mirror of
https://github.com/ytdl-org/youtube-dl
synced 2025-10-25 01:28:36 +09:00
Compare commits
45 Commits
2009.04.25
...
2009.08.08
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
0c8beb43f2 | ||
|
|
71b7300e63 | ||
|
|
8497c36d5a | ||
|
|
110cd3462e | ||
|
|
18963a36b0 | ||
|
|
df1ceb1fd9 | ||
|
|
7eb0e89742 | ||
|
|
8b07dec5f6 | ||
|
|
113e5266cc | ||
|
|
55e7c75e12 | ||
|
|
ff21a710ae | ||
|
|
7374795552 | ||
|
|
0cd61126fc | ||
|
|
e1f18b8a84 | ||
|
|
6a0015a7e0 | ||
|
|
7db85b2c70 | ||
|
|
f76c2df64e | ||
|
|
daa88ccc2e | ||
|
|
eb5d184157 | ||
|
|
5745bfdcdc | ||
|
|
320becd692 | ||
|
|
968aa88438 | ||
|
|
cbfff4db63 | ||
|
|
781daeabdb | ||
|
|
705804f5d1 | ||
|
|
1d50e3d153 | ||
|
|
d69a1c9189 | ||
|
|
488f619471 | ||
|
|
097ba9472b | ||
|
|
554f3e284c | ||
|
|
cab60d710a | ||
|
|
152edc0d4c | ||
|
|
b74c859d0f | ||
|
|
0e54320009 | ||
|
|
43f35682e9 | ||
|
|
ad274509aa | ||
|
|
d09744d055 | ||
|
|
1c76e23e0f | ||
|
|
42bcd27d3b | ||
|
|
2740c509b3 | ||
|
|
7b7759f5a4 | ||
|
|
8d2c83eda5 | ||
|
|
2f11508ada | ||
|
|
b65740e474 | ||
|
|
a825f0ca83 |
1
LATEST_VERSION
Normal file
1
LATEST_VERSION
Normal file
@@ -0,0 +1 @@
|
|||||||
|
2009.08.08
|
||||||
361
youtube-dl
361
youtube-dl
@@ -19,7 +19,7 @@ import urllib
|
|||||||
import urllib2
|
import urllib2
|
||||||
|
|
||||||
std_headers = {
|
std_headers = {
|
||||||
'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.0.8) Gecko/2009032609 Firefox/3.0.8',
|
'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.1.2) Gecko/20090729 Firefox/3.5.2',
|
||||||
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
|
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
|
||||||
'Accept': 'text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5',
|
'Accept': 'text/xml,application/xml,application/xhtml+xml,text/html;q=0.9,text/plain;q=0.8,image/png,*/*;q=0.5',
|
||||||
'Accept-Language': 'en-us,en;q=0.5',
|
'Accept-Language': 'en-us,en;q=0.5',
|
||||||
@@ -52,6 +52,29 @@ class PostProcessingError(Exception):
|
|||||||
"""
|
"""
|
||||||
pass
|
pass
|
||||||
|
|
||||||
|
class UnavailableFormatError(Exception):
|
||||||
|
"""Unavailable Format exception.
|
||||||
|
|
||||||
|
This exception will be thrown when a video is requested
|
||||||
|
in a format that is not available for that video.
|
||||||
|
"""
|
||||||
|
pass
|
||||||
|
|
||||||
|
class ContentTooShortError(Exception):
|
||||||
|
"""Content Too Short exception.
|
||||||
|
|
||||||
|
This exception may be raised by FileDownloader objects when a file they
|
||||||
|
download is too small for what the server announced first, indicating
|
||||||
|
the connection was probably interrupted.
|
||||||
|
"""
|
||||||
|
# Both in bytes
|
||||||
|
downloaded = None
|
||||||
|
expected = None
|
||||||
|
|
||||||
|
def __init__(self, downloaded, expected):
|
||||||
|
self.downloaded = downloaded
|
||||||
|
self.expected = expected
|
||||||
|
|
||||||
class FileDownloader(object):
|
class FileDownloader(object):
|
||||||
"""File Downloader class.
|
"""File Downloader class.
|
||||||
|
|
||||||
@@ -91,6 +114,7 @@ class FileDownloader(object):
|
|||||||
ignoreerrors: Do not stop on download errors.
|
ignoreerrors: Do not stop on download errors.
|
||||||
ratelimit: Download speed limit, in bytes/sec.
|
ratelimit: Download speed limit, in bytes/sec.
|
||||||
nooverwrites: Prevent overwriting files.
|
nooverwrites: Prevent overwriting files.
|
||||||
|
continuedl: Try to continue downloads if possible.
