suppress(object):
_exceptions = None
def __init__(self, *exceptions):
super(compat_contextlib_suppress, self).__init__()
# TODO: [Base]ExceptionGroup (3.12+)
self._exceptions = exceptions
def __enter__(self):
return self
def __exit__(self, exc_type, exc_val, exc_tb):
return exc_type is not None and issubclass(exc_type, self._exceptions or tuple())
# subprocess.Popen context manager
# avoids leaking handles if .communicate() is not called
try:
_Popen = subprocess.Popen
# check for required context manager attributes
_Popen.__enter__ and _Popen.__exit__
compat_subprocess_Popen = _Popen
except AttributeError:
# not a context manager - make one
from contextlib import contextmanager
@contextmanager
def compat_subprocess_Popen(*args, **kwargs):
popen = None
try:
popen = _Popen(*args, **kwargs)
yield popen
finally:
if popen:
for f in (popen.stdin, popen.stdout, popen.stderr):
if f:
# repeated .close() is OK, but just in case
with compat_contextlib_suppress(EnvironmentError):
f.close()
popen.wait()
# Fix https://github.com/ytdl-org/youtube-dl/issues/4223
# See http://bugs.python.org/issue9161 for what is broken
def workaround_optparse_bug9161():
@@ -2890,6 +3226,7 @@ else:
_terminal_size = collections.namedtuple('terminal_size', ['columns', 'lines'])
def compat_get_terminal_size(fallback=(80, 24)):
from .utils import process_communicate_or_kill
columns = compat_getenv('COLUMNS')
if columns:
columns = int(columns)
@@ -2906,7 +3243,7 @@ else:
sp = subprocess.Popen(
['stty', 'size'],
stdout=subprocess.PIPE, stderr=subprocess.PIPE)
out, err = sp.communicate()
out, err = process_communicate_or_kill(sp)
_lines, _columns = map(int, out.split())
except Exception:
_columns, _lines = _terminal_size(*fallback)
@@ -2917,15 +3254,16 @@ else:
lines = _lines
return _terminal_size(columns, lines)
try:
itertools.count(start=0, step=1)
compat_itertools_count = itertools.count
except TypeError: # Python 2.6
def compat_itertools_count(start=0, step=1):
n = start
while True:
yield n
n += step
yield start
start += step
if sys.version_info >= (3, 0):
from tokenize import tokenize as compat_tokenize_tokenize
@@ -2984,7 +3322,6 @@ except ImportError:
except ImportError:
compat_filter = filter
try:
from future_builtins import zip as compat_zip
except ImportError: # not 2.6+ or is 3.x
@@ -2994,6 +3331,82 @@ except ImportError: # not 2.6+ or is 3.x
compat_zip = zip
# method renamed between Py2/3
try:
from itertools import zip_longest as compat_itertools_zip_longest
except ImportError:
from itertools import izip_longest as compat_itertools_zip_longest
# new class in collections
try:
from collections import ChainMap as compat_collections_chain_map
# Py3.3's ChainMap is deficient
if sys.version_info < (3, 4):
raise ImportError
except ImportError:
# Py <= 3.3
class compat_collections_chain_map(compat_collections_abc.MutableMapping):
maps = [{}]
def __init__(self, *maps):
self.maps = list(maps) or [{}]
def __getitem__(self, k):
for m in self.maps:
if k in m:
return m[k]
raise KeyError(k)
def __setitem__(self, k, v):
self.maps[0].__setitem__(k, v)
return
def __contains__(self, k):
return any((k in m) for m in self.maps)
def __delitem(self, k):
if k in self.maps[0]:
del self.maps[0][k]
return
raise KeyError(k)
def __delitem__(self, k):
self.__delitem(k)
def __iter__(self):
return itertools.chain(*reversed(self.maps))
def __len__(self):
return len(iter(self))
# to match Py3, don't del directly
def pop(self, k, *args):
if self.__contains__(k):
off = self.__getitem__(k)
self.__delitem(k)
return off
elif len(args) > 0:
return args[0]
raise KeyError(k)
def new_child(self, m=None, **kwargs):
m = m or {}
m.update(kwargs)
return compat_collections_chain_map(m, *self.maps)
@property
def parents(self):
return compat_collections_chain_map(*(self.maps[1:]))
# Pythons disagree on the type of a pattern (RegexObject, _sre.SRE_Pattern, Pattern, ...?)
compat_re_Pattern = type(re.compile(''))
# and on the type of a match
compat_re_Match = type(re.match('a', 'a'))
if sys.version_info < (3, 3):
def compat_b64decode(s, *args, **kwargs):
if isinstance(s, compat_str):
@@ -3002,6 +3415,8 @@ if sys.version_info < (3, 3):
else:
compat_b64decode = base64.b64decode
compat_base64_b64decode = compat_b64decode
if platform.python_implementation() == 'PyPy' and sys.pypy_version_info < (5, 4, 0):
# PyPy2 prior to version 5.4.0 expects byte strings as Windows function
@@ -3021,28 +3436,97 @@ else:
return ctypes.WINFUNCTYPE(*args, **kwargs)
__all__ = [
if sys.version_info < (3, 0):
# open(file, mode='r', buffering=- 1, encoding=None, errors=None, newline=None, closefd=True) not: opener=None
def compat_open(file_, *args, **kwargs):
if len(args) > 6 or 'opener' in kwargs:
raise ValueError('open: unsupported argument "opener"')
return io.open(file_, *args, **kwargs)
else:
compat_open = open
# compat_register_utf8
def compat_register_utf8():
if sys.platform == 'win32':
# https://github.com/ytdl-org/youtube-dl/issues/820
from codecs import register, lookup
register(
lambda name: lookup('utf-8') if name == 'cp65001' else None)
# compat_datetime_timedelta_total_seconds
try:
compat_datetime_timedelta_total_seconds = datetime.timedelta.total_seconds
except AttributeError:
# Py 2.6
def compat_datetime_timedelta_total_seconds(td):
return (td.microseconds + (td.seconds + td.days * 24 * 3600) * 10**6) / 10**6
# optional decompression packages
# PyPi brotli package implements 'br' Content-Encoding
try:
import brotli as compat_brotli
except ImportError:
compat_brotli = None
# PyPi ncompress package implements 'compress' Content-Encoding
try:
import ncompress as compat_ncompress
except ImportError:
compat_ncompress = None
legacy = [
'compat_HTMLParseError',
'compat_HTMLParser',
'compat_HTTPError',
'compat_Struct',
'compat_b64decode',
'compat_basestring',
'compat_chr',
'compat_collections_abc',
'compat_cookiejar',
'compat_cookiejar_Cookie',
'compat_cookies',
'compat_cookies_SimpleCookie',
'compat_ctypes_WINFUNCTYPE',
'compat_etree_Element',
'compat_etree_fromstring',
'compat_etree_register_namespace',
'compat_expanduser',
'compat_getpass',
'compat_parse_qs',
'compat_realpath',
'compat_urllib_parse_parse_qs',
'compat_urllib_parse_unquote',
'compat_urllib_parse_unquote_plus',
'compat_urllib_parse_unquote_to_bytes',
'compat_urllib_parse_urlencode',
'compat_urllib_parse_urlparse',
'compat_urlparse',
'compat_urlretrieve',
'compat_xml_parse_error',
]
__all__ = [
'compat_html_parser_HTMLParseError',
'compat_html_parser_HTMLParser',
'compat_Struct',
'compat_base64_b64decode',
'compat_basestring',
'compat_brotli',
'compat_casefold',
'compat_chr',
'compat_collections_abc',
'compat_collections_chain_map',
'compat_datetime_timedelta_total_seconds',
'compat_http_cookiejar',
'compat_http_cookiejar_Cookie',
'compat_http_cookies',
'compat_http_cookies_SimpleCookie',
'compat_contextlib_suppress',
'compat_ctypes_WINFUNCTYPE',
'compat_etree_fromstring',
'compat_etree_iterfind',
'compat_filter',
'compat_get_terminal_size',
'compat_getenv',
'compat_getpass',
'compat_getpass_getpass',
'compat_html_entities',
'compat_html_entities_html5',
'compat_http_client',
@@ -3050,14 +3534,20 @@ __all__ = [
'compat_input',
'compat_integer_types',
'compat_itertools_count',
'compat_itertools_zip_longest',
'compat_kwargs',
'compat_map',
'compat_ncompress',
'compat_numeric_types',
'compat_open',
'compat_ord',
'compat_os_name',
'compat_parse_qs',
'compat_os_path_expanduser',
'compat_os_path_realpath',
'compat_print',
'compat_realpath',
'compat_re_Match',
'compat_re_Pattern',
'compat_register_utf8',
'compat_setenv',
'compat_shlex_quote',
'compat_shlex_split',
@@ -3066,20 +3556,18 @@ __all__ = [
'compat_struct_pack',
'compat_struct_unpack',
'compat_subprocess_get_DEVNULL',
'compat_subprocess_Popen',
'compat_tokenize_tokenize',
'compat_urllib_error',
'compat_urllib_parse',
'compat_urllib_parse_unquote',
'compat_urllib_parse_unquote_plus',
'compat_urllib_parse_unquote_to_bytes',
'compat_urllib_parse_urlencode',
'compat_urllib_parse_urlparse',
'compat_urllib_request',
'compat_urllib_request_DataHandler',
'compat_urllib_response',
'compat_urlparse',
'compat_urlretrieve',
'compat_xml_parse_error',
'compat_urllib_request_urlretrieve',
'compat_urllib_HTTPError',
'compat_xml_etree_ElementTree_Element',
'compat_xml_etree_ElementTree_ParseError',
'compat_xml_etree_register_namespace',
'compat_xpath',
'compat_zip',
'workaround_optparse_bug9161',

3
youtube_dl/downloader/__init__.py
View File

@@ -50,6 +50,9 @@ def _get_suitable_downloader(info_dict, params={}):
ed = get_external_downloader(external_downloader)
if ed.can_download(info_dict):
return ed
# Avoid using unwanted args since external_downloader was rejected
if params.get('external_downloader_args'):
params['external_downloader_args'] = None
protocol = info_dict['protocol']
if protocol.startswith('m3u8') and info_dict.get('is_live'):

28
youtube_dl/downloader/common.py
View File

@@ -88,17 +88,21 @@ class FileDownloader(object):
return '---.-%'
return '%6s' % ('%3.1f%%' % percent)
@staticmethod
def calc_eta(start, now, total, current):
@classmethod
def calc_eta(cls, start_or_rate, now_or_remaining, *args):
if len(args) < 2:
rate, remaining = (start_or_rate, now_or_remaining)
if None in (rate, remaining):
return None
return int(float(remaining) / rate)
start, now = (start_or_rate, now_or_remaining)
total, current = args[:2]
if total is None:
return None
if now is None:
now = time.time()
dif = now - start
if current == 0 or dif < 0.001: # One millisecond
return None
rate = float(current) / dif
return int((float(total) - float(current)) / rate)
rate = cls.calc_speed(start, now, current)
return rate and int((float(total) - float(current)) / rate)
@staticmethod
def format_eta(eta):
@@ -123,6 +127,12 @@ class FileDownloader(object):
def format_retries(retries):
return 'inf' if retries == float('inf') else '%.0f' % retries
@staticmethod
def filesize_or_none(unencoded_filename):
fn = encodeFilename(unencoded_filename)
if os.path.isfile(fn):
return os.path.getsize(fn)
@staticmethod
def best_block_size(elapsed_time, bytes):
new_min = max(bytes / 2.0, 1.0)
@@ -329,6 +339,10 @@ class FileDownloader(object):
def download(self, filename, info_dict):
"""Download to a filename using the info from info_dict
Return True on success and False otherwise
This method filters the `Cookie` header from the info_dict to prevent leaks.
Downloaders have their own way of handling cookies.
See: https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-v8mc-9377-rwjj
"""
nooverwrites_and_exists = (

47
youtube_dl/downloader/dash.py
View File

@@ -1,5 +1,7 @@
from __future__ import unicode_literals
import itertools
from .fragment import FragmentFD
from ..compat import compat_urllib_error
from ..utils import (
@@ -30,26 +32,28 @@ class DashSegmentsFD(FragmentFD):
fragment_retries = self.params.get('fragment_retries', 0)
skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
frag_index = 0
for i, fragment in enumerate(fragments):
frag_index += 1
for frag_index, fragment in enumerate(fragments, 1):
if frag_index <= ctx['fragment_index']:
continue
success = False
# In DASH, the first segment contains necessary headers to
# generate a valid MP4 file, so always abort for the first segment
fatal = i == 0 or not skip_unavailable_fragments
count = 0
while count <= fragment_retries:
fatal = frag_index == 1 or not skip_unavailable_fragments
fragment_url = fragment.get('url')
if not fragment_url:
assert fragment_base_url
fragment_url = urljoin(fragment_base_url, fragment['path'])
headers = info_dict.get('http_headers')
fragment_range = fragment.get('range')
if fragment_range:
headers = headers.copy() if headers else {}
headers['Range'] = 'bytes=%s' % (fragment_range,)
for count in itertools.count():
try:
fragment_url = fragment.get('url')
if not fragment_url:
assert fragment_base_url
fragment_url = urljoin(fragment_base_url, fragment['path'])
success, frag_content = self._download_fragment(ctx, fragment_url, info_dict)
success, frag_content = self._download_fragment(ctx, fragment_url, info_dict, headers)
if not success:
return False
self._append_fragment(ctx, frag_content)
break
except compat_urllib_error.HTTPError as err:
# YouTube may often return 404 HTTP error for a fragment causing the
# whole download to fail. However if the same fragment is immediately
@@ -57,22 +61,21 @@ class DashSegmentsFD(FragmentFD):
# is usually enough) thus allowing to download the whole file successfully.
# To be future-proof we will retry all fragments that fail with any
# HTTP error.
count += 1
if count <= fragment_retries:
self.report_retry_fragment(err, frag_index, count, fragment_retries)
if count < fragment_retries:
self.report_retry_fragment(err, frag_index, count + 1, fragment_retries)
continue
except DownloadError:
# Don't retry fragment if error occurred during HTTP downloading
# itself since it has own retry settings
if not fatal:
self.report_skip_fragment(frag_index)
break
raise
# itself since it has its own retry settings
if fatal:
raise
break
if count > fragment_retries:
if not success:
if not fatal:
self.report_skip_fragment(frag_index)
continue
self.report_error('giving up after %s fragment retries' % fragment_retries)
self.report_error('giving up after %s fragment retries' % count)
return False
self._finish_frag_download(ctx)

241
youtube_dl/downloader/external.py
View File

@@ -1,17 +1,24 @@
from __future__ import unicode_literals
import os.path
import os
import re
import subprocess
import sys
import tempfile
import time
from .common import FileDownloader
from ..compat import (
compat_setenv,
compat_str,
compat_subprocess_Popen,
)
from ..postprocessor.ffmpeg import FFmpegPostProcessor, EXT_TO_OUT_FORMATS
try:
from ..postprocessor.ffmpeg import FFmpegPostProcessor, EXT_TO_OUT_FORMATS
except ImportError:
FFmpegPostProcessor = None
from ..utils import (
cli_option,
cli_valueless_option,
@@ -22,6 +29,9 @@ from ..utils import (
handle_youtubedl_headers,
check_executable,
is_outdated_version,
process_communicate_or_kill,
T,
traverse_obj,
)
@@ -29,6 +39,7 @@ class ExternalFD(FileDownloader):
def real_download(self, filename, info_dict):
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
self._cookies_tempfile = None
try:
started = time.time()
@@ -41,6 +52,13 @@ class ExternalFD(FileDownloader):
# should take place
retval = 0
self.to_screen('[%s] Interrupted by user' % self.get_basename())
finally:
if self._cookies_tempfile and os.path.isfile(self._cookies_tempfile):
try:
os.remove(self._cookies_tempfile)
except OSError:
self.report_warning(
'Unable to delete temporary cookies file "{0}"'.format(self._cookies_tempfile))
if retval == 0:
status = {
@@ -96,6 +114,16 @@ class ExternalFD(FileDownloader):
def _configuration_args(self, default=[]):
return cli_configuration_args(self.params, 'external_downloader_args', default)
def _write_cookies(self):
if not self.ydl.cookiejar.filename:
tmp_cookies = tempfile.NamedTemporaryFile(suffix='.cookies', delete=False)
tmp_cookies.close()
self._cookies_tempfile = tmp_cookies.name
self.to_screen('[download] Writing temporary cookies file to "{0}"'.format(self._cookies_tempfile))
# real_download resets _cookies_tempfile; if it's None, save() will write to cookiejar.filename
self.ydl.cookiejar.save(self._cookies_tempfile, ignore_discard=True, ignore_expires=True)
return self.ydl.cookiejar.filename or self._cookies_tempfile
def _call_downloader(self, tmpfilename, info_dict):
""" Either overwrite this or implement _make_cmd """
cmd = [encodeArgument(a) for a in self._make_cmd(tmpfilename, info_dict)]
@@ -104,18 +132,26 @@ class ExternalFD(FileDownloader):
p = subprocess.Popen(
cmd, stderr=subprocess.PIPE)
_, stderr = p.communicate()
_, stderr = process_communicate_or_kill(p)
if p.returncode != 0:
self.to_stderr(stderr.decode('utf-8', 'replace'))
return p.returncode
@staticmethod
def _header_items(info_dict):
return traverse_obj(
info_dict, ('http_headers', T(dict.items), Ellipsis))
class CurlFD(ExternalFD):
AVAILABLE_OPT = '-V'
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '--location', '-o', tmpfilename]
for key, val in info_dict['http_headers'].items():
cmd = [self.exe, '--location', '-o', tmpfilename, '--compressed']
cookie_header = self.ydl.cookiejar.get_cookie_header(info_dict['url'])
if cookie_header:
cmd += ['--cookie', cookie_header]
for key, val in self._header_items(info_dict):
cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._bool_option('--continue-at', 'continuedl', '-', '0')
cmd += self._valueless_option('--silent', 'noprogress')
@@ -141,7 +177,7 @@ class CurlFD(ExternalFD):
# curl writes the progress to stderr so don't capture it.
p = subprocess.Popen(cmd)
p.communicate()
process_communicate_or_kill(p)
return p.returncode
@@ -150,8 +186,11 @@ class AxelFD(ExternalFD):
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '-o', tmpfilename]
for key, val in info_dict['http_headers'].items():
for key, val in self._header_items(info_dict):
cmd += ['-H', '%s: %s' % (key, val)]
cookie_header = self.ydl.cookiejar.get_cookie_header(info_dict['url'])
if cookie_header:
cmd += ['-H', 'Cookie: {0}'.format(cookie_header), '--max-redirect=0']
cmd += self._configuration_args()
cmd += ['--', info_dict['url']]
return cmd
@@ -161,8 +200,10 @@ class WgetFD(ExternalFD):
AVAILABLE_OPT = '--version'
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies']
for key, val in info_dict['http_headers'].items():
cmd = [self.exe, '-O', tmpfilename, '-nv', '--compression=auto']
if self.ydl.cookiejar.get_cookie_header(info_dict['url']):
cmd += ['--load-cookies', self._write_cookies()]
for key, val in self._header_items(info_dict):
cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._option('--limit-rate', 'ratelimit')
retry = self._option('--tries', 'retries')
@@ -171,7 +212,10 @@ class WgetFD(ExternalFD):
retry[1] = '0'
cmd += retry
cmd += self._option('--bind-address', 'source_address')
cmd += self._option('--proxy', 'proxy')
proxy = self.params.get('proxy')
if proxy:
for var in ('http_proxy', 'https_proxy'):
cmd += ['--execute', '%s=%s' % (var, proxy)]
cmd += self._valueless_option('--no-check-certificate', 'nocheckcertificate')
cmd += self._configuration_args()
cmd += ['--', info_dict['url']]
@@ -181,24 +225,121 @@ class WgetFD(ExternalFD):
class Aria2cFD(ExternalFD):
AVAILABLE_OPT = '-v'
@staticmethod
def _aria2c_filename(fn):
return fn if os.path.isabs(fn) else os.path.join('.', fn)
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '-c']
cmd += self._configuration_args([
'--min-split-size', '1M', '--max-connection-per-server', '4'])
dn = os.path.dirname(tmpfilename)
if dn:
cmd += ['--dir', dn]
cmd += ['--out', os.path.basename(tmpfilename)]
for key, val in info_dict['http_headers'].items():
cmd = [self.exe, '-c',
'--console-log-level=warn', '--summary-interval=0', '--download-result=hide',
'--http-accept-gzip=true', '--file-allocation=none', '-x16', '-j16', '-s16']
if 'fragments' in info_dict:
cmd += ['--allow-overwrite=true', '--allow-piece-length-change=true']
else:
cmd += ['--min-split-size', '1M']
if self.ydl.cookiejar.get_cookie_header(info_dict['url']):
cmd += ['--load-cookies={0}'.format(self._write_cookies())]
for key, val in self._header_items(info_dict):
cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._configuration_args(['--max-connection-per-server', '4'])
cmd += ['--out', os.path.basename(tmpfilename)]
cmd += self._option('--max-overall-download-limit', 'ratelimit')
cmd += self._option('--interface', 'source_address')
cmd += self._option('--all-proxy', 'proxy')
cmd += self._bool_option('--check-certificate', 'nocheckcertificate', 'false', 'true', '=')
cmd += self._bool_option('--remote-time', 'updatetime', 'true', 'false', '=')
cmd += ['--', info_dict['url']]
cmd += self._bool_option('--show-console-readout', 'noprogress', 'false', 'true', '=')
cmd += self._configuration_args()
# aria2c strips out spaces from the beginning/end of filenames and paths.
# We work around this issue by adding a "./" to the beginning of the
# filename and relative path, and adding a "/" at the end of the path.
# See: https://github.com/yt-dlp/yt-dlp/issues/276
# https://github.com/ytdl-org/youtube-dl/issues/20312
# https://github.com/aria2/aria2/issues/1373
dn = os.path.dirname(tmpfilename)
if dn:
cmd += ['--dir', self._aria2c_filename(dn) + os.path.sep]
if 'fragments' not in info_dict:
cmd += ['--out', self._aria2c_filename(os.path.basename(tmpfilename))]
cmd += ['--auto-file-renaming=false']
if 'fragments' in info_dict:
cmd += ['--file-allocation=none', '--uri-selector=inorder']
url_list_file = '%s.frag.urls' % (tmpfilename, )
url_list = []
for frag_index, fragment in enumerate(info_dict['fragments']):
fragment_filename = '%s-Frag%d' % (os.path.basename(tmpfilename), frag_index)
url_list.append('%s\n\tout=%s' % (fragment['url'], self._aria2c_filename(fragment_filename)))
stream, _ = self.sanitize_open(url_list_file, 'wb')
stream.write('\n'.join(url_list).encode())
stream.close()
cmd += ['-i', self._aria2c_filename(url_list_file)]
else:
cmd += ['--', info_dict['url']]
return cmd
class Aria2pFD(ExternalFD):
''' Aria2pFD class
This class support to use aria2p as downloader.
(Aria2p, a command-line tool and Python library to interact with an aria2c daemon process
through JSON-RPC.)
It can help you to get download progress more easily.
To use aria2p as downloader, you need to install aria2c and aria2p, aria2p can download with pip.
Then run aria2c in the background and enable with the --enable-rpc option.
'''
try:
import aria2p
__avail = True
except ImportError:
__avail = False
@classmethod
def available(cls):
return cls.__avail
def _call_downloader(self, tmpfilename, info_dict):
aria2 = self.aria2p.API(
self.aria2p.Client(
host='http://localhost',
port=6800,
secret=''
)
)
options = {
'min-split-size': '1M',
'max-connection-per-server': 4,
'auto-file-renaming': 'false',
}
options['dir'] = os.path.dirname(tmpfilename) or os.path.abspath('.')
options['out'] = os.path.basename(tmpfilename)
if self.ydl.cookiejar.get_cookie_header(info_dict['url']):
options['load-cookies'] = self._write_cookies()
options['header'] = []
for key, val in self._header_items(info_dict):
options['header'].append('{0}: {1}'.format(key, val))
download = aria2.add_uris([info_dict['url']], options)
status = {
'status': 'downloading',
'tmpfilename': tmpfilename,
}
started = time.time()
while download.status in ['active', 'waiting']:
download = aria2.get_download(download.gid)
status.update({
'downloaded_bytes': download.completed_length,
'total_bytes': download.total_length,
'elapsed': time.time() - started,
'eta': download.eta.total_seconds(),
'speed': download.download_speed,
})
self._hook_progress(status)
time.sleep(.5)
return download.status != 'complete'
class HttpieFD(ExternalFD):
@classmethod
def available(cls):
@@ -206,25 +347,34 @@ class HttpieFD(ExternalFD):
def _make_cmd(self, tmpfilename, info_dict):
cmd = ['http', '--download', '--output', tmpfilename, info_dict['url']]
for key, val in info_dict['http_headers'].items():
for key, val in self._header_items(info_dict):
cmd += ['%s:%s' % (key, val)]
# httpie 3.1.0+ removes the Cookie header on redirect, so this should be safe for now. [1]
# If we ever need cookie handling for redirects, we can export the cookiejar into a session. [2]
# 1: https://github.com/httpie/httpie/security/advisories/GHSA-9w4w-cpc8-h2fq
# 2: https://httpie.io/docs/cli/sessions
cookie_header = self.ydl.cookiejar.get_cookie_header(info_dict['url'])
if cookie_header:
cmd += ['Cookie:%s' % cookie_header]
return cmd
class FFmpegFD(ExternalFD):
@classmethod
def supports(cls, info_dict):
return info_dict['protocol'] in ('http', 'https', 'ftp', 'ftps', 'm3u8', 'rtsp', 'rtmp', 'mms')
return info_dict['protocol'] in ('http', 'https', 'ftp', 'ftps', 'm3u8', 'rtsp', 'rtmp', 'mms', 'http_dash_segments')
@classmethod
def available(cls):
return FFmpegPostProcessor().available
# actual availability can only be confirmed for an instance
return bool(FFmpegPostProcessor)
def _call_downloader(self, tmpfilename, info_dict):
url = info_dict['url']
ffpp = FFmpegPostProcessor(downloader=self)
# `downloader` means the parent `YoutubeDL`
ffpp = FFmpegPostProcessor(downloader=self.ydl)
if not ffpp.available:
self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
self.report_error('ffmpeg required for download but no ffmpeg (nor avconv) executable could be found. Please install one.')
return False
ffpp.check_version()
@@ -253,7 +403,15 @@ class FFmpegFD(ExternalFD):
# if end_time:
# args += ['-t', compat_str(end_time - start_time)]
if info_dict['http_headers'] and re.match(r'^https?://', url):
url = info_dict['url']
cookies = self.ydl.cookiejar.get_cookies_for_url(url)
if cookies:
args.extend(['-cookies', ''.join(
'{0}={1}; path={2}; domain={3};\r\n'.format(
cookie.name, cookie.value, cookie.path, cookie.domain)
for cookie in cookies)])
if info_dict.get('http_headers') and re.match(r'^https?://', url):
# Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv:
# [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header.
headers = handle_youtubedl_headers(info_dict['http_headers'])
@@ -333,18 +491,25 @@ class FFmpegFD(ExternalFD):
self._debug_cmd(args)
proc = subprocess.Popen(args, stdin=subprocess.PIPE, env=env)
try:
retval = proc.wait()
except KeyboardInterrupt:
# subprocces.run would send the SIGKILL signal to ffmpeg and the
# mp4 file couldn't be played, but if we ask ffmpeg to quit it
# produces a file that is playable (this is mostly useful for live
# streams). Note that Windows is not affected and produces playable
# files (see https://github.com/ytdl-org/youtube-dl/issues/8300).
if sys.platform != 'win32':
proc.communicate(b'q')
raise
# From [1], a PIPE opened in Popen() should be closed, unless
# .communicate() is called. Avoid leaking any PIPEs by using Popen
# as a context manager (newer Python 3.x and compat)
# Fixes "Resource Warning" in test/test_downloader_external.py
# [1] https://devpress.csdn.net/python/62fde12d7e66823466192e48.html
with compat_subprocess_Popen(args, stdin=subprocess.PIPE, env=env) as proc:
try:
retval = proc.wait()
except BaseException as e:
# subprocess.run would send the SIGKILL signal to ffmpeg and the
# mp4 file couldn't be played, but if we ask ffmpeg to quit it
# produces a file that is playable (this is mostly useful for live
# streams). Note that Windows is not affected and produces playable
# files (see https://github.com/ytdl-org/youtube-dl/issues/8300).
if isinstance(e, KeyboardInterrupt) and sys.platform != 'win32':
process_communicate_or_kill(proc, b'q')
else:
proc.kill()
raise
return retval

46
youtube_dl/downloader/fragment.py
View File

@@ -71,7 +71,7 @@ class FragmentFD(FileDownloader):
@staticmethod
def __do_ytdl_file(ctx):
return not ctx['live'] and not ctx['tmpfilename'] == '-'
return ctx['live'] is not True and ctx['tmpfilename'] != '-'
def _read_ytdl_file(self, ctx):
assert 'ytdl_corrupt' not in ctx
@@ -101,6 +101,13 @@ class FragmentFD(FileDownloader):
'url': frag_url,
'http_headers': headers or info_dict.get('http_headers'),
}
frag_resume_len = 0
if ctx['dl'].params.get('continuedl', True):
frag_resume_len = self.filesize_or_none(
self.temp_name(fragment_filename))
fragment_info_dict['frag_resume_len'] = frag_resume_len
ctx['frag_resume_len'] = frag_resume_len or 0
success = ctx['dl'].download(fragment_filename, fragment_info_dict)
if not success:
return False, None
@@ -124,9 +131,7 @@ class FragmentFD(FileDownloader):
del ctx['fragment_filename_sanitized']
def _prepare_frag_download(self, ctx):
if 'live' not in ctx:
ctx['live'] = False
if not ctx['live']:
if not ctx.setdefault('live', False):
total_frags_str = '%d' % ctx['total_frags']
ad_frags = ctx.get('ad_frags', 0)
if ad_frags:
@@ -136,10 +141,11 @@ class FragmentFD(FileDownloader):
self.to_screen(
'[%s] Total fragments: %s' % (self.FD_NAME, total_frags_str))
self.report_destination(ctx['filename'])
continuedl = self.params.get('continuedl', True)
dl = HttpQuietDownloader(
self.ydl,
{
'continuedl': True,
'continuedl': continuedl,
'quiet': True,
'noprogress': True,
'ratelimit': self.params.get('ratelimit'),
@@ -150,12 +156,11 @@ class FragmentFD(FileDownloader):
)
tmpfilename = self.temp_name(ctx['filename'])
open_mode = 'wb'
resume_len = 0
# Establish possible resume length
if os.path.isfile(encodeFilename(tmpfilename)):
resume_len = self.filesize_or_none(tmpfilename) or 0
if resume_len > 0:
open_mode = 'ab'
resume_len = os.path.getsize(encodeFilename(tmpfilename))
# Should be initialized before ytdl file check
ctx.update({
@@ -164,7 +169,8 @@ class FragmentFD(FileDownloader):
})
if self.__do_ytdl_file(ctx):
if os.path.isfile(encodeFilename(self.ytdl_filename(ctx['filename']))):
ytdl_file_exists = os.path.isfile(encodeFilename(self.ytdl_filename(ctx['filename'])))
if continuedl and ytdl_file_exists:
self._read_ytdl_file(ctx)
is_corrupt = ctx.get('ytdl_corrupt') is True
is_inconsistent = ctx['fragment_index'] > 0 and resume_len == 0
@@ -178,7 +184,12 @@ class FragmentFD(FileDownloader):
if 'ytdl_corrupt' in ctx:
del ctx['ytdl_corrupt']
self._write_ytdl_file(ctx)
else:
if not continuedl:
if ytdl_file_exists:
self._read_ytdl_file(ctx)
ctx['fragment_index'] = resume_len = 0
self._write_ytdl_file(ctx)
assert ctx['fragment_index'] == 0
@@ -209,6 +220,7 @@ class FragmentFD(FileDownloader):
start = time.time()
ctx.update({
'started': start,
'fragment_started': start,
# Amount of fragment's bytes downloaded by the time of the previous
# frag progress hook invocation
'prev_frag_downloaded_bytes': 0,
@@ -218,6 +230,9 @@ class FragmentFD(FileDownloader):
if s['status'] not in ('downloading', 'finished'):
return
if not total_frags and ctx.get('fragment_count'):
state['fragment_count'] = ctx['fragment_count']
time_now = time.time()
state['elapsed'] = time_now - start
frag_total_bytes = s.get('total_bytes') or 0
@@ -232,16 +247,17 @@ class FragmentFD(FileDownloader):
ctx['fragment_index'] = state['fragment_index']
state['downloaded_bytes'] += frag_total_bytes - ctx['prev_frag_downloaded_bytes']
ctx['complete_frags_downloaded_bytes'] = state['downloaded_bytes']
ctx['speed'] = state['speed'] = self.calc_speed(
ctx['fragment_started'], time_now, frag_total_bytes)
ctx['fragment_started'] = time.time()
ctx['prev_frag_downloaded_bytes'] = 0
else:
frag_downloaded_bytes = s['downloaded_bytes']
state['downloaded_bytes'] += frag_downloaded_bytes - ctx['prev_frag_downloaded_bytes']
ctx['speed'] = state['speed'] = self.calc_speed(
ctx['fragment_started'], time_now, frag_downloaded_bytes - ctx['frag_resume_len'])
if not ctx['live']:
state['eta'] = self.calc_eta(
start, time_now, estimated_size - resume_len,
state['downloaded_bytes'] - resume_len)
state['speed'] = s.get('speed') or ctx.get('speed')
ctx['speed'] = state['speed']
state['eta'] = self.calc_eta(state['speed'], estimated_size - state['downloaded_bytes'])
ctx['prev_frag_downloaded_bytes'] = frag_downloaded_bytes
self._hook_progress(state)
@@ -268,7 +284,7 @@ class FragmentFD(FileDownloader):
os.utime(ctx['filename'], (time.time(), filetime))
except Exception:
pass
downloaded_bytes = os.path.getsize(encodeFilename(ctx['filename']))
downloaded_bytes = self.filesize_or_none(ctx['filename']) or 0
self._hook_progress({
'downloaded_bytes': downloaded_bytes,

18
youtube_dl/downloader/http.py
View File

@@ -58,9 +58,9 @@ class HttpFD(FileDownloader):
if self.params.get('continuedl', True):
# Establish possible resume length
if os.path.isfile(encodeFilename(ctx.tmpfilename)):
ctx.resume_len = os.path.getsize(
encodeFilename(ctx.tmpfilename))
ctx.resume_len = info_dict.get('frag_resume_len')
if ctx.resume_len is None:
ctx.resume_len = self.filesize_or_none(ctx.tmpfilename) or 0
ctx.is_resume = ctx.resume_len > 0
@@ -115,9 +115,9 @@ class HttpFD(FileDownloader):
raise RetryDownload(err)
raise err
# When trying to resume, Content-Range HTTP header of response has to be checked
# to match the value of requested Range HTTP header. This is due to a webservers
# to match the value of requested Range HTTP header. This is due to webservers
# that don't support resuming and serve a whole file with no Content-Range
# set in response despite of requested Range (see
# set in response despite requested Range (see
# https://github.com/ytdl-org/youtube-dl/issues/6057#issuecomment-126129799)
if has_range:
content_range = ctx.data.headers.get('Content-Range')
@@ -141,7 +141,8 @@ class HttpFD(FileDownloader):
# Content-Range is either not present or invalid. Assuming remote webserver is
# trying to send the whole file, resume is not possible, so wiping the local file
# and performing entire redownload
self.report_unable_to_resume()
if range_start > 0:
self.report_unable_to_resume()
ctx.resume_len = 0
ctx.open_mode = 'wb'
ctx.data_len = int_or_none(ctx.data.info().get('Content-length', None))
@@ -293,10 +294,7 @@ class HttpFD(FileDownloader):
# Progress message
speed = self.calc_speed(start, now, byte_counter - ctx.resume_len)
if ctx.data_len is None:
eta = None
else:
eta = self.calc_eta(start, time.time(), ctx.data_len - ctx.resume_len, byte_counter - ctx.resume_len)
eta = self.calc_eta(speed, ctx.data_len and (ctx.data_len - byte_counter))
self._hook_progress({
'status': 'downloading',

10
youtube_dl/downloader/rtmp.py
View File

@@ -89,11 +89,13 @@ class RtmpFD(FileDownloader):
self.to_screen('')
cursor_in_new_line = True
self.to_screen('[rtmpdump] ' + line)
finally:
if not cursor_in_new_line:
self.to_screen('')
return proc.wait()
except BaseException: # Including KeyboardInterrupt
proc.kill()
proc.wait()
if not cursor_in_new_line:
self.to_screen('')
return proc.returncode
raise
url = info_dict['url']
player_url = info_dict.get('player_url')

57
youtube_dl/extractor/adn.py
View File

@@ -31,30 +31,34 @@ from ..utils import (
class ADNIE(InfoExtractor):
IE_DESC = 'Anime Digital Network'
_VALID_URL = r'https?://(?:www\.)?animedigitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
_TEST = {
'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
'md5': '0319c99885ff5547565cacb4f3f9348d',
IE_DESC = 'Animation Digital Network'
_VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
_TESTS = [{
'url': 'https://animationdigitalnetwork.fr/video/fruits-basket/9841-episode-1-a-ce-soir',
'md5': '1c9ef066ceb302c86f80c2b371615261',
'info_dict': {
'id': '7778',
'id': '9841',
'ext': 'mp4',
'title': 'Blue Exorcist - Kyôto Saga - Episode 1',
'description': 'md5:2f7b5aa76edbc1a7a92cedcda8a528d5',
'series': 'Blue Exorcist - Kyôto Saga',
'duration': 1467,
'release_date': '20170106',
'title': 'Fruits Basket - Episode 1',
'description': 'md5:14be2f72c3c96809b0ca424b0097d336',
'series': 'Fruits Basket',
'duration': 1437,
'release_date': '20190405',
'comment_count': int,
'average_rating': float,
'season_number': 2,
'episode': 'Début des hostilités',
'season_number': 1,
'episode': 'À ce soir !',
'episode_number': 1,
}
}
},
'skip': 'Only available in region (FR, ...)',
}, {
'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
'only_matching': True,
}]
_NETRC_MACHINE = 'animedigitalnetwork'
_BASE_URL = 'http://animedigitalnetwork.fr'
_API_BASE_URL = 'https://gw.api.animedigitalnetwork.fr/'
_NETRC_MACHINE = 'animationdigitalnetwork'
_BASE = 'animationdigitalnetwork.fr'
_API_BASE_URL = 'https://gw.api.' + _BASE + '/'
_PLAYER_BASE_URL = _API_BASE_URL + 'player/'
_HEADERS = {}
_LOGIN_ERR_MESSAGE = 'Unable to log in'
@@ -82,14 +86,14 @@ class ADNIE(InfoExtractor):
if subtitle_location:
enc_subtitles = self._download_webpage(
subtitle_location, video_id, 'Downloading subtitles data',
fatal=False, headers={'Origin': 'https://animedigitalnetwork.fr'})
fatal=False, headers={'Origin': 'https://' + self._BASE})
if not enc_subtitles:
return None
# http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
# http://animationdigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
dec_subtitles = intlist_to_bytes(aes_cbc_decrypt(
bytes_to_intlist(compat_b64decode(enc_subtitles[24:])),
bytes_to_intlist(binascii.unhexlify(self._K + 'ab9f52f5baae7c72')),
bytes_to_intlist(binascii.unhexlify(self._K + '7fac1178830cfe0c')),
bytes_to_intlist(compat_b64decode(enc_subtitles[:24]))
))
subtitles_json = self._parse_json(
@@ -138,9 +142,9 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
if not username:
return
try:
url = self._API_BASE_URL + 'authentication/login'
access_token = (self._download_json(
self._API_BASE_URL + 'authentication/login', None,
'Logging in', self._LOGIN_ERR_MESSAGE, fatal=False,
url, None, 'Logging in', self._LOGIN_ERR_MESSAGE, fatal=False,
data=urlencode_postdata({
'password': password,
'rememberMe': False,
@@ -153,7 +157,8 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
message = None
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
resp = self._parse_json(
e.cause.read().decode(), None, fatal=False) or {}
self._webpage_read_content(e.cause, url, username),
username, fatal=False) or {}
message = resp.get('message') or resp.get('code')
self.report_warning(message or self._LOGIN_ERR_MESSAGE)
@@ -211,7 +216,9 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
# This usually goes away with a different random pkcs1pad, so retry
continue
error = self._parse_json(e.cause.read(), video_id)
error = self._parse_json(
self._webpage_read_content(e.cause, links_url, video_id),
video_id, fatal=False) or {}
message = error.get('message')
if e.cause.code == 403 and error.get('code') == 'player-bad-geolocation-country':
self.raise_geo_restricted(msg=message)

27
youtube_dl/extractor/aenetworks.py
View File

@@ -8,6 +8,8 @@ from ..utils import (
ExtractorError,
GeoRestrictedError,
int_or_none,
remove_start,
traverse_obj,
update_url_query,
urlencode_postdata,
)
@@ -20,8 +22,8 @@ class AENetworksBaseIE(ThePlatformIE):
(?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com|
fyi\.tv
)/'''
_THEPLATFORM_KEY = 'crazyjava'
_THEPLATFORM_SECRET = 's3cr3t'
_THEPLATFORM_KEY = '43jXaGRQud'
_THEPLATFORM_SECRET = 'S10BPXHMlb'
_DOMAIN_MAP = {
'history.com': ('HISTORY', 'history'),
'aetv.com': ('AETV', 'aetv'),
@@ -33,14 +35,17 @@ class AENetworksBaseIE(ThePlatformIE):
}
def _extract_aen_smil(self, smil_url, video_id, auth=None):
query = {'mbr': 'true'}
query = {
'mbr': 'true',
'formats': 'M3U+none,MPEG-DASH+none,MPEG4,MP3',
}
if auth:
query['auth'] = auth
TP_SMIL_QUERY = [{
'assetTypes': 'high_video_ak',
'switch': 'hls_high_ak'
'switch': 'hls_high_ak',
}, {
'assetTypes': 'high_video_s3'
'assetTypes': 'high_video_s3',
}, {
'assetTypes': 'high_video_s3',
'switch': 'hls_high_fastly',
@@ -75,7 +80,14 @@ class AENetworksBaseIE(ThePlatformIE):
requestor_id, brand = self._DOMAIN_MAP[domain]
result = self._download_json(
'https://feeds.video.aetnd.com/api/v2/%s/videos' % brand,
filter_value, query={'filter[%s]' % filter_key: filter_value})['results'][0]
filter_value, query={'filter[%s]' % filter_key: filter_value})
result = traverse_obj(
result, ('results',
lambda k, v: k == 0 and v[filter_key] == filter_value),
get_all=False)
if not result:
raise ExtractorError('Show not found in A&E feed (too new?)', expected=True,
video_id=remove_start(filter_value, '/'))
title = result['title']
video_id = result['id']
media_url = result['publicUrl']
@@ -126,7 +138,7 @@ class AENetworksIE(AENetworksBaseIE):
'skip_download': True,
},
'add_ie': ['ThePlatform'],
'skip': 'This video is only available for users of participating TV providers.',
'skip': 'Geo-restricted - This content is not available in your location.'
}, {
'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1',
'info_dict': {
@@ -143,6 +155,7 @@ class AENetworksIE(AENetworksBaseIE):
'skip_download': True,
},
'add_ie': ['ThePlatform'],
'skip': 'This video is only available for users of participating TV providers.',
}, {
'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
'only_matching': True