|
||||||
"""
|
"""
|
||||||
|
|
||||||
params = None
|
params = None
|
||||||
@@ -119,10 +143,12 @@ class FileDownloader(object):
|
|||||||
def format_bytes(bytes):
|
def format_bytes(bytes):
|
||||||
if bytes is None:
|
if bytes is None:
|
||||||
return 'N/A'
|
return 'N/A'
|
||||||
if bytes == 0:
|
if type(bytes) is str:
|
||||||
|
bytes = float(bytes)
|
||||||
|
if bytes == 0.0:
|
||||||
exponent = 0
|
exponent = 0
|
||||||
else:
|
else:
|
||||||
exponent = long(math.log(float(bytes), 1024.0))
|
exponent = long(math.log(bytes, 1024.0))
|
||||||
suffix = 'bkMGTPEZY'[exponent]
|
suffix = 'bkMGTPEZY'[exponent]
|
||||||
converted = float(bytes) / float(1024**exponent)
|
converted = float(bytes) / float(1024**exponent)
|
||||||
return '%.2f%s' % (converted, suffix)
|
return '%.2f%s' % (converted, suffix)
|
||||||
@@ -159,13 +185,13 @@ class FileDownloader(object):
|
|||||||
new_min = max(bytes / 2.0, 1.0)
|
new_min = max(bytes / 2.0, 1.0)
|
||||||
new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
|
new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
|
||||||
if elapsed_time < 0.001:
|
if elapsed_time < 0.001:
|
||||||
return int(new_max)
|
return long(new_max)
|
||||||
rate = bytes / elapsed_time
|
rate = bytes / elapsed_time
|
||||||
if rate > new_max:
|
if rate > new_max:
|
||||||
return int(new_max)
|
return long(new_max)
|
||||||
if rate < new_min:
|
if rate < new_min:
|
||||||
return int(new_min)
|
return long(new_min)
|
||||||
return int(rate)
|
return long(rate)
|
||||||
|
|
||||||
@staticmethod
|
@staticmethod
|
||||||
def parse_bytes(bytestr):
|
def parse_bytes(bytestr):
|
||||||
@@ -177,6 +203,14 @@ class FileDownloader(object):
|
|||||||
multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
|
multiplier = 1024.0 ** 'bkmgtpezy'.index(matchobj.group(2).lower())
|
||||||
return long(round(number * multiplier))
|
return long(round(number * multiplier))
|
||||||
|
|
||||||
|
@staticmethod
|
||||||
|
def verify_url(url):
|
||||||
|
"""Verify a URL is valid and data could be downloaded."""
|
||||||
|
request = urllib2.Request(url, None, std_headers)
|
||||||
|
data = urllib2.urlopen(request)
|
||||||
|
data.read(1)
|
||||||
|
data.close()
|
||||||
|
|
||||||
def add_info_extractor(self, ie):
|
def add_info_extractor(self, ie):
|
||||||
"""Add an InfoExtractor object to the end of the list."""
|
"""Add an InfoExtractor object to the end of the list."""
|
||||||
self._ies.append(ie)
|
self._ies.append(ie)
|
||||||
@@ -195,7 +229,7 @@ class FileDownloader(object):
|
|||||||
|
|
||||||
def to_stderr(self, message):
|
def to_stderr(self, message):
|
||||||
"""Print message to stderr."""
|
"""Print message to stderr."""
|
||||||
print >>sys.stderr, message
|
print >>sys.stderr, message.encode(locale.getpreferredencoding())
|
||||||
|
|
||||||
def fixed_template(self):
|
def fixed_template(self):
|
||||||
"""Checks if the output template is fixed."""
|
"""Checks if the output template is fixed."""
|
||||||
@@ -236,57 +270,73 @@ class FileDownloader(object):
|
|||||||
self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
|
self.to_stdout(u'\r[download] %s of %s at %s ETA %s' %
|
||||||
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
|
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
|
||||||
|
|
||||||
|
def report_resuming_byte(self, resume_len):
|
||||||
|
"""Report attemtp to resume at given byte."""
|
||||||
|
self.to_stdout(u'[download] Resuming download at byte %s' % resume_len)
|
||||||
|
|
||||||
|
def report_file_already_downloaded(self, file_name):
|
||||||
|
"""Report file has already been fully downloaded."""
|
||||||
|
self.to_stdout(u'[download] %s has already been downloaded' % file_name)
|
||||||
|
|
||||||
|
def report_unable_to_resume(self):
|
||||||
|
"""Report it was impossible to resume download."""
|
||||||
|
self.to_stdout(u'[download] Unable to resume')
|
||||||
|
|
||||||
def report_finish(self):
|
def report_finish(self):
|
||||||
"""Report download finished."""
|
"""Report download finished."""
|
||||||
self.to_stdout(u'')
|
self.to_stdout(u'')
|
||||||
|
|
||||||
def process_info(self, info_dict):
|
def process_info(self, info_dict):
|
||||||
"""Process a single dictionary returned by an InfoExtractor."""
|
"""Process a single dictionary returned by an InfoExtractor."""
|
||||||
|
# Do nothing else if in simulate mode
|
||||||
|
if self.params.get('simulate', False):
|
||||||
|
try:
|
||||||
|
self.verify_url(info_dict['url'])
|
||||||
|
except (OSError, IOError, urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||||
|
raise UnavailableFormatError
|
||||||
|
|
||||||
# Forced printings
|
# Forced printings
|
||||||
if self.params.get('forcetitle', False):
|
if self.params.get('forcetitle', False):
|
||||||
print info_dict['title'].encode(locale.getpreferredencoding())
|
print info_dict['title'].encode(locale.getpreferredencoding())
|
||||||
if self.params.get('forceurl', False):
|
if self.params.get('forceurl', False):
|
||||||
print info_dict['url'].encode(locale.getpreferredencoding())
|
print info_dict['url'].encode(locale.getpreferredencoding())
|
||||||
|
|
||||||
# Do nothing else if in simulate mode
|
|
||||||
if self.params.get('simulate', False):
|
|
||||||
return
|
return
|
||||||
|
|
||||||
try:
|
try:
|
||||||
filename = self.params['outtmpl'] % info_dict
|
template_dict = dict(info_dict)
|
||||||
self.report_destination(filename)
|
template_dict['epoch'] = unicode(long(time.time()))
|
||||||
|
filename = self.params['outtmpl'] % template_dict
|
||||||
except (ValueError, KeyError), err:
|
except (ValueError, KeyError), err:
|
||||||
self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
|
self.trouble('ERROR: invalid output template or system charset: %s' % str(err))
|
||||||
if self.params['nooverwrites'] and os.path.exists(filename):
|
if self.params['nooverwrites'] and os.path.exists(filename):
|
||||||
self.to_stderr('WARNING: file exists: %s; skipping' % filename)
|
self.to_stderr(u'WARNING: file exists: %s; skipping' % filename)
|
||||||
return
|
return
|
||||||
|
|
||||||
try:
|
try:
|
||||||
self.pmkdir(filename)
|
self.pmkdir(filename)
|
||||||
except (OSError, IOError), err:
|
except (OSError, IOError), err:
|
||||||
self.trouble('ERROR: unable to create directories: %s' % str(err))
|
self.trouble('ERROR: unable to create directories: %s' % str(err))
|
||||||
return
|
return
|
||||||
|
|
||||||
try:
|
try:
|
||||||
outstream = open(filename, 'wb')
|
success = self._do_download(filename, info_dict['url'])
|
||||||
except (OSError, IOError), err:
|
except (OSError, IOError), err:
|
||||||
self.trouble('ERROR: unable to open for writing: %s' % str(err))
|
raise UnavailableFormatError
|
||||||
return
|
|
||||||
try:
|
|
||||||
self._do_download(outstream, info_dict['url'])
|
|
||||||
outstream.close()
|
|
||||||
except (OSError, IOError), err:
|
|
||||||
self.trouble('ERROR: unable to write video data: %s' % str(err))
|
|
||||||
return
|
|
||||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||||
self.trouble('ERROR: unable to download video data: %s' % str(err))
|
self.trouble('ERROR: unable to download video data: %s' % str(err))
|
||||||
return
|
return
|
||||||
|
except (ContentTooShortError, ), err:
|
||||||
|
self.trouble('ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
|
||||||
|
return
|
||||||
|
|
||||||
|
if success:
|
||||||
try:
|
try:
|
||||||
self.post_process(filename, info_dict)
|
self.post_process(filename, info_dict)
|
||||||
except (PostProcessingError), err:
|
except (PostProcessingError), err:
|
||||||
self.trouble('ERROR: postprocessing: %s' % str(err))
|
self.trouble('ERROR: postprocessing: %s' % str(err))
|
||||||
return
|
return
|
||||||
|
|
||||||
return
|
|
||||||
|
|
||||||
def download(self, url_list):
|
def download(self, url_list):
|
||||||
"""Download a given list of URLs."""
|
"""Download a given list of URLs."""