2
youtube_dl/extractor/aliexpress.py
View File

@@ -18,7 +18,7 @@ class AliExpressLiveIE(InfoExtractor):
'id': '2800002704436634',
'ext': 'mp4',
'title': 'CASIMA7.22',
'thumbnail': r're:http://.*\.jpg',
'thumbnail': r're:https?://.*\.jpg',
'uploader': 'CASIMA Official Store',
'timestamp': 1500717600,
'upload_date': '20170722',

89
youtube_dl/extractor/alsace20tv.py Normal file
View File

@@ -0,0 +1,89 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
clean_html,
dict_get,
get_element_by_class,
int_or_none,
unified_strdate,
url_or_none,
)
class Alsace20TVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?alsace20\.tv/(?:[\w-]+/)+[\w-]+-(?P<id>[\w]+)'
_TESTS = [{
'url': 'https://www.alsace20.tv/VOD/Actu/JT/Votre-JT-jeudi-3-fevrier-lyNHCXpYJh.html',
# 'md5': 'd91851bf9af73c0ad9b2cdf76c127fbb',
'info_dict': {
'id': 'lyNHCXpYJh',
'ext': 'mp4',
'description': 'md5:fc0bc4a0692d3d2dba4524053de4c7b7',
'title': 'Votre JT du jeudi 3 février',
'upload_date': '20220203',
'thumbnail': r're:https?://.+\.jpg',
'duration': 1073,
'view_count': int,
},
'params': {
'format': 'bestvideo',
},
}]
def _extract_video(self, video_id, url=None):
info = self._download_json(
'https://www.alsace20.tv/visionneuse/visio_v9_js.php?key=%s&habillage=0&mode=html' % (video_id, ),
video_id) or {}
title = info['titre']
formats = []
for res, fmt_url in (info.get('files') or {}).items():
formats.extend(
self._extract_smil_formats(fmt_url, video_id, fatal=False)
if '/smil:_' in fmt_url
else self._extract_mpd_formats(fmt_url, video_id, mpd_id=res, fatal=False))
self._sort_formats(formats)
webpage = (url and self._download_webpage(url, video_id, fatal=False)) or ''
thumbnail = url_or_none(dict_get(info, ('image', 'preview', )) or self._og_search_thumbnail(webpage))
upload_date = self._search_regex(r'/(\d{6})_', thumbnail, 'upload_date', default=None)
upload_date = unified_strdate('20%s-%s-%s' % (upload_date[:2], upload_date[2:4], upload_date[4:])) if upload_date else None
return {
'id': video_id,
'title': title,
'formats': formats,
'description': clean_html(get_element_by_class('wysiwyg', webpage)),
'upload_date': upload_date,
'thumbnail': thumbnail,
'duration': int_or_none(self._og_search_property('video:duration', webpage) if webpage else None),
'view_count': int_or_none(info.get('nb_vues')),
}
def _real_extract(self, url):
video_id = self._match_id(url)
return self._extract_video(video_id, url)
class Alsace20TVEmbedIE(Alsace20TVIE):
_VALID_URL = r'https?://(?:www\.)?alsace20\.tv/emb/(?P<id>[\w]+)'
_TESTS = [{
'url': 'https://www.alsace20.tv/emb/lyNHCXpYJh',
# 'md5': 'd91851bf9af73c0ad9b2cdf76c127fbb',
'info_dict': {
'id': 'lyNHCXpYJh',
'ext': 'mp4',
'title': 'Votre JT du jeudi 3 février',
'upload_date': '20220203',
'thumbnail': r're:https?://.+\.jpg',
'view_count': int,
},
'params': {
'format': 'bestvideo',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
return self._extract_video(video_id)

115
youtube_dl/extractor/americastestkitchen.py
View File

@@ -15,7 +15,7 @@ from ..utils import (
class AmericasTestKitchenIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:americastestkitchen|cooks(?:country|illustrated))\.com/(?P<resource_type>episode|videos)/(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?(?:americastestkitchen|cooks(?:country|illustrated))\.com/(?:cooks(?:country|illustrated)/)?(?P<resource_type>episode|videos)/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.americastestkitchen.com/episode/582-weeknight-japanese-suppers',
'md5': 'b861c3e365ac38ad319cfd509c30577f',
@@ -23,15 +23,20 @@ class AmericasTestKitchenIE(InfoExtractor):
'id': '5b400b9ee338f922cb06450c',
'title': 'Japanese Suppers',
'ext': 'mp4',
'display_id': 'weeknight-japanese-suppers',
'description': 'md5:64e606bfee910627efc4b5f050de92b3',
'thumbnail': r're:^https?://',
'timestamp': 1523318400,
'upload_date': '20180410',
'release_date': '20180410',
'timestamp': 1523304000,
'upload_date': '20180409',
'release_date': '20180409',
'series': "America's Test Kitchen",
'season': 'Season 18',
'season_number': 18,
'episode': 'Japanese Suppers',
'episode_number': 15,
'duration': 1376,
'thumbnail': r're:^https?://',
'average_rating': 0,
'view_count': int,
},
'params': {
'skip_download': True,
@@ -44,15 +49,20 @@ class AmericasTestKitchenIE(InfoExtractor):
'id': '5fbe8c61bda2010001c6763b',
'title': 'Simple Chicken Dinner',
'ext': 'mp4',
'display_id': 'atktv_2103_simple-chicken-dinner_full-episode_web-mp4',
'description': 'md5:eb68737cc2fd4c26ca7db30139d109e7',
'thumbnail': r're:^https?://',
'timestamp': 1610755200,
'upload_date': '20210116',
'release_date': '20210116',
'timestamp': 1610737200,
'upload_date': '20210115',
'release_date': '20210115',
'series': "America's Test Kitchen",
'season': 'Season 21',
'season_number': 21,
'episode': 'Simple Chicken Dinner',
'episode_number': 3,
'duration': 1397,
'thumbnail': r're:^https?://',
'view_count': int,
'average_rating': 0,
},
'params': {
'skip_download': True,
@@ -60,6 +70,12 @@ class AmericasTestKitchenIE(InfoExtractor):
}, {
'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon',
'only_matching': True,
}, {
'url': 'https://www.americastestkitchen.com/cookscountry/episode/564-when-only-chocolate-will-do',
'only_matching': True,
}, {
'url': 'https://www.americastestkitchen.com/cooksillustrated/videos/4478-beef-wellington',
'only_matching': True,
}, {
'url': 'https://www.cookscountry.com/episode/564-when-only-chocolate-will-do',
'only_matching': True,
@@ -94,7 +110,7 @@ class AmericasTestKitchenIE(InfoExtractor):
class AmericasTestKitchenSeasonIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?P<show>americastestkitchen|cookscountry)\.com/episodes/browse/season_(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?(?P<show>americastestkitchen|(?P<cooks>cooks(?:country|illustrated)))\.com(?:(?:/(?P<show2>cooks(?:country|illustrated)))?(?:/?$|(?<!ated)(?<!ated\.com)/episodes/browse/season_(?P<season>\d+)))'
_TESTS = [{
# ATK Season
'url': 'https://www.americastestkitchen.com/episodes/browse/season_1',
@@ -105,48 +121,93 @@ class AmericasTestKitchenSeasonIE(InfoExtractor):
'playlist_count': 13,
}, {
# Cooks Country Season
'url': 'https://www.cookscountry.com/episodes/browse/season_12',
'url': 'https://www.americastestkitchen.com/cookscountry/episodes/browse/season_12',
'info_dict': {
'id': 'season_12',
'title': 'Season 12',
},
'playlist_count': 13,
}, {
# America's Test Kitchen Series
'url': 'https://www.americastestkitchen.com/',
'info_dict': {
'id': 'americastestkitchen',
'title': 'America\'s Test Kitchen',
},
'playlist_count': 558,
}, {
# Cooks Country Series
'url': 'https://www.americastestkitchen.com/cookscountry',
'info_dict': {
'id': 'cookscountry',
'title': 'Cook\'s Country',
},
'playlist_count': 199,
}, {
'url': 'https://www.americastestkitchen.com/cookscountry/',
'only_matching': True,
}, {
'url': 'https://www.cookscountry.com/episodes/browse/season_12',
'only_matching': True,
}, {
'url': 'https://www.cookscountry.com',
'only_matching': True,
}, {
'url': 'https://www.americastestkitchen.com/cooksillustrated/',
'only_matching': True,
}, {
'url': 'https://www.cooksillustrated.com',
'only_matching': True,
}]
def _real_extract(self, url):
show_name, season_number = re.match(self._VALID_URL, url).groups()
season_number = int(season_number)
match = re.match(self._VALID_URL, url).groupdict()
show = match.get('show2')
show_path = ('/' + show) if show else ''
show = show or match['show']
season_number = int_or_none(match.get('season'))
slug = 'atk' if show_name == 'americastestkitchen' else 'cco'
slug, title = {
'americastestkitchen': ('atk', 'America\'s Test Kitchen'),
'cookscountry': ('cco', 'Cook\'s Country'),
'cooksillustrated': ('cio', 'Cook\'s Illustrated'),
}[show]
season = 'Season %d' % season_number
facet_filters = [
'search_document_klass:episode',
'search_show_slug:' + slug,
]
if season_number:
playlist_id = 'season_%d' % season_number
playlist_title = 'Season %d' % season_number
facet_filters.append('search_season_list:' + playlist_title)
else:
playlist_id = show
playlist_title = title
season_search = self._download_json(
'https://y1fnzxui30-dsn.algolia.net/1/indexes/everest_search_%s_season_desc_production' % slug,
season, headers={
'Origin': 'https://www.%s.com' % show_name,
playlist_id, headers={
'Origin': 'https://www.americastestkitchen.com',
'X-Algolia-API-Key': '8d504d0099ed27c1b73708d22871d805',
'X-Algolia-Application-Id': 'Y1FNZXUI30',
}, query={
'facetFilters': json.dumps([
'search_season_list:' + season,
'search_document_klass:episode',
'search_show_slug:' + slug,
]),
'attributesToRetrieve': 'description,search_%s_episode_number,search_document_date,search_url,title' % slug,
'facetFilters': json.dumps(facet_filters),
'attributesToRetrieve': 'description,search_%s_episode_number,search_document_date,search_url,title,search_atk_episode_season' % slug,
'attributesToHighlight': '',
'hitsPerPage': 1000,
})
def entries():
for episode in (season_search.get('hits') or []):
search_url = episode.get('search_url')
search_url = episode.get('search_url') # always formatted like '/episode/123-title-of-episode'
if not search_url:
continue
yield {
'_type': 'url',
'url': 'https://www.%s.com%s' % (show_name, search_url),
'id': try_get(episode, lambda e: e['objectID'].split('_')[-1]),
'url': 'https://www.americastestkitchen.com%s%s' % (show_path, search_url),
'id': try_get(episode, lambda e: e['objectID'].rsplit('_', 1)[-1]),
'title': episode.get('title'),
'description': episode.get('description'),
'timestamp': unified_timestamp(episode.get('search_document_date')),
@@ -156,4 +217,4 @@ class AmericasTestKitchenSeasonIE(InfoExtractor):
}
return self.playlist_result(
entries(), 'season_%d' % season_number, season)
entries(), playlist_id, playlist_title)

59
youtube_dl/extractor/bigo.py Normal file
View File

@@ -0,0 +1,59 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import ExtractorError, urlencode_postdata
class BigoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bigo\.tv/(?:[a-z]{2,}/)?(?P<id>[^/]+)'
_TESTS = [{
'url': 'https://www.bigo.tv/ja/221338632',
'info_dict': {
'id': '6576287577575737440',
'title': '土よ〜💁‍♂️ 休憩室/REST room',
'thumbnail': r're:https?://.+',
'uploader': '✨Shin💫',
'uploader_id': '221338632',
'is_live': True,
},
'skip': 'livestream',
}, {
'url': 'https://www.bigo.tv/th/Tarlerm1304',
'only_matching': True,
}, {
'url': 'https://bigo.tv/115976881',
'only_matching': True,
}]
def _real_extract(self, url):
user_id = self._match_id(url)
info_raw = self._download_json(
'https://bigo.tv/studio/getInternalStudioInfo',
user_id, data=urlencode_postdata({'siteId': user_id}))
if not isinstance(info_raw, dict):
raise ExtractorError('Received invalid JSON data')
if info_raw.get('code'):
raise ExtractorError(
'Bigo says: %s (code %s)' % (info_raw.get('msg'), info_raw.get('code')), expected=True)
info = info_raw.get('data') or {}
if not info.get('alive'):
raise ExtractorError('This user is offline.', expected=True)
return {
'id': info.get('roomId') or user_id,
'title': info.get('roomTopic') or info.get('nick_name') or user_id,
'formats': [{
'url': info.get('hls_src'),
'ext': 'mp4',
'protocol': 'm3u8',
}],
'thumbnail': info.get('snapshot'),
'uploader': info.get('nick_name'),
'uploader_id': user_id,
'is_live': True,
}

5
youtube_dl/extractor/bilibili.py
View File

@@ -369,6 +369,11 @@ class BilibiliAudioIE(BilibiliAudioBaseIE):
'filesize': int_or_none(play_data.get('size')),
}]
for a_format in formats:
a_format.setdefault('http_headers', {}).update({
'Referer': url,
})
song = self._call_api('song/info', au_id)
title = song['title']
statistic = song.get('statistic') or {}

173
youtube_dl/extractor/blerp.py Normal file
View File

@@ -0,0 +1,173 @@
# coding: utf-8
from __future__ import unicode_literals
import json
from ..utils import (
strip_or_none,
traverse_obj,
)
from .common import InfoExtractor
class BlerpIE(InfoExtractor):
IE_NAME = 'blerp'
_VALID_URL = r'https?://(?:www\.)?blerp\.com/soundbites/(?P<id>[0-9a-zA-Z]+)'
_TESTS = [{
'url': 'https://blerp.com/soundbites/6320fe8745636cb4dd677a5a',
'info_dict': {
'id': '6320fe8745636cb4dd677a5a',
'title': 'Samsung Galaxy S8 Over the Horizon Ringtone 2016',
'uploader': 'luminousaj',
'uploader_id': '5fb81e51aa66ae000c395478',
'ext': 'mp3',
'tags': ['samsung', 'galaxy', 's8', 'over the horizon', '2016', 'ringtone'],
}
}, {
'url': 'https://blerp.com/soundbites/5bc94ef4796001000498429f',
'info_dict': {
'id': '5bc94ef4796001000498429f',
'title': 'Yee',
'uploader': '179617322678353920',
'uploader_id': '5ba99cf71386730004552c42',
'ext': 'mp3',
'tags': ['YEE', 'YEET', 'wo ha haah catchy tune yee', 'yee']
}
}]
_GRAPHQL_OPERATIONNAME = "webBitePageGetBite"
_GRAPHQL_QUERY = (
'''query webBitePageGetBite($_id: MongoID!) {
web {
biteById(_id: $_id) {
...bitePageFrag
__typename
}
__typename
}
}
fragment bitePageFrag on Bite {
_id
title
userKeywords
keywords
color
visibility
isPremium
owned
price
extraReview
isAudioExists
image {
filename
original {
url
__typename
}
__typename
}
userReactions {
_id
reactions
createdAt
__typename
}
topReactions
totalSaveCount
saved
blerpLibraryType
license
licenseMetaData
playCount
totalShareCount
totalFavoriteCount
totalAddedToBoardCount
userCategory
userAudioQuality
audioCreationState
transcription
userTranscription
description
createdAt
updatedAt
author
listingType
ownerObject {
_id
username
profileImage {
filename
original {
url
__typename
}
__typename
}
__typename
}
transcription
favorited
visibility
isCurated
sourceUrl
audienceRating
strictAudienceRating
ownerId
reportObject {
reportedContentStatus
__typename
}
giphy {
mp4
gif
__typename
}
audio {
filename
original {
url
__typename
}
mp3 {
url
__typename
}
__typename
}
__typename
}
''')
def _real_extract(self, url):
audio_id = self._match_id(url)
data = {
'operationName': self._GRAPHQL_OPERATIONNAME,
'query': self._GRAPHQL_QUERY,
'variables': {
'_id': audio_id
}
}
headers = {
'Content-Type': 'application/json'
}
json_result = self._download_json('https://api.blerp.com/graphql',
audio_id, data=json.dumps(data).encode('utf-8'), headers=headers)
bite_json = json_result['data']['web']['biteById']
info_dict = {
'id': bite_json['_id'],
'url': bite_json['audio']['mp3']['url'],
'title': bite_json['title'],
'uploader': traverse_obj(bite_json, ('ownerObject', 'username'), expected_type=strip_or_none),
'uploader_id': traverse_obj(bite_json, ('ownerObject', '_id'), expected_type=strip_or_none),
'ext': 'mp3',
'tags': list(filter(None, map(strip_or_none, (traverse_obj(bite_json, 'userKeywords', expected_type=list) or []))) or None)
}
return info_dict

18
youtube_dl/extractor/bongacams.py
View File

@@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
import re
@@ -12,13 +13,28 @@ from ..utils import (
class BongaCamsIE(InfoExtractor):
_VALID_URL = r'https?://(?P<host>(?:[^/]+\.)?bongacams\d*\.com)/(?P<id>[^/?&#]+)'
_VALID_URL = r'https?://(?P<host>(?:[^/]+\.)?bongacams\d*\.(?:com|net))/(?P<id>[^/?&#]+)'
_TESTS = [{
'url': 'https://de.bongacams.com/azumi-8',
'only_matching': True,
}, {
'url': 'https://cn.bongacams.com/azumi-8',
'only_matching': True,
}, {
'url': 'https://de.bongacams.net/claireashton',
'info_dict': {
'id': 'claireashton',
'ext': 'mp4',
'title': r're:ClaireAshton \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
'age_limit': 18,
'uploader_id': 'ClaireAshton',
'uploader': 'ClaireAshton',
'like_count': int,
'is_live': True,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):

79
youtube_dl/extractor/caffeine.py Normal file
View File

@@ -0,0 +1,79 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
determine_ext,
int_or_none,
merge_dicts,
parse_iso8601,
T,
traverse_obj,
txt_or_none,
urljoin,
)
class CaffeineTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?caffeine\.tv/[^/]+/video/(?P<id>[0-9a-f-]+)'
_TESTS = [{
'url': 'https://www.caffeine.tv/TsuSurf/video/cffc0a00-e73f-11ec-8080-80017d29f26e',
'info_dict': {
'id': 'cffc0a00-e73f-11ec-8080-80017d29f26e',
'ext': 'mp4',
'title': 'GOOOOD MORNINNNNN #highlights',
'timestamp': 1654702180,
'upload_date': '20220608',
'uploader': 'TsuSurf',
'duration': 3145,
'age_limit': 17,
},
'params': {
'format': 'bestvideo',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
json_data = self._download_json(
'https://api.caffeine.tv/social/public/activity/' + video_id,
video_id)
broadcast_info = traverse_obj(json_data, ('broadcast_info', T(dict))) or {}
title = broadcast_info['broadcast_title']
video_url = broadcast_info['video_url']
ext = determine_ext(video_url)
if ext == 'm3u8':
formats = self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8',
fatal=False)
else:
formats = [{'url': video_url}]
self._sort_formats(formats)
return merge_dicts({
'id': video_id,
'title': title,
'formats': formats,
}, traverse_obj(json_data, {
'uploader': ((None, 'user'), 'username'),
}, get_all=False), traverse_obj(json_data, {
'like_count': ('like_count', T(int_or_none)),
'view_count': ('view_count', T(int_or_none)),
'comment_count': ('comment_count', T(int_or_none)),
'tags': ('tags', Ellipsis, T(txt_or_none)),
'is_live': 'is_live',
'uploader': ('user', 'name'),
}), traverse_obj(broadcast_info, {
'duration': ('content_duration', T(int_or_none)),
'timestamp': ('broadcast_start_time', T(parse_iso8601)),
'thumbnail': ('preview_image_path', T(lambda u: urljoin(url, u))),
'age_limit': ('content_rating', T(lambda r: r and {
# assume Apple Store ratings [1]
# 1. https://en.wikipedia.org/wiki/Mobile_software_content_rating_system
'FOUR_PLUS': 0,
'NINE_PLUS': 9,
'TWELVE_PLUS': 12,
'SEVENTEEN_PLUS': 17,
}.get(r, 17))),
}))

74
youtube_dl/extractor/callin.py Normal file
View File

@@ -0,0 +1,74 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
traverse_obj,
try_get,
)
class CallinIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?callin\.com/episode/(?:[^/#?-]+-)*(?P<id>[^/#?-]+)'
_TESTS = [{
'url': 'https://www.callin.com/episode/fcc-commissioner-brendan-carr-on-elons-PrumRdSQJW',
'md5': '14ede27ee2c957b7e4db93140fc0745c',
'info_dict': {
'id': 'PrumRdSQJW',
'ext': 'mp4',
'title': 'FCC Commissioner Brendan Carr on Elon’s Starlink',
'description': 'Or, why the government doesn’t like SpaceX',
'channel': 'The Pull Request',
'channel_url': 'https://callin.com/show/the-pull-request-ucnDJmEKAa',
}
}, {
'url': 'https://www.callin.com/episode/episode-81-elites-melt-down-over-student-debt-lzxMidUnjA',
'md5': '16f704ddbf82a27e3930533b12062f07',
'info_dict': {
'id': 'lzxMidUnjA',
'ext': 'mp4',
'title': 'Episode 81- Elites MELT DOWN over Student Debt Victory? Rumble in NYC?',
'description': 'Let’s talk todays episode about the primary election shake up in NYC and the elites melting down over student debt cancelation.',
'channel': 'The DEBRIEF With Briahna Joy Gray',
'channel_url': 'https://callin.com/show/the-debrief-with-briahna-joy-gray-siiFDzGegm',
}
}]
def _search_nextjs_data(self, webpage, video_id, transform_source=None, fatal=True, **kw):
return self._parse_json(
self._search_regex(
r'(?s)<script[^>]+id=[\'"]__NEXT_DATA__[\'"][^>]*>([^<]+)</script>',
webpage, 'next.js data', fatal=fatal, **kw),
video_id, transform_source=transform_source, fatal=fatal)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
next_data = self._search_nextjs_data(webpage, video_id)
episode = traverse_obj(next_data, ('props', 'pageProps', 'episode'), expected_type=dict)
if not episode:
raise ExtractorError('Failed to find episode data')
title = episode.get('title') or self._og_search_title(webpage)
description = episode.get('description') or self._og_search_description(webpage)
formats = []
formats.extend(self._extract_m3u8_formats(
episode.get('m3u8'), video_id, 'mp4',
entry_protocol='m3u8_native', fatal=False))
self._sort_formats(formats)
channel = try_get(episode, lambda x: x['show']['title'], compat_str)
channel_url = try_get(episode, lambda x: x['show']['linkObj']['resourceUrl'], compat_str)
return {
'id': video_id,
'title': title,
'description': description,
'formats': formats,
'channel': channel,
'channel_url': channel_url,
}

34
youtube_dl/extractor/cammodels.py
View File

@@ -3,7 +3,6 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
url_or_none,
)
@@ -20,32 +19,11 @@ class CamModelsIE(InfoExtractor):
def _real_extract(self, url):
user_id = self._match_id(url)
webpage = self._download_webpage(
url, user_id, headers=self.geo_verification_headers())
manifest_root = self._html_search_regex(
r'manifestUrlRoot=([^&\']+)', webpage, 'manifest', default=None)
if not manifest_root:
ERRORS = (
("I'm offline, but let's stay connected", 'This user is currently offline'),
('in a private show', 'This user is in a private show'),
('is currently performing LIVE', 'This model is currently performing live'),
)
for pattern, message in ERRORS:
if pattern in webpage:
error = message
expected = True
break
else:
error = 'Unable to find manifest URL root'
expected = False
raise ExtractorError(error, expected=expected)
manifest = self._download_json(
'%s%s.json' % (manifest_root, user_id), user_id)
'https://manifest-server.naiadsystems.com/live/s:%s.json' % user_id, user_id)
formats = []
thumbnails = []
for format_id, format_dict in manifest['formats'].items():
if not isinstance(format_dict, dict):
continue
@@ -85,6 +63,13 @@ class CamModelsIE(InfoExtractor):
'preference': -1,
})
else:
if format_id == 'jpeg':
thumbnails.append({
'url': f['url'],
'width': f['width'],
'height': f['height'],
'format_id': f['format_id'],
})
continue
formats.append(f)
self._sort_formats(formats)
@@ -92,6 +77,7 @@ class CamModelsIE(InfoExtractor):
return {
'id': user_id,
'title': self._live_title(user_id),
'thumbnails': thumbnails,
'is_live': True,
'formats': formats,
'age_limit': 18

178
youtube_dl/extractor/ceskatelevize.py
View File

@@ -12,35 +12,21 @@ from ..utils import (
ExtractorError,
float_or_none,
sanitized_Request,
unescapeHTML,
update_url_query,
str_or_none,
traverse_obj,
urlencode_postdata,
USER_AGENTS,
)
class CeskaTelevizeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/ivysilani/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
_VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/(?:ivysilani|porady|zive)/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
_TESTS = [{
'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
'info_dict': {
'id': '61924494877246241',
'ext': 'mp4',
'title': 'Hyde Park Civilizace: Život v Grónsku',
'description': 'md5:3fec8f6bb497be5cdb0c9e8781076626',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 3350,
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://www.ceskatelevize.cz/ivysilani/10441294653-hyde-park-civilizace/215411058090502/bonus/20641-bonus-01-en',
'info_dict': {
'id': '61924494877028507',
'ext': 'mp4',
'title': 'Hyde Park Civilizace: Bonus 01 - En',
'title': 'Bonus 01 - En - Hyde Park Civilizace',
'description': 'English Subtittles',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 81.3,
@@ -51,31 +37,111 @@ class CeskaTelevizeIE(InfoExtractor):
},
}, {
# live stream
'url': 'http://www.ceskatelevize.cz/ivysilani/zive/ct4/',
'url': 'http://www.ceskatelevize.cz/zive/ct1/',
'info_dict': {
'id': 402,
'id': '102',
'ext': 'mp4',
'title': r're:^ČT Sport \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'title': r'ČT1 - živé vysílání online',
'description': 'Sledujte živé vysílání kanálu ČT1 online. Vybírat si můžete i z dalších kanálů České televize na kterémkoli z vašich zařízení.',
'is_live': True,
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': 'Georestricted to Czech Republic',
}, {
# another
'url': 'http://www.ceskatelevize.cz/ivysilani/zive/ct4/',
'only_matching': True,
'info_dict': {
'id': 402,
'ext': 'mp4',
'title': r're:^ČT Sport \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'is_live': True,
},
# 'skip': 'Georestricted to Czech Republic',
}, {
'url': 'http://www.ceskatelevize.cz/ivysilani/embed/iFramePlayer.php?hash=d6a3e1370d2e4fa76296b90bad4dfc19673b641e&IDEC=217 562 22150/0004&channelID=1&width=100%25',
'only_matching': True,
}, {
# video with 18+ caution trailer
'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
'info_dict': {
'id': '215562210900007-bogotart',
'title': 'Bogotart - Queer',
'description': 'Hlavní město Kolumbie v doprovodu queer umělců. Vroucí svět plný vášně, sebevědomí, ale i násilí a bolesti',
},
'playlist': [{
'info_dict': {
'id': '61924494877311053',
'ext': 'mp4',
'title': 'Bogotart - Queer (Varování 18+)',
'duration': 11.9,
},
}, {
'info_dict': {
'id': '61924494877068022',
'ext': 'mp4',
'title': 'Bogotart - Queer (Queer)',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 1558.3,
},
}],
'params': {
# m3u8 download
'skip_download': True,
},
}, {
# iframe embed
'url': 'http://www.ceskatelevize.cz/porady/10614999031-neviditelni/21251212048/',
'only_matching': True,
}]
def _search_nextjs_data(self, webpage, video_id, **kw):
return self._parse_json(
self._search_regex(
r'(?s)<script[^>]+id=[\'"]__NEXT_DATA__[\'"][^>]*>([^<]+)</script>',
webpage, 'next.js data', **kw),
video_id, **kw)
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage, urlh = self._download_webpage_handle(url, playlist_id)
parsed_url = compat_urllib_parse_urlparse(urlh.geturl())
site_name = self._og_search_property('site_name', webpage, fatal=False, default='Česká televize')
playlist_title = self._og_search_title(webpage, default=None)
if site_name and playlist_title:
playlist_title = re.split(r'\s*[—|]\s*%s' % (site_name, ), playlist_title, 1)[0]
playlist_description = self._og_search_description(webpage, default=None)
if playlist_description:
playlist_description = playlist_description.replace('\xa0', ' ')
webpage = self._download_webpage(url, playlist_id)
type_ = 'IDEC'
if re.search(r'(^/porady|/zive)/', parsed_url.path):
next_data = self._search_nextjs_data(webpage, playlist_id)
if '/zive/' in parsed_url.path:
idec = traverse_obj(next_data, ('props', 'pageProps', 'data', 'liveBroadcast', 'current', 'idec'), get_all=False)
else:
idec = traverse_obj(next_data, ('props', 'pageProps', 'data', ('show', 'mediaMeta'), 'idec'), get_all=False)
if not idec:
idec = traverse_obj(next_data, ('props', 'pageProps', 'data', 'videobonusDetail', 'bonusId'), get_all=False)
if idec:
type_ = 'bonus'
if not idec:
raise ExtractorError('Failed to find IDEC id')
iframe_hash = self._download_webpage(
'https://www.ceskatelevize.cz/v-api/iframe-hash/',
playlist_id, note='Getting IFRAME hash')
query = {'hash': iframe_hash, 'origin': 'iVysilani', 'autoStart': 'true', type_: idec, }
webpage = self._download_webpage(
'https://www.ceskatelevize.cz/ivysilani/embed/iFramePlayer.php',
playlist_id, note='Downloading player', query=query)
NOT_AVAILABLE_STRING = 'This content is not available at your territory due to limited copyright.'
if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
self.raise_geo_restricted(NOT_AVAILABLE_STRING)
if any(not_found in webpage for not_found in ('Neplatný parametr pro videopřehrávač', 'IDEC nebyl nalezen', )):
raise ExtractorError('no video with IDEC available', video_id=idec, expected=True)
type_ = None
episode_id = None
@@ -100,7 +166,7 @@ class CeskaTelevizeIE(InfoExtractor):
data = {
'playlist[0][type]': type_,
'playlist[0][id]': episode_id,
'requestUrl': compat_urllib_parse_urlparse(url).path,
'requestUrl': parsed_url.path,
'requestSource': 'iVysilani',
}
@@ -108,7 +174,7 @@ class CeskaTelevizeIE(InfoExtractor):
for user_agent in (None, USER_AGENTS['Safari']):
req = sanitized_Request(
'https://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
'https://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist/',
data=urlencode_postdata(data))
req.add_header('Content-type', 'application/x-www-form-urlencoded')
@@ -130,9 +196,6 @@ class CeskaTelevizeIE(InfoExtractor):
req = sanitized_Request(compat_urllib_parse_unquote(playlist_url))
req.add_header('Referer', url)
playlist_title = self._og_search_title(webpage, default=None)
playlist_description = self._og_search_description(webpage, default=None)
playlist = self._download_json(req, playlist_id, fatal=False)
if not playlist:
continue
@@ -167,7 +230,7 @@ class CeskaTelevizeIE(InfoExtractor):
entries[num]['formats'].extend(formats)
continue
item_id = item.get('id') or item['assetId']
item_id = str_or_none(item.get('id') or item['assetId'])
title = item['title']
duration = float_or_none(item.get('duration'))
@@ -181,8 +244,6 @@ class CeskaTelevizeIE(InfoExtractor):
if playlist_len == 1:
final_title = playlist_title or title
if is_live:
final_title = self._live_title(final_title)
else:
final_title = '%s (%s)' % (playlist_title, title)
@@ -200,6 +261,8 @@ class CeskaTelevizeIE(InfoExtractor):
for e in entries:
self._sort_formats(e['formats'])
if len(entries) == 1:
return entries[0]
return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
def _get_subtitles(self, episode_id, subs):
@@ -236,54 +299,3 @@ class CeskaTelevizeIE(InfoExtractor):
yield line
return '\r\n'.join(_fix_subtitle(subtitles))
class CeskaTelevizePoradyIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/porady/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
_TESTS = [{
# video with 18+ caution trailer
'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
'info_dict': {
'id': '215562210900007-bogotart',
'title': 'Queer: Bogotart',
'description': 'Alternativní průvodce současným queer světem',
},
'playlist': [{
'info_dict': {
'id': '61924494876844842',
'ext': 'mp4',
'title': 'Queer: Bogotart (Varování 18+)',
'duration': 10.2,
},
}, {
'info_dict': {
'id': '61924494877068022',
'ext': 'mp4',
'title': 'Queer: Bogotart (Queer)',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 1558.3,
},
}],
'params': {
# m3u8 download
'skip_download': True,
},
}, {
# iframe embed
'url': 'http://www.ceskatelevize.cz/porady/10614999031-neviditelni/21251212048/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
data_url = update_url_query(unescapeHTML(self._search_regex(
(r'<span[^>]*\bdata-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?ceskatelevize\.cz/ivysilani/embed/iFramePlayer\.php.*?)\1'),
webpage, 'iframe player url', group='url')), query={
'autoStart': 'true',
})
return self.url_result(data_url, ie=CeskaTelevizeIE.ie_key())

69
youtube_dl/extractor/clipchamp.py Normal file
View File

@@ -0,0 +1,69 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
merge_dicts,
T,
traverse_obj,
unified_timestamp,
url_or_none,
)
class ClipchampIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?clipchamp\.com/watch/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://clipchamp.com/watch/gRXZ4ZhdDaU',
'info_dict': {
'id': 'gRXZ4ZhdDaU',
'ext': 'mp4',
'title': 'Untitled video',
'uploader': 'Alexander Schwartz',
'timestamp': 1680805580,
'upload_date': '20230406',
'thumbnail': r're:^https?://.+\.jpg',
},
'params': {
'skip_download': 'm3u8',
'format': 'bestvideo',
},
}]
_STREAM_URL_TMPL = 'https://%s.cloudflarestream.com/%s/manifest/video.%s'
_STREAM_URL_QUERY = {'parentOrigin': 'https://clipchamp.com'}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
data = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['video']
storage_location = data.get('storage_location')
if storage_location != 'cf_stream':
raise ExtractorError('Unsupported clip storage location "%s"' % (storage_location,))
path = data['download_url']
iframe = self._download_webpage(
'https://iframe.cloudflarestream.com/' + path, video_id, 'Downloading player iframe')
subdomain = self._search_regex(
r'''\bcustomer-domain-prefix\s*=\s*("|')(?P<sd>[\w-]+)\1''', iframe,
'subdomain', group='sd', fatal=False) or 'customer-2ut9yn3y6fta1yxe'
formats = self._extract_mpd_formats(
self._STREAM_URL_TMPL % (subdomain, path, 'mpd'), video_id,
query=self._STREAM_URL_QUERY, fatal=False, mpd_id='dash')
formats.extend(self._extract_m3u8_formats(
self._STREAM_URL_TMPL % (subdomain, path, 'm3u8'), video_id, 'mp4',
query=self._STREAM_URL_QUERY, fatal=False, m3u8_id='hls'))
return merge_dicts({
'id': video_id,
'formats': formats,
'uploader': ' '.join(traverse_obj(data, ('creator', ('first_name', 'last_name'), T(compat_str)))) or None,
}, traverse_obj(data, {
'title': ('project', 'project_name', T(compat_str)),
'timestamp': ('created_at', T(unified_timestamp)),
'thumbnail': ('thumbnail_url', T(url_or_none)),
}), rev=True)

809
youtube_dl/extractor/common.py
View File

File diff suppressed because it is too large Load Diff

148
youtube_dl/extractor/cpac.py Normal file
View File

@@ -0,0 +1,148 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
str_or_none,
try_get,
unified_timestamp,
update_url_query,
urljoin,
)
# compat_range
try:
if callable(xrange):
range = xrange
except (NameError, TypeError):
pass
class CPACIE(InfoExtractor):
IE_NAME = 'cpac'
_VALID_URL = r'https?://(?:www\.)?cpac\.ca/(?P<fr>l-)?episode\?id=(?P<id>[\da-f]{8}(?:-[\da-f]{4}){3}-[\da-f]{12})'
_TEST = {
# 'url': 'http://www.cpac.ca/en/programs/primetime-politics/episodes/65490909',
'url': 'https://www.cpac.ca/episode?id=fc7edcae-4660-47e1-ba61-5b7f29a9db0f',
'md5': 'e46ad699caafd7aa6024279f2614e8fa',
'info_dict': {
'id': 'fc7edcae-4660-47e1-ba61-5b7f29a9db0f',
'ext': 'mp4',
'upload_date': '20220215',
'title': 'News Conference to Celebrate National Kindness Week – February 15, 2022',
'description': 'md5:466a206abd21f3a6f776cdef290c23fb',
'timestamp': 1644901200,
},
'params': {
'format': 'bestvideo',
'hls_prefer_native': True,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
url_lang = 'fr' if '/l-episode?' in url else 'en'
content = self._download_json(
'https://www.cpac.ca/api/1/services/contentModel.json?url=/site/website/episode/index.xml&crafterSite=cpacca&id=' + video_id,
video_id)
video_url = try_get(content, lambda x: x['page']['details']['videoUrl'], compat_str)
formats = []
if video_url:
content = content['page']
title = str_or_none(content['details']['title_%s_t' % (url_lang, )])
formats = self._extract_m3u8_formats(video_url, video_id, m3u8_id='hls', ext='mp4')
for fmt in formats:
# prefer language to match URL
fmt_lang = fmt.get('language')
if fmt_lang == url_lang:
fmt['language_preference'] = 10
elif not fmt_lang:
fmt['language_preference'] = -1
else:
fmt['language_preference'] = -10
self._sort_formats(formats)
category = str_or_none(content['details']['category_%s_t' % (url_lang, )])
def is_live(v_type):
return (v_type == 'live') if v_type is not None else None
return {
'id': video_id,
'formats': formats,
'title': title,
'description': str_or_none(content['details'].get('description_%s_t' % (url_lang, ))),
'timestamp': unified_timestamp(content['details'].get('liveDateTime')),
'category': [category] if category else None,
'thumbnail': urljoin(url, str_or_none(content['details'].get('image_%s_s' % (url_lang, )))),
'is_live': is_live(content['details'].get('type')),
}
class CPACPlaylistIE(InfoExtractor):
IE_NAME = 'cpac:playlist'
_VALID_URL = r'(?i)https?://(?:www\.)?cpac\.ca/(?:program|search|(?P<fr>emission|rechercher))\?(?:[^&]+&)*?(?P<id>(?:id=\d+|programId=\d+|key=[^&]+))'
_TESTS = [{
'url': 'https://www.cpac.ca/program?id=6',
'info_dict': {
'id': 'id=6',
'title': 'Headline Politics',
'description': 'Watch CPAC’s signature long-form coverage of the day’s pressing political events as they unfold.',
},
'playlist_count': 10,
}, {
'url': 'https://www.cpac.ca/search?key=hudson&type=all&order=desc',
'info_dict': {
'id': 'key=hudson',
'title': 'hudson',
},
'playlist_count': 22,
}, {
'url': 'https://www.cpac.ca/search?programId=50',
'info_dict': {
'id': 'programId=50',
'title': '50',
},
'playlist_count': 9,
}, {
'url': 'https://www.cpac.ca/emission?id=6',
'only_matching': True,
}, {
'url': 'https://www.cpac.ca/rechercher?key=hudson&type=all&order=desc',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
url_lang = 'fr' if any(x in url for x in ('/emission?', '/rechercher?')) else 'en'
pl_type, list_type = ('program', 'itemList') if any(x in url for x in ('/program?', '/emission?')) else ('search', 'searchResult')
api_url = (
'https://www.cpac.ca/api/1/services/contentModel.json?url=/site/website/%s/index.xml&crafterSite=cpacca&%s'
% (pl_type, video_id, ))
content = self._download_json(api_url, video_id)
entries = []
total_pages = int_or_none(try_get(content, lambda x: x['page'][list_type]['totalPages']), default=1)
for page in range(1, total_pages + 1):
if page > 1:
api_url = update_url_query(api_url, {'page': '%d' % (page, ), })
content = self._download_json(
api_url, video_id,
note='Downloading continuation - %d' % (page, ),
fatal=False)
for item in try_get(content, lambda x: x['page'][list_type]['item'], list) or []:
episode_url = urljoin(url, try_get(item, lambda x: x['url_%s_s' % (url_lang, )]))
if episode_url:
entries.append(episode_url)
return self.playlist_result(
(self.url_result(entry) for entry in entries),
playlist_id=video_id,
playlist_title=try_get(content, lambda x: x['page']['program']['title_%s_t' % (url_lang, )]) or video_id.split('=')[-1],
playlist_description=try_get(content, lambda x: x['page']['program']['description_%s_t' % (url_lang, )]),
)

204
youtube_dl/extractor/dlf.py Normal file
View File

@@ -0,0 +1,204 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_str,
)
from ..utils import (
determine_ext,
extract_attributes,
int_or_none,
merge_dicts,
traverse_obj,
url_or_none,
variadic,
)
class DLFBaseIE(InfoExtractor):
_VALID_URL_BASE = r'https?://(?:www\.)?deutschlandfunk\.de/'
_BUTTON_REGEX = r'(<button[^>]+alt="Anhören"[^>]+data-audio-diraid[^>]*>)'
def _parse_button_attrs(self, button, audio_id=None):
attrs = extract_attributes(button)
audio_id = audio_id or attrs['data-audio-diraid']
url = traverse_obj(
attrs, 'data-audio-download-src', 'data-audio', 'data-audioreference',
'data-audio-src', expected_type=url_or_none)
ext = determine_ext(url)
formats = (self._extract_m3u8_formats(url, audio_id, fatal=False)
if ext == 'm3u8' else [{'url': url, 'ext': ext, 'vcodec': 'none'}])
self._sort_formats(formats)
def traverse_attrs(path):
path = list(variadic(path))
t = path.pop() if callable(path[-1]) else None
return traverse_obj(attrs, path, expected_type=t, get_all=False)
def txt_or_none(v, default=None):
return default if v is None else (compat_str(v).strip() or default)
return merge_dicts(*reversed([{
'id': audio_id,
# 'extractor_key': DLFIE.ie_key(),
# 'extractor': DLFIE.IE_NAME,
'formats': formats,
}, dict((k, traverse_attrs(v)) for k, v in {
'title': (('data-audiotitle', 'data-audio-title', 'data-audio-download-tracking-title'), txt_or_none),
'duration': (('data-audioduration', 'data-audio-duration'), int_or_none),
'thumbnail': ('data-audioimage', url_or_none),
'uploader': 'data-audio-producer',
'series': 'data-audio-series',
'channel': 'data-audio-origin-site-name',
'webpage_url': ('data-audio-download-tracking-path', url_or_none),
}.items())]))
class DLFIE(DLFBaseIE):
IE_NAME = 'dlf'
_VALID_URL = DLFBaseIE._VALID_URL_BASE + r'[\w-]+-dlf-(?P<id>[\da-f]{8})-100\.html'
_TESTS = [
# Audio as an HLS stream
{
'url': 'https://www.deutschlandfunk.de/tanz-der-saiteninstrumente-das-wild-strings-trio-aus-slowenien-dlf-03a3eb19-100.html',
'info_dict': {
'id': '03a3eb19',
'title': r're:Tanz der Saiteninstrumente [-/] Das Wild Strings Trio aus Slowenien',
'ext': 'm4a',
'duration': 3298,
'thumbnail': 'https://assets.deutschlandfunk.de/FALLBACK-IMAGE-AUDIO/512x512.png?t=1603714364673',
'uploader': 'Deutschlandfunk',
'series': 'On Stage',
'channel': 'deutschlandfunk'
},
'params': {
'skip_download': 'm3u8'
},
'skip': 'This webpage no longer exists'
}, {
'url': 'https://www.deutschlandfunk.de/russische-athleten-kehren-zurueck-auf-die-sportbuehne-ein-gefaehrlicher-tueroeffner-dlf-d9cc1856-100.html',
'info_dict': {
'id': 'd9cc1856',
'title': 'Russische Athleten kehren zurück auf die Sportbühne: Ein gefährlicher Türöffner',
'ext': 'mp3',
'duration': 291,
'thumbnail': 'https://assets.deutschlandfunk.de/FALLBACK-IMAGE-AUDIO/512x512.png?t=1603714364673',
'uploader': 'Deutschlandfunk',
'series': 'Kommentare und Themen der Woche',
'channel': 'deutschlandfunk'
}
},
]
def _real_extract(self, url):
audio_id = self._match_id(url)
webpage = self._download_webpage(url, audio_id)
return self._parse_button_attrs(
self._search_regex(self._BUTTON_REGEX, webpage, 'button'), audio_id)
class DLFCorpusIE(DLFBaseIE):
IE_NAME = 'dlf:corpus'
IE_DESC = 'DLF Multi-feed Archives'
_VALID_URL = DLFBaseIE._VALID_URL_BASE + r'(?P<id>(?![\w-]+-dlf-[\da-f]{8})[\w-]+-\d+)\.html'
_TESTS = [
# Recorded news broadcast with referrals to related broadcasts
{
'url': 'https://www.deutschlandfunk.de/fechten-russland-belarus-ukraine-protest-100.html',
'info_dict': {
'id': 'fechten-russland-belarus-ukraine-protest-100',
'title': r're:Wiederzulassung als neutrale Athleten [-/] Was die Rückkehr russischer und belarussischer Sportler beim Fechten bedeutet',
'description': 'md5:91340aab29c71aa7518ad5be13d1e8ad'
},
'playlist_mincount': 5,
'playlist': [{
'info_dict': {
'id': '1fc5d64a',
'title': r're:Wiederzulassung als neutrale Athleten [-/] Was die Rückkehr russischer und belarussischer Sportler beim Fechten bedeutet',
'ext': 'mp3',
'duration': 252,
'thumbnail': 'https://assets.deutschlandfunk.de/aad16241-6b76-4a09-958b-96d0ee1d6f57/512x512.jpg?t=1679480020313',
'uploader': 'Deutschlandfunk',
'series': 'Sport',
'channel': 'deutschlandfunk'
}
}, {
'info_dict': {
'id': '2ada145f',
'title': r're:(?:Sportpolitik / )?Fechtverband votiert für Rückkehr russischer Athleten',
'ext': 'mp3',
'duration': 336,
'thumbnail': 'https://assets.deutschlandfunk.de/FILE_93982766f7317df30409b8a184ac044a/512x512.jpg?t=1678547581005',
'uploader': 'Deutschlandfunk',
'series': 'Deutschlandfunk Nova',
'channel': 'deutschlandfunk-nova'
}
}, {
'info_dict': {
'id': '5e55e8c9',
'title': r're:Wiederzulassung von Russland und Belarus [-/] "Herumlavieren" des Fechter-Bundes sorgt für Unverständnis',
'ext': 'mp3',
'duration': 187,
'thumbnail': 'https://assets.deutschlandfunk.de/a595989d-1ed1-4a2e-8370-b64d7f11d757/512x512.jpg?t=1679173825412',
'uploader': 'Deutschlandfunk',
'series': 'Sport am Samstag',
'channel': 'deutschlandfunk'
}
}, {
'info_dict': {
'id': '47e1a096',
'title': r're:Rückkehr Russlands im Fechten [-/] "Fassungslos, dass es einfach so passiert ist"',
'ext': 'mp3',
'duration': 602,
'thumbnail': 'https://assets.deutschlandfunk.de/da4c494a-21cc-48b4-9cc7-40e09fd442c2/512x512.jpg?t=1678562155770',
'uploader': 'Deutschlandfunk',
'series': 'Sport am Samstag',
'channel': 'deutschlandfunk'
}
}, {
'info_dict': {
'id': '5e55e8c9',
'title': r're:Wiederzulassung von Russland und Belarus [-/] "Herumlavieren" des Fechter-Bundes sorgt für Unverständnis',
'ext': 'mp3',
'duration': 187,
'thumbnail': 'https://assets.deutschlandfunk.de/a595989d-1ed1-4a2e-8370-b64d7f11d757/512x512.jpg?t=1679173825412',
'uploader': 'Deutschlandfunk',
'series': 'Sport am Samstag',
'channel': 'deutschlandfunk'
}
}]
},
# Podcast feed with tag buttons, playlist count fluctuates
{
'url': 'https://www.deutschlandfunk.de/kommentare-und-themen-der-woche-100.html',
'info_dict': {
'id': 'kommentare-und-themen-der-woche-100',
'title': 'Meinung - Kommentare und Themen der Woche',
'description': 'md5:2901bbd65cd2d45e116d399a099ce5d5',
},
'playlist_mincount': 10,
},
# Podcast feed with no description
{
'url': 'https://www.deutschlandfunk.de/podcast-tolle-idee-100.html',
'info_dict': {
'id': 'podcast-tolle-idee-100',
'title': 'Wissenschaftspodcast - Tolle Idee! - Was wurde daraus?',
},
'playlist_mincount': 11,
},
]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
return self.playlist_result(
map(self._parse_button_attrs, re.findall(self._BUTTON_REGEX, webpage)),
playlist_id, self._html_search_meta(['og:title', 'twitter:title'], webpage, default=None),
self._html_search_meta(['description', 'og:description', 'twitter:description'], webpage, default=None))

101
youtube_dl/extractor/epidemicsound.py Normal file
View File

@@ -0,0 +1,101 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
float_or_none,
T,
traverse_obj,
txt_or_none,
unified_timestamp,
url_or_none,
)
class EpidemicSoundIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?epidemicsound\.com/track/(?P<id>[0-9a-zA-Z]+)'
_TESTS = [{
'url': 'https://www.epidemicsound.com/track/yFfQVRpSPz/',
'md5': 'd98ff2ddb49e8acab9716541cbc9dfac',
'info_dict': {
'id': '45014',
'display_id': 'yFfQVRpSPz',
'ext': 'mp3',
'tags': ['foley', 'door', 'knock', 'glass', 'window', 'glass door knock'],
'title': 'Door Knock Door 1',
'duration': 1,
'thumbnail': 'https://cdn.epidemicsound.com/curation-assets/commercial-release-cover-images/default-sfx/3000x3000.jpg',
'timestamp': 1415320353,
'upload_date': '20141107',
'age_limit': None,
# check that the "best" format was found, since test file MD5 doesn't
# distinguish the formats
'format': 'full',
},
}, {
'url': 'https://www.epidemicsound.com/track/mj8GTTwsZd/',
'md5': 'c82b745890f9baf18dc2f8d568ee3830',
'info_dict': {
'id': '148700',
'display_id': 'mj8GTTwsZd',
'ext': 'mp3',
'tags': ['liquid drum n bass', 'energetic'],
'title': 'Noplace',
'duration': 237,
'thumbnail': 'https://cdn.epidemicsound.com/curation-assets/commercial-release-cover-images/11138/3000x3000.jpg',
'timestamp': 1694426482,
'release_timestamp': 1700535606,
'upload_date': '20230911',
'age_limit': None,
'format': 'full',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
json_data = self._download_json('https://www.epidemicsound.com/json/track/' + video_id, video_id)
def fmt_or_none(f):
if not f.get('format'):
f['format'] = f.get('format_id')
elif not f.get('format_id'):
f['format_id'] = f['format']
if not (f['url'] and f['format']):
return
if f.get('format_note'):
f['format_note'] = 'track ID ' + f['format_note']
f['preference'] = -1 if f['format'] == 'full' else -2
return f
formats = traverse_obj(json_data, (
'stems', T(dict.items), Ellipsis, {
'format': (0, T(txt_or_none)),
'format_note': (1, 's3TrackId', T(txt_or_none)),
'format_id': (1, 'stemType', T(txt_or_none)),
'url': (1, 'lqMp3Url', T(url_or_none)),
}, T(fmt_or_none)))
self._sort_formats(formats)
info = traverse_obj(json_data, {
'id': ('id', T(txt_or_none)),
'tags': ('metadataTags', Ellipsis, T(txt_or_none)),
'title': ('title', T(txt_or_none)),
'duration': ('length', T(float_or_none)),
'timestamp': ('added', T(unified_timestamp)),
'thumbnail': (('imageUrl', 'cover'), T(url_or_none)),
'age_limit': ('isExplicit', T(lambda b: 18 if b else None)),
'release_timestamp': ('releaseDate', T(unified_timestamp)),
}, get_all=False)
info.update(traverse_obj(json_data, {
'categories': ('genres', Ellipsis, 'tag', T(txt_or_none)),
'tags': ('metadataTags', Ellipsis, T(txt_or_none)),
}))
info.update({
'display_id': video_id,
'formats': formats,
})
return info

87
youtube_dl/extractor/extractors.py
View File

@@ -51,6 +51,10 @@ from .anvato import AnvatoIE
from .aol import AolIE
from .allocine import AllocineIE
from .aliexpress import AliExpressLiveIE
from .alsace20tv import (
Alsace20TVIE,
Alsace20TVEmbedIE,
)
from .apa import APAIE
from .aparat import AparatIE
from .appleconnect import AppleConnectIE
@@ -115,6 +119,7 @@ from .bfmtv import (
)
from .bibeltv import BibelTVIE
from .bigflix import BigflixIE
from .bigo import BigoIE
from .bild import BildIE
from .bilibili import (
BiliBiliIE,
@@ -133,6 +138,7 @@ from .bleacherreport import (
BleacherReportIE,
BleacherReportCMSIE,
)
from .blerp import BlerpIE
from .bloomberg import BloombergIE
from .bokecc import BokeCCIE
from .bongacams import BongaCamsIE
@@ -153,6 +159,8 @@ from .businessinsider import BusinessInsiderIE
from .buzzfeed import BuzzFeedIE
from .byutv import BYUtvIE
from .c56 import C56IE
from .caffeine import CaffeineTVIE
from .callin import CallinIE
from .camdemy import (
CamdemyIE,
CamdemyFolderIE
@@ -203,10 +211,7 @@ from .ccc import (
from .ccma import CCMAIE
from .cctv import CCTVIE
from .cda import CDAIE
from .ceskatelevize import (
CeskaTelevizeIE,
CeskaTelevizePoradyIE,
)
from .ceskatelevize import CeskaTelevizeIE
from .channel9 import Channel9IE
from .charlierose import CharlieRoseIE
from .chaturbate import ChaturbateIE
@@ -222,6 +227,7 @@ from .ciscolive import (
CiscoLiveSearchIE,
)
from .cjsw import CJSWIE
from .clipchamp import ClipchampIE
from .cliphunter import CliphunterIE
from .clippit import ClippitIE
from .cliprs import ClipRsIE
@@ -254,6 +260,10 @@ from .commonprotocols import (
from .condenast import CondeNastIE
from .contv import CONtvIE
from .corus import CorusIE
from .cpac import (
CPACIE,
CPACPlaylistIE,
)
from .cracked import CrackedIE
from .crackle import CrackleIE
from .crooksandliars import CrooksAndLiarsIE
@@ -287,6 +297,10 @@ from .dbtv import DBTVIE
from .dctp import DctpTvIE
from .deezer import DeezerPlaylistIE
from .democracynow import DemocracynowIE
from .dlf import (
DLFCorpusIE,
DLFIE,
)
from .dfb import DFBIE
from .dhm import DHMIE
from .digg import DiggIE
@@ -344,6 +358,7 @@ from .ellentube import (
from .elpais import ElPaisIE
from .embedly import EmbedlyIE
from .engadget import EngadgetIE
from .epidemicsound import EpidemicSoundIE
from .eporner import EpornerIE
from .eroprofile import EroProfileIE
from .escapist import EscapistIE
@@ -368,6 +383,7 @@ from .fc2 import (
FC2EmbedIE,
)
from .fczenit import FczenitIE
from .fifa import FifaIE
from .filmon import (
FilmOnIE,
FilmOnChannelIE,
@@ -427,6 +443,7 @@ from .gamespot import GameSpotIE
from .gamestar import GameStarIE
from .gaskrank import GaskrankIE
from .gazeta import GazetaIE
from .gbnews import GBNewsIE
from .gdcvault import GDCVaultIE
from .gedidigital import GediDigitalIE
from .generic import GenericIE
@@ -434,6 +451,13 @@ from .gfycat import GfycatIE
from .giantbomb import GiantBombIE
from .giga import GigaIE
from .glide import GlideIE
from .globalplayer import (
GlobalPlayerLiveIE,
GlobalPlayerLivePlaylistIE,
GlobalPlayerAudioIE,
GlobalPlayerAudioEpisodeIE,
GlobalPlayerVideoIE
)
from .globo import (
GloboIE,
GloboArticleIE,
@@ -470,6 +494,7 @@ from .hotstar import (
)
from .howcast import HowcastIE
from .howstuffworks import HowStuffWorksIE
from .hrfernsehen import HRFernsehenIE
from .hrti import (
HRTiIE,
HRTiPlaylistIE,
@@ -546,8 +571,10 @@ from .khanacademy import (
from .kickstarter import KickStarterIE
from .kinja import KinjaEmbedIE
from .kinopoisk import KinoPoiskIE
from .kommunetv import KommunetvIE
from .konserthusetplay import KonserthusetPlayIE
from .krasview import KrasViewIE
from .kth import KTHIE
from .ku6 import Ku6IE
from .kusi import KUSIIE
from .kuwo import (
@@ -717,6 +744,7 @@ from .myvi import (
MyviIE,
MyviEmbedIE,
)
from .myvideoge import MyVideoGeIE
from .myvidster import MyVidsterIE
from .nationalgeographic import (
NationalGeographicVideoIE,
@@ -870,21 +898,13 @@ from .ooyala import (
)
from .ora import OraTVIE
from .orf import (
ORFTVthekIE,
ORFFM4IE,
ORFONIE,
ORFONLiveIE,
ORFFM4StoryIE,
ORFOE1IE,
ORFOE3IE,
ORFNOEIE,
ORFWIEIE,
ORFBGLIE,
ORFOOEIE,
ORFSTMIE,
ORFKTNIE,
ORFSBGIE,
ORFTIRIE,
ORFVBGIE,
ORFIPTVIE,
ORFPodcastIE,
ORFRadioIE,
ORFRadioCollectionIE,
)
from .outsidetv import OutsideTVIE
from .packtpub import (
@@ -901,6 +921,10 @@ from .parliamentliveuk import ParliamentLiveUKIE
from .patreon import PatreonIE
from .pbs import PBSIE
from .pearvideo import PearVideoIE
from .peekvids import (
PeekVidsIE,
PlayVidsIE,
)
from .peertube import PeerTubeIE
from .people import PeopleIE
from .performgroup import PerformGroupIE
@@ -957,6 +981,10 @@ from .pornhub import (
from .pornotube import PornotubeIE
from .pornovoisines import PornoVoisinesIE
from .pornoxo import PornoXOIE
from .pr0gramm import (
Pr0grammIE,
Pr0grammStaticIE,
)
from .puhutv import (
PuhuTVIE,
PuhuTVSerieIE,
@@ -994,6 +1022,10 @@ from .raywenderlich import (
RayWenderlichIE,
RayWenderlichCourseIE,
)
from .rbgtum import (
RbgTumIE,
RbgTumCourseIE,
)
from .rbmaradio import RBMARadioIE
from .rds import RDSIE
from .redbulltv import (
@@ -1049,6 +1081,10 @@ from .rutube import (
from .rutv import RUTVIE
from .ruutu import RuutuIE
from .ruv import RuvIE
from .s4c import (
S4CIE,
S4CSeriesIE,
)
from .safari import (
SafariIE,
SafariApiIE,
@@ -1184,6 +1220,7 @@ from .storyfire import (
from .streamable import StreamableIE
from .streamcloud import StreamcloudIE
from .streamcz import StreamCZIE
from .streamsb import StreamsbIE
from .streetvoice import StreetVoiceIE
from .stretchinternet import StretchInternetIE
from .stv import STVPlayerIE
@@ -1253,6 +1290,11 @@ from .theweatherchannel import TheWeatherChannelIE
from .thisamericanlife import ThisAmericanLifeIE
from .thisav import ThisAVIE
from .thisoldhouse import ThisOldHouseIE
from .thisvid import (
ThisVidIE,
ThisVidMemberIE,
ThisVidPlaylistIE,
)
from .threeqsdn import ThreeQSDNIE
from .tiktok import (
TikTokIE,
@@ -1537,6 +1579,7 @@ from .weibo import (
WeiboMobileIE
)
from .weiqitv import WeiqiTVIE
from .whyp import WhypIE
from .wistia import (
WistiaIE,
WistiaPlaylistIE,
@@ -1602,7 +1645,15 @@ from .younow import (
YouNowChannelIE,
YouNowMomentIE,
)
from .youporn import YouPornIE
from .youporn import (
YouPornIE,
YouPornCategoryIE,
YouPornChannelIE,
YouPornCollectionIE,
YouPornStarIE,
YouPornTagIE,
YouPornVideosIE,
)
from .yourporn import YourPornIE
from .yourupload import YourUploadIE
from .youtube import (

101
youtube_dl/extractor/fifa.py Normal file
View File

@@ -0,0 +1,101 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
traverse_obj,
unified_timestamp,
)
if not callable(getattr(InfoExtractor, '_match_valid_url', None)):
BaseInfoExtractor = InfoExtractor
import re
class InfoExtractor(BaseInfoExtractor):
@classmethod
def _match_valid_url(cls, url):
return re.match(cls._VALID_URL, url)
class FifaIE(InfoExtractor):
_VALID_URL = r'https?://www.fifa.com/fifaplus/(?P<locale>\w{2})/watch/([^#?]+/)?(?P<id>\w+)'
_TESTS = [{
'url': 'https://www.fifa.com/fifaplus/en/watch/7on10qPcnyLajDDU3ntg6y',
'info_dict': {
'id': '7on10qPcnyLajDDU3ntg6y',
'title': 'Italy v France | Final | 2006 FIFA World Cup Germany™ | Full Match Replay',
'description': 'md5:f4520d0ee80529c8ba4134a7d692ff8b',
'ext': 'mp4',
'categories': ['FIFA Tournaments'],
'thumbnail': 'https://digitalhub.fifa.com/transform/135e2656-3a51-407b-8810-6c34bec5b59b/FMR_2006_Italy_France_Final_Hero',
'duration': 8165,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.fifa.com/fifaplus/pt/watch/1cg5r5Qt6Qt12ilkDgb1sV',
'info_dict': {
'id': '1cg5r5Qt6Qt12ilkDgb1sV',
'title': 'Brazil v Germany | Semi-finals | 2014 FIFA World Cup Brazil™ | Extended Highlights',
'description': 'md5:d908c74ee66322b804ae2e521b02a855',
'ext': 'mp4',
'categories': ['FIFA Tournaments', 'Highlights'],
'thumbnail': 'https://digitalhub.fifa.com/transform/d8fe6f61-276d-4a73-a7fe-6878a35fd082/FIFAPLS_100EXTHL_2014BRAvGER_TMB',
'duration': 902,
'release_timestamp': 1404777600,
'release_date': '20140708',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.fifa.com/fifaplus/fr/watch/3C6gQH9C2DLwzNx7BMRQdp',
'info_dict': {
'id': '3C6gQH9C2DLwzNx7BMRQdp',
'title': 'Josimar goal against Northern Ireland | Classic Goals',
'description': 'md5:cbe7e7bb52f603c9f1fe9a4780fe983b',
'ext': 'mp4',
'categories': ['FIFA Tournaments', 'Goal'],
'duration': 28,
'thumbnail': 'https://digitalhub.fifa.com/transform/f9301391-f8d9-48b5-823e-c093ac5e3e11/CG_MEN_1986_JOSIMAR',
},
'params': {'skip_download': 'm3u8'},
}]
def _real_extract(self, url):
video_id, locale = self._match_valid_url(url).group('id', 'locale')
webpage = self._download_webpage(url, video_id)
preconnect_link = self._search_regex(
r'<link\b[^>]+\brel\s*=\s*"preconnect"[^>]+href\s*=\s*"([^"]+)"', webpage, 'Preconnect Link')
video_details = self._download_json(
'{preconnect_link}/sections/videoDetails/{video_id}'.format(**locals()), video_id, 'Downloading Video Details', fatal=False)
preplay_parameters = self._download_json(
'{preconnect_link}/videoPlayerData/{video_id}'.format(**locals()), video_id, 'Downloading Preplay Parameters')['preplayParameters']
content_data = self._download_json(
# 1. query string is expected to be sent as-is
# 2. `sig` must be appended
# 3. if absent, the call appears to work but the manifest is bad (404)
'https://content.uplynk.com/preplay/{contentId}/multiple.json?{queryStr}&sig={signature}'.format(**preplay_parameters),
video_id, 'Downloading Content Data')
# formats, subtitles = self._extract_m3u8_formats_and_subtitles(content_data['playURL'], video_id)
formats, subtitles = self._extract_m3u8_formats(content_data['playURL'], video_id, ext='mp4', entry_protocol='m3u8_native'), None
self._sort_formats(formats)
return {
'id': video_id,
'title': video_details['title'],
'description': video_details.get('description'),
'duration': int_or_none(video_details.get('duration')),
'release_timestamp': unified_timestamp(video_details.get('dateOfRelease')),
'categories': traverse_obj(video_details, (('videoCategory', 'videoSubcategory'),)),
'thumbnail': traverse_obj(video_details, ('backgroundImage', 'src')),
'formats': formats,
'subtitles': subtitles,
}

139
youtube_dl/extractor/gbnews.py Normal file
View File

@@ -0,0 +1,139 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
extract_attributes,
ExtractorError,
T,
traverse_obj,
txt_or_none,
url_or_none,
)
class GBNewsIE(InfoExtractor):
IE_DESC = 'GB News clips, features and live stream'
# \w+ is normally shows or news, but apparently any word redirects to the correct URL
_VALID_URL = r'https?://(?:www\.)?gbnews\.(?:uk|com)/(?:\w+/)?(?P<id>[^#?]+)'
_PLATFORM = 'safari'
_SSMP_URL = 'https://mm-v2.simplestream.com/ssmp/api.php'
_TESTS = [{
'url': 'https://www.gbnews.uk/shows/andrew-neils-message-to-companies-choosing-to-boycott-gb-news/106889',
'info_dict': {
'id': '106889',
'ext': 'mp4',
'title': "Andrew Neil's message to companies choosing to boycott GB News",
'description': 'md5:b281f5d22fd6d5eda64a4e3ba771b351',
},
'skip': '404 not found',
}, {
'url': 'https://www.gbnews.com/news/bbc-claudine-gay-harvard-university-antisemitism-row',
'info_dict': {
'id': '52264136',
'display_id': 'bbc-claudine-gay-harvard-university-antisemitism-row',
'ext': 'mp4',
'title': 'BBC deletes post after furious backlash over headline downplaying antisemitism',
'description': 'The post was criticised by former employers of the broadcaster',
},
}, {
'url': 'https://www.gbnews.uk/watchlive',
'info_dict': {
'id': '1069',
'display_id': 'watchlive',
'ext': 'mp4',
'title': 'GB News Live',
'is_live': True,
},
'params': {
'skip_download': 'm3u8',
},
}]
def _real_extract(self, url):
display_id = self._match_id(url).split('/')[-1]
webpage = self._download_webpage(url, display_id)
# extraction based on https://github.com/ytdl-org/youtube-dl/issues/29341
'''
<div id="video-106908"
class="simplestream"
data-id="GB001"
data-type="vod"
data-key="3Li3Nt2Qs8Ct3Xq9Fi5Uy0Mb2Bj0Qs"
data-token="f9c317c727dc07f515b20036c8ef14a6"
data-expiry="1624300052"
data-uvid="37900558"
data-poster="https://thumbnails.simplestreamcdn.com/gbnews/ondemand/37900558.jpg?width=700&"
data-npaw="false"
data-env="production">
'''
# exception if no match
video_data = self._search_regex(
r'(<div\s[^>]*\bclass\s*=\s*(\'|")(?!.*sidebar\b)simplestream(?:\s[\s\w$-]*)?\2[^>]*>)',
webpage, 'video data')
video_data = extract_attributes(video_data)
ss_id = video_data.get('data-id')
if not ss_id:
raise ExtractorError('Simplestream ID not found')
json_data = self._download_json(
self._SSMP_URL, display_id,
note='Downloading Simplestream JSON metadata',
errnote='Unable to download Simplestream JSON metadata',
query={
'id': ss_id,
'env': video_data.get('data-env', 'production'),
}, fatal=False)
meta_url = traverse_obj(json_data, ('response', 'api_hostname'))
if not meta_url:
raise ExtractorError('No API host found')
uvid = video_data['data-uvid']
dtype = video_data.get('data-type')
stream_data = self._download_json(
'%s/api/%s/stream/%s' % (meta_url, 'show' if dtype == 'vod' else dtype, uvid),
uvid,
query={
'key': video_data.get('data-key'),
'platform': self._PLATFORM,
},
headers={
'Token': video_data.get('data-token'),
'Token-Expiry': video_data.get('data-expiry'),
'Uvid': uvid,
}, fatal=False)
stream_url = traverse_obj(stream_data, (
'response', 'stream', T(url_or_none)))
if not stream_url:
raise ExtractorError('No stream data/URL')
# now known to be a dict
stream_data = stream_data['response']
drm = stream_data.get('drm')
if drm:
self.report_drm(uvid)
formats = self._extract_m3u8_formats(
stream_url, uvid, ext='mp4', entry_protocol='m3u8_native',
fatal=False)
# exception if no formats
self._sort_formats(formats)
return {
'id': uvid,
'display_id': display_id,
'title': (traverse_obj(stream_data, ('title', T(txt_or_none)))
or self._og_search_title(webpage, default=None)
or display_id.replace('-', ' ').capitalize()),
'description': self._og_search_description(webpage, default=None),
'thumbnail': (traverse_obj(video_data, ('data-poster', T(url_or_none)))
or self._og_search_thumbnail(webpage)),
'formats': formats,
'is_live': (dtype == 'live') or None,
}

219
youtube_dl/extractor/generic.py
View File

@@ -28,6 +28,7 @@ from ..utils import (
mimetype2ext,
orderedSet,
parse_duration,
parse_resolution,
sanitized_Request,
smuggle_url,
unescapeHTML,
@@ -35,6 +36,7 @@ from ..utils import (
unsmuggle_url,
UnsupportedError,
url_or_none,
urljoin,
xpath_attr,
xpath_text,
xpath_with_ns,
@@ -2227,6 +2229,116 @@ class GenericIE(InfoExtractor):
# Sibnet embed (https://help.sibnet.ru/?sibnet_video_embed)
'url': 'https://phpbb3.x-tk.ru/bbcode-video-sibnet-t24.html',
'only_matching': True,
}, {
# KVS Player
'url': 'https://www.kvs-demo.com/videos/105/kelis-4th-of-july/',
'info_dict': {
'id': '105',
'display_id': 'kelis-4th-of-july',
'ext': 'mp4',
'title': 'Kelis - 4th Of July',
'thumbnail': r're:https://(?:www\.)?kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
},
}, {
# KVS Player
'url': 'https://www.kvs-demo.com/embed/105/',
'info_dict': {
'id': '105',
'display_id': 'kelis-4th-of-july',
'ext': 'mp4',
'title': 'Kelis - 4th Of July / Embed Player',
'thumbnail': r're:https://(?:www\.)?kvs-demo.com/contents/videos_screenshots/0/105/preview.jpg',
},
'params': {
'skip_download': True,
},
}, {
# KVS Player (tested also in thisvid.py)
'url': 'https://youix.com/video/leningrad-zoj/',
'md5': '94f96ba95706dc3880812b27b7d8a2b8',
'info_dict': {
'id': '18485',
'display_id': 'leningrad-zoj',
'ext': 'mp4',
'title': 'Клип: Ленинград - ЗОЖ скачать, смотреть онлайн | Youix.com',
'thumbnail': r're:https://youix.com/contents/videos_screenshots/18000/18485/preview(?:_480x320_youix_com.mp4)?\.jpg',
},
}, {
# KVS Player
'url': 'https://youix.com/embed/18485',
'md5': '94f96ba95706dc3880812b27b7d8a2b8',
'info_dict': {
'id': '18485',
'display_id': 'leningrad-zoj',
'ext': 'mp4',
'title': 'Ленинград - ЗОЖ',
'thumbnail': r're:https://youix.com/contents/videos_screenshots/18000/18485/preview(?:_480x320_youix_com.mp4)?\.jpg',
},
}, {
# KVS Player
'url': 'https://bogmedia.org/videos/21217/40-nochey-40-nights-2016/',
'md5': '94166bdb26b4cb1fb9214319a629fc51',
'info_dict': {
'id': '21217',
'display_id': '40-nochey-2016',
'ext': 'mp4',
'title': '40 ночей (2016) - BogMedia.org',
'description': 'md5:4e6d7d622636eb7948275432eb256dc3',
'thumbnail': 'https://bogmedia.org/contents/videos_screenshots/21000/21217/preview_480p.mp4.jpg',
},
}, {
# KVS Player (for sites that serve kt_player.js via non-https urls)
'url': 'http://www.camhub.world/embed/389508',
'md5': 'fbe89af4cfb59c8fd9f34a202bb03e32',
'info_dict': {
'id': '389508',
'display_id': 'syren-de-mer-onlyfans-05-07-2020have-a-happy-safe-holiday5f014e68a220979bdb8cd-source',
'ext': 'mp4',
'title': 'Syren De Mer onlyfans_05-07-2020Have_a_happy_safe_holiday5f014e68a220979bdb8cd_source / Embed плеер',
'thumbnail': r're:https?://www\.camhub\.world/contents/videos_screenshots/389000/389508/preview\.mp4\.jpg',
},
}, {
'url': 'https://mrdeepfakes.com/video/5/selena-gomez-pov-deep-fakes',
'md5': 'fec4ad5ec150f655e0c74c696a4a2ff4',
'info_dict': {
'id': '5',
'display_id': 'selena-gomez-pov-deep-fakes',
'ext': 'mp4',
'title': 'Selena Gomez POV (Deep Fakes) DeepFake Porn - MrDeepFakes',
'description': 'md5:17d1f84b578c9c26875ac5ef9a932354',
'height': 720,
'age_limit': 18,
},
}, {
'url': 'https://shooshtime.com/videos/284002/just-out-of-the-shower-joi/',
'md5': 'e2f0a4c329f7986280b7328e24036d60',
'info_dict': {
'id': '284002',
'display_id': 'just-out-of-the-shower-joi',
'ext': 'mp4',
'title': 'Just Out Of The Shower JOI - Shooshtime',
'height': 720,
'age_limit': 18,
},
}, {
# would like to use the yt-dl test video but searching for
# '"\'/\\ä↭𝕐' fails, so using an old vid from YouTube Korea
'note': 'Test default search',
'url': 'Shorts로 허락 필요없이 놀자! (BTS편)',
'info_dict': {
'id': 'usDGO4Zb-dc',
'ext': 'mp4',
'title': 'YouTube Shorts로 허락 필요없이 놀자! (BTS편)',
'description': 'md5:96e31607eba81ab441567b5e289f4716',
'upload_date': '20211107',
'uploader': 'YouTube Korea',
'location': '대한민국',
},
'params': {
'default_search': 'ytsearch',
'skip_download': True,
},
'expected_warnings': ['uploader id'],
},
]
@@ -2332,6 +2444,88 @@ class GenericIE(InfoExtractor):
'title': title,
}
def _extract_kvs(self, url, webpage, video_id):
def getlicensetoken(license):
modlicense = license.replace('$', '').replace('0', '1')
center = int(len(modlicense) / 2)
fronthalf = int(modlicense[:center + 1])
backhalf = int(modlicense[center:])
modlicense = compat_str(4 * abs(fronthalf - backhalf))
def parts():
for o in range(0, center + 1):
for i in range(1, 5):
yield compat_str((int(license[o + i]) + int(modlicense[o])) % 10)
return ''.join(parts())
def getrealurl(video_url, license_code):
if not video_url.startswith('function/0/'):
return video_url # not obfuscated
url_path, _, url_query = video_url.partition('?')
urlparts = url_path.split('/')[2:]
license = getlicensetoken(license_code)
newmagic = urlparts[5][:32]
def spells(x, o):
l = (o + sum(int(n) for n in license[o:])) % 32
for i in range(0, len(x)):
yield {l: x[o], o: x[l]}.get(i, x[i])
for o in range(len(newmagic) - 1, -1, -1):
newmagic = ''.join(spells(newmagic, o))
urlparts[5] = newmagic + urlparts[5][32:]
return '/'.join(urlparts) + '?' + url_query
flashvars = self._search_regex(
r'(?s)<script\b[^>]*>.*?var\s+flashvars\s*=\s*(\{.+?\});.*?</script>',
webpage, 'flashvars')
flashvars = self._parse_json(flashvars, video_id, transform_source=js_to_json)
# extract the part after the last / as the display_id from the
# canonical URL.
display_id = self._search_regex(
r'(?:<link href="https?://[^"]+/(.+?)/?" rel="canonical"\s*/?>'
r'|<link rel="canonical" href="https?://[^"]+/(.+?)/?"\s*/?>)',
webpage, 'display_id', fatal=False
)
title = self._html_search_regex(r'<(?:h1|title)>(?:Video: )?(.+?)</(?:h1|title)>', webpage, 'title')
thumbnail = flashvars['preview_url']
if thumbnail.startswith('//'):
protocol, _, _ = url.partition('/')
thumbnail = protocol + thumbnail
url_keys = list(filter(re.compile(r'^video_(?:url|alt_url\d*)$').match, flashvars.keys()))
formats = []
for key in url_keys:
if '/get_file/' not in flashvars[key]:
continue
format_id = flashvars.get(key + '_text', key)
formats.append(merge_dicts(
parse_resolution(format_id) or parse_resolution(flashvars[key]), {
'url': urljoin(url, getrealurl(flashvars[key], flashvars['license_code'])),
'format_id': format_id,
'ext': 'mp4',
'http_headers': {'Referer': url},
}))
if not formats[-1].get('height'):
formats[-1]['quality'] = 1
self._sort_formats(formats)
return {
'id': flashvars['video_id'],
'display_id': display_id,
'title': title,
'thumbnail': thumbnail,
'formats': formats,
}
def _real_extract(self, url):
if url.startswith('//'):
return self.url_result(self.http_scheme() + url)
@@ -2540,9 +2734,16 @@ class GenericIE(InfoExtractor):
# but actually don't.
AGE_LIMIT_MARKERS = [
r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
r'>[^<]*you acknowledge you are at least (\d+) years old',
r'>\s*(?:18\s+U(?:\.S\.C\.|SC)\s+)?(?:§+\s*)?2257\b',
]
if any(re.search(marker, webpage) for marker in AGE_LIMIT_MARKERS):
age_limit = 18
for marker in AGE_LIMIT_MARKERS:
m = re.search(marker, webpage)
if not m:
continue
age_limit = max(
age_limit or 0,
int_or_none(m.groups() and m.group(1), default=18))
# video uploader is domain name
video_uploader = self._search_regex(
@@ -3389,6 +3590,20 @@ class GenericIE(InfoExtractor):
info_dict['formats'] = formats
return info_dict
# Look for generic KVS player (before ld+json for tests)
found = self._search_regex(
(r'<script\b[^>]+?\bsrc\s*=\s*(["\'])https?://(?:\S+?/)+kt_player\.js\?v=(?P<ver>\d+(?:\.\d+)+)\1[^>]*>',
# kt_player('kt_player', 'https://i.shoosh.co/player/kt_player.swf?v=5.5.1', ...
r'kt_player\s*\(\s*(["\'])(?:(?!\1)[\w\W])+\1\s*,\s*(["\'])https?://(?:\S+?/)+kt_player\.swf\?v=(?P<ver>\d+(?:\.\d+)+)\2\s*,',
), webpage, 'KVS player', group='ver', default=False)
if found:
self.report_extraction('%s: KVS Player' % (video_id, ))
if found.split('.')[0] not in ('4', '5', '6'):
self.report_warning('Untested major version (%s) in player engine - download may fail.' % (found, ))
return merge_dicts(
self._extract_kvs(url, webpage, video_id),
info_dict)
# Looking for http://schema.org/VideoObject
json_ld = self._search_json_ld(
webpage, video_id, default={}, expected_type='VideoObject')