|
||||||
if len(url_list) > 1 and self.fixed_template():
|
if len(url_list) > 1 and self.fixed_template():
|
||||||
@@ -322,21 +372,43 @@ class FileDownloader(object):
|
|||||||
if info is None:
|
if info is None:
|
||||||
break
|
break
|
||||||
|
|
||||||
def _do_download(self, stream, url):
|
def _do_download(self, filename, url):
|
||||||
|
stream = None
|
||||||
|
open_mode = 'ab'
|
||||||
|
|
||||||
|
basic_request = urllib2.Request(url, None, std_headers)
|
||||||
request = urllib2.Request(url, None, std_headers)
|
request = urllib2.Request(url, None, std_headers)
|
||||||
|
|
||||||
|
# Attempt to resume download with "continuedl" option
|
||||||
|
if os.path.isfile(filename):
|
||||||
|
resume_len = os.path.getsize(filename)
|
||||||
|
else:
|
||||||
|
resume_len = 0
|
||||||
|
if self.params['continuedl'] and resume_len != 0:
|
||||||
|
self.report_resuming_byte(resume_len)
|
||||||
|
request.add_header('Range','bytes=%d-' % resume_len)
|
||||||
|
|
||||||
|
# Establish connection
|
||||||
|
try:
|
||||||
data = urllib2.urlopen(request)
|
data = urllib2.urlopen(request)
|
||||||
|
except (urllib2.HTTPError, ), err:
|
||||||
|
if err.code != 416: # 416 is 'Requested range not satisfiable'
|
||||||
|
raise
|
||||||
|
data = urllib2.urlopen(basic_request)
|
||||||
|
content_length = data.info()['Content-Length']
|
||||||
|
if content_length is not None and long(content_length) == resume_len:
|
||||||
|
self.report_file_already_downloaded(filename)
|
||||||
|
return True
|
||||||
|
else:
|
||||||
|
self.report_unable_to_resume()
|
||||||
|
open_mode = 'wb'
|
||||||
|
|
||||||
data_len = data.info().get('Content-length', None)
|
data_len = data.info().get('Content-length', None)
|
||||||
data_len_str = self.format_bytes(data_len)
|
data_len_str = self.format_bytes(data_len)
|
||||||
byte_counter = 0
|
byte_counter = 0
|
||||||
block_size = 1024
|
block_size = 1024
|
||||||
start = time.time()
|
start = time.time()
|
||||||
while True:
|
while True:
|
||||||
# Progress message
|
|
||||||
percent_str = self.calc_percent(byte_counter, data_len)
|
|
||||||
eta_str = self.calc_eta(start, time.time(), data_len, byte_counter)
|
|
||||||
speed_str = self.calc_speed(start, time.time(), byte_counter)
|
|
||||||
self.report_progress(percent_str, data_len_str, speed_str, eta_str)
|
|
||||||
|
|
||||||
# Download and write
|
# Download and write
|
||||||
before = time.time()
|
before = time.time()
|
||||||
data_block = data.read(block_size)
|
data_block = data.read(block_size)
|
||||||
@@ -345,15 +417,31 @@ class FileDownloader(object):
|
|||||||
if data_block_len == 0:
|
if data_block_len == 0:
|
||||||
break
|
break
|
||||||
byte_counter += data_block_len
|
byte_counter += data_block_len
|
||||||
|
|
||||||
|
# Open file just in time
|
||||||
|
if stream is None:
|
||||||
|
try:
|
||||||
|
stream = open(filename, open_mode)
|
||||||
|
self.report_destination(filename)
|
||||||
|
except (OSError, IOError), err:
|
||||||
|
self.trouble('ERROR: unable to open for writing: %s' % str(err))
|
||||||
|
return False
|
||||||
stream.write(data_block)
|
stream.write(data_block)
|
||||||
block_size = self.best_block_size(after - before, data_block_len)
|
block_size = self.best_block_size(after - before, data_block_len)
|
||||||
|
|
||||||
|
# Progress message
|
||||||
|
percent_str = self.calc_percent(byte_counter, data_len)
|
||||||
|
eta_str = self.calc_eta(start, time.time(), data_len, byte_counter)
|
||||||
|
speed_str = self.calc_speed(start, time.time(), byte_counter)
|
||||||
|
self.report_progress(percent_str, data_len_str, speed_str, eta_str)
|
||||||
|
|
||||||
# Apply rate limit
|
# Apply rate limit
|
||||||
self.slow_down(start, byte_counter)
|
self.slow_down(start, byte_counter)
|
||||||
|
|
||||||
self.report_finish()
|
self.report_finish()
|
||||||
if data_len is not None and str(byte_counter) != data_len:
|
if data_len is not None and str(byte_counter) != data_len:
|
||||||
raise ValueError('Content too short: %s/%s bytes' % (byte_counter, data_len))
|
raise ContentTooShortError(byte_counter, long(data_len))
|
||||||
|
return True
|
||||||
|
|
||||||
class InfoExtractor(object):
|
class InfoExtractor(object):
|
||||||
"""Information Extractor class.
|
"""Information Extractor class.
|
||||||
@@ -424,6 +512,13 @@ class YoutubeIE(InfoExtractor):
|
|||||||
_LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en'
|
_LOGIN_URL = 'http://www.youtube.com/signup?next=/&gl=US&hl=en'
|
||||||
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
|
_AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en'
|
||||||
_NETRC_MACHINE = 'youtube'
|
_NETRC_MACHINE = 'youtube'
|
||||||
|
_available_formats = ['22', '35', '18', '5', '17', '13'] # listed in order of priority for -b flag
|
||||||
|
_video_extensions = {
|
||||||
|
'13': '3gp',
|
||||||
|
'17': 'mp4',
|
||||||
|
'18': 'mp4',
|
||||||
|
'22': 'mp4',
|
||||||
|
}
|
||||||
|
|
||||||
@staticmethod
|
@staticmethod
|
||||||
def suitable(url):
|
def suitable(url):
|
||||||
@@ -464,9 +559,9 @@ class YoutubeIE(InfoExtractor):
|
|||||||
"""Report attempt to confirm age."""
|
"""Report attempt to confirm age."""
|
||||||
self._downloader.to_stdout(u'[youtube] Confirming age')
|
self._downloader.to_stdout(u'[youtube] Confirming age')
|
||||||
|
|
||||||
def report_webpage_download(self, video_id):
|
def report_video_info_webpage_download(self, video_id):
|
||||||
"""Report attempt to download webpage."""
|
"""Report attempt to download video info webpage."""