273
youtube_dl/extractor/globalplayer.py Normal file
View File

@@ -0,0 +1,273 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
clean_html,
join_nonempty,
merge_dicts,
parse_duration,
str_or_none,
T,
traverse_obj,
unified_strdate,
unified_timestamp,
urlhandle_detect_ext,
)
class GlobalPlayerBaseIE(InfoExtractor):
def _get_page_props(self, url, video_id):
webpage = self._download_webpage(url, video_id)
return self._search_nextjs_data(webpage, video_id)['props']['pageProps']
def _request_ext(self, url, video_id):
return urlhandle_detect_ext(self._request_webpage( # Server rejects HEAD requests
url, video_id, note='Determining source extension'))
@staticmethod
def _clean_desc(x):
x = clean_html(x)
if x:
x = x.replace('\xa0', ' ')
return x
def _extract_audio(self, episode, series):
return merge_dicts({
'vcodec': 'none',
}, traverse_obj(series, {
'series': 'title',
'series_id': 'id',
'thumbnail': 'imageUrl',
'uploader': 'itunesAuthor', # podcasts only
}), traverse_obj(episode, {
'id': 'id',
'description': ('description', T(self._clean_desc)),
'duration': ('duration', T(parse_duration)),
'thumbnail': 'imageUrl',
'url': 'streamUrl',
'timestamp': (('pubDate', 'startDate'), T(unified_timestamp)),
'title': 'title',
}, get_all=False), rev=True)
class GlobalPlayerLiveIE(GlobalPlayerBaseIE):
_VALID_URL = r'https?://www\.globalplayer\.com/live/(?P<id>\w+)/\w+'
_TESTS = [{
'url': 'https://www.globalplayer.com/live/smoothchill/uk/',
'info_dict': {
'id': '2mx1E',
'ext': 'aac',
'display_id': 'smoothchill-uk',
'title': 're:^Smooth Chill.+$',
'thumbnail': 'https://herald.musicradio.com/media/f296ade8-50c9-4f60-911f-924e96873620.png',
'description': 'Music To Chill To',
# 'live_status': 'is_live',
'is_live': True,
},
}, {
# national station
'url': 'https://www.globalplayer.com/live/heart/uk/',
'info_dict': {
'id': '2mwx4',
'ext': 'aac',
'description': 'turn up the feel good!',
'thumbnail': 'https://herald.musicradio.com/media/49b9e8cb-15bf-4bf2-8c28-a4850cc6b0f3.png',
# 'live_status': 'is_live',
'is_live': True,
'title': 're:^Heart UK.+$',
'display_id': 'heart-uk',
},
}, {
# regional variation
'url': 'https://www.globalplayer.com/live/heart/london/',
'info_dict': {
'id': 'AMqg',
'ext': 'aac',
'thumbnail': 'https://herald.musicradio.com/media/49b9e8cb-15bf-4bf2-8c28-a4850cc6b0f3.png',
'title': 're:^Heart London.+$',
# 'live_status': 'is_live',
'is_live': True,
'display_id': 'heart-london',
'description': 'turn up the feel good!',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
station = self._get_page_props(url, video_id)['station']
stream_url = station['streamUrl']
return merge_dicts({
'id': station['id'],
'display_id': (
join_nonempty('brandSlug', 'slug', from_dict=station)
or station.get('legacyStationPrefix')),
'url': stream_url,
'ext': self._request_ext(stream_url, video_id),
'vcodec': 'none',
'is_live': True,
}, {
'title': self._live_title(traverse_obj(
station, (('name', 'brandName'), T(str_or_none)),
get_all=False)),
}, traverse_obj(station, {
'description': 'tagline',
'thumbnail': 'brandLogo',
}), rev=True)
class GlobalPlayerLivePlaylistIE(GlobalPlayerBaseIE):
_VALID_URL = r'https?://www\.globalplayer\.com/playlists/(?P<id>\w+)'
_TESTS = [{
# "live playlist"
'url': 'https://www.globalplayer.com/playlists/8bLk/',
'info_dict': {
'id': '8bLk',
'ext': 'aac',
# 'live_status': 'is_live',
'is_live': True,
'description': r're:(?s).+\bclassical\b.+\bClassic FM Hall [oO]f Fame\b',
'thumbnail': 'https://images.globalplayer.com/images/551379?width=450&signature=oMLPZIoi5_dBSHnTMREW0Xg76mA=',
'title': 're:Classic FM Hall of Fame.+$'
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
station = self._get_page_props(url, video_id)['playlistData']
stream_url = station['streamUrl']
return merge_dicts({
'id': video_id,
'url': stream_url,
'ext': self._request_ext(stream_url, video_id),
'vcodec': 'none',
'is_live': True,
}, traverse_obj(station, {
'title': 'title',
'description': ('description', T(self._clean_desc)),
'thumbnail': 'image',
}), rev=True)
class GlobalPlayerAudioIE(GlobalPlayerBaseIE):
_VALID_URL = r'https?://www\.globalplayer\.com/(?:(?P<podcast>podcasts)/|catchup/\w+/\w+/)(?P<id>\w+)/?(?:$|[?#])'
_TESTS = [{
# podcast
'url': 'https://www.globalplayer.com/podcasts/42KuaM/',
'playlist_mincount': 5,
'info_dict': {
'id': '42KuaM',
'title': 'Filthy Ritual',
'thumbnail': 'md5:60286e7d12d795bd1bbc9efc6cee643e',
'categories': ['Society & Culture', 'True Crime'],
'uploader': 'Global',
'description': r're:(?s).+\bscam\b.+?\bseries available now\b',
},
}, {
# radio catchup
'url': 'https://www.globalplayer.com/catchup/lbc/uk/46vyD7z/',
'playlist_mincount': 2,
'info_dict': {
'id': '46vyD7z',
'description': 'Nick Ferrari At Breakfast is Leading Britain\'s Conversation.',
'title': 'Nick Ferrari',
'thumbnail': 'md5:4df24d8a226f5b2508efbcc6ae874ebf',
},
}]
def _real_extract(self, url):
video_id, podcast = self._match_valid_url(url).group('id', 'podcast')
props = self._get_page_props(url, video_id)
series = props['podcastInfo'] if podcast else props['catchupInfo']
return merge_dicts({
'_type': 'playlist',
'id': video_id,
'entries': [self._extract_audio(ep, series) for ep in traverse_obj(
series, ('episodes', lambda _, v: v['id'] and v['streamUrl']))],
'categories': traverse_obj(series, ('categories', Ellipsis, 'name')) or None,
}, traverse_obj(series, {
'description': ('description', T(self._clean_desc)),
'thumbnail': 'imageUrl',
'title': 'title',
'uploader': 'itunesAuthor', # podcasts only
}), rev=True)
class GlobalPlayerAudioEpisodeIE(GlobalPlayerBaseIE):
_VALID_URL = r'https?://www\.globalplayer\.com/(?:(?P<podcast>podcasts)|catchup/\w+/\w+)/episodes/(?P<id>\w+)/?(?:$|[?#])'
_TESTS = [{
# podcast
'url': 'https://www.globalplayer.com/podcasts/episodes/7DrfNnE/',
'info_dict': {
'id': '7DrfNnE',
'ext': 'mp3',
'title': 'Filthy Ritual - Trailer',
'description': 'md5:1f1562fd0f01b4773b590984f94223e0',
'thumbnail': 'md5:60286e7d12d795bd1bbc9efc6cee643e',
'duration': 225.0,
'timestamp': 1681254900,
'series': 'Filthy Ritual',
'series_id': '42KuaM',
'upload_date': '20230411',
'uploader': 'Global',
},
}, {
# radio catchup
'url': 'https://www.globalplayer.com/catchup/lbc/uk/episodes/2zGq26Vcv1fCWhddC4JAwETXWe/',
'only_matching': True,
# expired: refresh the details with a current show for a full test
'info_dict': {
'id': '2zGq26Vcv1fCWhddC4JAwETXWe',
'ext': 'm4a',
'timestamp': 1682056800,
'series': 'Nick Ferrari',
'thumbnail': 'md5:4df24d8a226f5b2508efbcc6ae874ebf',
'upload_date': '20230421',
'series_id': '46vyD7z',
'description': 'Nick Ferrari At Breakfast is Leading Britain\'s Conversation.',
'title': 'Nick Ferrari',
'duration': 10800.0,
},
}]
def _real_extract(self, url):
video_id, podcast = self._match_valid_url(url).group('id', 'podcast')
props = self._get_page_props(url, video_id)
episode = props['podcastEpisode'] if podcast else props['catchupEpisode']
return self._extract_audio(
episode, traverse_obj(episode, 'podcast', 'show', expected_type=dict) or {})
class GlobalPlayerVideoIE(GlobalPlayerBaseIE):
_VALID_URL = r'https?://www\.globalplayer\.com/videos/(?P<id>\w+)'
_TESTS = [{
'url': 'https://www.globalplayer.com/videos/2JsSZ7Gm2uP/',
'info_dict': {
'id': '2JsSZ7Gm2uP',
'ext': 'mp4',
'description': 'md5:6a9f063c67c42f218e42eee7d0298bfd',
'thumbnail': 'md5:d4498af48e15aae4839ce77b97d39550',
'upload_date': '20230420',
'title': 'Treble Malakai Bayoh sings a sublime Handel aria at Classic FM Live',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
meta = self._get_page_props(url, video_id)['videoData']
return merge_dicts({
'id': video_id,
}, traverse_obj(meta, {
'url': 'url',
'thumbnail': ('image', 'url'),
'title': 'title',
'upload_date': ('publish_date', T(unified_strdate)),
'description': 'description',
}), rev=True)

101
youtube_dl/extractor/hrfernsehen.py Normal file
View File

@@ -0,0 +1,101 @@
# coding: utf-8
from __future__ import unicode_literals
import json
import re
from ..utils import (
int_or_none,
unified_timestamp,
unescapeHTML
)
from .common import InfoExtractor
class HRFernsehenIE(InfoExtractor):
IE_NAME = 'hrfernsehen'
_VALID_URL = r'^https?://www\.(?:hr-fernsehen|hessenschau)\.de/.*,video-(?P<id>[0-9]{6})\.html'
_TESTS = [{
'url': 'https://www.hessenschau.de/tv-sendung/hessenschau-vom-26082020,video-130546.html',
'md5': '5c4e0ba94677c516a2f65a84110fc536',
'info_dict': {
'id': '130546',
'ext': 'mp4',
'description': 'Sturmtief Kirsten fegt über Hessen / Die Corona-Pandemie – eine Chronologie / '
'Sterbehilfe: Die Lage in Hessen / Miss Hessen leitet zwei eigene Unternehmen / '
'Pop-Up Museum zeigt Schwarze Unterhaltung und Black Music',
'subtitles': {'de': [{
'url': 'https://hr-a.akamaihd.net/video/as/hessenschau/2020_08/hrLogo_200826200407_L385592_512x288-25p-500kbit.vtt'
}]},
'timestamp': 1598470200,
'upload_date': '20200826',
'thumbnail': 'https://www.hessenschau.de/tv-sendung/hs_ganz-1554~_t-1598465545029_v-16to9__medium.jpg',
'title': 'hessenschau vom 26.08.2020'
}
}, {
'url': 'https://www.hr-fernsehen.de/sendungen-a-z/mex/sendungen/fair-und-gut---was-hinter-aldis-eigenem-guetesiegel-steckt,video-130544.html',
'only_matching': True
}]
_GEO_COUNTRIES = ['DE']
def extract_airdate(self, loader_data):
airdate_str = loader_data.get('mediaMetadata', {}).get('agf', {}).get('airdate')
if airdate_str is None:
return None
return unified_timestamp(airdate_str)
def extract_formats(self, loader_data):
stream_formats = []
for stream_obj in loader_data["videoResolutionLevels"]:
stream_format = {
'format_id': str(stream_obj['verticalResolution']) + "p",
'height': stream_obj['verticalResolution'],
'url': stream_obj['url'],
}
quality_information = re.search(r'([0-9]{3,4})x([0-9]{3,4})-([0-9]{2})p-([0-9]{3,4})kbit',
stream_obj['url'])
if quality_information:
stream_format['width'] = int_or_none(quality_information.group(1))
stream_format['height'] = int_or_none(quality_information.group(2))
stream_format['fps'] = int_or_none(quality_information.group(3))
stream_format['tbr'] = int_or_none(quality_information.group(4))
stream_formats.append(stream_format)
self._sort_formats(stream_formats)
return stream_formats
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_meta(
['og:title', 'twitter:title', 'name'], webpage)
description = self._html_search_meta(
['description'], webpage)
loader_str = unescapeHTML(self._search_regex(r"data-new-hr-mediaplayer-loader='([^']*)'", webpage, "ardloader"))
loader_data = json.loads(loader_str)
info = {
'id': video_id,
'title': title,
'description': description,
'formats': self.extract_formats(loader_data),
'timestamp': self.extract_airdate(loader_data)
}
if "subtitle" in loader_data:
info["subtitles"] = {"de": [{"url": loader_data["subtitle"]}]}
thumbnails = list(set([t for t in loader_data.get("previewImageUrl", {}).values()]))
if len(thumbnails) > 0:
info["thumbnails"] = [{"url": t} for t in thumbnails]
return info

347
youtube_dl/extractor/ign.py
View File

@@ -1,19 +1,29 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_filter as filter,
compat_HTTPError,
compat_parse_qs,
compat_urllib_parse_urlparse,
compat_urlparse,
)
from ..utils import (
HEADRequest,
determine_ext,
error_to_compat_str,
extract_attributes,
ExtractorError,
int_or_none,
merge_dicts,
orderedSet,
parse_iso8601,
strip_or_none,
try_get,
traverse_obj,
url_or_none,
urljoin,
)
@@ -22,14 +32,102 @@ class IGNBaseIE(InfoExtractor):
return self._download_json(
'http://apis.ign.com/{0}/v3/{0}s/slug/{1}'.format(self._PAGE_TYPE, slug), slug)
def _checked_call_api(self, slug):
try:
return self._call_api(slug)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
e.cause.args = e.cause.args or [
e.cause.geturl(), e.cause.getcode(), e.cause.reason]
raise ExtractorError(
'Content not found: expired?', cause=e.cause,
expected=True)
raise
def _extract_video_info(self, video, fatal=True):
video_id = video['videoId']
formats = []
refs = traverse_obj(video, 'refs', expected_type=dict) or {}
m3u8_url = url_or_none(refs.get('m3uUrl'))
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
f4m_url = url_or_none(refs.get('f4mUrl'))
if f4m_url:
formats.extend(self._extract_f4m_formats(
f4m_url, video_id, f4m_id='hds', fatal=False))
for asset in (video.get('assets') or []):
asset_url = url_or_none(asset.get('url'))
if not asset_url:
continue
formats.append({
'url': asset_url,
'tbr': int_or_none(asset.get('bitrate'), 1000),
'fps': int_or_none(asset.get('frame_rate')),
'height': int_or_none(asset.get('height')),
'width': int_or_none(asset.get('width')),
})
mezzanine_url = traverse_obj(
video, ('system', 'mezzanineUrl'), expected_type=url_or_none)
if mezzanine_url:
formats.append({
'ext': determine_ext(mezzanine_url, 'mp4'),
'format_id': 'mezzanine',
'preference': 1,
'url': mezzanine_url,
})
if formats or fatal:
self._sort_formats(formats)
else:
return
thumbnails = traverse_obj(
video, ('thumbnails', Ellipsis, {'url': 'url'}), expected_type=url_or_none)
tags = traverse_obj(
video, ('tags', Ellipsis, 'displayName'),
expected_type=lambda x: x.strip() or None)
metadata = traverse_obj(video, 'metadata', expected_type=dict) or {}
title = traverse_obj(
metadata, 'longTitle', 'title', 'name',
expected_type=lambda x: x.strip() or None)
return {
'id': video_id,
'title': title,
'description': strip_or_none(metadata.get('description')),
'timestamp': parse_iso8601(metadata.get('publishDate')),
'duration': int_or_none(metadata.get('duration')),
'thumbnails': thumbnails,
'formats': formats,
'tags': tags,
}
# yt-dlp shim
@classmethod
def _extract_from_webpage(cls, url, webpage):
for embed_url in orderedSet(
cls._extract_embed_urls(url, webpage) or [], lazy=True):
yield cls.url_result(embed_url, None if cls._VALID_URL is False else cls)
class IGNIE(IGNBaseIE):
"""
Extractor for some of the IGN sites, like www.ign.com, es.ign.com de.ign.com.
Some videos of it.ign.com are also supported
"""
_VALID_URL = r'https?://(?:.+?\.ign|www\.pcmag)\.com/videos/(?:\d{4}/\d{2}/\d{2}/)?(?P<id>[^/?&#]+)'
_VIDEO_PATH_RE = r'/(?:\d{4}/\d{2}/\d{2}/)?(?P<id>.+?)'
_PLAYLIST_PATH_RE = r'(?:/?\?(?P<filt>[^&#]+))?'
_VALID_URL = (
r'https?://(?:.+?\.ign|www\.pcmag)\.com/videos(?:%s)'
% '|'.join((_VIDEO_PATH_RE + r'(?:[/?&#]|$)', _PLAYLIST_PATH_RE)))
IE_NAME = 'ign.com'
_PAGE_TYPE = 'video'
@@ -44,7 +142,10 @@ class IGNIE(IGNBaseIE):
'timestamp': 1370440800,
'upload_date': '20130605',
'tags': 'count:9',
}
},
'params': {
'nocheckcertificate': True,
},
}, {
'url': 'http://www.pcmag.com/videos/2015/01/06/010615-whats-new-now-is-gogo-snooping-on-your-data',
'md5': 'f1581a6fe8c5121be5b807684aeac3f6',
@@ -56,86 +157,51 @@ class IGNIE(IGNBaseIE):
'timestamp': 1420571160,
'upload_date': '20150106',
'tags': 'count:4',
}
},
'skip': '404 Not Found',
}, {
'url': 'https://www.ign.com/videos/is-a-resident-evil-4-remake-on-the-way-ign-daily-fix',
'only_matching': True,
}]
@classmethod
def _extract_embed_urls(cls, url, webpage):
grids = re.findall(
r'''(?s)<section\b[^>]+\bclass\s*=\s*['"](?:[\w-]+\s+)*?content-feed-grid(?!\B|-)[^>]+>(.+?)</section[^>]*>''',
webpage)
return filter(None,
(urljoin(url, m.group('path')) for m in re.finditer(
r'''<a\b[^>]+\bhref\s*=\s*('|")(?P<path>/videos%s)\1'''
% cls._VIDEO_PATH_RE, grids[0] if grids else '')))
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
display_id = m.group('id')
if display_id:
return self._extract_video(url, display_id)
display_id = m.group('filt') or 'all'
return self._extract_playlist(url, display_id)
def _extract_playlist(self, url, display_id):
webpage = self._download_webpage(url, display_id)
return self.playlist_result(
(self.url_result(u, ie=self.ie_key())
for u in self._extract_embed_urls(url, webpage)),
playlist_id=display_id)
def _extract_video(self, url, display_id):
display_id = self._match_id(url)
video = self._call_api(display_id)
video_id = video['videoId']
metadata = video['metadata']
title = metadata.get('longTitle') or metadata.get('title') or metadata['name']
video = self._checked_call_api(display_id)
formats = []
refs = video.get('refs') or {}
info = self._extract_video_info(video)
m3u8_url = refs.get('m3uUrl')
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
f4m_url = refs.get('f4mUrl')
if f4m_url:
formats.extend(self._extract_f4m_formats(
f4m_url, video_id, f4m_id='hds', fatal=False))
for asset in (video.get('assets') or []):
asset_url = asset.get('url')
if not asset_url:
continue
formats.append({
'url': asset_url,
'tbr': int_or_none(asset.get('bitrate'), 1000),
'fps': int_or_none(asset.get('frame_rate')),
'height': int_or_none(asset.get('height')),
'width': int_or_none(asset.get('width')),
})
mezzanine_url = try_get(video, lambda x: x['system']['mezzanineUrl'])
if mezzanine_url:
formats.append({
'ext': determine_ext(mezzanine_url, 'mp4'),
'format_id': 'mezzanine',
'preference': 1,
'url': mezzanine_url,
})
self._sort_formats(formats)
thumbnails = []
for thumbnail in (video.get('thumbnails') or []):
thumbnail_url = thumbnail.get('url')
if not thumbnail_url:
continue
thumbnails.append({
'url': thumbnail_url,
})
tags = []
for tag in (video.get('tags') or []):
display_name = tag.get('displayName')
if not display_name:
continue
tags.append(display_name)
return {
'id': video_id,
'title': title,
'description': strip_or_none(metadata.get('description')),
'timestamp': parse_iso8601(metadata.get('publishDate')),
'duration': int_or_none(metadata.get('duration')),
return merge_dicts({
'display_id': display_id,
'thumbnails': thumbnails,
'formats': formats,
'tags': tags,
}
}, info)
class IGNVideoIE(InfoExtractor):
class IGNVideoIE(IGNBaseIE):
_VALID_URL = r'https?://.+?\.ign\.com/(?:[a-z]{2}/)?[^/]+/(?P<id>\d+)/(?:video|trailer)/'
_TESTS = [{
'url': 'http://me.ign.com/en/videos/112203/video/how-hitman-aims-to-be-different-than-every-other-s',
@@ -147,7 +213,8 @@ class IGNVideoIE(InfoExtractor):
'description': 'Taking out assassination targets in Hitman has never been more stylish.',
'timestamp': 1444665600,
'upload_date': '20151012',
}
},
'expected_warnings': ['HTTP Error 400: Bad Request'],
}, {
'url': 'http://me.ign.com/ar/angry-birds-2/106533/video/lrd-ldyy-lwl-lfylm-angry-birds',
'only_matching': True,
@@ -167,22 +234,38 @@ class IGNVideoIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
req = HEADRequest(url.rsplit('/', 1)[0] + '/embed')
url = self._request_webpage(req, video_id).geturl()
parsed_url = compat_urlparse.urlparse(url)
embed_url = compat_urlparse.urlunparse(
parsed_url._replace(path=parsed_url.path.rsplit('/', 1)[0] + '/embed'))
webpage, urlh = self._download_webpage_handle(embed_url, video_id)
new_url = urlh.geturl()
ign_url = compat_parse_qs(
compat_urllib_parse_urlparse(url).query).get('url', [None])[0]
compat_urlparse.urlparse(new_url).query).get('url', [None])[-1]
if ign_url:
return self.url_result(ign_url, IGNIE.ie_key())
return self.url_result(url)
video = self._search_regex(r'(<div\b[^>]+\bdata-video-id\s*=\s*[^>]+>)', webpage, 'video element', fatal=False)
if not video:
if new_url == url:
raise ExtractorError('Redirect loop: ' + url)
return self.url_result(new_url)
video = extract_attributes(video)
video_data = video.get('data-settings') or '{}'
video_data = self._parse_json(video_data, video_id)['video']
info = self._extract_video_info(video_data)
return merge_dicts({
'display_id': video_id,
}, info)
class IGNArticleIE(IGNBaseIE):
_VALID_URL = r'https?://.+?\.ign\.com/(?:articles(?:/\d{4}/\d{2}/\d{2})?|(?:[a-z]{2}/)?feature/\d+)/(?P<id>[^/?&#]+)'
_VALID_URL = r'https?://.+?\.ign\.com/(?:articles(?:/\d{4}/\d{2}/\d{2})?|(?:[a-z]{2}/)?(?:[\w-]+/)*?feature/\d+)/(?P<id>[^/?&#]+)'
_PAGE_TYPE = 'article'
_TESTS = [{
'url': 'http://me.ign.com/en/feature/15775/100-little-things-in-gta-5-that-will-blow-your-mind',
'info_dict': {
'id': '524497489e4e8ff5848ece34',
'id': '72113',
'title': '100 Little Things in GTA 5 That Will Blow Your Mind',
},
'playlist': [
@@ -190,7 +273,7 @@ class IGNArticleIE(IGNBaseIE):
'info_dict': {
'id': '5ebbd138523268b93c9141af17bec937',
'ext': 'mp4',
'title': 'GTA 5 Video Review',
'title': 'Grand Theft Auto V Video Review',
'description': 'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.',
'timestamp': 1379339880,
'upload_date': '20130916',
@@ -200,7 +283,7 @@ class IGNArticleIE(IGNBaseIE):
'info_dict': {
'id': '638672ee848ae4ff108df2a296418ee2',
'ext': 'mp4',
'title': '26 Twisted Moments from GTA 5 in Slow Motion',
'title': 'GTA 5 In Slow Motion',
'description': 'The twisted beauty of GTA 5 in stunning slow motion.',
'timestamp': 1386878820,
'upload_date': '20131212',
@@ -208,16 +291,17 @@ class IGNArticleIE(IGNBaseIE):
},
],
'params': {
'playlist_items': '2-3',
'skip_download': True,
},
'expected_warnings': ['Backend fetch failed'],
}, {
'url': 'http://www.ign.com/articles/2014/08/15/rewind-theater-wild-trailer-gamescom-2014?watch',
'info_dict': {
'id': '53ee806780a81ec46e0790f8',
'title': 'Rewind Theater - Wild Trailer Gamescom 2014',
},
'playlist_count': 2,
'playlist_count': 1,
'expected_warnings': ['Backend fetch failed'],
}, {
# videoId pattern
'url': 'http://www.ign.com/articles/2017/06/08/new-ducktales-short-donalds-birthday-doesnt-go-as-planned',
@@ -240,18 +324,91 @@ class IGNArticleIE(IGNBaseIE):
'only_matching': True,
}]
def _checked_call_api(self, slug):
try:
return self._call_api(slug)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError):
e.cause.args = e.cause.args or [
e.cause.geturl(), e.cause.getcode(), e.cause.reason]
if e.cause.code == 404:
raise ExtractorError(
'Content not found: expired?', cause=e.cause,
expected=True)
elif e.cause.code == 503:
self.report_warning(error_to_compat_str(e.cause))
return
raise
def _search_nextjs_data(self, webpage, video_id, **kw):
return self._parse_json(
self._search_regex(
r'(?s)<script[^>]+id=[\'"]__NEXT_DATA__[\'"][^>]*>([^<]+)</script>',
webpage, 'next.js data', **kw),
video_id, **kw)
def _real_extract(self, url):
display_id = self._match_id(url)
article = self._call_api(display_id)
article = self._checked_call_api(display_id)
def entries():
media_url = try_get(article, lambda x: x['mediaRelations'][0]['media']['metadata']['url'])
if media_url:
yield self.url_result(media_url, IGNIE.ie_key())
for content in (article.get('content') or []):
for video_url in re.findall(r'(?:\[(?:ignvideo\s+url|youtube\s+clip_id)|<iframe[^>]+src)="([^"]+)"', content):
yield self.url_result(video_url)
if article:
# obsolete ?
def entries():
media_url = traverse_obj(
article, ('mediaRelations', 0, 'media', 'metadata', 'url'),
expected_type=url_or_none)
if media_url:
yield self.url_result(media_url, IGNIE.ie_key())
for content in (article.get('content') or []):
for video_url in re.findall(r'(?:\[(?:ignvideo\s+url|youtube\s+clip_id)|<iframe[^>]+src)="([^"]+)"', content):
if url_or_none(video_url):
yield self.url_result(video_url)
return self.playlist_result(
entries(), article.get('articleId'),
traverse_obj(
article, ('metadata', 'headline'),
expected_type=lambda x: x.strip() or None))
webpage = self._download_webpage(url, display_id)
playlist_id = self._html_search_meta('dable:item_id', webpage, default=None)
if playlist_id:
def entries():
for m in re.finditer(
r'''(?s)<object\b[^>]+\bclass\s*=\s*("|')ign-videoplayer\1[^>]*>(?P<params>.+?)</object''',
webpage):
flashvars = self._search_regex(
r'''(<param\b[^>]+\bname\s*=\s*("|')flashvars\2[^>]*>)''',
m.group('params'), 'flashvars', default='')
flashvars = compat_parse_qs(extract_attributes(flashvars).get('value') or '')
v_url = url_or_none((flashvars.get('url') or [None])[-1])
if v_url:
yield self.url_result(v_url)
else:
playlist_id = self._search_regex(
r'''\bdata-post-id\s*=\s*("|')(?P<id>[\da-f]+)\1''',
webpage, 'id', group='id', default=None)
nextjs_data = self._search_nextjs_data(webpage, display_id)
def entries():
for player in traverse_obj(
nextjs_data,
('props', 'apolloState', 'ROOT_QUERY', lambda k, _: k.startswith('videoPlayerProps('), '__ref')):
# skip promo links (which may not always be served, eg GH CI servers)
if traverse_obj(nextjs_data,
('props', 'apolloState', player.replace('PlayerProps', 'ModernContent')),
expected_type=dict):
continue
video = traverse_obj(nextjs_data, ('props', 'apolloState', player), expected_type=dict) or {}
info = self._extract_video_info(video, fatal=False)
if info:
yield merge_dicts({
'display_id': display_id,
}, info)
return self.playlist_result(
entries(), article.get('articleId'),
strip_or_none(try_get(article, lambda x: x['metadata']['headline'])))
entries(), playlist_id or display_id,
re.sub(r'\s+-\s+IGN\s*$', '', self._og_search_title(webpage, default='')) or None)

348
youtube_dl/extractor/imgur.py
View File

@@ -1,101 +1,267 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
ExtractorError,
float_or_none,
int_or_none,
js_to_json,
merge_dicts,
mimetype2ext,
ExtractorError,
parse_iso8601,
T,
traverse_obj,
txt_or_none,
url_or_none,
)
class ImgurIE(InfoExtractor):
_VALID_URL = r'https?://(?:i\.)?imgur\.com/(?!(?:a|gallery|(?:t(?:opic)?|r)/[^/]+)/)(?P<id>[a-zA-Z0-9]+)'
class ImgurBaseIE(InfoExtractor):
# hard-coded value, as also used by ArchiveTeam
_CLIENT_ID = '546c25a59c58ad7'
@classmethod
def _imgur_result(cls, item_id):
return cls.url_result('imgur:%s' % item_id, ImgurIE.ie_key(), item_id)
def _call_api(self, endpoint, video_id, **kwargs):
return self._download_json(
'https://api.imgur.com/post/v1/%s/%s?client_id=%s&include=media,account' % (endpoint, video_id, self._CLIENT_ID),
video_id, **kwargs)
@staticmethod
def get_description(s):
if 'Discover the magic of the internet at Imgur' in s:
return None
return txt_or_none(s)
class ImgurIE(ImgurBaseIE):
_VALID_URL = r'''(?x)
(?:
https?://(?:i\.)?imgur\.com/(?!(?:a|gallery|t|topic|r)/)|
imgur:
)(?P<id>[a-zA-Z0-9]+)
'''
_TESTS = [{
'url': 'https://i.imgur.com/A61SaA1.gifv',
'url': 'https://imgur.com/A61SaA1',
'info_dict': {
'id': 'A61SaA1',
'ext': 'mp4',
'title': 're:Imgur GIF$|MRW gifv is up and running without any bugs$',
'timestamp': 1416446068,
'upload_date': '20141120',
},
}, {
'url': 'https://imgur.com/A61SaA1',
'url': 'https://i.imgur.com/A61SaA1.gifv',
'only_matching': True,
}, {
'url': 'https://i.imgur.com/crGpqCV.mp4',
'only_matching': True,
}, {
# no title
# previously, no title
'url': 'https://i.imgur.com/jxBXAMC.gifv',
'only_matching': True,
'info_dict': {
'id': 'jxBXAMC',
'ext': 'mp4',
'title': 'Fahaka puffer feeding',
'timestamp': 1533835503,
'upload_date': '20180809',
},
}]
def _extract_twitter_formats(self, html, tw_id='twitter', **kwargs):
fatal = kwargs.pop('fatal', False)
tw_stream = self._html_search_meta('twitter:player:stream', html, fatal=fatal, **kwargs)
if not tw_stream:
return []
ext = mimetype2ext(self._html_search_meta(
'twitter:player:stream:content_type', html, default=None))
width, height = (int_or_none(self._html_search_meta('twitter:player:' + v, html, default=None))
for v in ('width', 'height'))
return [{
'format_id': tw_id,
'url': tw_stream,
'ext': ext or determine_ext(tw_stream),
'width': width,
'height': height,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._call_api('media', video_id, fatal=False, expected_status=404)
webpage = self._download_webpage(
'https://i.imgur.com/{id}.gifv'.format(id=video_id), video_id)
'https://i.imgur.com/{id}.gifv'.format(id=video_id), video_id, fatal=not data) or ''
width = int_or_none(self._og_search_property(
'video:width', webpage, default=None))
height = int_or_none(self._og_search_property(
'video:height', webpage, default=None))
if not traverse_obj(data, ('media', 0, (
('type', T(lambda t: t == 'video' or None)),
('metadata', 'is_animated'))), get_all=False):
raise ExtractorError(
'%s is not a video or animated image' % video_id,
expected=True)
media_fmt = traverse_obj(data, ('media', 0, {
'url': ('url', T(url_or_none)),
'ext': 'ext',
'width': ('width', T(int_or_none)),
'height': ('height', T(int_or_none)),
'filesize': ('size', T(int_or_none)),
'acodec': ('metadata', 'has_sound', T(lambda b: None if b else 'none')),
}))
media_url = traverse_obj(media_fmt, 'url')
if media_url:
if not media_fmt.get('ext'):
media_fmt['ext'] = mimetype2ext(traverse_obj(
data, ('media', 0, 'mime_type'))) or determine_ext(media_url)
if traverse_obj(data, ('media', 0, 'type')) == 'image':
media_fmt['acodec'] = 'none'
media_fmt.setdefault('preference', -10)
tw_formats = self._extract_twitter_formats(webpage)
if traverse_obj(tw_formats, (0, 'url')) == media_url:
tw_formats = []
else:
# maybe this isn't an animated image/video?
self._check_formats(tw_formats, video_id)
video_elements = self._search_regex(
r'(?s)<div class="video-elements">(.*?)</div>',
webpage, 'video elements', default=None)
if not video_elements:
if not (video_elements or tw_formats or media_url):
raise ExtractorError(
'No sources found for video %s. Maybe an image?' % video_id,
'No sources found for video %s. Maybe a plain image?' % video_id,
expected=True)
formats = []
for m in re.finditer(r'<source\s+src="(?P<src>[^"]+)"\s+type="(?P<type>[^"]+)"', video_elements):
formats.append({
'format_id': m.group('type').partition('/')[2],
'url': self._proto_relative_url(m.group('src')),
'ext': mimetype2ext(m.group('type')),
'width': width,
'height': height,
def mung_format(fmt, *extra):
fmt.update({
'http_headers': {
'User-Agent': 'youtube-dl (like wget)',
},
})
for d in extra:
fmt.update(d)
return fmt
gif_json = self._search_regex(
r'(?s)var\s+videoItem\s*=\s*(\{.*?\})',
webpage, 'GIF code', fatal=False)
if gif_json:
gifd = self._parse_json(
gif_json, video_id, transform_source=js_to_json)
formats.append({
'format_id': 'gif',
'preference': -10,
'width': width,
'height': height,
'ext': 'gif',
'acodec': 'none',
'vcodec': 'gif',
'container': 'gif',
'url': self._proto_relative_url(gifd['gifUrl']),
'filesize': gifd.get('size'),
'http_headers': {
'User-Agent': 'youtube-dl (like wget)',
},
})
if video_elements:
def og_get_size(media_type):
return dict((p, int_or_none(self._og_search_property(
':'.join((media_type, p)), webpage, default=None)))
for p in ('width', 'height'))
size = og_get_size('video')
if all(v is None for v in size.values()):
size = og_get_size('image')
formats = traverse_obj(
re.finditer(r'<source\s+src="(?P<src>[^"]+)"\s+type="(?P<type>[^"]+)"', video_elements),
(Ellipsis, {
'format_id': ('type', T(lambda s: s.partition('/')[2])),
'url': ('src', T(self._proto_relative_url)),
'ext': ('type', T(mimetype2ext)),
}, T(lambda f: mung_format(f, size))))
gif_json = self._search_regex(
r'(?s)var\s+videoItem\s*=\s*(\{.*?\})',
webpage, 'GIF code', fatal=False)
MUST_BRANCH = (None, T(lambda _: None))
formats.extend(traverse_obj(gif_json, (
T(lambda j: self._parse_json(
j, video_id, transform_source=js_to_json, fatal=False)), {
'url': ('gifUrl', T(self._proto_relative_url)),
'filesize': ('size', T(int_or_none)),
}, T(lambda f: mung_format(f, size, {
'format_id': 'gif',
'preference': -10, # gifs are worse than videos
'ext': 'gif',
'acodec': 'none',
'vcodec': 'gif',
'container': 'gif',
})), MUST_BRANCH)))
else:
formats = []
# maybe add formats from JSON or page Twitter metadata
if not any((u == media_url) for u in traverse_obj(formats, (Ellipsis, 'url'))):
formats.append(mung_format(media_fmt))
tw_url = traverse_obj(tw_formats, (0, 'url'))
if not any((u == tw_url) for u in traverse_obj(formats, (Ellipsis, 'url'))):
formats.extend(mung_format(f) for f in tw_formats)
self._sort_formats(formats)
return {
return merge_dicts(traverse_obj(data, {
'uploader_id': ('account_id', T(txt_or_none),
T(lambda a: a if int_or_none(a) != 0 else None)),
'uploader': ('account', 'username', T(txt_or_none)),
'uploader_url': ('account', 'avatar_url', T(url_or_none)),
'like_count': ('upvote_count', T(int_or_none)),
'dislike_count': ('downvote_count', T(int_or_none)),
'comment_count': ('comment_count', T(int_or_none)),
'age_limit': ('is_mature', T(lambda x: 18 if x else None)),
'timestamp': (('updated_at', 'created_at'), T(parse_iso8601)),
'release_timestamp': ('created_at', T(parse_iso8601)),
}, get_all=False), traverse_obj(data, ('media', 0, 'metadata', {
'title': ('title', T(txt_or_none)),
'description': ('description', T(self.get_description)),
'duration': ('duration', T(float_or_none)),
'timestamp': (('updated_at', 'created_at'), T(parse_iso8601)),
'release_timestamp': ('created_at', T(parse_iso8601)),
})), {
'id': video_id,
'formats': formats,
'title': self._og_search_title(webpage, default=video_id),
}
'title': self._og_search_title(webpage, default='Imgur video ' + video_id),
'description': self.get_description(self._og_search_description(webpage)),
'thumbnail': url_or_none(self._html_search_meta('thumbnailUrl', webpage, default=None)),
})
class ImgurGalleryIE(InfoExtractor):
class ImgurGalleryBaseIE(ImgurBaseIE):
_GALLERY = True
def _real_extract(self, url):
gallery_id = self._match_id(url)
data = self._call_api('albums', gallery_id, fatal=False, expected_status=404)
info = traverse_obj(data, {
'title': ('title', T(txt_or_none)),
'description': ('description', T(self.get_description)),
})
if traverse_obj(data, 'is_album'):
def yield_media_ids():
for m_id in traverse_obj(data, (
'media', lambda _, v: v.get('type') == 'video' or v['metadata']['is_animated'],
'id', T(txt_or_none))):
yield m_id
# if a gallery with exactly one video, apply album metadata to video
media_id = (
self._GALLERY
and traverse_obj(data, ('image_count', T(lambda c: c == 1)))
and next(yield_media_ids(), None))
if not media_id:
result = self.playlist_result(
map(self._imgur_result, yield_media_ids()), gallery_id)
result.update(info)
return result
gallery_id = media_id
result = self._imgur_result(gallery_id)
info['_type'] = 'url_transparent'
result.update(info)
return result
class ImgurGalleryIE(ImgurGalleryBaseIE):
IE_NAME = 'imgur:gallery'
_VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:gallery|(?:t(?:opic)?|r)/[^/]+)/(?P<id>[a-zA-Z0-9]+)'
@@ -106,49 +272,93 @@ class ImgurGalleryIE(InfoExtractor):
'title': 'Adding faces make every GIF better',
},
'playlist_count': 25,
'skip': 'Zoinks! You\'ve taken a wrong turn.',
}, {
# TODO: static images - replace with animated/video gallery
'url': 'http://imgur.com/topic/Aww/ll5Vk',
'only_matching': True,
}, {
'url': 'https://imgur.com/gallery/YcAQlkx',
'add_ies': ['Imgur'],
'info_dict': {
'id': 'YcAQlkx',
'ext': 'mp4',
'title': 'Classic Steve Carell gif...cracks me up everytime....damn the repost downvotes....',
}
'timestamp': 1358554297,
'upload_date': '20130119',
'uploader_id': '1648642',
'uploader': 'wittyusernamehere',
},
}, {
# TODO: static image - replace with animated/video gallery
'url': 'http://imgur.com/topic/Funny/N8rOudd',
'only_matching': True,
}, {
'url': 'http://imgur.com/r/aww/VQcQPhM',
'only_matching': True,
'add_ies': ['Imgur'],
'info_dict': {
'id': 'VQcQPhM',
'ext': 'mp4',
'title': 'The boss is here',
'timestamp': 1476494751,
'upload_date': '20161015',
'uploader_id': '19138530',
'uploader': 'thematrixcam',
},
},
# from PR #16674
{
'url': 'https://imgur.com/t/unmuted/6lAn9VQ',
'info_dict': {
'id': '6lAn9VQ',
'title': 'Penguins !',
},
'playlist_count': 3,
}, {
'url': 'https://imgur.com/t/unmuted/kx2uD3C',
'add_ies': ['Imgur'],
'info_dict': {
'id': 'ZVMv45i',
'ext': 'mp4',
'title': 'Intruder',
'timestamp': 1528129683,
'upload_date': '20180604',
},
}, {
'url': 'https://imgur.com/t/unmuted/wXSK0YH',
'add_ies': ['Imgur'],
'info_dict': {
'id': 'JCAP4io',
'ext': 'mp4',
'title': 're:I got the blues$',
'description': 'Luka’s vocal stylings.\n\nFP edit: don’t encourage me. I’ll never stop posting Luka and friends.',
'timestamp': 1527809525,
'upload_date': '20180531',
},
}]
def _real_extract(self, url):
gallery_id = self._match_id(url)
data = self._download_json(
'https://imgur.com/gallery/%s.json' % gallery_id,
gallery_id)['data']['image']
if data.get('is_album'):
entries = [
self.url_result('http://imgur.com/%s' % image['hash'], ImgurIE.ie_key(), image['hash'])
for image in data['album_images']['images'] if image.get('hash')]
return self.playlist_result(entries, gallery_id, data.get('title'), data.get('description'))
return self.url_result('http://imgur.com/%s' % gallery_id, ImgurIE.ie_key(), gallery_id)
class ImgurAlbumIE(ImgurGalleryIE):
class ImgurAlbumIE(ImgurGalleryBaseIE):
IE_NAME = 'imgur:album'
_VALID_URL = r'https?://(?:i\.)?imgur\.com/a/(?P<id>[a-zA-Z0-9]+)'
_GALLERY = False
_TESTS = [{
# TODO: only static images - replace with animated/video gallery
'url': 'http://imgur.com/a/j6Orj',
'only_matching': True,
},
# from PR #21693
{
'url': 'https://imgur.com/a/iX265HX',
'info_dict': {
'id': 'j6Orj',
'title': 'A Literary Analysis of "Star Wars: The Force Awakens"',
'id': 'iX265HX',
'title': 'enen-no-shouboutai'
},
'playlist_count': 12,
'playlist_count': 2,
}, {
'url': 'https://imgur.com/a/8pih2Ed',
'info_dict': {
'id': '8pih2Ed'
},
'playlist_mincount': 1,
}]

9
youtube_dl/extractor/infoq.py
View File

@@ -1,6 +1,9 @@
# coding: utf-8
from __future__ import unicode_literals
from ..utils import (
ExtractorError,
)
from ..compat import (
compat_b64decode,
@@ -90,7 +93,11 @@ class InfoQIE(BokeCCBaseIE):
}]
def _extract_http_audio(self, webpage, video_id):
fields = self._form_hidden_inputs('mp3Form', webpage)
try:
fields = self._form_hidden_inputs('mp3Form', webpage)
except ExtractorError:
fields = {}
http_audio_url = fields.get('filename')
if not http_audio_url:
return []