|
||||||
self._downloader.to_stdout(u'[youtube] %s: Downloading video webpage' % video_id)
|
self._downloader.to_stdout(u'[youtube] %s: Downloading video info webpage' % video_id)
|
||||||
|
|
||||||
def report_information_extraction(self, video_id):
|
def report_information_extraction(self, video_id):
|
||||||
"""Report attempt to extract video information."""
|
"""Report attempt to extract video information."""
|
||||||
@@ -476,6 +571,10 @@ class YoutubeIE(InfoExtractor):
|
|||||||
"""Report extracted video URL."""
|
"""Report extracted video URL."""
|
||||||
self._downloader.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url))
|
self._downloader.to_stdout(u'[youtube] %s: URL: %s' % (video_id, video_real_url))
|
||||||
|
|
||||||
|
def report_unavailable_format(self, video_id, format):
|
||||||
|
"""Report extracted video URL."""
|
||||||
|
self._downloader.to_stdout(u'[youtube] %s: Format %s not available' % (video_id, format))
|
||||||
|
|
||||||
def _real_initialize(self):
|
def _real_initialize(self):
|
||||||
if self._downloader is None:
|
if self._downloader is None:
|
||||||
return
|
return
|
||||||
@@ -554,54 +653,65 @@ class YoutubeIE(InfoExtractor):
|
|||||||
video_id = mobj.group(2)
|
video_id = mobj.group(2)
|
||||||
|
|
||||||
# Downloader parameters
|
# Downloader parameters
|
||||||
|
best_quality = False
|
||||||
format_param = None
|
format_param = None
|
||||||
|
quality_index = 0
|
||||||
if self._downloader is not None:
|
if self._downloader is not None:
|
||||||
params = self._downloader.params
|
params = self._downloader.params
|
||||||
format_param = params.get('format', None)
|
format_param = params.get('format', None)
|
||||||
|
if format_param == '0':
|
||||||
|
format_param = self._available_formats[quality_index]
|
||||||
|
best_quality = True
|
||||||
|
|
||||||
|
while True:
|
||||||
# Extension
|
# Extension
|
||||||
video_extension = {
|
video_extension = self._video_extensions.get(format_param, 'flv')
|
||||||
'17': '3gp',
|
|
||||||
'18': 'mp4',
|
|
||||||
'22': 'mp4',
|
|
||||||
}.get(format_param, 'flv')
|
|
||||||
|
|
||||||
# Normalize URL, including format
|
# Get video info
|
||||||
normalized_url = 'http://www.youtube.com/watch?v=%s&gl=US&hl=en' % video_id
|
video_info_url = 'http://www.youtube.com/get_video_info?&video_id=%s&el=detailpage&ps=default&eurl=&gl=US&hl=en' % video_id
|
||||||
if format_param is not None:
|
request = urllib2.Request(video_info_url, None, std_headers)
|
||||||
normalized_url = '%s&fmt=%s' % (normalized_url, format_param)
|
|
||||||
request = urllib2.Request(normalized_url, None, std_headers)
|
|
||||||
try:
|
try:
|
||||||
self.report_webpage_download(video_id)
|
self.report_video_info_webpage_download(video_id)
|
||||||
video_webpage = urllib2.urlopen(request).read()
|
video_info_webpage = urllib2.urlopen(request).read()
|
||||||
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
|
||||||
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % str(err))
|
self._downloader.trouble(u'ERROR: unable to download video info webpage: %s' % str(err))
|
||||||
return
|
return
|
||||||
self.report_information_extraction(video_id)
|
self.report_information_extraction(video_id)
|
||||||
|
|
||||||
# "t" param
|
# "t" param
|
||||||
mobj = re.search(r', "t": "([^"]+)"', video_webpage)
|
mobj = re.search(r'(?m)&token=([^&]+)(?:&|$)', video_info_webpage)
|
||||||
if mobj is None:
|
if mobj is None:
|
||||||
self._downloader.trouble(u'ERROR: unable to extract "t" parameter')
|
# Attempt to see if YouTube has issued an error message
|
||||||
|
mobj = re.search(r'(?m)&reason=([^&]+)(?:&|$)', video_info_webpage)
|
||||||
|
if mobj is None:
|
||||||
|
self._downloader.trouble(u'ERROR: unable to extract "t" parameter for unknown reason')
|
||||||
|
stream = open('reportme-ydl-%s.dat' % time.time(), 'wb')
|
||||||
|
stream.write(video_info_webpage)
|
||||||
|
stream.close()
|
||||||
|
else:
|
||||||
|
reason = urllib.unquote_plus(mobj.group(1))
|
||||||
|
self._downloader.trouble(u'ERROR: YouTube said: %s' % reason.decode('utf-8'))
|
||||||
return
|
return
|
||||||
video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&el=detailpage&ps=' % (video_id, mobj.group(1))
|
token = urllib.unquote(mobj.group(1))
|
||||||
|
video_real_url = 'http://www.youtube.com/get_video?video_id=%s&t=%s&eurl=&el=detailpage&ps=default&gl=US&hl=en' % (video_id, token)
|
||||||
if format_param is not None:
|
if format_param is not None:
|
||||||
video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
|
video_real_url = '%s&fmt=%s' % (video_real_url, format_param)
|
||||||
self.report_video_url(video_id, video_real_url)
|
self.report_video_url(video_id, video_real_url)
|
||||||
|
|
||||||
# uploader
|
# uploader
|
||||||
mobj = re.search(r"var watchUsername = '([^']+)';", video_webpage)
|
mobj = re.search(r'(?m)&author=([^&]+)(?:&|$)', video_info_webpage)
|
||||||
if mobj is None:
|
if mobj is None:
|
||||||
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
|
self._downloader.trouble(u'ERROR: unable to extract uploader nickname')
|
||||||
return
|
return
|
||||||
video_uploader = mobj.group(1)
|
video_uploader = urllib.unquote(mobj.group(1))
|
||||||
|
|
||||||
# title
|
# title
|
||||||
mobj = re.search(r'(?im)<title>YouTube - ([^<]*)</title>', video_webpage)
|
mobj = re.search(r'(?m)&title=([^&]+)(?:&|$)', video_info_webpage)
|
||||||
if mobj is None:
|
if mobj is None:
|
||||||
self._downloader.trouble(u'ERROR: unable to extract video title')
|
self._downloader.trouble(u'ERROR: unable to extract video title')
|
||||||
return
|
return
|
||||||
video_title = mobj.group(1).decode('utf-8')
|
video_title = urllib.unquote(mobj.group(1))
|
||||||
|
video_title = video_title.decode('utf-8')
|
||||||
video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
|
video_title = re.sub(ur'(?u)&(.+?);', self.htmlentity_transform, video_title)
|
||||||
video_title = video_title.replace(os.sep, u'%')
|
video_title = video_title.replace(os.sep, u'%')
|
||||||
|
|
||||||
@@ -609,6 +719,7 @@ class YoutubeIE(InfoExtractor):
|
|||||||
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
|
simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
|
||||||
simple_title = simple_title.strip(ur'_')
|
simple_title = simple_title.strip(ur'_')
|
||||||
|
|
||||||
|
try:
|
||||||
# Process video information
|
# Process video information
|
||||||
self._downloader.process_info({
|
self._downloader.process_info({
|
||||||
'id': video_id.decode('utf-8'),
|
'id': video_id.decode('utf-8'),
|
||||||
@@ -619,6 +730,24 @@ class YoutubeIE(InfoExtractor):
|
|||||||
'ext': video_extension.decode('utf-8'),
|
'ext': video_extension.decode('utf-8'),
|
||||||
})
|
})
|
||||||
|
|
||||||
|
return
|
||||||
|
|
||||||
|
except UnavailableFormatError, err:
|
||||||
|
if best_quality:
|
||||||
|
if quality_index == len(self._available_formats) - 1:
|
||||||
|
# I don't ever expect this to happen
|
||||||
|
self._downloader.trouble(u'ERROR: no known formats available for video')
|
||||||
|
return
|
||||||
|
else:
|
||||||
|
self.report_unavailable_format(video_id, format_param)
|
||||||
|
quality_index += 1
|
||||||
|
format_param = self._available_formats[quality_index]
|
||||||
|
continue
|
||||||
|
else:
|
||||||
|
self._downloader.trouble('ERROR: format not available for video')
|
||||||
|
return
|
||||||
|
|
||||||
|
|
||||||
class MetacafeIE(InfoExtractor):
|
class MetacafeIE(InfoExtractor):
|
||||||
"""Information Extractor for metacafe.com."""
|
"""Information Extractor for metacafe.com."""