382
youtube_dl/extractor/itv.py
View File

@@ -3,123 +3,266 @@ from __future__ import unicode_literals
import json
import re
import sys
from .common import InfoExtractor
from .brightcove import BrightcoveNewIE
from ..compat import (
compat_HTTPError,
compat_integer_types,
compat_kwargs,
compat_urlparse,
)
from ..utils import (
clean_html,
determine_ext,
error_to_compat_str,
extract_attributes,
get_element_by_class,
JSON_LD_RE,
ExtractorError,
get_element_by_attribute,
int_or_none,
merge_dicts,
parse_duration,
parse_iso8601,
remove_start,
smuggle_url,
strip_or_none,
traverse_obj,
url_or_none,
urljoin,
)
class ITVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?itv\.com/hub/[^/]+/(?P<id>[0-9a-zA-Z]+)'
_GEO_COUNTRIES = ['GB']
class ITVBaseIE(InfoExtractor):
def _search_nextjs_data(self, webpage, video_id, **kw):
transform_source = kw.pop('transform_source', None)
fatal = kw.pop('fatal', True)
return self._parse_json(
self._search_regex(
r'''<script\b[^>]+\bid=('|")__NEXT_DATA__\1[^>]*>(?P<js>[^<]+)</script>''',
webpage, 'next.js data', group='js', fatal=fatal, **kw),
video_id, transform_source=transform_source, fatal=fatal)
def __handle_request_webpage_error(self, err, video_id=None, errnote=None, fatal=True):
if errnote is False:
return False
if errnote is None:
errnote = 'Unable to download webpage'
errmsg = '%s: %s' % (errnote, error_to_compat_str(err))
if fatal:
raise ExtractorError(errmsg, sys.exc_info()[2], cause=err, video_id=video_id)
else:
self._downloader.report_warning(errmsg)
return False
@staticmethod
def _vanilla_ua_header():
return {'User-Agent': 'Mozilla/5.0'}
def _download_webpage_handle(self, url, video_id, *args, **kwargs):
# specialised to (a) use vanilla UA (b) detect geo-block
params = self._downloader.params
nkwargs = {}
if (
'user_agent' not in params
and not any(re.match(r'(?i)user-agent\s*:', h)
for h in (params.get('headers') or []))
and 'User-Agent' not in (kwargs.get('headers') or {})):
kwargs.setdefault('headers', {})
kwargs['headers'] = self._vanilla_ua_header()
nkwargs = kwargs
if kwargs.get('expected_status') is not None:
exp = kwargs['expected_status']
if isinstance(exp, compat_integer_types):
exp = [exp]
if isinstance(exp, (list, tuple)) and 403 not in exp:
kwargs['expected_status'] = [403]
kwargs['expected_status'].extend(exp)
nkwargs = kwargs
else:
kwargs['expected_status'] = 403
nkwargs = kwargs
if nkwargs:
kwargs = compat_kwargs(kwargs)
ret = super(ITVBaseIE, self)._download_webpage_handle(url, video_id, *args, **kwargs)
if ret is False:
return ret
webpage, urlh = ret
if urlh.getcode() == 403:
# geo-block error is like this, with an unnecessary 'Of':
# '{\n "Message" : "Request Originated Outside Of Allowed Geographic Region",\
# \n "TransactionId" : "oas-magni-475082-xbYF0W"\n}'
if '"Request Originated Outside Of Allowed Geographic Region"' in webpage:
self.raise_geo_restricted(countries=['GB'])
ret = self.__handle_request_webpage_error(
compat_HTTPError(urlh.geturl(), 403, 'HTTP Error 403: Forbidden', urlh.headers, urlh),
fatal=kwargs.get('fatal'))
return ret
class ITVIE(ITVBaseIE):
_VALID_URL = r'https?://(?:www\.)?itv\.com/(?:(?P<w>watch)|hub)/[^/]+/(?(w)[\w-]+/)(?P<id>\w+)'
_IE_DESC = 'ITVX'
_TESTS = [{
'note': 'Hub URLs redirect to ITVX',
'url': 'https://www.itv.com/hub/liar/2a4547a0012',
'info_dict': {
'id': '2a4547a0012',
'ext': 'mp4',
'title': 'Liar - Series 2 - Episode 6',
'description': 'md5:d0f91536569dec79ea184f0a44cca089',
'series': 'Liar',
'season_number': 2,
'episode_number': 6,
},
'params': {
# m3u8 download
'skip_download': True,
},
'only_matching': True,
}, {
# unavailable via data-playlist-url
'note': 'Hub page unavailable via data-playlist-url (404 now)',
'url': 'https://www.itv.com/hub/through-the-keyhole/2a2271a0033',
'only_matching': True,
}, {
# InvalidVodcrid
'note': 'Hub page with InvalidVodcrid (404 now)',
'url': 'https://www.itv.com/hub/james-martins-saturday-morning/2a5159a0034',
'only_matching': True,
}, {
# ContentUnavailable
'note': 'Hub page with ContentUnavailable (404 now)',
'url': 'https://www.itv.com/hub/whos-doing-the-dishes/2a2898a0024',
'only_matching': True,
}]
}, {
'note': 'ITVX, or itvX, show',
'url': 'https://www.itv.com/watch/vera/1a7314/1a7314a0014',
'md5': 'bd0ad666b2c058fffe7d036785880064',
'info_dict': {
'id': '1a7314a0014',
'ext': 'mp4',
'title': 'Vera - Series 3 - Episode 4 - Prodigal Son',
'description': 'Vera and her team investigate the fatal stabbing of an ex-Met police officer outside a busy Newcastle nightclub - but there aren\'t many clues.',
'timestamp': 1653591600,
'upload_date': '20220526',
'uploader': 'ITVX',
'thumbnail': r're:https://\w+\.itv\.com/images/(?:\w+/)+\d+x\d+\?',
'duration': 5340.8,
'age_limit': 16,
'series': 'Vera',
'series_number': 3,
'episode': 'Prodigal Son',
'episode_number': 4,
'channel': 'ITV3',
'categories': list,
},
'params': {
# m3u8 download
# 'skip_download': True,
},
'skip': 'only available in UK',
}, {
'note': 'Latest ITV news bulletin: details change daily',
'url': 'https://www.itv.com/watch/news/varies-but-is-not-checked/6js5d0f',
'info_dict': {
'id': '6js5d0f',
'ext': 'mp4',
'title': r're:The latest ITV News headlines - \S.+',
'description': r'''re:.* today's top stories from the ITV News team.$''',
'timestamp': int,
'upload_date': r're:2\d\d\d(?:0[1-9]|1[0-2])(?:[012][1-9]|3[01])',
'uploader': 'ITVX',
'thumbnail': r're:https://images\.ctfassets\.net/(?:\w+/)+[\w.]+\.(?:jpg|png)',
'duration': float,
'age_limit': None,
},
'params': {
# variable download
# 'skip_download': True,
},
'skip': 'only available in UK',
}
]
def _og_extract(self, webpage, require_title=False):
return {
'title': self._og_search_title(webpage, fatal=require_title),
'description': self._og_search_description(webpage, default=None),
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'uploader': self._og_search_property('site_name', webpage, default=None),
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
params = extract_attributes(self._search_regex(
r'(?s)(<[^>]+id="video"[^>]*>)', webpage, 'params'))
ios_playlist_url = params.get('data-video-playlist') or params['data-video-id']
hmac = params['data-video-hmac']
webpage = self._download_webpage(url, video_id)
# now quite different params!
params = extract_attributes(self._search_regex(
r'''(<[^>]+\b(?:class|data-testid)\s*=\s*("|')genie-container\2[^>]*>)''',
webpage, 'params'))
ios_playlist_url = traverse_obj(
params, 'data-video-id', 'data-video-playlist',
get_all=False, expected_type=url_or_none)
headers = self.geo_verification_headers()
headers.update({
'Accept': 'application/vnd.itv.vod.playlist.v2+json',
'Content-Type': 'application/json',
'hmac': hmac.upper(),
})
ios_playlist = self._download_json(
ios_playlist_url, video_id, data=json.dumps({
'user': {
'itvUserId': '',
'entitlements': [],
'token': ''
},
'device': {
'manufacturer': 'Safari',
'model': '5',
'manufacturer': 'Mobile Safari',
'model': '5.1',
'os': {
'name': 'Windows NT',
'version': '6.1',
'type': 'desktop'
'name': 'iOS',
'version': '5.0',
'type': ' mobile'
}
},
'client': {
'version': '4.1',
'id': 'browser'
'id': 'browser',
'supportsAdPods': True,
'service': 'itv.x',
'appversion': '2.43.28',
},
'variantAvailability': {
'player': 'hls',
'featureset': {
'min': ['hls', 'aes', 'outband-webvtt'],
'max': ['hls', 'aes', 'outband-webvtt']
},
'platformTag': 'dotcom'
'platformTag': 'mobile'
}
}).encode(), headers=headers)
video_data = ios_playlist['Playlist']['Video']
ios_base_url = video_data.get('Base')
ios_base_url = traverse_obj(video_data, 'Base', expected_type=url_or_none)
media_url = (
(lambda u: url_or_none(urljoin(ios_base_url, u)))
if ios_base_url else url_or_none)
formats = []
for media_file in (video_data.get('MediaFiles') or []):
href = media_file.get('Href')
for media_file in traverse_obj(video_data, 'MediaFiles', expected_type=list) or []:
href = traverse_obj(media_file, 'Href', expected_type=media_url)
if not href:
continue
if ios_base_url:
href = ios_base_url + href
ext = determine_ext(href)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
href, video_id, 'mp4', entry_protocol='m3u8_native',
href, video_id, 'mp4', entry_protocol='m3u8',
m3u8_id='hls', fatal=False))
else:
formats.append({
'url': href,
})
self._sort_formats(formats)
for f in formats:
f.setdefault('http_headers', {})
f['http_headers'].update(self._vanilla_ua_header())
subtitles = {}
subs = video_data.get('Subtitles') or []
for sub in subs:
if not isinstance(sub, dict):
continue
href = url_or_none(sub.get('Href'))
for sub in traverse_obj(video_data, 'Subtitles', expected_type=list) or []:
href = traverse_obj(sub, 'Href', expected_type=url_or_none)
if not href:
continue
subtitles.setdefault('en', []).append({
@@ -127,59 +270,132 @@ class ITVIE(InfoExtractor):
'ext': determine_ext(href, 'vtt'),
})
info = self._search_json_ld(webpage, video_id, default={})
if not info:
json_ld = self._parse_json(self._search_regex(
JSON_LD_RE, webpage, 'JSON-LD', '{}',
group='json_ld'), video_id, fatal=False)
if json_ld and json_ld.get('@type') == 'BreadcrumbList':
for ile in (json_ld.get('itemListElement:') or []):
item = ile.get('item:') or {}
if item.get('@type') == 'TVEpisode':
item['@context'] = 'http://schema.org'
info = self._json_ld(item, video_id, fatal=False) or {}
break
next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default='{}')
video_data.update(traverse_obj(next_data, ('props', 'pageProps', ('title', 'episode')), expected_type=dict)[0] or {})
title = traverse_obj(video_data, 'headerTitle', 'episodeTitle')
info = self._og_extract(webpage, require_title=not title)
tn = info.pop('thumbnail', None)
if tn:
info['thumbnails'] = [{'url': tn}]
# num. episode title
num_ep_title = video_data.get('numberedEpisodeTitle')
if not num_ep_title:
num_ep_title = clean_html(get_element_by_attribute('data-testid', 'episode-hero-description-strong', webpage))
num_ep_title = num_ep_title and num_ep_title.rstrip(' -')
ep_title = strip_or_none(
video_data.get('episodeTitle')
or (num_ep_title.split('.', 1)[-1] if num_ep_title else None))
title = title or re.sub(r'\s+-\s+ITVX$', '', info['title'])
if ep_title and ep_title != title:
title = title + ' - ' + ep_title
def get_thumbnails():
tns = []
for w, x in (traverse_obj(video_data, ('imagePresets'), expected_type=dict) or {}).items():
if isinstance(x, dict):
for y, z in x.items():
tns.append({'id': w + '_' + y, 'url': z})
return tns or None
video_str = lambda *x: traverse_obj(
video_data, *x, get_all=False, expected_type=strip_or_none)
return merge_dicts({
'id': video_id,
'title': self._html_search_meta(['og:title', 'twitter:title'], webpage),
'title': title,
'formats': formats,
'subtitles': subtitles,
'duration': parse_duration(video_data.get('Duration')),
'description': clean_html(get_element_by_class('episode-info__synopsis', webpage)),
# parsing hh:mm:ss:nnn not yet patched
'duration': parse_duration(re.sub(r'(\d{2})(:)(\d{3}$)', r'\1.\3', video_data.get('Duration') or '')),
'description': video_str('synopsis'),
'timestamp': traverse_obj(video_data, 'broadcastDateTime', 'dateTime', expected_type=parse_iso8601),
'thumbnails': get_thumbnails(),
'series': video_str('showTitle', 'programmeTitle'),
'series_number': int_or_none(video_data.get('seriesNumber')),
'episode': ep_title,
'episode_number': int_or_none((num_ep_title or '').split('.')[0]),
'channel': video_str('channel'),
'categories': traverse_obj(video_data, ('categories', 'formatted'), expected_type=list),
'age_limit': {False: 16, True: 0}.get(video_data.get('isChildrenCategory')),
}, info)
class ITVBTCCIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?itv\.com/btcc/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TEST = {
'url': 'http://www.itv.com/btcc/races/btcc-2018-all-the-action-from-brands-hatch',
class ITVBTCCIE(ITVBaseIE):
_VALID_URL = r'https?://(?:www\.)?itv\.com/(?!(?:watch|hub)/)(?:[^/]+/)+(?P<id>[^/?#&]+)'
_IE_DESC = 'ITV articles: News, British Touring Car Championship'
_TESTS = [{
'note': 'British Touring Car Championship',
'url': 'https://www.itv.com/btcc/articles/btcc-2018-all-the-action-from-brands-hatch',
'info_dict': {
'id': 'btcc-2018-all-the-action-from-brands-hatch',
'title': 'BTCC 2018: All the action from Brands Hatch',
},
'playlist_mincount': 9,
}
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1582188683001/HkiHLnNRx_default/index.html?videoId=%s'
}, {
'note': 'redirects to /btcc/articles/...',
'url': 'http://www.itv.com/btcc/races/btcc-2018-all-the-action-from-brands-hatch',
'only_matching': True,
}, {
'note': 'news article',
'url': 'https://www.itv.com/news/wales/2020-07-23/sean-fletcher-shows-off-wales-coastline-in-new-itv-series-as-british-tourists-opt-for-staycations',
'info_dict': {
'id': 'sean-fletcher-shows-off-wales-coastline-in-new-itv-series-as-british-tourists-opt-for-staycations',
'title': '''Sean Fletcher on why Wales' coastline should be your 'staycation' destination | ITV News''',
},
'playlist_mincount': 1,
}]
# should really be a class var of the BC IE
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
BRIGHTCOVE_ACCOUNT = '1582188683001'
BRIGHTCOVE_PLAYER = 'HkiHLnNRx'
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
webpage, urlh = self._download_webpage_handle(url, playlist_id)
link = compat_urlparse.urlparse(urlh.geturl()).path.strip('/')
entries = [
self.url_result(
smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % video_id, {
# ITV does not like some GB IP ranges, so here are some
# IP blocks it accepts
'geo_ip_blocks': [
'193.113.0.0/16', '54.36.162.0/23', '159.65.16.0/21'
],
'referrer': url,
}),
ie=BrightcoveNewIE.ie_key(), video_id=video_id)
for video_id in re.findall(r'data-video-id=["\'](\d+)', webpage)]
next_data = self._search_nextjs_data(webpage, playlist_id, fatal=False, default='{}')
path_prefix = compat_urlparse.urlparse(next_data.get('assetPrefix') or '').path.strip('/')
link = remove_start(link, path_prefix).strip('/')
content = traverse_obj(
next_data, ('props', 'pageProps', Ellipsis),
expected_type=lambda x: x if x['link'] == link else None,
get_all=False, default={})
content = traverse_obj(
content, ('body', 'content', Ellipsis, 'data'),
expected_type=lambda x: x if x.get('name') == 'Brightcove' or x.get('type') == 'Brightcove' else None)
contraband = {
# ITV does not like some GB IP ranges, so here are some
# IP blocks it accepts
'geo_ip_blocks': [
'193.113.0.0/16', '54.36.162.0/23', '159.65.16.0/21'
],
'referrer': urlh.geturl(),
}
def entries():
for data in content or []:
video_id = data.get('id')
if not video_id:
continue
account = data.get('accountId') or self.BRIGHTCOVE_ACCOUNT
player = data.get('playerId') or self.BRIGHTCOVE_PLAYER
yield self.url_result(
smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % (account, player, video_id), contraband),
ie=BrightcoveNewIE.ie_key(), video_id=video_id)
# obsolete ?
for video_id in re.findall(r'''data-video-id=["'](\d+)''', webpage):
yield self.url_result(
smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % (self.BRIGHTCOVE_ACCOUNT, self.BRIGHTCOVE_PLAYER, video_id), contraband),
ie=BrightcoveNewIE.ie_key(), video_id=video_id)
title = self._og_search_title(webpage, fatal=False)
return self.playlist_result(entries, playlist_id, title)
return self.playlist_result(entries(), playlist_id, title)

2
youtube_dl/extractor/kaltura.py
View File

@@ -373,5 +373,5 @@ class KalturaIE(InfoExtractor):
'duration': info.get('duration'),
'timestamp': info.get('createdAt'),
'uploader_id': info.get('userId') if info.get('userId') != 'None' else None,
'view_count': info.get('plays'),
'view_count': int_or_none(info.get('plays')),
}

35
youtube_dl/extractor/kommunetv.py Normal file
View File

@@ -0,0 +1,35 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import update_url
class KommunetvIE(InfoExtractor):
_VALID_URL = r'https://(\w+).kommunetv.no/archive/(?P<id>\w+)'
_TEST = {
'url': 'https://oslo.kommunetv.no/archive/921',
'md5': '5f102be308ee759be1e12b63d5da4bbc',
'info_dict': {
'id': '921',
'title': 'Bystyremøte',
'ext': 'mp4'
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
headers = {
'Accept': 'application/json'
}
data = self._download_json('https://oslo.kommunetv.no/api/streams?streamType=1&id=%s' % video_id, video_id, headers=headers)
title = data['stream']['title']
file = data['playlist'][0]['playlist'][0]['file']
url = update_url(file, query=None, fragment=None)
formats = self._extract_m3u8_formats(url, video_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
self._sort_formats(formats)
return {
'id': video_id,
'formats': formats,
'title': title
}

31
youtube_dl/extractor/kth.py Normal file
View File

@@ -0,0 +1,31 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import smuggle_url
class KTHIE(InfoExtractor):
_VALID_URL = r'https?://play\.kth\.se/(?:[^/]+/)+(?P<id>[a-z0-9_]+)'
_TEST = {
'url': 'https://play.kth.se/media/Lunch+breakA+De+nya+aff%C3%A4rerna+inom+Fordonsdalen/0_uoop6oz9',
'md5': 'd83ada6d00ca98b73243a88efe19e8a6',
'info_dict': {
'id': '0_uoop6oz9',
'ext': 'mp4',
'title': 'md5:bd1d6931facb6828762a33e6ce865f37',
'thumbnail': 're:https?://.+/thumbnail/.+',
'duration': 3516,
'timestamp': 1647345358,
'upload_date': '20220315',
'uploader_id': 'md5:0ec23e33a89e795a4512930c8102509f',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
result = self.url_result(
smuggle_url('kaltura:308:%s' % video_id, {
'service_url': 'https://api.kaltura.nordu.net'}),
'Kaltura')
return result

123
youtube_dl/extractor/manyvids.py
View File

@@ -1,11 +1,16 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
determine_ext,
extract_attributes,
int_or_none,
str_to_int,
url_or_none,
urlencode_postdata,
)
@@ -20,17 +25,20 @@ class ManyVidsIE(InfoExtractor):
'id': '133957',
'ext': 'mp4',
'title': 'everthing about me (Preview)',
'uploader': 'ellyxxix',
'view_count': int,
'like_count': int,
},
}, {
# full video
'url': 'https://www.manyvids.com/Video/935718/MY-FACE-REVEAL/',
'md5': 'f3e8f7086409e9b470e2643edb96bdcc',
'md5': 'bb47bab0e0802c2a60c24ef079dfe60f',
'info_dict': {
'id': '935718',
'ext': 'mp4',
'title': 'MY FACE REVEAL',
'description': 'md5:ec5901d41808b3746fed90face161612',
'uploader': 'Sarah Calanthe',
'view_count': int,
'like_count': int,
},
@@ -39,17 +47,50 @@ class ManyVidsIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
real_url = 'https://www.manyvids.com/video/%s/gtm.js' % (video_id, )
try:
webpage = self._download_webpage(real_url, video_id)
except Exception:
# probably useless fallback
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
r'data-(?:video-filepath|meta-video)\s*=s*(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'video URL', group='url')
info = self._search_regex(
r'''(<div\b[^>]*\bid\s*=\s*(['"])pageMetaDetails\2[^>]*>)''',
webpage, 'meta details', default='')
info = extract_attributes(info)
title = self._html_search_regex(
(r'<span[^>]+class=["\']item-title[^>]+>([^<]+)',
r'<h2[^>]+class=["\']h2 m-0["\'][^>]*>([^<]+)'),
webpage, 'title', default=None) or self._html_search_meta(
'twitter:title', webpage, 'title', fatal=True)
player = self._search_regex(
r'''(<div\b[^>]*\bid\s*=\s*(['"])rmpPlayerStream\2[^>]*>)''',
webpage, 'player details', default='')
player = extract_attributes(player)
video_urls_and_ids = (
(info.get('data-meta-video'), 'video'),
(player.get('data-video-transcoded'), 'transcoded'),
(player.get('data-video-filepath'), 'filepath'),
(self._og_search_video_url(webpage, secure=False, default=None), 'og_video'),
)
def txt_or_none(s, default=None):
return (s.strip() or default) if isinstance(s, compat_str) else default
uploader = txt_or_none(info.get('data-meta-author'))
def mung_title(s):
if uploader:
s = re.sub(r'^\s*%s\s+[|-]' % (re.escape(uploader), ), '', s)
return txt_or_none(s)
title = (
mung_title(info.get('data-meta-title'))
or self._html_search_regex(
(r'<span[^>]+class=["\']item-title[^>]+>([^<]+)',
r'<h2[^>]+class=["\']h2 m-0["\'][^>]*>([^<]+)'),
webpage, 'title', default=None)
or self._html_search_meta(
'twitter:title', webpage, 'title', fatal=True))
title = re.sub(r'\s*[|-]\s+ManyVids\s*$', '', title) or title
if any(p in webpage for p in ('preview_videos', '_preview.mp4')):
title += ' (Preview)'
@@ -62,7 +103,8 @@ class ManyVidsIE(InfoExtractor):
# Sets some cookies
self._download_webpage(
'https://www.manyvids.com/includes/ajax_repository/you_had_me_at_hello.php',
video_id, fatal=False, data=urlencode_postdata({
video_id, note='Setting format cookies', fatal=False,
data=urlencode_postdata({
'mvtoken': mv_token,
'vid': video_id,
}), headers={
@@ -70,23 +112,56 @@ class ManyVidsIE(InfoExtractor):
'X-Requested-With': 'XMLHttpRequest'
})
if determine_ext(video_url) == 'm3u8':
formats = self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls')
else:
formats = [{'url': video_url}]
formats = []
for v_url, fmt in video_urls_and_ids:
v_url = url_or_none(v_url)
if not v_url:
continue
if determine_ext(v_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
v_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls'))
else:
formats.append({
'url': v_url,
'format_id': fmt,
})
like_count = int_or_none(self._search_regex(
r'data-likes=["\'](\d+)', webpage, 'like count', default=None))
view_count = str_to_int(self._html_search_regex(
r'(?s)<span[^>]+class="views-wrapper"[^>]*>(.+?)</span', webpage,
'view count', default=None))
self._remove_duplicate_formats(formats)
for f in formats:
if f.get('height') is None:
f['height'] = int_or_none(
self._search_regex(r'_(\d{2,3}[02468])_', f['url'], 'video height', default=None))
if '/preview/' in f['url']:
f['format_id'] = '_'.join(filter(None, (f.get('format_id'), 'preview')))
f['preference'] = -10
if 'transcoded' in f['format_id']:
f['preference'] = f.get('preference', -1) - 1
self._sort_formats(formats)
def get_likes():
likes = self._search_regex(
r'''(<a\b[^>]*\bdata-id\s*=\s*(['"])%s\2[^>]*>)''' % (video_id, ),
webpage, 'likes', default='')
likes = extract_attributes(likes)
return int_or_none(likes.get('data-likes'))
def get_views():
return str_to_int(self._html_search_regex(
r'''(?s)<span\b[^>]*\bclass\s*=["']views-wrapper\b[^>]+>.+?<span\b[^>]+>\s*(\d[\d,.]*)\s*</span>''',
webpage, 'view count', default=None))
return {
'id': video_id,
'title': title,
'view_count': view_count,
'like_count': like_count,
'formats': formats,
'description': txt_or_none(info.get('data-meta-description')),
'uploader': txt_or_none(info.get('data-meta-author')),
'thumbnail': (
url_or_none(info.get('data-meta-image'))
or url_or_none(player.get('data-video-screenshot'))),
'view_count': get_views(),
'like_count': get_likes(),
}

6
youtube_dl/extractor/mediaset.py
View File

@@ -24,7 +24,7 @@ class MediasetIE(ThePlatformBaseIE):
(?:(?:www|static3)\.)?mediasetplay\.mediaset\.it/
(?:
(?:video|on-demand|movie)/(?:[^/]+/)+[^/]+_|
player/index\.html\?.*?\bprogramGuid=
player(?:/v\d+)?/index\.html\?.*?\bprogramGuid=
)
)(?P<id>[0-9A-Z]{16,})
'''
@@ -73,6 +73,10 @@ class MediasetIE(ThePlatformBaseIE):
# iframe twitter (from http://www.wittytv.it/se-prima-mi-fidavo-zero/)
'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665104&id=665104',
'only_matching': True,
}, {
# embedUrl (from https://www.wittytv.it/amici/est-ce-que-tu-maimes-gabriele-5-dicembre-copia/)
'url': 'https://static3.mediasetplay.mediaset.it/player/v2/index.html?partnerId=wittytv&configId=&programGuid=FD00000000153323&autoplay=true&purl=http://www.wittytv.it/amici/est-ce-que-tu-maimes-gabriele-5-dicembre-copia/',
'only_matching': True,
}, {
'url': 'mediaset:FAFU000000665924',
'only_matching': True,

2
youtube_dl/extractor/minds.py
View File

@@ -78,7 +78,7 @@ class MindsIE(MindsBaseIE):
else:
return self.url_result(entity['perma_url'])
else:
assert(entity['subtype'] == 'video')
assert (entity['subtype'] == 'video')
video_id = entity_id
# 1080p and webm formats available only on the sources array
video = self._call_api(

30
youtube_dl/extractor/mixcloud.py
View File

@@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
import itertools
@@ -10,7 +11,7 @@ from ..compat import (
compat_ord,
compat_str,
compat_urllib_parse_unquote,
compat_zip
compat_zip as zip,
)
from ..utils import (
int_or_none,
@@ -24,7 +25,7 @@ class MixcloudBaseIE(InfoExtractor):
def _call_api(self, object_type, object_fields, display_id, username, slug=None):
lookup_key = object_type + 'Lookup'
return self._download_json(
'https://www.mixcloud.com/graphql', display_id, query={
'https://app.mixcloud.com/graphql', display_id, query={
'query': '''{
%s(lookup: {username: "%s"%s}) {
%s
@@ -44,7 +45,7 @@ class MixcloudIE(MixcloudBaseIE):
'ext': 'm4a',
'title': 'Cryptkeeper',
'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
'uploader': 'Daniel Holbach',
'uploader': 'dholbach', # was: 'Daniel Holbach',
'uploader_id': 'dholbach',
'thumbnail': r're:https?://.*\.jpg',
'view_count': int,
@@ -57,7 +58,7 @@ class MixcloudIE(MixcloudBaseIE):
'id': 'gillespeterson_caribou-7-inch-vinyl-mix-chat',
'ext': 'mp3',
'title': 'Caribou 7 inch Vinyl Mix & Chat',
'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
'description': r're:Last week Dan Snaith aka Caribou swung by the Brownswood.{136}',
'uploader': 'Gilles Peterson Worldwide',
'uploader_id': 'gillespeterson',
'thumbnail': 're:https?://.*',
@@ -65,6 +66,23 @@ class MixcloudIE(MixcloudBaseIE):
'timestamp': 1422987057,
'upload_date': '20150203',
},
'params': {
'skip_download': '404 not found',
},
}, {
'url': 'https://www.mixcloud.com/gillespeterson/carnival-m%C3%BAsica-popular-brasileira-mix/',
'info_dict': {
'id': 'gillespeterson_carnival-música-popular-brasileira-mix',
'ext': 'm4a',
'title': 'Carnival Música Popular Brasileira Mix',
'description': r're:Gilles was recently in Brazil to play at Boiler Room.{208}',
'timestamp': 1454347174,
'upload_date': '20160201',
'uploader': 'Gilles Peterson Worldwide',
'uploader_id': 'gillespeterson',
'thumbnail': 're:https?://.*',
'view_count': int,
},
}, {
'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/',
'only_matching': True,
@@ -76,10 +94,10 @@ class MixcloudIE(MixcloudBaseIE):
"""Encrypt/Decrypt XOR cipher. Both ways are possible because it's XOR."""
return ''.join([
compat_chr(compat_ord(ch) ^ compat_ord(k))
for ch, k in compat_zip(ciphertext, itertools.cycle(key))])
for ch, k in zip(ciphertext, itertools.cycle(key))])
def _real_extract(self, url):
username, slug = re.match(self._VALID_URL, url).groups()
username, slug = self._match_valid_url(url).groups()
username, slug = compat_urllib_parse_unquote(username), compat_urllib_parse_unquote(slug)
track_id = '%s_%s' % (username, slug)

42
youtube_dl/extractor/motherless.py
View File

@@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
import datetime
@@ -71,7 +72,7 @@ class MotherlessIE(InfoExtractor):
'title': 'a/ Hot Teens',
'categories': list,
'upload_date': '20210104',
'uploader_id': 'yonbiw',
'uploader_id': 'anonymous',
'thumbnail': r're:https?://.*\.jpg',
'age_limit': 18,
},
@@ -125,9 +126,10 @@ class MotherlessIE(InfoExtractor):
kwargs = {_AGO_UNITS.get(uploaded_ago[-1]): delta}
upload_date = (datetime.datetime.utcnow() - datetime.timedelta(**kwargs)).strftime('%Y%m%d')
comment_count = webpage.count('class="media-comment-contents"')
comment_count = len(re.findall(r'''class\s*=\s*['"]media-comment-contents\b''', webpage))
uploader_id = self._html_search_regex(
r'"thumb-member-username">\s+<a href="/m/([^"]+)"',
(r'''<span\b[^>]+\bclass\s*=\s*["']username\b[^>]*>([^<]+)</span>''',
r'''(?s)['"](?:media-meta-member|thumb-member-username)\b[^>]+>\s*<a\b[^>]+\bhref\s*=\s*['"]/m/([^"']+)'''),
webpage, 'uploader_id')
categories = self._html_search_meta('keywords', webpage, default=None)
@@ -169,7 +171,18 @@ class MotherlessGroupIE(InfoExtractor):
'description': 'Sex can be funny. Wide smiles,laugh, games, fun of '
'any kind!'
},
'playlist_mincount': 9,
'playlist_mincount': 0,
'expected_warnings': [
'This group has no videos.',
]
}, {
'url': 'https://motherless.com/g/beautiful_cock',
'info_dict': {
'id': 'beautiful_cock',
'title': 'Beautiful Cock',
'description': 'Group for lovely cocks yours, mine, a friends anything human',
},
'playlist_mincount': 2500,
}]
@classmethod
@@ -208,16 +221,23 @@ class MotherlessGroupIE(InfoExtractor):
r'<title>([\w\s]+\w)\s+-', webpage, 'title', fatal=False)
description = self._html_search_meta(
'description', webpage, fatal=False)
page_count = self._int(self._search_regex(
r'(\d+)</(?:a|span)><(?:a|span)[^>]+>\s*NEXT',
webpage, 'page_count'), 'page_count')
page_count = str_to_int(self._search_regex(
r'(\d+)\s*</(?:a|span)>\s*<(?:a|span)[^>]+(?:>\s*NEXT|\brel\s*=\s*["\']?next)\b',
webpage, 'page_count', default=0))
if not page_count:
message = self._search_regex(
r'''class\s*=\s*['"]error-page\b[^>]*>\s*<p[^>]*>\s*(?P<error_msg>[^<]+)(?<=\S)\s*''',
webpage, 'error_msg', default=None) or 'This group has no videos.'
self.report_warning(message, group_id)
page_count = 1
PAGE_SIZE = 80
def _get_page(idx):
webpage = self._download_webpage(
page_url, group_id, query={'page': idx + 1},
note='Downloading page %d/%d' % (idx + 1, page_count)
)
if idx > 0:
webpage = self._download_webpage(
page_url, group_id, query={'page': idx + 1},
note='Downloading page %d/%d' % (idx + 1, page_count)
)
for entry in self._extract_entries(webpage, url):
yield entry

4
youtube_dl/extractor/myspass.py
View File

@@ -35,7 +35,9 @@ class MySpassIE(InfoExtractor):
title = xpath_text(metadata, 'title', fatal=True)
video_url = xpath_text(metadata, 'url_flv', 'download url', True)
video_id_int = int(video_id)
for group in re.search(r'/myspass2009/\d+/(\d+)/(\d+)/(\d+)/', video_url).groups():
grps = re.search(r'/myspass2009/\d+/(\d+)/(\d+)/(\d+)/', video_url)
for group in grps.groups() if grps else []:
group_int = int(group)
if group_int > video_id_int:
video_url = video_url.replace(

87
youtube_dl/extractor/myvideoge.py Normal file
View File

@@ -0,0 +1,87 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
clean_html,
get_element_by_id,
get_element_by_class,
int_or_none,
js_to_json,
MONTH_NAMES,
qualities,
unified_strdate,
)
class MyVideoGeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?myvideo\.ge/v/(?P<id>[0-9]+)'
_TEST = {
'url': 'https://www.myvideo.ge/v/3941048',
'md5': '8c192a7d2b15454ba4f29dc9c9a52ea9',
'info_dict': {
'id': '3941048',
'ext': 'mp4',
'title': 'The best prikol',
'upload_date': '20200611',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'chixa33',
'description': 'md5:5b067801318e33c2e6eea4ab90b1fdd3',
},
# working from local dev system
'skip': 'site blocks CI servers',
}
_MONTH_NAMES_KA = ['იანვარი', 'თებერვალი', 'მარტი', 'აპრილი', 'მაისი', 'ივნისი', 'ივლისი', 'აგვისტო', 'სექტემბერი', 'ოქტომბერი', 'ნოემბერი', 'დეკემბერი']
_quality = staticmethod(qualities(('SD', 'HD')))
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = (
self._og_search_title(webpage, default=None)
or clean_html(get_element_by_class('my_video_title', webpage))
or self._html_search_regex(r'<title\b[^>]*>([^<]+)</title\b', webpage, 'title'))
jwplayer_sources = self._parse_json(
self._search_regex(
r'''(?s)jwplayer\s*\(\s*['"]mvplayer['"]\s*\)\s*\.\s*setup\s*\(.*?\bsources\s*:\s*(\[.*?])\s*[,});]''', webpage, 'jwplayer sources', fatal=False)
or '',
video_id, transform_source=js_to_json, fatal=False)
formats = self._parse_jwplayer_formats(jwplayer_sources or [], video_id)
for f in formats or []:
f['preference'] = self._quality(f['format_id'])
self._sort_formats(formats)
description = (
self._og_search_description(webpage)
or get_element_by_id('long_desc_holder', webpage)
or self._html_search_meta('description', webpage))
uploader = self._search_regex(r'<a[^>]+class="mv_user_name"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False)
upload_date = get_element_by_class('mv_vid_upl_date', webpage)
# as ka locale may not be present roll a local date conversion
upload_date = (unified_strdate(
# translate any ka month to an en one
re.sub('|'.join(self._MONTH_NAMES_KA),
lambda m: MONTH_NAMES['en'][self._MONTH_NAMES_KA.index(m.group(0))],
upload_date, re.I))
if upload_date else None)
return {
'id': video_id,
'title': title,
'description': description,
'uploader': uploader,
'formats': formats,
'thumbnail': self._og_search_thumbnail(webpage),
'upload_date': upload_date,
'view_count': int_or_none(get_element_by_class('mv_vid_views', webpage)),
'like_count': int_or_none(get_element_by_id('likes_count', webpage)),
'dislike_count': int_or_none(get_element_by_id('dislikes_count', webpage)),
}

157
youtube_dl/extractor/neteasemusic.py
View File

@@ -1,20 +1,32 @@
# coding: utf-8
from __future__ import unicode_literals
from hashlib import md5
from base64 import b64encode
from binascii import hexlify
from datetime import datetime
from hashlib import md5
from random import randint
import json
import re
import time
from .common import InfoExtractor
from ..aes import aes_ecb_encrypt, pkcs7_padding
from ..compat import (
compat_urllib_parse_urlencode,
compat_str,
compat_itertools_count,
)
from ..utils import (
sanitized_Request,
ExtractorError,
bytes_to_intlist,
error_to_compat_str,
float_or_none,
int_or_none,
intlist_to_bytes,
sanitized_Request,
std_headers,
try_get,
)
@@ -35,32 +47,106 @@ class NetEaseMusicBaseIE(InfoExtractor):
result = b64encode(m.digest()).decode('ascii')
return result.replace('/', '_').replace('+', '-')
@classmethod
def make_player_api_request_data_and_headers(cls, song_id, bitrate):
KEY = b'e82ckenh8dichen8'
URL = '/api/song/enhance/player/url'
now = int(time.time() * 1000)
rand = randint(0, 1000)
cookie = {
'osver': None,
'deviceId': None,
'appver': '8.0.0',
'versioncode': '140',
'mobilename': None,
'buildver': '1623435496',
'resolution': '1920x1080',
'__csrf': '',
'os': 'pc',
'channel': None,
'requestId': '{0}_{1:04}'.format(now, rand),
}
request_text = json.dumps(
{'ids': '[{0}]'.format(song_id), 'br': bitrate, 'header': cookie},
separators=(',', ':'))
message = 'nobody{0}use{1}md5forencrypt'.format(
URL, request_text).encode('latin1')
msg_digest = md5(message).hexdigest()
data = '{0}-36cd479b6b5-{1}-36cd479b6b5-{2}'.format(
URL, request_text, msg_digest)
data = pkcs7_padding(bytes_to_intlist(data))
encrypted = intlist_to_bytes(aes_ecb_encrypt(data, bytes_to_intlist(KEY)))
encrypted_params = hexlify(encrypted).decode('ascii').upper()
cookie = '; '.join(
['{0}={1}'.format(k, v if v is not None else 'undefined')
for [k, v] in cookie.items()])
headers = {
'User-Agent': std_headers['User-Agent'],
'Content-Type': 'application/x-www-form-urlencoded',
'Referer': 'https://music.163.com',
'Cookie': cookie,
}
return ('params={0}'.format(encrypted_params), headers)
def _call_player_api(self, song_id, bitrate):
url = 'https://interface3.music.163.com/eapi/song/enhance/player/url'
data, headers = self.make_player_api_request_data_and_headers(song_id, bitrate)
try:
msg = 'empty result'
result = self._download_json(
url, song_id, data=data.encode('ascii'), headers=headers)
if result:
return result
except ExtractorError as e:
if type(e.cause) in (ValueError, TypeError):
# JSON load failure
raise
except Exception as e:
msg = error_to_compat_str(e)
self.report_warning('%s API call (%s) failed: %s' % (
song_id, bitrate, msg))
return {}
def extract_formats(self, info):
err = 0
formats = []
song_id = info['id']
for song_format in self._FORMATS:
details = info.get(song_format)
if not details:
continue
song_file_path = '/%s/%s.%s' % (
self._encrypt(details['dfsId']), details['dfsId'], details['extension'])
# 203.130.59.9, 124.40.233.182, 115.231.74.139, etc is a reverse proxy-like feature
# from NetEase's CDN provider that can be used if m5.music.126.net does not
# work, especially for users outside of Mainland China
# via: https://github.com/JixunMoe/unblock-163/issues/3#issuecomment-163115880
for host in ('http://m5.music.126.net', 'http://115.231.74.139/m1.music.126.net',
'http://124.40.233.182/m1.music.126.net', 'http://203.130.59.9/m1.music.126.net'):
song_url = host + song_file_path
bitrate = int_or_none(details.get('bitrate')) or 999000
data = self._call_player_api(song_id, bitrate)
for song in try_get(data, lambda x: x['data'], list) or []:
song_url = try_get(song, lambda x: x['url'])
if not song_url:
continue
if self._is_valid_url(song_url, info['id'], 'song'):
formats.append({
'url': song_url,
'ext': details.get('extension'),
'abr': float_or_none(details.get('bitrate'), scale=1000),
'abr': float_or_none(song.get('br'), scale=1000),
'format_id': song_format,
'filesize': details.get('size'),
'asr': details.get('sr')
'filesize': int_or_none(song.get('size')),
'asr': int_or_none(details.get('sr')),
})
break
elif err == 0:
err = try_get(song, lambda x: x['code'], int)
if not formats:
msg = 'No media links found'
if err != 0 and (err < 200 or err >= 400):
raise ExtractorError(
'%s (site code %d)' % (msg, err, ), expected=True)
else:
self.raise_geo_restricted(
msg + ': probably this video is not available from your location due to geo restriction.',
countries=['CN'])
return formats
@classmethod
@@ -76,33 +162,19 @@ class NetEaseMusicBaseIE(InfoExtractor):
class NetEaseMusicIE(NetEaseMusicBaseIE):
IE_NAME = 'netease:song'
IE_DESC = '网易云音乐'
_VALID_URL = r'https?://music\.163\.com/(#/)?song\?id=(?P<id>[0-9]+)'
_VALID_URL = r'https?://(y\.)?music\.163\.com/(?:[#m]/)?song\?.*?\bid=(?P<id>[0-9]+)'
_TESTS = [{
'url': 'http://music.163.com/#/song?id=32102397',
'md5': 'f2e97280e6345c74ba9d5677dd5dcb45',
'md5': '3e909614ce09b1ccef4a3eb205441190',
'info_dict': {
'id': '32102397',
'ext': 'mp3',
'title': 'Bad Blood (feat. Kendrick Lamar)',
'title': 'Bad Blood',
'creator': 'Taylor Swift / Kendrick Lamar',
'upload_date': '20150517',
'timestamp': 1431878400,
'description': 'md5:a10a54589c2860300d02e1de821eb2ef',
'upload_date': '20150516',
'timestamp': 1431792000,
'description': 'md5:25fc5f27e47aad975aa6d36382c7833c',
},
'skip': 'Blocked outside Mainland China',
}, {
'note': 'No lyrics translation.',
'url': 'http://music.163.com/#/song?id=29822014',
'info_dict': {
'id': '29822014',
'ext': 'mp3',
'title': '听见下雨的声音',
'creator': '周杰伦',
'upload_date': '20141225',
'timestamp': 1419523200,
'description': 'md5:a4d8d89f44656af206b7b2555c0bce6c',
},
'skip': 'Blocked outside Mainland China',
}, {
'note': 'No lyrics.',
'url': 'http://music.163.com/song?id=17241424',
@@ -112,9 +184,9 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
'title': 'Opus 28',
'creator': 'Dustin O\'Halloran',
'upload_date': '20080211',
'description': 'md5:f12945b0f6e0365e3b73c5032e1b0ff4',
'timestamp': 1202745600,
},
'skip': 'Blocked outside Mainland China',
}, {
'note': 'Has translated name.',
'url': 'http://music.163.com/#/song?id=22735043',
@@ -128,7 +200,18 @@ class NetEaseMusicIE(NetEaseMusicBaseIE):
'timestamp': 1264608000,
'alt_title': '说出愿望吧(Genie)',
},
'skip': 'Blocked outside Mainland China',
}, {
'url': 'https://y.music.163.com/m/song?app_version=8.8.45&id=95670&uct2=sKnvS4+0YStsWkqsPhFijw%3D%3D&dlt=0846',
'md5': '95826c73ea50b1c288b22180ec9e754d',
'info_dict': {
'id': '95670',
'ext': 'mp3',
'title': '国际歌',
'creator': '马备',
'upload_date': '19911130',
'timestamp': 691516800,
'description': 'md5:1ba2f911a2b0aa398479f595224f2141',
},
}]
def _process_lyrics(self, lyrics_info):