|
||||||
|
|
||||||
@@ -703,19 +832,21 @@ class MetacafeIE(InfoExtractor):
|
|||||||
|
|
||||||
# Extract URL, uploader and title from webpage
|
# Extract URL, uploader and title from webpage
|
||||||
self.report_extraction(video_id)
|
self.report_extraction(video_id)
|
||||||
mobj = re.search(r'(?m)&mediaURL=(http.*?\.flv)', webpage)
|
mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
|
||||||
if mobj is None:
|
if mobj is None:
|
||||||
self._downloader.trouble(u'ERROR: unable to extract media URL')
|
self._downloader.trouble(u'ERROR: unable to extract media URL')
|
||||||
return
|
return
|
||||||
mediaURL = urllib.unquote(mobj.group(1))
|
mediaURL = urllib.unquote(mobj.group(1))
|
||||||
|
|
||||||
mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
|
#mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
|
||||||
if mobj is None:
|
#if mobj is None:
|
||||||
self._downloader.trouble(u'ERROR: unable to extract gdaKey')
|
# self._downloader.trouble(u'ERROR: unable to extract gdaKey')
|
||||||
return
|
# return
|
||||||
gdaKey = mobj.group(1)
|
#gdaKey = mobj.group(1)
|
||||||
|
#
|
||||||
|
#video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
|
||||||
|
|
||||||
video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
|
video_url = mediaURL
|
||||||
|
|
||||||
mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
|
mobj = re.search(r'(?im)<title>(.*) - Video</title>', webpage)
|
||||||
if mobj is None:
|
if mobj is None:
|
||||||
@@ -729,6 +860,7 @@ class MetacafeIE(InfoExtractor):
|
|||||||
return
|
return
|
||||||
video_uploader = mobj.group(1)
|
video_uploader = mobj.group(1)
|
||||||
|
|
||||||
|
try:
|
||||||
# Process video information
|
# Process video information
|
||||||
self._downloader.process_info({
|
self._downloader.process_info({
|
||||||
'id': video_id.decode('utf-8'),
|
'id': video_id.decode('utf-8'),
|
||||||
@@ -738,6 +870,8 @@ class MetacafeIE(InfoExtractor):
|
|||||||
'stitle': simple_title,
|
'stitle': simple_title,
|
||||||
'ext': video_extension.decode('utf-8'),
|
'ext': video_extension.decode('utf-8'),
|
||||||
})
|
})
|
||||||
|
except UnavailableFormatError:
|
||||||
|
self._downloader.trouble(u'ERROR: format not available for video')
|
||||||
|
|
||||||
|
|
||||||
class YoutubeSearchIE(InfoExtractor):
|
class YoutubeSearchIE(InfoExtractor):
|
||||||
@@ -780,7 +914,7 @@ class YoutubeSearchIE(InfoExtractor):
|
|||||||
return
|
return
|
||||||
else:
|
else:
|
||||||
try:
|
try:
|
||||||
n = int(prefix)
|
n = long(prefix)
|
||||||
if n <= 0:
|
if n <= 0:
|
||||||
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
|
self._downloader.trouble(u'ERROR: invalid download number %s for query "%s"' % (n, query))
|
||||||
return
|
return
|
||||||
@@ -789,7 +923,7 @@ class YoutubeSearchIE(InfoExtractor):
|
|||||||
n = self._max_youtube_results
|
n = self._max_youtube_results
|
||||||
self._download_n_results(query, n)
|
self._download_n_results(query, n)
|
||||||
return
|
return
|
||||||
except ValueError: # parsing prefix as int fails
|
except ValueError: # parsing prefix as integer fails
|
||||||
self._download_n_results(query, 1)
|
self._download_n_results(query, 1)
|
||||||
return
|
return
|
||||||
|
|
||||||
@@ -835,7 +969,7 @@ class YoutubePlaylistIE(InfoExtractor):
|
|||||||
_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)'
|
_VALID_URL = r'(?:http://)?(?:\w+\.)?youtube.com/view_play_list\?p=(.+)'
|
||||||
_TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
|
_TEMPLATE_URL = 'http://www.youtube.com/view_play_list?p=%s&page=%s&gl=US&hl=en'
|
||||||
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
|
_VIDEO_INDICATOR = r'/watch\?v=(.+?)&'
|
||||||
_MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s'
|
_MORE_PAGES_INDICATOR = r'/view_play_list?p=%s&page=%s'
|
||||||
_youtube_ie = None
|
_youtube_ie = None
|
||||||
|
|
||||||
def __init__(self, youtube_ie, downloader=None):
|
def __init__(self, youtube_ie, downloader=None):
|
||||||
@@ -881,7 +1015,7 @@ class YoutubePlaylistIE(InfoExtractor):
|
|||||||
ids_in_page.append(mobj.group(1))
|
ids_in_page.append(mobj.group(1))
|
||||||
video_ids.extend(ids_in_page)
|
video_ids.extend(ids_in_page)
|
||||||
|
|
||||||
if (self._MORE_PAGES_INDICATOR % (playlist_id, pagenum + 1)) not in page:
|
if (self._MORE_PAGES_INDICATOR % (playlist_id.upper(), pagenum + 1)) not in page:
|
||||||
break
|
break
|
||||||
pagenum = pagenum + 1
|
pagenum = pagenum + 1
|
||||||
|
|
||||||
@@ -919,7 +1053,7 @@ class PostProcessor(object):
|
|||||||
"""Run the PostProcessor.
|
"""Run the PostProcessor.
|
||||||
|
|
||||||
The "information" argument is a dictionary like the ones
|
The "information" argument is a dictionary like the ones
|
||||||
returned by InfoExtractors. The only difference is that this
|
composed by InfoExtractors. The only difference is that this
|
||||||
one has an extra field called "filepath" that points to the
|
one has an extra field called "filepath" that points to the
|
||||||
downloaded file.
|
downloaded file.