21
youtube_dl/extractor/nhk.py
View File

@@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
import re
@@ -7,7 +8,7 @@ from ..utils import urljoin
class NhkBaseIE(InfoExtractor):
_API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7a/%s/%s/%s/all%s.json'
_API_URL_TEMPLATE = 'https://nwapi.nhk.jp/nhkworld/%sod%slist/v7b/%s/%s/%s/all%s.json'
_BASE_URL_REGEX = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/ondemand'
_TYPE_REGEX = r'/(?P<type>video|audio)/'
@@ -23,7 +24,7 @@ class NhkBaseIE(InfoExtractor):
def _extract_episode_info(self, url, episode=None):
fetch_episode = episode is None
lang, m_type, episode_id = re.match(NhkVodIE._VALID_URL, url).groups()
if episode_id.isdigit():
if len(episode_id) == 7:
episode_id = episode_id[:4] + '-' + episode_id[4:]
is_video = m_type == 'video'
@@ -84,7 +85,8 @@ class NhkBaseIE(InfoExtractor):
class NhkVodIE(NhkBaseIE):
_VALID_URL = r'%s%s(?P<id>\d{7}|[^/]+?-\d{8}-[0-9a-z]+)' % (NhkBaseIE._BASE_URL_REGEX, NhkBaseIE._TYPE_REGEX)
# the 7-character IDs can have alphabetic chars too: assume [a-z] rather than just [a-f], eg
_VALID_URL = r'%s%s(?P<id>[0-9a-z]{7}|[^/]+?-\d{8}-[0-9a-z]+)' % (NhkBaseIE._BASE_URL_REGEX, NhkBaseIE._TYPE_REGEX)
# Content available only for a limited period of time. Visit
# https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples.
_TESTS = [{
@@ -124,6 +126,19 @@ class NhkVodIE(NhkBaseIE):
}, {
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/audio/j_art-20150903-1/',
'only_matching': True,
}, {
# video, alphabetic character in ID #29670
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/9999a34/',
'only_matching': True,
'info_dict': {
'id': 'qfjay6cg',
'ext': 'mp4',
'title': 'DESIGN TALKS plus - Fishermen’s Finery',
'description': 'md5:8a8f958aaafb0d7cb59d38de53f1e448',
'thumbnail': r're:^https?:/(/[a-z0-9.-]+)+\.jpg\?w=1920&h=1080$',
'upload_date': '20210615',
'timestamp': 1623722008,
}
}]
def _real_extract(self, url):

3
youtube_dl/extractor/nrk.py
View File

@@ -60,8 +60,7 @@ class NRKBaseIE(InfoExtractor):
return self._download_json(
urljoin('https://psapi.nrk.no/', path),
video_id, note or 'Downloading %s JSON' % item,
fatal=fatal, query=query,
headers={'Accept-Encoding': 'gzip, deflate, br'})
fatal=fatal, query=query)
class NRKIE(NRKBaseIE):

4
youtube_dl/extractor/openload.py
View File

@@ -7,6 +7,7 @@ import subprocess
import tempfile
from ..compat import (
compat_open as open,
compat_urlparse,
compat_kwargs,
)
@@ -16,6 +17,7 @@ from ..utils import (
ExtractorError,
get_exe_version,
is_outdated_version,
process_communicate_or_kill,
std_headers,
)
@@ -226,7 +228,7 @@ class PhantomJSwrapper(object):
self.exe, '--ssl-protocol=any',
self._TMP_FILES['script'].name
], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
out, err = p.communicate()
out, err = process_communicate_or_kill(p)
if p.returncode != 0:
raise ExtractorError(
'Executing JS failed\n:' + encodeArgument(err))

1149
youtube_dl/extractor/orf.py
View File

File diff suppressed because it is too large Load Diff

9
youtube_dl/extractor/palcomp3.py
View File

@@ -8,7 +8,7 @@ from ..compat import compat_str
from ..utils import (
int_or_none,
str_or_none,
try_get,
traverse_obj,
)
@@ -109,7 +109,7 @@ class PalcoMP3ArtistIE(PalcoMP3BaseIE):
}
name'''
@ classmethod
@classmethod
def suitable(cls, url):
return False if re.match(PalcoMP3IE._VALID_URL, url) else super(PalcoMP3ArtistIE, cls).suitable(url)
@@ -118,7 +118,8 @@ class PalcoMP3ArtistIE(PalcoMP3BaseIE):
artist = self._call_api(artist_slug, self._ARTIST_FIELDS_TMPL)['artist']
def entries():
for music in (try_get(artist, lambda x: x['musics']['nodes'], list) or []):
for music in traverse_obj(artist, (
'musics', 'nodes', lambda _, m: m['musicID'])):
yield self._parse_music(music)
return self.playlist_result(
@@ -137,7 +138,7 @@ class PalcoMP3VideoIE(PalcoMP3BaseIE):
'title': 'Maiara e Maraisa - Você Faz Falta Aqui - DVD Ao Vivo Em Campo Grande',
'description': 'md5:7043342c09a224598e93546e98e49282',
'upload_date': '20161107',
'uploader_id': 'maiaramaraisaoficial',
'uploader_id': '@maiaramaraisaoficial',
'uploader': 'Maiara e Maraisa',
}
}]

193
youtube_dl/extractor/peekvids.py Normal file
View File

@@ -0,0 +1,193 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
get_element_by_class,
int_or_none,
merge_dicts,
url_or_none,
)
class PeekVidsIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://(?:www\.)?peekvids\.com/
(?:(?:[^/?#]+/){2}|embed/?\?(?:[^#]*&)?v=)
(?P<id>[^/?&#]*)
'''
_TESTS = [{
'url': 'https://peekvids.com/pc/dane-jones-cute-redhead-with-perfect-tits-with-mini-vamp/BSyLMbN0YCd',
'md5': '2ff6a357a9717dc9dc9894b51307e9a2',
'info_dict': {
'id': '1262717',
'display_id': 'BSyLMbN0YCd',
'title': ' Dane Jones - Cute redhead with perfect tits with Mini Vamp',
'ext': 'mp4',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'md5:0a61df3620de26c0af8963b1a730cd69',
'timestamp': 1642579329,
'upload_date': '20220119',
'duration': 416,
'view_count': int,
'age_limit': 18,
'uploader': 'SEXYhub.com',
'categories': list,
'tags': list,
},
}]
_DOMAIN = 'www.peekvids.com'
def _get_detail(self, html):
return get_element_by_class('detail-video-block', html)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id, expected_status=429)
if '>Rate Limit Exceeded' in webpage:
raise ExtractorError(
'[%s] %s: %s' % (self.IE_NAME, video_id, 'You are suspected as a bot. Wait, or pass the captcha test on the site and provide --cookies.'),
expected=True)
title = self._html_search_regex(r'(?s)<h1\b[^>]*>(.+?)</h1>', webpage, 'title')
display_id = video_id
video_id = self._search_regex(r'(?s)<video\b[^>]+\bdata-id\s*=\s*["\']?([\w-]+)', webpage, 'short video ID')
srcs = self._download_json(
'https://%s/v-alt/%s' % (self._DOMAIN, video_id), video_id,
note='Downloading list of source files')
formats = [{
'url': f_url,
'format_id': f_id,
'height': int_or_none(f_id),
} for f_url, f_id in (
(url_or_none(f_v), f_match.group(1))
for f_v, f_match in (
(v, re.match(r'^data-src(\d{3,})$', k))
for k, v in srcs.items() if v) if f_match)
if f_url
]
if not formats:
formats = [{'url': url} for url in srcs.values()]
self._sort_formats(formats)
info = self._search_json_ld(webpage, video_id, expected_type='VideoObject', default={})
info.pop('url', None)
# may not have found the thumbnail if it was in a list in the ld+json
info.setdefault('thumbnail', self._og_search_thumbnail(webpage))
detail = self._get_detail(webpage) or ''
info['description'] = self._html_search_regex(
r'(?s)(.+?)(?:%s\s*<|<ul\b)' % (re.escape(info.get('description', '')), ),
detail, 'description', default=None) or None
info['title'] = re.sub(r'\s*[,-][^,-]+$', '', info.get('title') or title) or self._generic_title(url)
def cat_tags(name, html):
l = self._html_search_regex(
r'(?s)<span\b[^>]*>\s*%s\s*:\s*</span>(.+?)</li>' % (re.escape(name), ),
html, name, default='')
return [x for x in re.split(r'\s+', l) if x]
return merge_dicts({
'id': video_id,
'display_id': display_id,
'age_limit': 18,
'formats': formats,
'categories': cat_tags('Categories', detail),
'tags': cat_tags('Tags', detail),
'uploader': self._html_search_regex(r'[Uu]ploaded\s+by\s(.+?)"', webpage, 'uploader', default=None),
}, info)
class PlayVidsIE(PeekVidsIE):
_VALID_URL = r'https?://(?:www\.)?playvids\.com/(?:embed/|\w\w?/)?(?P<id>[^/?#]*)'
_TESTS = [{
'url': 'https://www.playvids.com/U3pBrYhsjXM/pc/dane-jones-cute-redhead-with-perfect-tits-with-mini-vamp',
'md5': '2f12e50213dd65f142175da633c4564c',
'info_dict': {
'id': '1978030',
'display_id': 'U3pBrYhsjXM',
'title': ' Dane Jones - Cute redhead with perfect tits with Mini Vamp',
'ext': 'mp4',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'md5:0a61df3620de26c0af8963b1a730cd69',
'timestamp': 1640435839,
'upload_date': '20211225',
'duration': 416,
'view_count': int,
'age_limit': 18,
'uploader': 'SEXYhub.com',
'categories': list,
'tags': list,
},
}, {
'url': 'https://www.playvids.com/es/U3pBrYhsjXM/pc/dane-jones-cute-redhead-with-perfect-tits-with-mini-vamp',
'only_matching': True,
}, {
'url': 'https://www.playvids.com/embed/U3pBrYhsjXM',
'only_matching': True,
}, {
'url': 'https://www.playvids.com/bKmGLe3IwjZ/sv/brazzers-800-phone-sex-madison-ivy-always-on-the-line',
'md5': 'e783986e596cafbf46411a174ab42ba6',
'info_dict': {
'id': '762385',
'display_id': 'bKmGLe3IwjZ',
'ext': 'mp4',
'title': 'Brazzers - 1 800 Phone Sex: Madison Ivy Always On The Line 6',
'description': 'md5:bdcd2db2b8ad85831a491d7c8605dcef',
'timestamp': 1516958544,
'upload_date': '20180126',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 480,
'uploader': 'Brazzers',
'age_limit': 18,
'view_count': int,
'age_limit': 18,
'categories': list,
'tags': list,
},
}, {
'url': 'https://www.playvids.com/v/47iUho33toY',
'md5': 'b056b5049d34b648c1e86497cf4febce',
'info_dict': {
'id': '700621',
'display_id': '47iUho33toY',
'ext': 'mp4',
'title': 'KATEE OWEN STRIPTIASE IN SEXY RED LINGERIE',
'description': None,
'timestamp': 1507052209,
'upload_date': '20171003',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 332,
'uploader': 'Cacerenele',
'age_limit': 18,
'view_count': int,
'categories': list,
'tags': list,
}
}, {
'url': 'https://www.playvids.com/z3_7iwWCmqt/sexy-teen-filipina-striptease-beautiful-pinay-bargirl-strips-and-dances',
'md5': 'efa09be9f031314b7b7e3bc6510cd0df',
'info_dict': {
'id': '1523518',
'display_id': 'z3_7iwWCmqt',
'ext': 'mp4',
'title': 'SEXY TEEN FILIPINA STRIPTEASE - Beautiful Pinay Bargirl Strips and Dances',
'description': None,
'timestamp': 1607470323,
'upload_date': '20201208',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 593,
'uploader': 'yorours',
'age_limit': 18,
'view_count': int,
'categories': list,
'tags': list,
},
}]
_DOMAIN = 'www.playvids.com'
def _get_detail(self, html):
return get_element_by_class('detail-block', html)

105
youtube_dl/extractor/pr0gramm.py Normal file
View File

@@ -0,0 +1,105 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
import re
from ..utils import (
merge_dicts,
)
class Pr0grammStaticIE(InfoExtractor):
# Possible urls:
# https://pr0gramm.com/static/5466437
_VALID_URL = r'https?://pr0gramm\.com/static/(?P<id>[0-9]+)'
_TEST = {
'url': 'https://pr0gramm.com/static/5466437',
'md5': '52fa540d70d3edc286846f8ca85938aa',
'info_dict': {
'id': '5466437',
'ext': 'mp4',
'title': 'pr0gramm-5466437 by g11st',
'uploader': 'g11st',
'upload_date': '20221221',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
# Fetch media sources
entries = self._parse_html5_media_entries(url, webpage, video_id)
media_info = entries[0]
# this raises if there are no formats
self._sort_formats(media_info.get('formats') or [])
# Fetch author
uploader = self._html_search_regex(r'by\W+([\w-]+)\W+', webpage, 'uploader')
# Fetch approx upload timestamp from filename
# Have None-defaults in case the extraction fails
uploadDay = None
uploadMon = None
uploadYear = None
uploadTimestr = None
# (//img.pr0gramm.com/2022/12/21/62ae8aa5e2da0ebf.mp4)
m = re.search(r'//img\.pr0gramm\.com/(?P<year>[\d]+)/(?P<mon>[\d]+)/(?P<day>[\d]+)/\w+\.\w{,4}', webpage)
if (m):
# Up to a day of accuracy should suffice...
uploadDay = m.groupdict().get('day')
uploadMon = m.groupdict().get('mon')
uploadYear = m.groupdict().get('year')
uploadTimestr = uploadYear + uploadMon + uploadDay
return merge_dicts({
'id': video_id,
'title': 'pr0gramm-%s%s' % (video_id, (' by ' + uploader) if uploader else ''),
'uploader': uploader,
'upload_date': uploadTimestr
}, media_info)
# This extractor is for the primary url (used for sharing, and appears in the
# location bar) Since this page loads the DOM via JS, yt-dl can't find any
# video information here. So let's redirect to a compatibility version of
# the site, which does contain the <video>-element by itself, without requiring
# js to be ran.
class Pr0grammIE(InfoExtractor):
# Possible urls:
# https://pr0gramm.com/new/546637
# https://pr0gramm.com/new/video/546637
# https://pr0gramm.com/top/546637
# https://pr0gramm.com/top/video/546637
# https://pr0gramm.com/user/g11st/uploads/5466437
# https://pr0gramm.com/user/froschler/dafur-ist-man-hier/5091290
# https://pr0gramm.com/user/froschler/reinziehen-1elf/5232030
# https://pr0gramm.com/user/froschler/1elf/5232030
# https://pr0gramm.com/new/5495710:comment62621020 <- this is not the id!
# https://pr0gramm.com/top/fruher war alles damals/5498175
_VALID_URL = r'https?:\/\/pr0gramm\.com\/(?!static/\d+).+?\/(?P<id>[\d]+)(:|$)'
_TEST = {
'url': 'https://pr0gramm.com/new/video/5466437',
'info_dict': {
'id': '5466437',
'ext': 'mp4',
'title': 'pr0gramm-5466437 by g11st',
'uploader': 'g11st',
'upload_date': '20221221',
}
}
def _generic_title():
return "oof"
def _real_extract(self, url):
video_id = self._match_id(url)
return self.url_result(
'https://pr0gramm.com/static/' + video_id,
video_id=video_id,
ie=Pr0grammStaticIE.ie_key())

122
youtube_dl/extractor/rai.py
View File

@@ -5,15 +5,16 @@ import re
from .common import InfoExtractor
from ..compat import (
compat_urlparse,
compat_str,
compat_urlparse,
)
from ..utils import (
ExtractorError,
determine_ext,
ExtractorError,
find_xpath_attr,
fix_xml_ampersands,
GeoRestrictedError,
HEADRequest,
int_or_none,
parse_duration,
remove_start,
@@ -96,12 +97,100 @@ class RaiBaseIE(InfoExtractor):
if not formats and geoprotection is True:
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
formats.extend(self._create_http_urls(relinker_url, formats))
return dict((k, v) for k, v in {
'is_live': is_live,
'duration': duration,
'formats': formats,
}.items() if v is not None)
def _create_http_urls(self, relinker_url, fmts):
_RELINKER_REG = r'https?://(?P<host>[^/]+?)/(?:i/)?(?P<extra>[^/]+?)/(?P<path>.+?)/(?P<id>\w+)(?:_(?P<quality>[\d\,]+))?(?:\.mp4|/playlist\.m3u8).+?'
_MP4_TMPL = '%s&overrideUserAgentRule=mp4-%s'
_QUALITY = {
# tbr: w, h
'250': [352, 198],
'400': [512, 288],
'700': [512, 288],
'800': [700, 394],
'1200': [736, 414],
'1800': [1024, 576],
'2400': [1280, 720],
'3200': [1440, 810],
'3600': [1440, 810],
'5000': [1920, 1080],
'10000': [1920, 1080],
}
def test_url(url):
resp = self._request_webpage(
HEADRequest(url), None, headers={'User-Agent': 'Rai'},
fatal=False, errnote=False, note=False)
if resp is False:
return False
if resp.code == 200:
return False if resp.url == url else resp.url
return None
def get_format_info(tbr):
import math
br = int_or_none(tbr)
if len(fmts) == 1 and not br:
br = fmts[0].get('tbr')
if br > 300:
tbr = compat_str(math.floor(br / 100) * 100)
else:
tbr = '250'
# try extracting info from available m3u8 formats
format_copy = None
for f in fmts:
if f.get('tbr'):
br_limit = math.floor(br / 100)
if br_limit - 1 <= math.floor(f['tbr'] / 100) <= br_limit + 1:
format_copy = f.copy()
return {
'width': format_copy.get('width'),
'height': format_copy.get('height'),
'tbr': format_copy.get('tbr'),
'vcodec': format_copy.get('vcodec'),
'acodec': format_copy.get('acodec'),
'fps': format_copy.get('fps'),
'format_id': 'https-%s' % tbr,
} if format_copy else {
'width': _QUALITY[tbr][0],
'height': _QUALITY[tbr][1],
'format_id': 'https-%s' % tbr,
'tbr': int(tbr),
}
loc = test_url(_MP4_TMPL % (relinker_url, '*'))
if not isinstance(loc, compat_str):
return []
mobj = re.match(
_RELINKER_REG,
test_url(relinker_url) or '')
if not mobj:
return []
available_qualities = mobj.group('quality').split(',') if mobj.group('quality') else ['*']
available_qualities = [i for i in available_qualities if i]
formats = []
for q in available_qualities:
fmt = {
'url': _MP4_TMPL % (relinker_url, q),
'protocol': 'https',
'ext': 'mp4',
}
fmt.update(get_format_info(q))
formats.append(fmt)
return formats
@staticmethod
def _extract_subtitles(url, video_data):
STL_EXT = 'stl'
@@ -151,6 +240,22 @@ class RaiPlayIE(RaiBaseIE):
'params': {
'skip_download': True,
},
}, {
# 1080p direct mp4 url
'url': 'https://www.raiplay.it/video/2021/03/Leonardo-S1E1-b5703b02-82ee-475a-85b6-c9e4a8adf642.html',
'md5': '2e501e8651d72f05ffe8f5d286ad560b',
'info_dict': {
'id': 'b5703b02-82ee-475a-85b6-c9e4a8adf642',
'ext': 'mp4',
'title': 'Leonardo - S1E1',
'alt_title': 'St 1 Ep 1 - Episodio 1',
'description': 'md5:f5360cd267d2de146e4e3879a5a47d31',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Rai 1',
'duration': 3229,
'series': 'Leonardo',
'season': 'Season 1',
},
}, {
'url': 'http://www.raiplay.it/video/2016/11/gazebotraindesi-efebe701-969c-4593-92f3-285f0d1ce750.html?',
'only_matching': True,
@@ -158,6 +263,10 @@ class RaiPlayIE(RaiBaseIE):
# subtitles at 'subtitlesArray' key (see #27698)
'url': 'https://www.raiplay.it/video/2020/12/Report---04-01-2021-2e90f1de-8eee-4de4-ac0e-78d21db5b600.html',
'only_matching': True,
}, {
# DRM protected
'url': 'https://www.raiplay.it/video/2020/09/Lo-straordinario-mondo-di-Zoey-S1E1-Lo-straordinario-potere-di-Zoey-ed493918-1d32-44b7-8454-862e473d00ff.html',
'only_matching': True,
}]
def _real_extract(self, url):
@@ -166,6 +275,13 @@ class RaiPlayIE(RaiBaseIE):
media = self._download_json(
base + '.json', video_id, 'Downloading video JSON')
if try_get(
media,
(lambda x: x['rights_management']['rights']['drm'],
lambda x: x['program_info']['rights_management']['rights']['drm']),
dict):
raise ExtractorError('This video is DRM protected.', expected=True)
title = media['name']
video = media['video']
@@ -307,7 +423,7 @@ class RaiIE(RaiBaseIE):
}, {
# with ContentItem in og:url
'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-efb17665-691c-45d5-a60c-5301333cbb0c.html',
'md5': '6865dd00cf0bbf5772fdd89d59bd768a',
'md5': '06345bd97c932f19ffb129973d07a020',
'info_dict': {
'id': 'efb17665-691c-45d5-a60c-5301333cbb0c',
'ext': 'mp4',

97
youtube_dl/extractor/rbgtum.py Normal file
View File

@@ -0,0 +1,97 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class RbgTumIE(InfoExtractor):
_VALID_URL = r'https://live\.rbg\.tum\.de/w/(?P<id>.+)'
_TESTS = [{
# Combined view
'url': 'https://live.rbg.tum.de/w/cpp/22128',
'md5': '53a5e7b3e07128e33bbf36687fe1c08f',
'info_dict': {
'id': 'cpp/22128',
'ext': 'mp4',
'title': 'Lecture: October 18. 2022',
'series': 'Concepts of C++ programming (IN2377)',
}
}, {
# Presentation only
'url': 'https://live.rbg.tum.de/w/I2DL/12349/PRES',
'md5': '36c584272179f3e56b0db5d880639cba',
'info_dict': {
'id': 'I2DL/12349/PRES',
'ext': 'mp4',
'title': 'Lecture 3: Introduction to Neural Networks',
'series': 'Introduction to Deep Learning (IN2346)',
}
}, {
# Camera only
'url': 'https://live.rbg.tum.de/w/fvv-info/16130/CAM',
'md5': 'e04189d92ff2f56aedf5cede65d37aad',
'info_dict': {
'id': 'fvv-info/16130/CAM',
'ext': 'mp4',
'title': 'Fachschaftsvollversammlung',
'series': 'Fachschaftsvollversammlung Informatik',
}
}, ]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
m3u8 = self._html_search_regex(r'(https://.+?\.m3u8)', webpage, 'm3u8')
lecture_title = self._html_search_regex(r'(?si)<h1.*?>(.*)</h1>', webpage, 'title')
lecture_series_title = self._html_search_regex(
r'(?s)<title\b[^>]*>\s*(?:TUM-Live\s\|\s?)?([^:]+):?.*?</title>', webpage, 'series')
formats = self._extract_m3u8_formats(m3u8, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
self._sort_formats(formats)
return {
'id': video_id,
'title': lecture_title,
'series': lecture_series_title,
'formats': formats,
}
class RbgTumCourseIE(InfoExtractor):
_VALID_URL = r'https://live\.rbg\.tum\.de/course/(?P<id>.+)'
_TESTS = [{
'url': 'https://live.rbg.tum.de/course/2022/S/fpv',
'info_dict': {
'title': 'Funktionale Programmierung und Verifikation (IN0003)',
'id': '2022/S/fpv',
},
'params': {
'noplaylist': False,
},
'playlist_count': 13,
}, {
'url': 'https://live.rbg.tum.de/course/2022/W/set',
'info_dict': {
'title': 'SET FSMPIC',
'id': '2022/W/set',
},
'params': {
'noplaylist': False,
},
'playlist_count': 6,
}, ]
def _real_extract(self, url):
course_id = self._match_id(url)
webpage = self._download_webpage(url, course_id)
lecture_series_title = self._html_search_regex(r'(?si)<h1.*?>(.*)</h1>', webpage, 'title')
lecture_urls = []
for lecture_url in re.findall(r'(?i)href="/w/(.+)(?<!/cam)(?<!/pres)(?<!/chat)"', webpage):
lecture_urls.append(self.url_result('https://live.rbg.tum.de/w/' + lecture_url, ie=RbgTumIE.ie_key()))
return self.playlist_result(lecture_urls, course_id, lecture_series_title)

124
youtube_dl/extractor/s4c.py Normal file
View File

@@ -0,0 +1,124 @@
# coding: utf-8
from __future__ import unicode_literals
from functools import partial as partial_f
from .common import InfoExtractor
from ..utils import (
float_or_none,
merge_dicts,
T,
traverse_obj,
txt_or_none,
url_or_none,
)
class S4CIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?s4c\.cymru/clic/programme/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.s4c.cymru/clic/programme/861362209',
'info_dict': {
'id': '861362209',
'ext': 'mp4',
'title': 'Y Swn',
'description': 'md5:f7681a30e4955b250b3224aa9fe70cf0',
'duration': 5340,
'thumbnail': 'https://www.s4c.cymru/amg/1920x1080/Y_Swn_2023S4C_099_ii.jpg',
},
}, {
'url': 'https://www.s4c.cymru/clic/programme/856636948',
'info_dict': {
'id': '856636948',
'ext': 'mp4',
'title': 'Am Dro',
'duration': 2880,
'description': 'md5:100d8686fc9a632a0cb2db52a3433ffe',
'thumbnail': 'https://www.s4c.cymru/amg/1920x1080/Am_Dro_2022-23S4C_P6_4005.jpg',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
details = self._download_json(
'https://www.s4c.cymru/df/full_prog_details',
video_id, query={
'lang': 'e',
'programme_id': video_id,
}, fatal=False)
player_config = self._download_json(
'https://player-api.s4c-cdn.co.uk/player-configuration/prod', video_id, query={
'programme_id': video_id,
'signed': '0',
'lang': 'en',
'mode': 'od',
'appId': 'clic',
'streamName': '',
}, note='Downloading player config JSON')
m3u8_url = self._download_json(
'https://player-api.s4c-cdn.co.uk/streaming-urls/prod', video_id, query={
'mode': 'od',
'application': 'clic',
'region': 'WW',
'extra': 'false',
'thirdParty': 'false',
'filename': player_config['filename'],
}, note='Downloading streaming urls JSON')['hls']
formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', m3u8_id='hls', entry_protocol='m3u8_native')
self._sort_formats(formats)
subtitles = {}
for sub in traverse_obj(player_config, ('subtitles', lambda _, v: url_or_none(v['0']))):
subtitles.setdefault(sub.get('3', 'en'), []).append({
'url': sub['0'],
'name': sub.get('1'),
})
return merge_dicts({
'id': video_id,
'formats': formats,
'subtitles': subtitles,
'thumbnail': url_or_none(player_config.get('poster')),
}, traverse_obj(details, ('full_prog_details', 0, {
'title': (('programme_title', 'series_title'), T(txt_or_none)),
'description': ('full_billing', T(txt_or_none)),
'duration': ('duration', T(partial_f(float_or_none, invscale=60))),
}), get_all=False),
rev=True)
class S4CSeriesIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?s4c\.cymru/clic/series/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.s4c.cymru/clic/series/864982911',
'playlist_mincount': 6,
'info_dict': {
'id': '864982911',
'title': 'Iaith ar Daith',
},
}, {
'url': 'https://www.s4c.cymru/clic/series/866852587',
'playlist_mincount': 8,
'info_dict': {
'id': '866852587',
'title': 'FFIT Cymru',
},
}]
def _real_extract(self, url):
series_id = self._match_id(url)
series_details = self._download_json(
'https://www.s4c.cymru/df/series_details', series_id, query={
'lang': 'e',
'series_id': series_id,
'show_prog_in_series': 'Y'
}, note='Downloading series details JSON')
return self.playlist_result(
(self.url_result('https://www.s4c.cymru/clic/programme/' + episode_id, S4CIE, episode_id)
for episode_id in traverse_obj(series_details, ('other_progs_in_series', Ellipsis, 'id'))),
playlist_id=series_id, playlist_title=traverse_obj(
series_details, ('full_prog_details', 0, 'series_title', T(txt_or_none))))

2
youtube_dl/extractor/streamcz.py
View File

@@ -62,7 +62,7 @@ class StreamCZIE(InfoExtractor):
if not stream.get('url'):
continue
yield merge_dicts({
'format_id': '{}-{}'.format(format_id, ext),
'format_id': '-'.join((format_id, ext)),
'ext': ext,
'source_preference': pref,
'url': urljoin(spl_url, stream['url']),

61
youtube_dl/extractor/streamsb.py Normal file
View File

@@ -0,0 +1,61 @@
# coding: utf-8
from __future__ import unicode_literals
import binascii
import random
import re
import string
from .common import InfoExtractor
from ..utils import urljoin, url_basename
def to_ascii_hex(str1):
return binascii.hexlify(str1.encode('utf-8')).decode('ascii')
def generate_random_string(length):
return ''.join(random.choice(string.ascii_letters + string.digits) for _ in range(length))
class StreamsbIE(InfoExtractor):
_DOMAINS = ('viewsb.com', )
_VALID_URL = r'https://(?P<domain>%s)/(?P<id>.+)' % '|'.join(_DOMAINS)
_TEST = {
'url': 'https://viewsb.com/dxfvlu4qanjx',
'md5': '488d111a63415369bf90ea83adc8a325',
'info_dict': {
'id': 'dxfvlu4qanjx',
'ext': 'mp4',
'title': 'Sintel'
}
}
def _real_extract(self, url):
domain, video_id = re.match(self._VALID_URL, url).group('domain', 'id')
webpage = self._download_webpage(url, video_id)
iframe_rel_url = self._search_regex(r'''(?i)<iframe\b[^>]+\bsrc\s*=\s*('|")(?P<path>/.*\.html)\1''', webpage, 'iframe', group='path')
iframe_url = urljoin('https://' + domain, iframe_rel_url)
iframe_data = self._download_webpage(iframe_url, video_id)
app_version = self._search_regex(r'''<script\b[^>]+\bsrc\s*=\s*["|'].*/app\.min\.(\d+)\.js''', iframe_data, 'app version', fatal=False) or '50'
video_code = url_basename(iframe_url).rsplit('.')[0]
length = 12
req = '||'.join((generate_random_string(length), video_code, generate_random_string(length), 'streamsb'))
ereq = 'https://{0}/sources{1}/{2}'.format(domain, app_version, to_ascii_hex(req))
video_data = self._download_webpage(ereq, video_id, headers={
'Referer': iframe_url,
'watchsb': 'sbstream',
})
player_data = self._parse_json(video_data, video_id)
title = player_data['stream_data']['title']
formats = self._extract_m3u8_formats(player_data['stream_data']['file'], video_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
return {
'id': video_id,
'formats': formats,
'title': title,
}

4
youtube_dl/extractor/telegraaf.py
View File

@@ -34,7 +34,9 @@ class TelegraafIE(InfoExtractor):
article_id = self._match_id(url)
video_id = self._download_json(
'https://www.telegraaf.nl/graphql', article_id, query={
'https://app.telegraaf.nl/graphql', article_id,
headers={'User-Agent': 'De Telegraaf/6.8.11 (Android 11; en_US)'},
query={
'query': '''{
article(uid: %s) {
videos {

47
youtube_dl/extractor/telewebion.py
View File

@@ -3,17 +3,23 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
float_or_none,
int_or_none,
url_or_none,
)
class TelewebionIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?telewebion\.com/#!/episode/(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?telewebion\.com/(episode|clip)/(?P<id>[a-zA-Z0-9]+)'
_TEST = {
'url': 'http://www.telewebion.com/#!/episode/1263668/',
'url': 'http://www.telewebion.com/episode/0x1b3139c/',
'info_dict': {
'id': '1263668',
'id': '0x1b3139c',
'ext': 'mp4',
'title': 'قرعه\u200cکشی لیگ قهرمانان اروپا',
'thumbnail': r're:^https?://.*\.jpg',
'thumbnail': r're:^https?://static\.telewebion\.com/episodeImages/.*/default',
'view_count': int,
},
'params': {
@@ -25,31 +31,24 @@ class TelewebionIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
secure_token = self._download_webpage(
'http://m.s2.telewebion.com/op/op?action=getSecurityToken', video_id)
episode_details = self._download_json(
'http://m.s2.telewebion.com/op/op', video_id,
query={'action': 'getEpisodeDetails', 'episode_id': video_id})
episode_details = self._download_json('https://gateway.telewebion.ir/kandoo/episode/getEpisodeDetail/?EpisodeId={0}'.format(video_id), video_id)
episode_details = episode_details['body']['queryEpisode'][0]
m3u8_url = 'http://m.s1.telewebion.com/smil/%s.m3u8?filepath=%s&m3u8=1&secure_token=%s' % (
video_id, episode_details['file_path'], secure_token)
channel_id = episode_details['channel']['descriptor']
episode_image_id = episode_details.get('image')
episode_image = 'https://static.telewebion.com/episodeImages/{0}/default'.format(episode_image_id) if episode_image_id else None
m3u8_url = 'https://cdna.telewebion.com/{0}/episode/{1}/playlist.m3u8'.format(channel_id, video_id)
formats = self._extract_m3u8_formats(
m3u8_url, video_id, ext='mp4', m3u8_id='hls')
picture_paths = [
episode_details.get('picture_path'),
episode_details.get('large_picture_path'),
]
thumbnails = [{
'url': picture_path,
'preference': idx,
} for idx, picture_path in enumerate(picture_paths) if picture_path is not None]
m3u8_url, video_id, ext='mp4', m3u8_id='hls',
entry_protocol='m3u8_native')
self._sort_formats(formats)
return {
'id': video_id,
'title': episode_details['title'],
'formats': formats,
'thumbnails': thumbnails,
'view_count': episode_details.get('view_count'),
'thumbnail': url_or_none(episode_image),
'view_count': int_or_none(episode_details.get('view_count')),
'duration': float_or_none(episode_details.get('duration')),
}

218
youtube_dl/extractor/thisvid.py Normal file
View File

@@ -0,0 +1,218 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import itertools
from .common import InfoExtractor
from ..compat import (
compat_urlparse,
)
from ..utils import (
clean_html,
get_element_by_class,
int_or_none,
merge_dicts,
url_or_none,
urljoin,
)
class ThisVidIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?thisvid\.com/(?P<type>videos|embed)/(?P<id>[A-Za-z0-9-]+)'
_TESTS = [{
'url': 'https://thisvid.com/videos/sitting-on-ball-tight-jeans/',
'md5': '839becb572995687e11a69dc4358a386',
'info_dict': {
'id': '3533241',
'ext': 'mp4',
'title': 'Sitting on ball tight jeans',
'description': 'md5:372353bb995883d1b65fddf507489acd',
'thumbnail': r're:https?://\w+\.thisvid\.com/(?:[^/]+/)+3533241/preview\.jpg',
'uploader_id': '150629',
'uploader': 'jeanslevisjeans',
'age_limit': 18,
}
}, {
'url': 'https://thisvid.com/embed/3533241/',
'md5': '839becb572995687e11a69dc4358a386',
'info_dict': {
'id': '3533241',
'ext': 'mp4',
'title': 'Sitting on ball tight jeans',
'thumbnail': r're:https?://\w+\.thisvid\.com/(?:[^/]+/)+3533241/preview\.jpg',
'uploader_id': '150629',
'uploader': 'jeanslevisjeans',
'age_limit': 18,
}
}]
def _real_extract(self, url):
main_id, type_ = re.match(self._VALID_URL, url).group('id', 'type')
webpage = self._download_webpage(url, main_id)
title = self._html_search_regex(
r'<title\b[^>]*?>(?:Video:\s+)?(.+?)(?:\s+-\s+ThisVid(?:\.com| tube))?</title>',
webpage, 'title')
if type_ == 'embed':
# look for more metadata
video_alt_url = url_or_none(self._search_regex(
r'''video_alt_url\s*:\s+'(%s/)',''' % (self._VALID_URL, ),
webpage, 'video_alt_url', default=None))
if video_alt_url and video_alt_url != url:
webpage = self._download_webpage(
video_alt_url, main_id,
note='Redirecting embed to main page', fatal=False) or webpage
video_holder = get_element_by_class('video-holder', webpage) or ''
if '>This video is a private video' in video_holder:
self.raise_login_required(
(clean_html(video_holder) or 'Private video').split('\n', 1)[0])
uploader = self._html_search_regex(
r'''(?s)<span\b[^>]*>Added by:\s*</span><a\b[^>]+\bclass\s*=\s*["']author\b[^>]+\bhref\s*=\s*["']https://thisvid\.com/members/([0-9]+/.{3,}?)\s*</a>''',
webpage, 'uploader', default='')
uploader = re.split(r'''/["'][^>]*>\s*''', uploader)
if len(uploader) == 2:
# id must be non-empty, uploader could be ''
uploader_id, uploader = uploader
uploader = uploader or None
else:
uploader_id = uploader = None
return merge_dicts({
'_type': 'url_transparent',
'title': title,
'age_limit': 18,
'uploader': uploader,
'uploader_id': uploader_id,
}, self.url_result(url, ie='Generic'))
class ThisVidMemberIE(InfoExtractor):
_VALID_URL = r'https?://thisvid\.com/members/(?P<id>\d+)'
_TESTS = [{
'url': 'https://thisvid.com/members/2140501/',
'info_dict': {
'id': '2140501',
'title': 'Rafflesia\'s Profile',
},
'playlist_mincount': 16,
}, {
'url': 'https://thisvid.com/members/2140501/favourite_videos/',
'info_dict': {
'id': '2140501',
'title': 'Rafflesia\'s Favourite Videos',
},
'playlist_mincount': 15,
}, {
'url': 'https://thisvid.com/members/636468/public_videos/',
'info_dict': {
'id': '636468',
'title': 'Happymouth\'s Public Videos',
},
'playlist_mincount': 196,
},
]
def _urls(self, html):
for m in re.finditer(r'''<a\b[^>]+\bhref\s*=\s*["'](?P<url>%s\b)[^>]+>''' % (ThisVidIE._VALID_URL, ), html):
yield m.group('url')
def _real_extract(self, url):
pl_id = self._match_id(url)
webpage = self._download_webpage(url, pl_id)
title = re.split(
r'(?i)\s*\|\s*ThisVid\.com\s*$',
self._og_search_title(webpage, default=None) or self._html_search_regex(r'(?s)<title\b[^>]*>(.+?)</title', webpage, 'title', fatal=False) or '', 1)[0] or None
def entries(page_url, html=None):
for page in itertools.count(1):
if not html:
html = self._download_webpage(
page_url, pl_id, note='Downloading page %d' % (page, ),
fatal=False) or ''
for u in self._urls(html):
yield u
next_page = get_element_by_class('pagination-next', html) or ''
if next_page:
# member list page
next_page = urljoin(url, self._search_regex(
r'''<a\b[^>]+\bhref\s*=\s*("|')(?P<url>(?!#)(?:(?!\1).)+)''',
next_page, 'next page link', group='url', default=None))
# in case a member page should have pagination-next with empty link, not just `else:`
if next_page is None:
# playlist page
parsed_url = compat_urlparse.urlparse(page_url)
base_path, num = parsed_url.path.rsplit('/', 1)
num = int_or_none(num)
if num is None:
base_path, num = parsed_url.path.rstrip('/'), 1
parsed_url = parsed_url._replace(path=base_path + ('/%d' % (num + 1, )))
next_page = compat_urlparse.urlunparse(parsed_url)
if page_url == next_page:
next_page = None
if not next_page:
break
page_url, html = next_page, None
return self.playlist_from_matches(
entries(url, webpage), playlist_id=pl_id, playlist_title=title, ie='ThisVid')
class ThisVidPlaylistIE(ThisVidMemberIE):
_VALID_URL = r'https?://thisvid\.com/playlist/(?P<id>\d+)/video/(?P<video_id>[A-Za-z0-9-]+)'
_TESTS = [{
'url': 'https://thisvid.com/playlist/6615/video/big-italian-booty-28/',
'info_dict': {
'id': '6615',
'title': 'Underwear Stuff',
},
'playlist_mincount': 200,
}, {
'url': 'https://thisvid.com/playlist/6615/video/big-italian-booty-28/',
'info_dict': {
'id': '1072387',
'ext': 'mp4',
'title': 'Big Italian Booty 28',
'description': 'md5:1bccf7b13765e18fb27bf764dba7ede2',
'uploader_id': '367912',
'uploader': 'Jcmusclefun',
'age_limit': 18,
},
'params': {
'noplaylist': True,
},
}]
def _get_video_url(self, pl_url):
video_id = re.match(self._VALID_URL, pl_url).group('video_id')
return urljoin(pl_url, '/videos/%s/' % (video_id, ))
def _urls(self, html):
for m in re.finditer(r'''<a\b[^>]+\bhref\s*=\s*["'](?P<url>%s\b)[^>]+>''' % (self._VALID_URL, ), html):
yield self._get_video_url(m.group('url'))
def _real_extract(self, url):
pl_id = self._match_id(url)
if self._downloader.params.get('noplaylist'):
self.to_screen('Downloading just the featured video because of --no-playlist')
return self.url_result(self._get_video_url(url), 'ThisVid')
self.to_screen(
'Downloading playlist %s - add --no-playlist to download just the featured video' % (pl_id, ))
result = super(ThisVidPlaylistIE, self)._real_extract(url)
# rework title returned as `the title - the title`
title = result['title']
t_len = len(title)
if t_len > 5 and t_len % 2 != 0:
t_len = t_len // 2
if title[t_len] == '-':
title = [t.strip() for t in (title[:t_len], title[t_len + 1:])]
if title[0] and title[0] == title[1]:
result['title'] = title[0]
return result

2
youtube_dl/extractor/uktvplay.py
View File

@@ -5,7 +5,7 @@ from .common import InfoExtractor
class UKTVPlayIE(InfoExtractor):
_VALID_URL = r'https?://uktvplay\.uktv\.co\.uk/(?:.+?\?.*?\bvideo=|([^/]+/)*watch-online/)(?P<id>\d+)'
_VALID_URL = r'https?://uktvplay\.(?:uktv\.)?co\.uk/(?:.+?\?.*?\bvideo=|([^/]+/)*watch-online/)(?P<id>\d+)'
_TESTS = [{
'url': 'https://uktvplay.uktv.co.uk/shows/world-at-war/c/200/watch-online/?video=2117008346001',
'info_dict': {

171
youtube_dl/extractor/vbox7.py
View File

@@ -2,9 +2,22 @@
from __future__ import unicode_literals
import re
import time
from .common import InfoExtractor
from ..utils import ExtractorError
from ..compat import compat_kwargs
from ..utils import (
base_url,
determine_ext,
ExtractorError,
float_or_none,
merge_dicts,
T,
traverse_obj,
txt_or_none,
url_basename,
url_or_none,
)
class Vbox7IE(InfoExtractor):
@@ -20,23 +33,27 @@ class Vbox7IE(InfoExtractor):
)
(?P<id>[\da-fA-F]+)
'''
_EMBED_REGEX = [r'<iframe[^>]+src=(?P<q>["\'])(?P<url>(?:https?:)?//vbox7\.com/emb/external\.php.+?)(?P=q)']
_GEO_COUNTRIES = ['BG']
_TESTS = [{
'url': 'http://vbox7.com/play:0946fff23c',
'md5': 'a60f9ab3a3a2f013ef9a967d5f7be5bf',
# the http: URL just redirects here
'url': 'https://vbox7.com/play:0946fff23c',
'md5': '50ca1f78345a9c15391af47d8062d074',
'info_dict': {
'id': '0946fff23c',
'ext': 'mp4',
'title': 'Борисов: Притеснен съм за бъдещето на България',
'description': 'По думите му е опасно страната ни да бъде обявена за "сигурна"',
'thumbnail': r're:^https?://.*\.jpg$',
'timestamp': 1470982814,
'upload_date': '20160812',
'uploader': 'zdraveibulgaria',
'thumbnail': r're:^https?://.*\.jpg$',
'view_count': int,
'duration': 2640,
},
'params': {
'proxy': '127.0.0.1:8118',
},
'expected_warnings': [
'Unable to download webpage',
],
}, {
'url': 'http://vbox7.com/play:249bb972c2',
'md5': '99f65c0c9ef9b682b97313e052734c3f',
@@ -44,8 +61,15 @@ class Vbox7IE(InfoExtractor):
'id': '249bb972c2',
'ext': 'mp4',
'title': 'Смях! Чудо - чист за секунди - Скрита камера',
'description': 'Смях! Чудо - чист за секунди - Скрита камера',
'timestamp': 1360215023,
'upload_date': '20130207',
'uploader': 'svideteliat_ot_varshava',
'thumbnail': 'https://i49.vbox7.com/o/249/249bb972c20.jpg',
'view_count': int,
'duration': 83,
},
'skip': 'georestricted',
'expected_warnings': ['Failed to download m3u8 information'],
}, {
'url': 'http://vbox7.com/emb/external.php?vid=a240d20f9c&autoplay=1',
'only_matching': True,
@@ -54,52 +78,127 @@ class Vbox7IE(InfoExtractor):
'only_matching': True,
}]
@staticmethod
def _extract_url(webpage):
mobj = re.search(
r'<iframe[^>]+src=(?P<q>["\'])(?P<url>(?:https?:)?//vbox7\.com/emb/external\.php.+?)(?P=q)',
webpage)
@classmethod
def _extract_url(cls, webpage):
mobj = re.search(cls._EMBED_REGEX[0], webpage)
if mobj:
return mobj.group('url')
# specialisation to transform what looks like ld+json that
# may contain invalid character combinations
# transform_source=None, fatal=True
def _parse_json(self, json_string, video_id, *args, **kwargs):
if '"@context"' in json_string[:30]:
# this is ld+json, or that's the way to bet
transform_source = args[0] if len(args) > 0 else kwargs.get('transform_source')
if not transform_source:
def fix_chars(src):
# fix malformed ld+json: replace raw CRLFs with escaped LFs
return re.sub(
r'"[^"]+"', lambda m: re.sub(r'\r?\n', r'\\n', m.group(0)), src)
if len(args) > 0:
args = (fix_chars,) + args[1:]
else:
kwargs['transform_source'] = fix_chars
kwargs = compat_kwargs(kwargs)
return super(Vbox7IE, self)._parse_json(
json_string, video_id, *args, **kwargs)
def _real_extract(self, url):
video_id = self._match_id(url)
url = 'https://vbox7.com/play:%s' % (video_id,)
now = time.time()
response = self._download_json(
'https://www.vbox7.com/ajax/video/nextvideo.php?vid=%s' % video_id,
video_id)
'https://www.vbox7.com/aj/player/item/options', video_id,
query={'vid': video_id}, headers={'Referer': url})
# estimate time to which possible `ago` member is relative
now = now + 0.5 * (time.time() - now)
if 'error' in response:
if traverse_obj(response, 'error'):
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, response['error']), expected=True)
video = response['options']
src_url = traverse_obj(response, ('options', 'src', T(url_or_none))) or ''
title = video['title']
video_url = video['src']
if '/na.mp4' in video_url:
fmt_base = url_basename(src_url).rsplit('.', 1)[0].rsplit('_', 1)[0]
if fmt_base in ('na', 'vn'):
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
uploader = video.get('uploader')
ext = determine_ext(src_url)
if ext == 'mpd':
# extract MPD
try:
formats, subtitles = self._extract_mpd_formats_and_subtitles(
src_url, video_id, 'dash', fatal=False)
except KeyError: # fatal doesn't catch this
self.report_warning('Failed to parse MPD manifest')
formats, subtitles = [], {}
elif ext != 'm3u8':
formats = [{
'url': src_url,
}] if src_url else []
subtitles = {}
webpage = self._download_webpage(
'http://vbox7.com/play:%s' % video_id, video_id, fatal=None)
if src_url:
# possibly extract HLS, based on https://github.com/yt-dlp/yt-dlp/pull/9100
fmt_base = base_url(src_url) + fmt_base
# prepare for _extract_m3u8_formats_and_subtitles()
# hls_formats, hls_subs = self._extract_m3u8_formats_and_subtitles(
hls_formats = self._extract_m3u8_formats(
'{0}.m3u8'.format(fmt_base), video_id, m3u8_id='hls', fatal=False)
formats.extend(hls_formats)
# self._merge_subtitles(hls_subs, target=subtitles)
info = {}
# In case MPD/HLS cannot be parsed, or anyway, get mp4 combined
# formats usually provided to Safari, iOS, and old Windows
video = response['options']
resolutions = (1080, 720, 480, 240, 144)
highest_res = traverse_obj(video, (
'highestRes', T(int))) or resolutions[0]
resolutions = traverse_obj(video, (
'resolutions', lambda _, r: highest_res >= int(r) > 0)) or resolutions
mp4_formats = traverse_obj(resolutions, (
Ellipsis, T(lambda res: {
'url': '{0}_{1}.mp4'.format(fmt_base, res),
'format_id': 'http-{0}'.format(res),
'height': res,
})))
# if above formats are flaky, enable the line below
# self._check_formats(mp4_formats, video_id)
formats.extend(mp4_formats)
if webpage:
info = self._search_json_ld(
webpage.replace('"/*@context"', '"@context"'), video_id,
fatal=False)
self._sort_formats(formats)
info.update({
webpage = self._download_webpage(url, video_id, fatal=False) or ''
info = self._search_json_ld(
webpage.replace('"/*@context"', '"@context"'), video_id,
fatal=False) if webpage else {}
if not info.get('title'):
info['title'] = traverse_obj(response, (
'options', 'title', T(txt_or_none))) or self._og_search_title(webpage)
def if_missing(k):
return lambda x: None if k in info else x
info = merge_dicts(info, {
'id': video_id,
'title': title,
'url': video_url,
'uploader': uploader,
'thumbnail': self._proto_relative_url(
'formats': formats,
'subtitles': subtitles or None,
}, info, traverse_obj(response, ('options', {
'uploader': ('uploader', T(txt_or_none)),
'timestamp': ('ago', T(if_missing('timestamp')), T(lambda t: int(round((now - t) / 60.0)) * 60)),
'duration': ('duration', T(if_missing('duration')), T(float_or_none)),
})))
if 'thumbnail' not in info:
info['thumbnail'] = self._proto_relative_url(
info.get('thumbnail') or self._og_search_thumbnail(webpage),
'http:'),
})
'https:'),
return info

44
youtube_dl/extractor/videa.py
View File

@@ -6,22 +6,31 @@ import re
import string
from .common import InfoExtractor
from ..compat import (
compat_b64decode,
compat_ord,
compat_struct_pack,
)
from ..utils import (
ExtractorError,
int_or_none,
mimetype2ext,
parse_codecs,
parse_qs,
update_url_query,
urljoin,
xpath_element,
xpath_text,
)
from ..compat import (
compat_b64decode,
compat_ord,
compat_struct_pack,
compat_urlparse,
)
def compat_random_choices(population, *args, **kwargs):
# weights=None, *, cum_weights=None, k=1
# limited implementation needed here
weights = args[0] if args else kwargs.get('weights')
assert all(w is None for w in (weights, kwargs.get('cum_weights')))
k = kwargs.get('k', 1)
return ''.join(random.choice(population) for _ in range(k))
class VideaIE(InfoExtractor):
@@ -35,6 +44,7 @@ class VideaIE(InfoExtractor):
)
(?P<id>[^?#&]+)
'''
_EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//videa\.hu/player\?.*?\bv=.+?)\1']
_TESTS = [{
'url': 'http://videa.hu/videok/allatok/az-orult-kigyasz-285-kigyot-kigyo-8YfIAjxwWGwT8HVQ',
'md5': '97a7af41faeaffd9f1fc864a7c7e7603',
@@ -44,6 +54,7 @@ class VideaIE(InfoExtractor):
'title': 'Az őrült kígyász 285 kígyót enged szabadon',
'thumbnail': r're:^https?://.*',
'duration': 21,
'age_limit': 0,
},
}, {
'url': 'http://videa.hu/videok/origo/jarmuvek/supercars-elozes-jAHDWfWSJH5XuFhH',
@@ -54,6 +65,7 @@ class VideaIE(InfoExtractor):
'title': 'Supercars előzés',
'thumbnail': r're:^https?://.*',
'duration': 64,
'age_limit': 0,
},
}, {
'url': 'http://videa.hu/player?v=8YfIAjxwWGwT8HVQ',
@@ -64,6 +76,7 @@ class VideaIE(InfoExtractor):
'title': 'Az őrült kígyász 285 kígyót enged szabadon',
'thumbnail': r're:^https?://.*',
'duration': 21,
'age_limit': 0,
},
}, {
'url': 'http://videa.hu/player/v/8YfIAjxwWGwT8HVQ?autoplay=1',
@@ -80,11 +93,14 @@ class VideaIE(InfoExtractor):
}]
_STATIC_SECRET = 'xHb0ZvME5q8CBcoQi6AngerDu3FGO9fkUlwPmLVY_RTzj2hJIS4NasXWKy1td7p'
@staticmethod
def _extract_urls(webpage):
return [url for _, url in re.findall(
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//videa\.hu/player\?.*?\bv=.+?)\1',
webpage)]
@classmethod
def _extract_urls(cls, webpage):
def yield_urls():
for pattern in cls._EMBED_REGEX:
for m in re.finditer(pattern, webpage):
yield m.group('url')
return list(yield_urls())
@staticmethod
def rc4(cipher_text, key):
@@ -130,13 +146,13 @@ class VideaIE(InfoExtractor):
for i in range(0, 32):
result += s[i - (self._STATIC_SECRET.index(l[i]) - 31)]
query = compat_urlparse.parse_qs(compat_urlparse.urlparse(player_url).query)
random_seed = ''.join(random.choice(string.ascii_letters + string.digits) for _ in range(8))
query = parse_qs(player_url)
random_seed = ''.join(compat_random_choices(string.ascii_letters + string.digits, k=8))
query['_s'] = random_seed
query['_t'] = result[:16]
b64_info, handle = self._download_webpage_handle(
'http://videa.hu/videaplayer_get_xml.php', video_id, query=query)
'http://videa.hu/player/xml', video_id, query=query)
if b64_info.startswith('<?xml'):
info = self._parse_xml(b64_info, video_id)
else:

59
youtube_dl/extractor/vidlii.py
View File

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
float_or_none,
get_element_by_id,
@@ -11,6 +12,7 @@ from ..utils import (
strip_or_none,
unified_strdate,
urljoin,
str_to_int,
)
@@ -35,6 +37,26 @@ class VidLiiIE(InfoExtractor):
'categories': ['News & Politics'],
'tags': ['Vidlii', 'Jan', 'Videogames'],
}
}, {
# HD
'url': 'https://www.vidlii.com/watch?v=2Ng8Abj2Fkl',
'md5': '450e7da379c884788c3a4fa02a3ce1a4',
'info_dict': {
'id': '2Ng8Abj2Fkl',
'ext': 'mp4',
'title': 'test',
'description': 'md5:cc55a86032a7b6b3cbfd0f6b155b52e9',
'thumbnail': 'https://www.vidlii.com/usfi/thmp/2Ng8Abj2Fkl.jpg',
'uploader': 'VidLii',
'uploader_url': 'https://www.vidlii.com/user/VidLii',
'upload_date': '20200927',
'duration': 5,
'view_count': int,
'comment_count': int,
'average_rating': float,
'categories': ['Film & Animation'],
'tags': list,
},
}, {
'url': 'https://www.vidlii.com/embed?v=tJluaH4BJ3v&a=0',
'only_matching': True,
@@ -46,11 +68,32 @@ class VidLiiIE(InfoExtractor):
webpage = self._download_webpage(
'https://www.vidlii.com/watch?v=%s' % video_id, video_id)
video_url = self._search_regex(
r'src\s*:\s*(["\'])(?P<url>(?:https?://)?(?:(?!\1).)+)\1', webpage,
'video url', group='url')
formats = []
title = self._search_regex(
def add_format(format_url, height=None):
height = int(self._search_regex(r'(\d+)\.mp4',
format_url, 'height', default=360))
formats.append({
'url': format_url,
'format_id': '%dp' % height if height else None,
'height': height,
})
sources = re.findall(
r'src\s*:\s*(["\'])(?P<url>(?:https?://)?(?:(?!\1).)+)\1',
webpage)
formats = []
if len(sources) > 1:
add_format(sources[1][1])
self._check_formats(formats, video_id)
if len(sources) > 0:
add_format(sources[0][1])
self._sort_formats(formats)
title = self._html_search_regex(
(r'<h1>([^<]+)</h1>', r'<title>([^<]+) - VidLii<'), webpage,
'title')
@@ -82,9 +125,9 @@ class VidLiiIE(InfoExtractor):
default=None) or self._search_regex(
r'duration\s*:\s*(\d+)', webpage, 'duration', fatal=False))
view_count = int_or_none(self._search_regex(
(r'<strong>(\d+)</strong> views',
r'Views\s*:\s*<strong>(\d+)</strong>'),
view_count = str_to_int(self._html_search_regex(
(r'<strong>([\d,.]+)</strong> views',
r'Views\s*:\s*<strong>([\d,.]+)</strong>'),
webpage, 'view count', fatal=False))
comment_count = int_or_none(self._search_regex(
@@ -109,7 +152,7 @@ class VidLiiIE(InfoExtractor):
return {
'id': video_id,
'url': video_url,
'formats': formats,
'title': title,
'description': description,
'thumbnail': thumbnail,

81
youtube_dl/extractor/vimeo.py
View File

@@ -261,27 +261,33 @@ class VimeoIE(VimeoBaseInfoExtractor):
# _VALID_URL matches Vimeo URLs
_VALID_URL = r'''(?x)
https?://
(?:
(?:
www|
player
)
\.
)?
vimeo(?:pro)?\.com/
(?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
(?:.*?/)?
(?:
(?:
play_redirect_hls|
moogaloop\.swf)\?clip_id=
)?
(?:videos?/)?
(?P<id>[0-9]+)
(?:/(?P<unlisted_hash>[\da-f]{10}))?
/?(?:[?&].*)?(?:[#].*)?$
'''
https?://
(?:
(?:
www|
player
)
\.
)?
vimeo(?:pro)?\.com/
(?:
(?P<u>user)|
(?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
(?:.*?/)??
(?P<q>
(?:
play_redirect_hls|
moogaloop\.swf)\?clip_id=
)?
(?:videos?/)?
)
(?P<id>[0-9]+)
(?(u)
/(?!videos|likes)[^/?#]+/?|
(?(q)|/(?P<unlisted_hash>[\da-f]{10}))?
)
(?:(?(q)[&]|(?(u)|/?)[?]).+?)?(?:[#].*)?$
'''
IE_NAME = 'vimeo'
_TESTS = [
{
@@ -517,15 +523,34 @@ class VimeoIE(VimeoBaseInfoExtractor):
'url': 'https://vimeo.com/7809605',
'only_matching': True,
},
{
'url': 'https://vimeo.com/160743502/abd0e13fb4',
'only_matching': True,
},
{
# requires passing unlisted_hash(a52724358e) to load_download_config request
'url': 'https://vimeo.com/392479337/a52724358e',
'only_matching': True,
}
},
{
# similar, but all numeric: ID must be 581039021, not 9603038895
# issue #29690
'url': 'https://vimeo.com/581039021/9603038895',
'info_dict': {
'id': '581039021',
# these have to be provided but we don't care
'ext': 'mp4',
'timestamp': 1627621014,
'title': 're:.+',
'uploader_id': 're:.+',
'uploader': 're:.+',
'upload_date': r're:\d+',
},
'params': {
'skip_download': True,
},
},
{
# user playlist alias -> https://vimeo.com/258705797
'url': 'https://vimeo.com/user26785108/newspiritualguide',
'only_matching': True,
},
# https://gettingthingsdone.com/workflowmap/
# vimeo embed with check-password page protected by Referer header
]
@@ -648,8 +673,8 @@ class VimeoIE(VimeoBaseInfoExtractor):
raise
if '//player.vimeo.com/video/' in url:
config = self._parse_json(self._search_regex(
r'\bconfig\s*=\s*({.+?})\s*;', webpage, 'info section'), video_id)
config = self._search_json(
r'\b(?:playerC|c)onfig\s*=', webpage, 'info section', video_id)
if config.get('view') == 4:
config = self._verify_player_video_password(
redirect_url, video_id, headers)

15
youtube_dl/extractor/vvvvid.py
View File

@@ -64,6 +64,18 @@ class VVVVIDIE(InfoExtractor):
'params': {
'skip_download': True,
},
}, {
# video_type == 'video/dash'
'url': 'https://www.vvvvid.it/show/683/made-in-abyss/1542/693786/nanachi',
'info_dict': {
'id': '693786',
'ext': 'mp4',
'title': 'Nanachi',
},
'params': {
'skip_download': True,
'format': 'mp4',
},
}, {
'url': 'https://www.vvvvid.it/show/434/perche-dovrei-guardarlo-di-dario-moccia/437/489048',
'only_matching': True
@@ -205,6 +217,9 @@ class VVVVIDIE(InfoExtractor):
})
is_youtube = True
break
elif video_type == 'video/dash':
formats.extend(self._extract_m3u8_formats(
embed_code, video_id, 'mp4', m3u8_id='hls', fatal=False))
else:
formats.extend(self._extract_wowza_formats(
'http://sb.top-ix.org/videomg/_definst_/mp4:%s/playlist.m3u8' % embed_code, video_id))

2
youtube_dl/extractor/wat.py
View File

@@ -57,7 +57,7 @@ class WatIE(InfoExtractor):
# 'http://www.wat.tv/interface/contentv4s/' + video_id, video_id)
video_data = self._download_json(
'https://mediainfo.tf1.fr/mediainfocombo/' + video_id,
video_id, query={'context': 'MYTF1'})
video_id, query={'context': 'MYTF1', 'pver': '4001000'})
video_info = video_data['media']
error_desc = video_info.get('error_desc')

55
youtube_dl/extractor/whyp.py Normal file
View File

@@ -0,0 +1,55 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
float_or_none,
merge_dicts,
str_or_none,
T,
traverse_obj,
url_or_none,
)
class WhypIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?whyp\.it/tracks/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.whyp.it/tracks/18337/home-page-example-track-b4kq7',
'md5': 'c1187b42ebf8605284e3dc92aeb33d16',
'info_dict': {
'url': 'https://cdn.whyp.it/50eb17cc-e9ff-4e18-b89b-dc9206a95cb1.mp3',
'id': '18337',
'title': 'Home Page Example Track',
'description': r're:(?s).+\bexample track\b',
'ext': 'mp3',
'duration': 52.82,
'uploader': 'Brad',
'uploader_id': '1',
'thumbnail': 'https://cdn.whyp.it/a537bb36-3373-4c61-96c8-27fc1b2f427a.jpg',
},
}, {
'url': 'https://www.whyp.it/tracks/18337',
'only_matching': True,
}]
def _real_extract(self, url):
unique_id = self._match_id(url)
webpage = self._download_webpage(url, unique_id)
data = self._search_nuxt_data(webpage, unique_id)['rawTrack']
return merge_dicts({
'url': data['audio_url'],
'id': unique_id,
}, traverse_obj(data, {
'title': 'title',
'description': 'description',
'duration': ('duration', T(float_or_none)),
'uploader': ('user', 'username'),
'uploader_id': ('user', 'id', T(str_or_none)),
'thumbnail': ('artwork_url', T(url_or_none)),
}), {
'ext': 'mp3',
'vcodec': 'none',
'http_headers': {'Referer': 'https://whyp.it/'},
}, rev=True)

290
youtube_dl/extractor/xfileshare.py
View File

@@ -4,20 +4,28 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_chr
from ..compat import (
compat_chr,
compat_zip as zip,
)
from ..utils import (
clean_html,
decode_packed_codes,
determine_ext,
ExtractorError,
get_element_by_id,
int_or_none,
js_to_json,
merge_dicts,
T,
traverse_obj,
url_or_none,
urlencode_postdata,
)
# based on openload_decode from 2bfeee69b976fe049761dd3012e30b637ee05a58
def aa_decode(aa_code):
symbol_table = [
symbol_table = (
('7', '((ﾟｰﾟ) + (o^_^o))'),
('6', '((o^_^o) +(o^_^o))'),
('5', '((ﾟｰﾟ) + (ﾟΘﾟ))'),
@@ -26,84 +34,180 @@ def aa_decode(aa_code):
('3', '(o^_^o)'),
('1', '(ﾟΘﾟ)'),
('0', '(c^_^o)'),
]
('+', ''),
)
delim = '(ﾟДﾟ)[ﾟεﾟ]+'
ret = ''
for aa_char in aa_code.split(delim):
def chr_from_code(c):
for val, pat in symbol_table:
aa_char = aa_char.replace(pat, val)
aa_char = aa_char.replace('+ ', '')
m = re.match(r'^\d+', aa_char)
if m:
ret += compat_chr(int(m.group(0), 8))
c = c.replace(pat, val)
if c.startswith(('u', 'U')):
base = 16
c = c[1:]
else:
m = re.match(r'^u([\da-f]+)', aa_char)
if m:
ret += compat_chr(int(m.group(1), 16))
return ret
base = 10
c = int_or_none(c, base=base)
return '' if c is None else compat_chr(c)
return ''.join(
chr_from_code(aa_char)
for aa_char in aa_code.split(delim))
class XFileShareIE(InfoExtractor):
_SITES = (
(r'aparat\.cam', 'Aparat'),
(r'clipwatching\.com', 'ClipWatching'),
(r'gounlimited\.to', 'GoUnlimited'),
(r'govid\.me', 'GoVid'),
(r'holavid\.com', 'HolaVid'),
(r'streamty\.com', 'Streamty'),
(r'thevideobee\.to', 'TheVideoBee'),
(r'uqload\.com', 'Uqload'),
(r'vidbom\.com', 'VidBom'),
(r'vidlo\.us', 'vidlo'),
(r'vidlocker\.xyz', 'VidLocker'),
(r'vidshare\.tv', 'VidShare'),
(r'vup\.to', 'VUp'),
# status check 2024-02: site availability, G site: search
(r'aparat\.cam', 'Aparat'), # Cloudflare says host error 522, apparently changed to wolfstreeam.tv
(r'filemoon\.sx/.', 'FileMoon'),
(r'gounlimited\.to', 'GoUnlimited'), # no media pages listed
(r'govid\.me', 'GoVid'), # no media pages listed
(r'highstream\.tv', 'HighStream'), # clipwatching.com redirects here
(r'holavid\.com', 'HolaVid'), # Cloudflare says host error 522
# (r'streamty\.com', 'Streamty'), # no media pages listed, connection timeout
# (r'thevideobee\.to', 'TheVideoBee'), # no pages listed, refuses connection
(r'uqload\.to', 'Uqload'), # .com, .co redirect here
(r'(?:vedbam\.xyz|vadbam.net)', 'V?dB?m'), # vidbom.com redirects here, but no valid media pages listed
(r'vidlo\.us', 'vidlo'), # no valid media pages listed
(r'vidlocker\.xyz', 'VidLocker'), # no media pages listed
(r'(?:w\d\.)?viidshar\.com', 'VidShare'), # vidshare.tv redirects here
# (r'vup\.to', 'VUp'), # domain not found
(r'wolfstream\.tv', 'WolfStream'),
(r'xvideosharing\.com', 'XVideoSharing'),
(r'xvideosharing\.com', 'XVideoSharing'), # just started showing 'maintenance mode'
)
IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
IE_DESC = 'XFileShare-based sites: %s' % ', '.join(list(zip(*_SITES))[1])
_VALID_URL = (r'https?://(?:www\.)?(?P<host>%s)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
% '|'.join(site for site in list(zip(*_SITES))[0]))
_EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:%s)/embed-[0-9a-zA-Z]+.*?)\1' % '|'.join(site for site in list(zip(*_SITES))[0])]
_FILE_NOT_FOUND_REGEXES = (
r'>(?:404 - )?File Not Found<',
r'>The file was removed by administrator<',
)
_TITLE_REGEXES = (
r'style="z-index: [0-9]+;">([^<]+)</span>',
r'<td nowrap>([^<]+)</td>',
r'h4-fine[^>]*>([^<]+)<',
r'>Watch (.+)[ <]',
r'<h2 class="video-page-head">([^<]+)</h2>',
r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<', # streamin.to (dead)
r'title\s*:\s*"([^"]+)"', # govid.me
)
_SOURCE_URL_REGEXES = (
r'(?:file|src)\s*:\s*(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1',
r'file_link\s*=\s*(["\'])(?P<url>http(?:(?!\1).)+)\1',
r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http(?:(?!\2).)+)\2\)',
r'<embed[^>]+src=(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1',
)
_THUMBNAIL_REGEXES = (
r'<video[^>]+poster="([^"]+)"',
r'(?:image|poster)\s*:\s*["\'](http[^"\']+)["\'],',
)
_TESTS = [{
'url': 'http://xvideosharing.com/fq65f94nd2ve',
'md5': '4181f63957e8fe90ac836fa58dc3c8a6',
'note': 'link in `sources`',
'url': 'https://uqload.to/dcsu06gdb45o',
'md5': '7f8db187b254379440bf4fcad094ae86',
'info_dict': {
'id': 'fq65f94nd2ve',
'id': 'dcsu06gdb45o',
'ext': 'mp4',
'title': 'sample',
'thumbnail': r're:http://.*\.jpg',
'title': 'f2e31015957e74c8c8427982e161c3fc mp4',
'thumbnail': r're:https://.*\.jpg'
},
'params': {
'nocheckcertificate': True,
},
'expected_warnings': ['Unable to extract JWPlayer data'],
}, {
'note': 'link in decoded `sources`',
'url': 'https://xvideosharing.com/1tlg6agrrdgc',
'md5': '2608ce41932c1657ae56258a64e647d9',
'info_dict': {
'id': '1tlg6agrrdgc',
'ext': 'mp4',
'title': '0121',
'thumbnail': r're:https?://.*\.jpg',
},
'skip': 'This server is in maintenance mode.',
}, {
'note': 'JWPlayer link in un-p,a,c,k,e,d JS',
'url': 'https://filemoon.sx/e/dw40rxrzruqz',
'md5': '5a713742f57ac4aef29b74733e8dda01',
'info_dict': {
'id': 'dw40rxrzruqz',
'title': 'dw40rxrzruqz',
'ext': 'mp4'
},
}, {
'note': 'JWPlayer link in un-p,a,c,k,e,d JS',
'url': 'https://vadbam.net/6lnbkci96wly.html',
'md5': 'a1616800076177e2ac769203957c54bc',
'info_dict': {
'id': '6lnbkci96wly',
'title': 'Heart Crime S01 E03 weciima autos',
'ext': 'mp4'
},
}, {
'note': 'JWPlayer link in clear',
'url': 'https://w1.viidshar.com/nnibe0xf0h79.html',
'md5': 'f0a580ce9df06cc61b4a5c979d672367',
'info_dict': {
'id': 'nnibe0xf0h79',
'title': 'JaGa 68ar',
'ext': 'mp4'
},
'params': {
'skip_download': 'ffmpeg',
},
'expected_warnings': ['hlsnative has detected features it does not support'],
}, {
'note': 'JWPlayer link in clear',
'url': 'https://wolfstream.tv/a3drtehyrg52.html',
'md5': '1901d86a79c5e0c6a51bdc9a4cfd3769',
'info_dict': {
'id': 'a3drtehyrg52',
'title': 'NFL 2023 W04 DET@GB',
'ext': 'mp4'
},
}, {
'url': 'https://aparat.cam/n4d6dh0wvlpr',
'only_matching': True,
}, {
'url': 'https://wolfstream.tv/nthme29v9u2x',
'url': 'https://uqload.to/ug5somm0ctnk.html',
'only_matching': True,
}, {
'url': 'https://highstream.tv/2owiyz3sjoux',
'only_matching': True,
}, {
'url': 'https://vedbam.xyz/6lnbkci96wly.html',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return [
mobj.group('url')
for mobj in re.finditer(
r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:%s)/embed-[0-9a-zA-Z]+.*?)\1'
% '|'.join(site for site in list(zip(*XFileShareIE._SITES))[0]),
webpage)]
@classmethod
def _extract_urls(cls, webpage):
def yield_urls():
for regex in cls._EMBED_REGEX:
for mobj in re.finditer(regex, webpage):
yield mobj.group('url')
return list(yield_urls())
def _real_extract(self, url):
host, video_id = re.match(self._VALID_URL, url).groups()
host, video_id = self._match_valid_url(url).group('host', 'id')
url = 'https://%s/' % host + ('embed-%s.html' % video_id if host in ('govid.me', 'vidlo.us') else video_id)
url = 'https://%s/%s' % (
host,
'embed-%s.html' % video_id if host in ('govid.me', 'vidlo.us') else video_id)
webpage = self._download_webpage(url, video_id)
if any(re.search(p, webpage) for p in self._FILE_NOT_FOUND_REGEXES):
container_div = get_element_by_id('container', webpage) or webpage
if self._search_regex(
r'>This server is in maintenance mode\.', container_div,
'maint error', group=0, default=None):
raise ExtractorError(clean_html(container_div), expected=True)
if self._search_regex(
self._FILE_NOT_FOUND_REGEXES, container_div,
'missing video error', group=0, default=None):
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
fields = self._hidden_inputs(webpage)
@@ -122,59 +226,43 @@ class XFileShareIE(InfoExtractor):
'Content-type': 'application/x-www-form-urlencoded',
})
title = (self._search_regex(
(r'style="z-index: [0-9]+;">([^<]+)</span>',
r'<td nowrap>([^<]+)</td>',
r'h4-fine[^>]*>([^<]+)<',
r'>Watch (.+)[ <]',
r'<h2 class="video-page-head">([^<]+)</h2>',
r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<', # streamin.to
r'title\s*:\s*"([^"]+)"'), # govid.me
webpage, 'title', default=None) or self._og_search_title(
webpage, default=None) or video_id).strip()
title = (
self._search_regex(self._TITLE_REGEXES, webpage, 'title', default=None)
or self._og_search_title(webpage, default=None)
or video_id).strip()
for regex, func in (
(r'(eval\(function\(p,a,c,k,e,d\){.+)', decode_packed_codes),
(r'(ﾟ.+)', aa_decode)):
obf_code = self._search_regex(regex, webpage, 'obfuscated code', default=None)
if obf_code:
webpage = webpage.replace(obf_code, func(obf_code))
obf_code = True
while obf_code:
for regex, func in (
(r'(?s)(?<!-)\b(eval\(function\(p,a,c,k,e,d\)\{(?:(?!</script>).)+\)\))',
decode_packed_codes),
(r'(ﾟ.+)', aa_decode)):
obf_code = self._search_regex(regex, webpage, 'obfuscated code', default=None)
if obf_code:
webpage = webpage.replace(obf_code, func(obf_code))
break
formats = []
jwplayer_data = self._find_jwplayer_data(
webpage.replace(r'\'', '\''), video_id)
result = self._parse_jwplayer_data(
jwplayer_data, video_id, require_title=False,
m3u8_id='hls', mpd_id='dash')
jwplayer_data = self._search_regex(
[
r'jwplayer\("[^"]+"\)\.load\(\[({.+?})\]\);',
r'jwplayer\("[^"]+"\)\.setup\(({.+?})\);',
], webpage,
'jwplayer data', default=None)
if jwplayer_data:
jwplayer_data = self._parse_json(
jwplayer_data.replace(r"\'", "'"), video_id, js_to_json)
if not traverse_obj(result, 'formats'):
if jwplayer_data:
formats = self._parse_jwplayer_data(
jwplayer_data, video_id, False,
m3u8_id='hls', mpd_id='dash')['formats']
if not formats:
urls = []
for regex in (
r'(?:file|src)\s*:\s*(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1',
r'file_link\s*=\s*(["\'])(?P<url>http(?:(?!\1).)+)\1',
r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http(?:(?!\2).)+)\2\)',
r'<embed[^>]+src=(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1'):
self.report_warning(
'Failed to extract JWPlayer formats', video_id=video_id)
urls = set()
for regex in self._SOURCE_URL_REGEXES:
for mobj in re.finditer(regex, webpage):
video_url = mobj.group('url')
if video_url not in urls:
urls.append(video_url)
urls.add(mobj.group('url'))
sources = self._search_regex(
r'sources\s*:\s*(\[(?!{)[^\]]+\])', webpage, 'sources', default=None)
if sources:
urls.extend(self._parse_json(sources, video_id))
urls.update(traverse_obj(sources, (T(lambda s: self._parse_json(s, video_id)), Ellipsis)))
formats = []
for video_url in urls:
for video_url in traverse_obj(urls, (Ellipsis, T(url_or_none))):
if determine_ext(video_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4',
@@ -185,17 +273,19 @@ class XFileShareIE(InfoExtractor):
'url': video_url,
'format_id': 'sd',
})
self._sort_formats(formats)
result = {'formats': formats}
self._sort_formats(result['formats'])
thumbnail = self._search_regex(
[
r'<video[^>]+poster="([^"]+)"',
r'(?:image|poster)\s*:\s*["\'](http[^"\']+)["\'],',
], webpage, 'thumbnail', default=None)
self._THUMBNAIL_REGEXES, webpage, 'thumbnail', default=None)
return {
if not (title or result.get('title')):
title = self._generic_title(url) or video_id
return merge_dicts(result, {
'id': video_id,
'title': title,
'title': title or None,
'thumbnail': thumbnail,
'formats': formats,
}
'http_headers': {'Referer': url}
})

25
youtube_dl/extractor/xhamster.py
View File

@@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
import itertools
@@ -23,7 +24,7 @@ from ..utils import (
class XHamsterIE(InfoExtractor):
_DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com)'
_DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com|xhday\.com|xhvid\.com)'
_VALID_URL = r'''(?x)
https?://
(?:.+?\.)?%s/
@@ -34,7 +35,7 @@ class XHamsterIE(InfoExtractor):
''' % _DOMAINS
_TESTS = [{
'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
'md5': '98b4687efb1ffd331c4197854dc09e8f',
'md5': '34e1ab926db5dc2750fed9e1f34304bb',
'info_dict': {
'id': '1509445',
'display_id': 'femaleagent-shy-beauty-takes-the-bait',
@@ -43,6 +44,7 @@ class XHamsterIE(InfoExtractor):
'timestamp': 1350194821,
'upload_date': '20121014',
'uploader': 'Ruseful2011',
'uploader_id': 'ruseful2011',
'duration': 893,
'age_limit': 18,
},
@@ -72,6 +74,7 @@ class XHamsterIE(InfoExtractor):
'timestamp': 1454948101,
'upload_date': '20160208',
'uploader': 'parejafree',
'uploader_id': 'parejafree',
'duration': 72,
'age_limit': 18,
},
@@ -117,6 +120,12 @@ class XHamsterIE(InfoExtractor):
}, {
'url': 'http://de.xhamster.com/videos/skinny-girl-fucks-herself-hard-in-the-forest-xhnBJZx',
'only_matching': True,
}, {
'url': 'https://xhday.com/videos/strapless-threesome-xhh7yVf',
'only_matching': True,
}, {
'url': 'https://xhvid.com/videos/lk-mm-xhc6wn6',
'only_matching': True,
}]
def _real_extract(self, url):
@@ -245,6 +254,7 @@ class XHamsterIE(InfoExtractor):
else:
categories = None
uploader_url = url_or_none(try_get(video, lambda x: x['author']['pageURL']))
return {
'id': video_id,
'display_id': display_id,
@@ -253,6 +263,8 @@ class XHamsterIE(InfoExtractor):
'timestamp': int_or_none(video.get('created')),
'uploader': try_get(
video, lambda x: x['author']['name'], compat_str),
'uploader_url': uploader_url,
'uploader_id': uploader_url.split('/')[-1] if uploader_url else None,
'thumbnail': video.get('thumbURL'),
'duration': int_or_none(video.get('duration')),
'view_count': int_or_none(video.get('views')),
@@ -261,7 +273,7 @@ class XHamsterIE(InfoExtractor):
'dislike_count': int_or_none(try_get(
video, lambda x: x['rating']['dislikes'], int)),
'comment_count': int_or_none(video.get('views')),
'age_limit': age_limit,
'age_limit': age_limit if age_limit is not None else 18,
'categories': categories,
'formats': formats,
}
@@ -352,6 +364,7 @@ class XHamsterIE(InfoExtractor):
'description': description,
'upload_date': upload_date,
'uploader': uploader,
'uploader_id': uploader.lower() if uploader else None,
'thumbnail': thumbnail,
'duration': duration,
'view_count': view_count,
@@ -420,6 +433,12 @@ class XHamsterUserIE(InfoExtractor):
'id': 'firatkaan',
},
'playlist_mincount': 1,
}, {
'url': 'https://xhday.com/users/mobhunter',
'only_matching': True,
}, {
'url': 'https://xhvid.com/users/pelushe21',
'only_matching': True,
}]
def _entries(self, user_id):

23
youtube_dl/extractor/yandexmusic.py
View File

@@ -106,6 +106,25 @@ class YandexMusicTrackIE(YandexMusicBaseIE):
}, {
'url': 'http://music.yandex.com/album/540508/track/4878838',
'only_matching': True,
}, {
'url': 'https://music.yandex.ru/album/16302456/track/85430762',
'md5': '11b8d50ab03b57738deeaadf661a0a48',
'info_dict': {
'id': '85430762',
'ext': 'mp3',
'abr': 128,
'title': 'Haddadi Von Engst, Phonic Youth, Super Flu - Til The End (Super Flu Remix)',
'filesize': int,
'duration': 431.14,
'track': 'Til The End (Super Flu Remix)',
'album': 'Til The End',
'album_artist': 'Haddadi Von Engst, Phonic Youth',
'artist': 'Haddadi Von Engst, Phonic Youth, Super Flu',
'release_year': 2021,
'genre': 'house',
'disc_number': 1,
'track_number': 2,
}
}]
def _real_extract(self, url):
@@ -116,10 +135,14 @@ class YandexMusicTrackIE(YandexMusicBaseIE):
'track', tld, url, track_id, 'Downloading track JSON',
{'track': '%s:%s' % (track_id, album_id)})['track']
track_title = track['title']
track_version = track.get('version')
if track_version:
track_title = '%s (%s)' % (track_title, track_version)
download_data = self._download_json(
'https://music.yandex.ru/api/v2.1/handlers/track/%s:%s/web-album_track-track-track-main/download/m' % (track_id, album_id),
track_id, 'Downloading track location url JSON',
query={'hq': 1},
headers={'X-Retpath-Y': url})
fd_data = self._download_json(

606
youtube_dl/extractor/youporn.py
View File

@@ -1,19 +1,38 @@
# coding: utf-8
from __future__ import unicode_literals
import itertools
import re
from time import sleep
from .common import InfoExtractor
from ..utils import (
clean_html,
extract_attributes,
ExtractorError,
get_element_by_class,
get_element_by_id,
int_or_none,
str_to_int,
merge_dicts,
parse_count,
parse_qs,
T,
traverse_obj,
unified_strdate,
url_or_none,
urljoin,
)
class YouPornIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?'
_VALID_URL = (
r'youporn:(?P<id>\d+)',
r'''(?x)
https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P<id>\d+)
(?:/(?:(?P<display_id>[^/?#&]+)/?)?)?(?:[#?]|$)
'''
)
_EMBED_REGEX = [r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?youporn\.com/embed/\d+)']
_TESTS = [{
'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
'md5': '3744d24c50438cf5b6f6d59feb5055c2',
@@ -33,7 +52,7 @@ class YouPornIE(InfoExtractor):
'tags': list,
'age_limit': 18,
},
'skip': 'This video has been disabled',
'skip': 'This video has been deactivated',
}, {
# Unknown uploader
'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
@@ -65,57 +84,104 @@ class YouPornIE(InfoExtractor):
}, {
'url': 'https://www.youporn.com/watch/13922959/femdom-principal/',
'only_matching': True,
}, {
'url': 'https://www.youporn.com/watch/16290308/tinderspecial-trailer1/',
'info_dict': {
'id': '16290308',
'age_limit': 18,
'categories': [],
'description': None, # SEO spam using title removed
'display_id': 'tinderspecial-trailer1',
'duration': 298.0,
'ext': 'mp4',
'upload_date': '20201123',
'uploader': 'Ersties',
'tags': [],
'thumbnail': 'https://fi1.ypncdn.com/m=eaSaaTbWx/202011/23/16290308/original/3.jpg',
'timestamp': 1606147564,
'title': 'Tinder In Real Life',
'view_count': int,
}
}]
@staticmethod
def _extract_urls(webpage):
return re.findall(
r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?youporn\.com/embed/\d+)',
webpage)
@classmethod
def _extract_urls(cls, webpage):
def yield_urls():
for p in cls._EMBED_REGEX:
for m in re.finditer(p, webpage):
yield m.group('url')
return list(yield_urls())
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
# A different video ID (data-video-id) is hidden in the page but
# never seems to be used
video_id, display_id = self._match_valid_url(url).group('id', 'display_id')
url = 'http://www.youporn.com/watch/%s' % (video_id,)
webpage = self._download_webpage(
url, video_id, headers={'Cookie': 'age_verified=1'})
definitions = self._download_json(
'https://www.youporn.com/api/video/media_definitions/%s/' % video_id,
display_id)
watchable = self._search_regex(
r'''(<div\s[^>]*\bid\s*=\s*('|")?watch-container(?(2)\2|(?!-)\b)[^>]*>)''',
webpage, 'watchability', default=None)
if not watchable:
msg = re.split(r'\s{4}', clean_html(get_element_by_id(
'mainContent', webpage)) or '')[0]
raise ExtractorError(
('%s says: %s' % (self.IE_NAME, msg))
if msg else 'Video unavailable: no reason found',
expected=True)
# internal ID ?
# video_id = extract_attributes(watchable).get('data-video-id')
playervars = self._search_json(
r'\bplayervars\s*:', webpage, 'playervars', video_id)
def get_fmt(x):
v_url = url_or_none(x.get('videoUrl'))
if v_url:
x['videoUrl'] = v_url
return (x['format'], x)
defs_by_format = dict(traverse_obj(playervars, (
'mediaDefinitions', lambda _, v: v.get('format'), T(get_fmt))))
def get_format_data(f):
if f not in defs_by_format:
return []
return self._download_json(
defs_by_format[f]['videoUrl'], video_id, '{0}-formats'.format(f))
formats = []
for definition in definitions:
if not isinstance(definition, dict):
continue
video_url = url_or_none(definition.get('videoUrl'))
if not video_url:
continue
f = {
'url': video_url,
'filesize': int_or_none(definition.get('videoSize')),
}
height = int_or_none(definition.get('quality'))
# Try to extract only the actual master m3u8 first, avoiding the duplicate single resolution "master" m3u8s
for hls_url in traverse_obj(
get_format_data('hls'),
(lambda _, v: not isinstance(v['defaultQuality'], bool), 'videoUrl'),
(Ellipsis, 'videoUrl')):
formats.extend(self._extract_m3u8_formats(
hls_url, video_id, 'mp4', fatal=False, m3u8_id='hls',
entry_protocol='m3u8_native'))
for f in traverse_obj(get_format_data('mp4'), (
lambda _, v: v.get('videoUrl'), {
'url': ('videoUrl', T(url_or_none)),
'filesize': ('videoSize', T(int_or_none)),
'height': ('quality', T(int_or_none)),
}, T(lambda x: x.get('videoUrl') and x))):
# Video URL's path looks like this:
# /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
# /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
# /videos/201703/11/109285532/1080P_4000K_109285532.mp4
# We will benefit from it by extracting some metadata
mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', f['videoUrl'])
if mobj:
if not height:
height = int(mobj.group('height'))
bitrate = int(mobj.group('bitrate'))
f.update({
'format_id': '%dp-%dk' % (height, bitrate),
'tbr': bitrate,
})
f['height'] = height
if not f.get('height'):
f['height'] = int(mobj.group('height'))
f['tbr'] = int(mobj.group('bitrate'))
f['format_id'] = '%dp-%dk' % (f['height'], f['tbr'])
formats.append(f)
self._sort_formats(formats)
webpage = self._download_webpage(
'http://www.youporn.com/watch/%s' % video_id, display_id,
headers={'Cookie': 'age_verified=1'})
title = self._html_search_regex(
r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>',
webpage, 'title', default=None) or self._og_search_title(
@@ -130,27 +196,30 @@ class YouPornIE(InfoExtractor):
thumbnail = self._search_regex(
r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
webpage, 'thumbnail', fatal=False, group='thumbnail')
duration = int_or_none(self._html_search_meta(
'video:duration', webpage, 'duration', fatal=False))
duration = traverse_obj(playervars, ('duration', T(int_or_none)))
if duration is None:
duration = int_or_none(self._html_search_meta(
'video:duration', webpage, 'duration', fatal=False))
uploader = self._html_search_regex(
r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
webpage, 'uploader', fatal=False)
upload_date = unified_strdate(self._html_search_regex(
[r'UPLOADED:\s*<span>([^<]+)',
(r'UPLOADED:\s*<span>([^<]+)',
r'Date\s+[Aa]dded:\s*<span>([^<]+)',
r'(?s)<div[^>]+class=["\']videoInfo(?:Date|Time)["\'][^>]*>(.+?)</div>'],
r'''(?s)<div[^>]+class=["']videoInfo(?:Date|Time)\b[^>]*>(.+?)</div>''',
r'(?s)<label\b[^>]*>Uploaded[^<]*</label>\s*<span\b[^>]*>(.+?)</span>'),
webpage, 'upload date', fatal=False))
age_limit = self._rta_search(webpage)
view_count = None
views = self._search_regex(
r'(<div[^>]+\bclass=["\']js_videoInfoViews["\']>)', webpage,
'views', default=None)
r'(<div\s[^>]*\bdata-value\s*=[^>]+>)\s*<label>Views:</label>',
webpage, 'views', default=None)
if views:
view_count = str_to_int(extract_attributes(views).get('data-value'))
comment_count = str_to_int(self._search_regex(
view_count = parse_count(extract_attributes(views).get('data-value'))
comment_count = parse_count(self._search_regex(
r'>All [Cc]omments? \(([\d,.]+)\)',
webpage, 'comment count', default=None))
@@ -166,7 +235,10 @@ class YouPornIE(InfoExtractor):
r'(?s)Tags:.*?</div>\s*<div[^>]+class=["\']tagBoxContent["\'][^>]*>(.+?)</div>',
'tags')
return {
data = self._search_json_ld(webpage, video_id, expected_type='VideoObject', fatal=False) or {}
data.pop('url', None)
result = merge_dicts(data, {
'id': video_id,
'display_id': display_id,
'title': title,
@@ -181,4 +253,442 @@ class YouPornIE(InfoExtractor):
'tags': tags,
'age_limit': age_limit,
'formats': formats,
}
})
# Remove promotional non-description
if result.get('description', '').startswith(
'Watch %s online' % (result['title'],)):
del result['description']
return result
class YouPornListBase(InfoExtractor):
# pattern in '.title-text' element of page section containing videos
_PLAYLIST_TITLEBAR_RE = r'\s+[Vv]ideos\s*$'
_PAGE_RETRY_COUNT = 0 # ie, no retry
_PAGE_RETRY_DELAY = 2 # seconds
def _get_next_url(self, url, pl_id, html):
return urljoin(url, self._search_regex(
r'''<a\s[^>]*?\bhref\s*=\s*("|')(?P<url>(?:(?!\1)[^>])+)\1''',
get_element_by_id('next', html) or '', 'next page',
group='url', default=None))
@classmethod
def _get_title_from_slug(cls, title_slug):
return re.sub(r'[_-]', ' ', title_slug)
def _entries(self, url, pl_id, html=None, page_num=None):
# separates page sections
PLAYLIST_SECTION_RE = (
r'''<div\s[^>]*\bclass\s*=\s*('|")(?:[\w$-]+\s+|\s)*?title-bar(?:\s+[\w$-]+|\s)*\1[^>]*>'''
)
# contains video link
VIDEO_URL_RE = r'''(?x)
<div\s[^>]*\bdata-video-id\s*=\s*('|")\d+\1[^>]*>\s*
(?:<div\b[\s\S]+?</div>\s*)*
<a\s[^>]*\bhref\s*=\s*('|")(?P<url>(?:(?!\2)[^>])+)\2
'''
def yield_pages(url, html=html, page_num=page_num):
fatal = not html
for pnum in itertools.count(start=page_num or 1):
if not html:
html = self._download_webpage(
url, pl_id, note='Downloading page %d' % pnum,
fatal=fatal)
if not html:
break
fatal = False
yield (url, html, pnum)
# explicit page: extract just that page
if page_num is not None:
break
next_url = self._get_next_url(url, pl_id, html)
if not next_url or next_url == url:
break
url, html = next_url, None
def retry_page(msg, tries_left, page_data):
if tries_left <= 0:
return
self.report_warning(msg, pl_id)
sleep(self._PAGE_RETRY_DELAY)
return next(
yield_pages(page_data[0], page_num=page_data[2]), None)
def yield_entries(html):
for frag in re.split(PLAYLIST_SECTION_RE, html):
if not frag:
continue
t_text = get_element_by_class('title-text', frag or '')
if not (t_text and re.search(self._PLAYLIST_TITLEBAR_RE, t_text)):
continue
for m in re.finditer(VIDEO_URL_RE, frag):
video_url = urljoin(url, m.group('url'))
if video_url:
yield self.url_result(video_url)
last_first_url = None
for page_data in yield_pages(url, html=html, page_num=page_num):
# page_data: url, html, page_num
first_url = None
tries_left = self._PAGE_RETRY_COUNT + 1
while tries_left > 0:
tries_left -= 1
for from_ in yield_entries(page_data[1]):
# may get the same page twice instead of empty page
# or (site bug) intead of actual next page
if not first_url:
first_url = from_['url']
if first_url == last_first_url:
# sometimes (/porntags/) the site serves the previous page
# instead but may provide the correct page after a delay
page_data = retry_page(
'Retrying duplicate page...', tries_left, page_data)
if page_data:
first_url = None
break
continue
yield from_
else:
if not first_url and 'no-result-paragarph1' in page_data[1]:
page_data = retry_page(
'Retrying empty page...', tries_left, page_data)
if page_data:
continue
else:
# success/failure
break
# may get an infinite (?) sequence of empty pages
if not first_url:
break
last_first_url = first_url
def _real_extract(self, url, html=None):
# exceptionally, id may be None
m_dict = self._match_valid_url(url).groupdict()
pl_id, page_type, sort = (m_dict.get(k) for k in ('id', 'type', 'sort'))
qs = parse_qs(url)
for q, v in qs.items():
if v:
qs[q] = v[-1]
else:
del qs[q]
base_id = pl_id or 'YouPorn'
title = self._get_title_from_slug(base_id)
if page_type:
title = '%s %s' % (page_type.capitalize(), title)
base_id = [base_id.lower()]
if sort is None:
title += ' videos'
else:
title = '%s videos by %s' % (title, re.sub(r'[_-]', ' ', sort))
base_id.append(sort)
if qs:
ps = ['%s=%s' % item for item in sorted(qs.items())]
title += ' (%s)' % ','.join(ps)
base_id.extend(ps)
pl_id = '/'.join(base_id)
return self.playlist_result(
self._entries(url, pl_id, html=html,
page_num=int_or_none(qs.get('page'))),
playlist_id=pl_id, playlist_title=title)
class YouPornCategoryIE(YouPornListBase):
IE_DESC = 'YouPorn category, with sorting, filtering and pagination'
_VALID_URL = r'''(?x)
https?://(?:www\.)?youporn\.com/
(?P<type>category)/(?P<id>[^/?#&]+)
(?:/(?P<sort>popular|views|rating|time|duration))?/?(?:[#?]|$)
'''
_TESTS = [{
'note': 'Full list with pagination',
'url': 'https://www.youporn.com/category/lingerie/popular/',
'info_dict': {
'id': 'lingerie/popular',
'title': 'Category lingerie videos by popular',
},
'playlist_mincount': 39,
}, {
'note': 'Filtered paginated list with single page result',
'url': 'https://www.youporn.com/category/lingerie/duration/?min_minutes=10',
'info_dict': {
'id': 'lingerie/duration/min_minutes=10',
'title': 'Category lingerie videos by duration (min_minutes=10)',
},
'playlist_maxcount': 30,
}, {
'note': 'Single page of full list',
'url': 'https://www.youporn.com/category/lingerie/popular?page=1',
'info_dict': {
'id': 'lingerie/popular/page=1',
'title': 'Category lingerie videos by popular (page=1)',
},
'playlist_count': 30,
}]
class YouPornChannelIE(YouPornListBase):
IE_DESC = 'YouPorn channel, with sorting and pagination'
_VALID_URL = r'''(?x)
https?://(?:www\.)?youporn\.com/
(?P<type>channel)/(?P<id>[^/?#&]+)
(?:/(?P<sort>rating|views|duration))?/?(?:[#?]|$)
'''
_TESTS = [{
'note': 'Full list with pagination',
'url': 'https://www.youporn.com/channel/x-feeds/',
'info_dict': {
'id': 'x-feeds',
'title': 'Channel X-Feeds videos',
},
'playlist_mincount': 37,
}, {
'note': 'Single page of full list (no filters here)',
'url': 'https://www.youporn.com/channel/x-feeds/duration?page=1',
'info_dict': {
'id': 'x-feeds/duration/page=1',
'title': 'Channel X-Feeds videos by duration (page=1)',
},
'playlist_count': 24,
}]
@staticmethod
def _get_title_from_slug(title_slug):
return re.sub(r'_', ' ', title_slug).title()
class YouPornCollectionIE(YouPornListBase):
IE_DESC = 'YouPorn collection (user playlist), with sorting and pagination'
_VALID_URL = r'''(?x)
https?://(?:www\.)?youporn\.com/
(?P<type>collection)s/videos/(?P<id>\d+)
(?:/(?P<sort>rating|views|time|duration))?/?(?:[#?]|$)
'''
_PLAYLIST_TITLEBAR_RE = r'^\s*Videos\s+in\s'
_TESTS = [{
'note': 'Full list with pagination',
'url': 'https://www.youporn.com/collections/videos/33044251/',
'info_dict': {
'id': '33044251',
'title': 'Collection Sexy Lips videos',
'uploader': 'ph-littlewillyb',
},
'playlist_mincount': 50,
}, {
'note': 'Single page of full list (no filters here)',
'url': 'https://www.youporn.com/collections/videos/33044251/time?page=1',
'info_dict': {
'id': '33044251/time/page=1',
'title': 'Collection Sexy Lips videos by time (page=1)',
'uploader': 'ph-littlewillyb',
},
'playlist_count': 20,
}]
def _real_extract(self, url):
pl_id = self._match_id(url)
html = self._download_webpage(url, pl_id)
playlist = super(YouPornCollectionIE, self)._real_extract(url, html=html)
infos = re.sub(r'\s+', ' ', clean_html(get_element_by_class(
'collection-infos', html)) or '')
title, uploader = self._search_regex(
r'^\s*Collection: (?P<title>.+?) \d+ VIDEOS \d+ VIEWS \d+ days LAST UPDATED From: (?P<uploader>[\w_-]+)',
infos, 'title/uploader', group=('title', 'uploader'), default=(None, None))
return merge_dicts({
'title': playlist['title'].replace(playlist['id'].split('/')[0], title),
'uploader': uploader,
}, playlist) if title else playlist
class YouPornTagIE(YouPornListBase):
IE_DESC = 'YouPorn tag (porntags), with sorting, filtering and pagination'
_VALID_URL = r'''(?x)
https?://(?:www\.)?youporn\.com/
porn(?P<type>tag)s/(?P<id>[^/?#&]+)
(?:/(?P<sort>views|rating|time|duration))?/?(?:[#?]|$)
'''
_PLAYLIST_TITLEBAR_RE = r'^\s*Videos\s+tagged\s'
_PAGE_RETRY_COUNT = 1
_TESTS = [{
'note': 'Full list with pagination',
'url': 'https://www.youporn.com/porntags/austrian',
'info_dict': {
'id': 'austrian',
'title': 'Tag austrian videos',
},
'playlist_mincount': 35,
'expected_warnings': ['Retrying duplicate page'],
}, {
'note': 'Filtered paginated list with single page result',
'url': 'https://www.youporn.com/porntags/austrian/duration/?min_minutes=10',
'info_dict': {
'id': 'austrian/duration/min_minutes=10',
'title': 'Tag austrian videos by duration (min_minutes=10)',
},
# number of videos per page is (row x col) 2x3 + 6x4 + 2, or + 3,
# or more, varying with number of ads; let's set max as 9x4
# NB col 1 may not be shown in non-JS page with site CSS and zoom 100%
'playlist_maxcount': 32,
'expected_warnings': ['Retrying duplicate page', 'Retrying empty page'],
}, {
'note': 'Single page of full list',
'url': 'https://www.youporn.com/porntags/austrian/?page=1',
'info_dict': {
'id': 'austrian/page=1',
'title': 'Tag austrian videos (page=1)',
},
'playlist_mincount': 32,
'playlist_maxcount': 34,
'expected_warnings': ['Retrying duplicate page', 'Retrying empty page'],
}]
# YP tag navigation is broken, loses sort
def _get_next_url(self, url, pl_id, html):
next_url = super(YouPornTagIE, self)._get_next_url(url, pl_id, html)
if next_url:
n = self._match_valid_url(next_url)
if n:
s = n.groupdict().get('sort')
if s:
u = self._match_valid_url(url)
if u:
u = u.groupdict().get('sort')
if s and not u:
n = n.end('sort')
next_url = next_url[:n] + '/' + u + next_url[n:]
return next_url
class YouPornStarIE(YouPornListBase):
IE_DESC = 'YouPorn Pornstar, with description, sorting and pagination'
_VALID_URL = r'''(?x)
https?://(?:www\.)?youporn\.com/
(?P<type>pornstar)/(?P<id>[^/?#&]+)
(?:/(?P<sort>rating|views|duration))?/?(?:[#?]|$)
'''
_PLAYLIST_TITLEBAR_RE = r'^\s*Videos\s+[fF]eaturing\s'
_TESTS = [{
'note': 'Full list with pagination',
'url': 'https://www.youporn.com/pornstar/daynia/',
'info_dict': {
'id': 'daynia',
'title': 'Pornstar Daynia videos',
'description': r're:Daynia Rank \d+ Videos \d+ Views [\d,.]+ .+ Subscribers \d+',
},
'playlist_mincount': 45,
}, {
'note': 'Single page of full list (no filters here)',
'url': 'https://www.youporn.com/pornstar/daynia/?page=1',
'info_dict': {
'id': 'daynia/page=1',
'title': 'Pornstar Daynia videos (page=1)',
'description': 're:.{180,}',
},
'playlist_count': 26,
}]
@staticmethod
def _get_title_from_slug(title_slug):
return re.sub(r'_', ' ', title_slug).title()
def _real_extract(self, url):
pl_id = self._match_id(url)
html = self._download_webpage(url, pl_id)
playlist = super(YouPornStarIE, self)._real_extract(url, html=html)
INFO_ELEMENT_RE = r'''(?x)
<div\s[^>]*\bclass\s*=\s*('|")(?:[\w$-]+\s+|\s)*?pornstar-info-wrapper(?:\s+[\w$-]+|\s)*\1[^>]*>
(?P<info>[\s\S]+?)(?:</div>\s*){6,}
'''
infos = self._search_regex(INFO_ELEMENT_RE, html, 'infos', group='info', default='')
if infos:
infos = re.sub(
r'(?:\s*nl=nl)+\s*', ' ',
re.sub(r'(?u)\s+', ' ', clean_html(
re.sub('\n', 'nl=nl', infos)))).replace('ribe Subsc', '')
return merge_dicts({
'description': infos.strip() or None,
}, playlist)
class YouPornVideosIE(YouPornListBase):
IE_DESC = 'YouPorn video (browse) playlists, with sorting, filtering and pagination'
_VALID_URL = r'''(?x)
https?://(?:www\.)?youporn\.com/
(?:(?P<id>browse)/)?
(?P<sort>(?(id)
(?:duration|rating|time|views)|
(?:most_(?:favou?rit|view)ed|recommended|top_rated)?))
(?:[/#?]|$)
'''
_PLAYLIST_TITLEBAR_RE = r'\s+(?:[Vv]ideos|VIDEOS)\s*$'
_TESTS = [{
'note': 'Full list with pagination (too long for test)',
'url': 'https://www.youporn.com/',
'info_dict': {
'id': 'youporn',
'title': 'YouPorn videos',
},
'only_matching': True,
}, {
'note': 'Full list with pagination (too long for test)',
'url': 'https://www.youporn.com/recommended',
'info_dict': {
'id': 'youporn/recommended',
'title': 'YouPorn videos by recommended',
},
'only_matching': True,
}, {
'note': 'Full list with pagination (too long for test)',
'url': 'https://www.youporn.com/top_rated',
'info_dict': {
'id': 'youporn/top_rated',
'title': 'YouPorn videos by top rated',
},
'only_matching': True,
}, {
'note': 'Full list with pagination (too long for test)',
'url': 'https://www.youporn.com/browse/time',
'info_dict': {
'id': 'browse/time',
'title': 'YouPorn videos by time',
},
'only_matching': True,
}, {
'note': 'Filtered paginated list with single page result',
'url': 'https://www.youporn.com/most_favorited/?res=VR&max_minutes=2',
'info_dict': {
'id': 'youporn/most_favorited/max_minutes=2/res=VR',
'title': 'YouPorn videos by most favorited (max_minutes=2,res=VR)',
},
'playlist_mincount': 10,
'playlist_maxcount': 28,
}, {
'note': 'Filtered paginated list with several pages',
'url': 'https://www.youporn.com/most_favorited/?res=VR&max_minutes=5',
'info_dict': {
'id': 'youporn/most_favorited/max_minutes=5/res=VR',
'title': 'YouPorn videos by most favorited (max_minutes=5,res=VR)',
},
'playlist_mincount': 45,
}, {
'note': 'Single page of full list',
'url': 'https://www.youporn.com/browse/time?page=1',
'info_dict': {
'id': 'browse/time/page=1',
'title': 'YouPorn videos by time (page=1)',
},
'playlist_count': 36,
}]
@staticmethod
def _get_title_from_slug(title_slug):
return 'YouPorn' if title_slug == 'browse' else title_slug

1330
youtube_dl/extractor/youtube.py
View File

File diff suppressed because it is too large Load Diff

169
youtube_dl/extractor/zdf.py
View File

@@ -8,13 +8,14 @@ from ..compat import compat_str
from ..utils import (
determine_ext,
ExtractorError,
extract_attributes,
float_or_none,
int_or_none,
merge_dicts,
NO_DEFAULT,
orderedSet,
parse_codecs,
qualities,
str_or_none,
try_get,
unified_timestamp,
update_url_query,
@@ -57,28 +58,39 @@ class ZDFBaseIE(InfoExtractor):
format_urls.add(format_url)
mime_type = meta.get('mimeType')
ext = determine_ext(format_url)
join_nonempty = lambda s, l: s.join(filter(None, l))
meta_map = lambda t: map(lambda x: str_or_none(meta.get(x)), t)
if mime_type == 'application/x-mpegURL' or ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
new_formats = self._extract_m3u8_formats(
format_url, video_id, 'mp4', m3u8_id='hls',
entry_protocol='m3u8_native', fatal=False))
entry_protocol='m3u8_native', fatal=False)
elif mime_type == 'application/f4m+xml' or ext == 'f4m':
formats.extend(self._extract_f4m_formats(
update_url_query(format_url, {'hdcore': '3.7.0'}), video_id, f4m_id='hds', fatal=False))
new_formats = self._extract_f4m_formats(
update_url_query(format_url, {'hdcore': '3.7.0'}), video_id, f4m_id='hds', fatal=False)
else:
f = parse_codecs(meta.get('mimeCodec'))
if not f:
data = meta.get('type', '').split('_')
if try_get(data, lambda x: x[2]) == ext:
f = dict(zip(('vcodec', 'acodec'), data[1]))
format_id = ['http']
for p in (meta.get('type'), meta.get('quality')):
if p and isinstance(p, compat_str):
format_id.append(p)
format_id.extend(join_nonempty('-', meta_map(('type', 'quality'))))
f.update({
'url': format_url,
'format_id': '-'.join(format_id),
'format_note': meta.get('quality'),
'language': meta.get('language'),
'quality': qualities(self._QUALITIES)(meta.get('quality')),
'preference': -10,
'tbr': int_or_none(self._search_regex(r'_(\d+)k_', format_url, 'tbr', default=None))
})
formats.append(f)
new_formats = [f]
formats.extend(merge_dicts(f, {
'format_note': join_nonempty(',', meta_map(('quality', 'class'))),
'language': meta.get('language'),
'language_preference': 10 if meta.get('class') == 'main' else -10 if meta.get('class') == 'ad' else -1,
'quality': qualities(self._QUALITIES)(meta.get('quality')),
}) for f in new_formats)
def _extract_ptmd(self, ptmd_url, video_id, api_token, referrer):
ptmd = self._call_api(
@@ -107,6 +119,7 @@ class ZDFBaseIE(InfoExtractor):
'type': f.get('type'),
'mimeType': f.get('mimeType'),
'quality': quality.get('quality'),
'class': track.get('class'),
'language': track.get('language'),
})
self._sort_formats(formats)
@@ -171,6 +184,20 @@ class ZDFIE(ZDFBaseIE):
'duration': 2615,
'timestamp': 1465021200,
'upload_date': '20160604',
'thumbnail': 'https://www.zdf.de/assets/mauve-im-labor-100~768x432?cb=1464909117806',
},
}, {
'url': 'https://www.zdf.de/funk/druck-11790/funk-alles-ist-verzaubert-102.html',
'md5': '1b93bdec7d02fc0b703c5e7687461628',
'info_dict': {
'ext': 'mp4',
'id': 'video_funk_1770473',
'duration': 1278,
'description': 'Die Neue an der Schule verdreht Ismail den Kopf.',
'title': 'Alles ist verzaubert',
'timestamp': 1635520560,
'upload_date': '20211029',
'thumbnail': 'https://www.zdf.de/assets/teaser-funk-alles-ist-verzaubert-100~1920x1080?cb=1636466431799',
},
}, {
# Same as https://www.phoenix.de/sendungen/dokumentationen/gesten-der-maechtigen-i-a-89468.html?ref=suche
@@ -204,6 +231,19 @@ class ZDFIE(ZDFBaseIE):
'timestamp': 1641355200,
'upload_date': '20220105',
},
'skip': 'No longer available "Diese Seite wurde leider nicht gefunden"'
}, {
'url': 'https://www.zdf.de/serien/soko-stuttgart/das-geld-anderer-leute-100.html',
'info_dict': {
'id': '191205_1800_sendung_sok8',
'ext': 'mp4',
'title': 'Das Geld anderer Leute',
'description': 'md5:cb6f660850dc5eb7d1ab776ea094959d',
'duration': 2581.0,
'timestamp': 1654790700,
'upload_date': '20220609',
'thumbnail': 'https://epg-image.zdf.de/fotobase-webdelivery/images/e2d7e55a-09f0-424e-ac73-6cac4dd65f35?layout=2400x1350',
},
}]
def _extract_entry(self, url, player, content, video_id):
@@ -265,15 +305,16 @@ class ZDFIE(ZDFBaseIE):
'https://zdf-cdn.live.cellular.de/mediathekV2/document/%s' % video_id,
video_id)
document = video['document']
title = document['titel']
content_id = document['basename']
formats = []
format_urls = set()
for f in document['formitaeten']:
self._extract_format(content_id, formats, format_urls, f)
formitaeten = try_get(video, lambda x: x['document']['formitaeten'], list)
document = formitaeten and video['document']
if formitaeten:
title = document['titel']
content_id = document['basename']
format_urls = set()
for f in formitaeten or []:
self._extract_format(content_id, formats, format_urls, f)
self._sort_formats(formats)
thumbnails = []
@@ -320,9 +361,9 @@ class ZDFChannelIE(ZDFBaseIE):
'url': 'https://www.zdf.de/sport/das-aktuelle-sportstudio',
'info_dict': {
'id': 'das-aktuelle-sportstudio',
'title': 'das aktuelle sportstudio | ZDF',
'title': 'das aktuelle sportstudio',
},
'playlist_mincount': 23,
'playlist_mincount': 18,
}, {
'url': 'https://www.zdf.de/dokumentation/planet-e',
'info_dict': {
@@ -330,6 +371,14 @@ class ZDFChannelIE(ZDFBaseIE):
'title': 'planet e.',
},
'playlist_mincount': 50,
}, {
'url': 'https://www.zdf.de/gesellschaft/aktenzeichen-xy-ungeloest',
'info_dict': {
'id': 'aktenzeichen-xy-ungeloest',
'title': 'Aktenzeichen XY... ungelöst',
'entries': "lambda x: not any('xy580-fall1-kindermoerder-gesucht-100' in e['url'] for e in x)",
},
'playlist_mincount': 2,
}, {
'url': 'https://www.zdf.de/filme/taunuskrimi/',
'only_matching': True,
@@ -339,60 +388,36 @@ class ZDFChannelIE(ZDFBaseIE):
def suitable(cls, url):
return False if ZDFIE.suitable(url) else super(ZDFChannelIE, cls).suitable(url)
def _og_search_title(self, webpage, fatal=False):
title = super(ZDFChannelIE, self)._og_search_title(webpage, fatal=fatal)
return re.split(r'\s+[-|]\s+ZDF(?:mediathek)?$', title or '')[0] or None
def _real_extract(self, url):
channel_id = self._match_id(url)
webpage = self._download_webpage(url, channel_id)
entries = [
self.url_result(item_url, ie=ZDFIE.ie_key())
for item_url in orderedSet(re.findall(
r'data-plusbar-url=["\'](http.+?\.html)', webpage))]
matches = re.finditer(
r'''<div\b[^>]*?\sdata-plusbar-id\s*=\s*(["'])(?P<p_id>[\w-]+)\1[^>]*?\sdata-plusbar-url=\1(?P<url>%s)\1''' % ZDFIE._VALID_URL,
webpage)
return self.playlist_result(
entries, channel_id, self._og_search_title(webpage, fatal=False))
if self._downloader.params.get('noplaylist', False):
entry = next(
(self.url_result(m.group('url'), ie=ZDFIE.ie_key()) for m in matches),
None)
self.to_screen('Downloading just the main video because of --no-playlist')
if entry:
return entry
else:
self.to_screen('Downloading playlist %s - add --no-playlist to download just the main video' % (channel_id, ))
r"""
player = self._extract_player(webpage, channel_id)
def check_video(m):
v_ref = self._search_regex(
r'''(<a\b[^>]*?\shref\s*=[^>]+?\sdata-target-id\s*=\s*(["'])%s\2[^>]*>)''' % (m.group('p_id'), ),
webpage, 'check id', default='')
v_ref = extract_attributes(v_ref)
return v_ref.get('data-target-video-type') != 'novideo'
channel_id = self._search_regex(
r'docId\s*:\s*(["\'])(?P<id>(?!\1).+?)\1', webpage,
'channel id', group='id')
channel = self._call_api(
'https://api.zdf.de/content/documents/%s.json' % channel_id,
player, url, channel_id)
items = []
for module in channel['module']:
for teaser in try_get(module, lambda x: x['teaser'], list) or []:
t = try_get(
teaser, lambda x: x['http://zdf.de/rels/target'], dict)
if not t:
continue
items.extend(try_get(
t,
lambda x: x['resultsWithVideo']['http://zdf.de/rels/search/results'],
list) or [])
items.extend(try_get(
module,
lambda x: x['filterRef']['resultsWithVideo']['http://zdf.de/rels/search/results'],
list) or [])
entries = []
entry_urls = set()
for item in items:
t = try_get(item, lambda x: x['http://zdf.de/rels/target'], dict)
if not t:
continue
sharing_url = t.get('http://zdf.de/rels/sharing-url')
if not sharing_url or not isinstance(sharing_url, compat_str):
continue
if sharing_url in entry_urls:
continue
entry_urls.add(sharing_url)
entries.append(self.url_result(
sharing_url, ie=ZDFIE.ie_key(), video_id=t.get('id')))
return self.playlist_result(entries, channel_id, channel.get('title'))
"""
return self.playlist_from_matches(
(m.group('url') for m in matches if check_video(m)),
channel_id, self._og_search_title(webpage, fatal=False))

1146
youtube_dl/jsinterp.py
View File

File diff suppressed because it is too large Load Diff

28
youtube_dl/options.py
View File

@@ -11,6 +11,7 @@ from .compat import (
compat_get_terminal_size,
compat_getenv,
compat_kwargs,
compat_open as open,
compat_shlex_split,
)
from .utils import (
@@ -41,14 +42,11 @@ def _hide_login_info(opts):
def parseOpts(overrideArguments=None):
def _readOptions(filename_bytes, default=[]):
try:
optionf = open(filename_bytes)
optionf = open(filename_bytes, encoding=preferredencoding())
except IOError:
return default # silently skip if file is not present
try:
# FIXME: https://github.com/ytdl-org/youtube-dl/commit/dfe5fa49aed02cf36ba9f743b11b0903554b5e56
contents = optionf.read()
if sys.version_info < (3,):
contents = contents.decode(preferredencoding())
res = compat_shlex_split(contents, comments=True)
finally:
optionf.close()
@@ -270,11 +268,11 @@ def parseOpts(overrideArguments=None):
selection.add_option(
'--match-title',
dest='matchtitle', metavar='REGEX',
help='Download only matching titles (regex or caseless sub-string)')
help='Download only matching titles (case-insensitive regex or alphanumeric sub-string)')
selection.add_option(
'--reject-title',
dest='rejecttitle', metavar='REGEX',
help='Skip download for matching titles (regex or caseless sub-string)')
help='Skip download for matching titles (case-insensitive regex or alphanumeric sub-string)')
selection.add_option(
'--max-downloads',
dest='max_downloads', metavar='NUMBER', type=int, default=None,
@@ -535,6 +533,10 @@ def parseOpts(overrideArguments=None):
'--no-check-certificate',
action='store_true', dest='no_check_certificate', default=False,
help='Suppress HTTPS certificate validation')
workarounds.add_option(
'--no-check-extensions',
action='store_true', dest='no_check_extensions', default=False,
help='Suppress file extension validation')
workarounds.add_option(
'--prefer-insecure',
'--prefer-unsecure', action='store_true', dest='prefer_insecure',
@@ -546,12 +548,14 @@ def parseOpts(overrideArguments=None):
workarounds.add_option(
'--referer',
metavar='URL', dest='referer', default=None,
help='Specify a custom referer, use if the video access is restricted to one domain',
help='Specify a custom Referer: use if the video access is restricted to one domain',
)
workarounds.add_option(
'--add-header',
metavar='FIELD:VALUE', dest='headers', action='append',
help='Specify a custom HTTP header and its value, separated by a colon \':\'. You can use this option multiple times',
help=('Specify a custom HTTP header and its value, separated by a colon \':\'. You can use this option multiple times. '
'NB Use --cookies rather than adding a Cookie header if its contents may be sensitive; '
'data from a Cookie header will be sent to all domains, not just the one intended')
)
workarounds.add_option(
'--bidi-workaround',
@@ -733,9 +737,13 @@ def parseOpts(overrideArguments=None):
'--no-part',
action='store_true', dest='nopart', default=False,
help='Do not use .part files - write directly into output file')
filesystem.add_option(
'--mtime',
action='store_true', dest='updatetime', default=True,
help='Use the Last-modified header to set the file modification time (default)')
filesystem.add_option(
'--no-mtime',
action='store_false', dest='updatetime', default=True,
action='store_false', dest='updatetime',
help='Do not use the Last-modified header to set the file modification time')
filesystem.add_option(
'--write-description',
@@ -801,7 +809,7 @@ def parseOpts(overrideArguments=None):
postproc.add_option(
'--postprocessor-args',
dest='postprocessor_args', metavar='ARGS',
help='Give these arguments to the postprocessor')
help='Give these arguments to the postprocessor (if postprocessing is required)')
postproc.add_option(
'-k', '--keep-video',
action='store_true', dest='keepvideo', default=False,

7
youtube_dl/postprocessor/embedthumbnail.py
View File

@@ -13,10 +13,13 @@ from ..utils import (
encodeFilename,
PostProcessingError,
prepend_extension,
process_communicate_or_kill,
replace_extension,
shell_quote
shell_quote,
)
from ..compat import compat_open as open
class EmbedThumbnailPPError(PostProcessingError):
pass
@@ -109,7 +112,7 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
self._downloader.to_screen('[debug] AtomicParsley command line: %s' % shell_quote(cmd))
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
stdout, stderr = p.communicate()
stdout, stderr = process_communicate_or_kill(p)
if p.returncode != 0:
msg = stderr.decode('utf-8', 'replace').strip()

59
youtube_dl/postprocessor/ffmpeg.py
View File

@@ -1,6 +1,5 @@
from __future__ import unicode_literals
import io
import os
import subprocess
import time
@@ -9,6 +8,7 @@ import re
from .common import AudioConversionError, PostProcessor
from ..compat import compat_open as open
from ..utils import (
encodeArgument,
encodeFilename,
@@ -16,6 +16,7 @@ from ..utils import (
is_outdated_version,
PostProcessingError,
prepend_extension,
process_communicate_or_kill,
shell_quote,
subtitles_filename,
dfxp2srt,
@@ -73,8 +74,11 @@ class FFmpegPostProcessor(PostProcessor):
return FFmpegPostProcessor(downloader)._versions
def _determine_executables(self):
programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe']
# ordered to match prefer_ffmpeg!
convs = ['ffmpeg', 'avconv']
probes = ['ffprobe', 'avprobe']
prefer_ffmpeg = True
programs = convs + probes
def get_ffmpeg_version(path):
ver = get_exe_version(path, args=['-version'])
@@ -95,6 +99,7 @@ class FFmpegPostProcessor(PostProcessor):
self._paths = None
self._versions = None
location = None
if self._downloader:
prefer_ffmpeg = self._downloader.params.get('prefer_ffmpeg', True)
location = self._downloader.params.get('ffmpeg_location')
@@ -117,33 +122,21 @@ class FFmpegPostProcessor(PostProcessor):
location = os.path.dirname(os.path.abspath(location))
if basename in ('ffmpeg', 'ffprobe'):
prefer_ffmpeg = True
self._paths = dict(
(p, p if location is None else os.path.join(location, p))
for p in programs)
self._versions = dict(
x for x in (
(p, get_ffmpeg_version(self._paths[p])) for p in programs)
if x[1] is not None)
self._paths = dict(
(p, os.path.join(location, p)) for p in programs)
self._versions = dict(
(p, get_ffmpeg_version(self._paths[p])) for p in programs)
if self._versions is None:
self._versions = dict(
(p, get_ffmpeg_version(p)) for p in programs)
self._paths = dict((p, p) for p in programs)
if prefer_ffmpeg is False:
prefs = ('avconv', 'ffmpeg')
else:
prefs = ('ffmpeg', 'avconv')
for p in prefs:
if self._versions[p]:
self.basename = p
break
if prefer_ffmpeg is False:
prefs = ('avprobe', 'ffprobe')
else:
prefs = ('ffprobe', 'avprobe')
for p in prefs:
if self._versions[p]:
self.probe_basename = p
break
basenames = [None, None]
for i, progs in enumerate((convs, probes)):
for p in progs[::-1 if prefer_ffmpeg is False else 1]:
if self._versions.get(p):
basenames[i] = p
break
self.basename, self.probe_basename = basenames
@property
def available(self):
@@ -180,7 +173,7 @@ class FFmpegPostProcessor(PostProcessor):
handle = subprocess.Popen(
cmd, stderr=subprocess.PIPE,
stdout=subprocess.PIPE, stdin=subprocess.PIPE)
stdout_data, stderr_data = handle.communicate()
stdout_data, stderr_data = process_communicate_or_kill(handle)
expected_ret = 0 if self.probe_available else 1
if handle.wait() != expected_ret:
return None
@@ -228,7 +221,7 @@ class FFmpegPostProcessor(PostProcessor):
if self._downloader.params.get('verbose', False):
self._downloader.to_screen('[debug] ffmpeg command line: %s' % shell_quote(cmd))
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE)
stdout, stderr = p.communicate()
stdout, stderr = process_communicate_or_kill(p)
if p.returncode != 0:
stderr = stderr.decode('utf-8', 'replace')
msgs = stderr.strip().split('\n')
@@ -492,7 +485,7 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
chapters = info.get('chapters', [])
if chapters:
metadata_filename = replace_extension(filename, 'meta')
with io.open(metadata_filename, 'wt', encoding='utf-8') as f:
with open(metadata_filename, 'w', encoding='utf-8') as f:
def ffmpeg_escape(text):
return re.sub(r'(=|;|#|\\|\n)', r'\\\1', text)
@@ -635,7 +628,7 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor):
with open(dfxp_file, 'rb') as f:
srt_data = dfxp2srt(f.read())
with io.open(srt_file, 'wt', encoding='utf-8') as f:
with open(srt_file, 'w', encoding='utf-8') as f:
f.write(srt_data)
old_file = srt_file
@@ -651,7 +644,7 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor):
self.run_ffmpeg(old_file, new_file, ['-f', new_format])
with io.open(new_file, 'rt', encoding='utf-8') as f:
with open(new_file, 'r', encoding='utf-8') as f:
subs[lang] = {
'ext': new_ext,
'data': f.read(),

2
youtube_dl/postprocessor/metadatafromtitle.py
View File

@@ -40,6 +40,8 @@ class MetadataFromTitlePP(PostProcessor):
% self._titleformat)
return [], info
for attribute, value in match.groupdict().items():
if value is None:
continue
info[attribute] = value
self._downloader.to_screen(
'[fromtitle] parsed %s: %s'

2
youtube_dl/swfinterp.py
View File

@@ -727,7 +727,7 @@ class SWFInterpreter(object):
stack.append(res)
continue
assert isinstance(obj, (dict, _ScopeDict)),\
assert isinstance(obj, (dict, _ScopeDict)), \
'Accessing member %r on %r' % (pname, obj)
res = obj.get(pname, undefined)
stack.append(res)

10
youtube_dl/traversal.py Normal file
View File

@@ -0,0 +1,10 @@
# coding: utf-8
# TODO: move these utils.fns here and move import to utils
# flake8: noqa
from .utils import (
dict_get,
get_first,
T,
traverse_obj,
)

8
youtube_dl/update.py
View File

@@ -1,6 +1,5 @@
from __future__ import unicode_literals
import io
import json
import traceback
import hashlib
@@ -9,7 +8,10 @@ import subprocess
import sys
from zipimport import zipimporter
from .compat import compat_realpath
from .compat import (
compat_open as open,
compat_realpath,
)
from .utils import encode_compat_str
from .version import __version__
@@ -127,7 +129,7 @@ def update_self(to_screen, verbose, opener):
try:
bat = os.path.join(directory, 'youtube-dl-updater.bat')
with io.open(bat, 'w') as batfile:
with open(bat, 'w') as batfile:
batfile.write('''
@echo off
echo Waiting for file handle to be closed ...

1553
youtube_dl/utils.py
View File

File diff suppressed because it is too large Load Diff