|
||||||
|
|
||||||
@@ -950,75 +1084,95 @@ if __name__ == '__main__':
|
|||||||
# Parse command line
|
# Parse command line
|
||||||
parser = optparse.OptionParser(
|
parser = optparse.OptionParser(
|
||||||
usage='Usage: %prog [options] url...',
|
usage='Usage: %prog [options] url...',
|
||||||
version='2009.04.25',
|
version='2009.08.08',
|
||||||
conflict_handler='resolve',
|
conflict_handler='resolve',
|
||||||
)
|
)
|
||||||
|
|
||||||
parser.add_option('-h', '--help',
|
parser.add_option('-h', '--help',
|
||||||
action='help', help='print this help text and exit')
|
action='help', help='print this help text and exit')
|
||||||
parser.add_option('-v', '--version',
|
parser.add_option('-v', '--version',
|
||||||
action='version', help='print program version and exit')
|
action='version', help='print program version and exit')
|
||||||
parser.add_option('-u', '--username',
|
|
||||||
dest='username', metavar='UN', help='account username')
|
|
||||||
parser.add_option('-p', '--password',
|
|
||||||
dest='password', metavar='PW', help='account password')
|
|
||||||
parser.add_option('-o', '--output',
|
|
||||||
dest='outtmpl', metavar='TPL', help='output filename template')
|
|
||||||
parser.add_option('-q', '--quiet',
|
|
||||||
action='store_true', dest='quiet', help='activates quiet mode', default=False)
|
|
||||||
parser.add_option('-s', '--simulate',
|
|
||||||
action='store_true', dest='simulate', help='do not download video', default=False)
|
|
||||||
parser.add_option('-t', '--title',
|
|
||||||
action='store_true', dest='usetitle', help='use title in file name', default=False)
|
|
||||||
parser.add_option('-l', '--literal',
|
|
||||||
action='store_true', dest='useliteral', help='use literal title in file name', default=False)
|
|
||||||
parser.add_option('-n', '--netrc',
|
|
||||||
action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
|
|
||||||
parser.add_option('-g', '--get-url',
|
|
||||||
action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
|
|
||||||
parser.add_option('-e', '--get-title',
|
|
||||||
action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
|
|
||||||
parser.add_option('-f', '--format',
|
|
||||||
dest='format', metavar='FMT', help='video format code')
|
|
||||||
parser.add_option('-m', '--mobile-version',
|
|
||||||
action='store_const', dest='format', help='alias for -f 17', const='17')
|
|
||||||
parser.add_option('-d', '--high-def',
|
|
||||||
action='store_const', dest='format', help='alias for -f 22', const='22')
|
|
||||||
parser.add_option('-i', '--ignore-errors',
|
parser.add_option('-i', '--ignore-errors',
|
||||||
action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
|
action='store_true', dest='ignoreerrors', help='continue on download errors', default=False)
|
||||||
parser.add_option('-r', '--rate-limit',
|
parser.add_option('-r', '--rate-limit',
|
||||||
dest='ratelimit', metavar='L', help='download rate limit (e.g. 50k or 44.6m)')
|
dest='ratelimit', metavar='L', help='download rate limit (e.g. 50k or 44.6m)')
|
||||||
parser.add_option('-a', '--batch-file',
|
|
||||||
|
authentication = optparse.OptionGroup(parser, 'Authentication Options')
|
||||||
|
authentication.add_option('-u', '--username',
|
||||||
|
dest='username', metavar='UN', help='account username')
|
||||||
|
authentication.add_option('-p', '--password',
|
||||||
|
dest='password', metavar='PW', help='account password')
|
||||||
|
authentication.add_option('-n', '--netrc',
|
||||||
|
action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
|
||||||
|
parser.add_option_group(authentication)
|
||||||
|
|
||||||
|
video_format = optparse.OptionGroup(parser, 'Video Format Options')
|
||||||
|
video_format.add_option('-f', '--format',
|
||||||
|
action='store', dest='format', metavar='FMT', help='video format code')
|
||||||
|
video_format.add_option('-b', '--best-quality',
|
||||||
|
action='store_const', dest='format', help='download the best quality video possible', const='0')
|
||||||
|
video_format.add_option('-m', '--mobile-version',
|
||||||
|
action='store_const', dest='format', help='alias for -f 17', const='17')
|
||||||
|
video_format.add_option('-d', '--high-def',
|
||||||
|
action='store_const', dest='format', help='alias for -f 22', const='22')
|
||||||
|
parser.add_option_group(video_format)
|
||||||
|
|
||||||
|
verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options')
|
||||||
|
verbosity.add_option('-q', '--quiet',
|
||||||
|
action='store_true', dest='quiet', help='activates quiet mode', default=False)
|
||||||
|
verbosity.add_option('-s', '--simulate',
|
||||||
|
action='store_true', dest='simulate', help='do not download video', default=False)
|
||||||
|
verbosity.add_option('-g', '--get-url',
|
||||||
|
action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
|
||||||
|
verbosity.add_option('-e', '--get-title',
|
||||||
|
action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
|
||||||
|
parser.add_option_group(verbosity)
|
||||||
|
|
||||||
|
filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
|
||||||
|
filesystem.add_option('-t', '--title',
|
||||||
|
action='store_true', dest='usetitle', help='use title in file name', default=False)
|
||||||
|
filesystem.add_option('-l', '--literal',
|
||||||
|
action='store_true', dest='useliteral', help='use literal title in file name', default=False)
|
||||||
|
filesystem.add_option('-o', '--output',
|
||||||
|
dest='outtmpl', metavar='TPL', help='output filename template')
|
||||||
|
filesystem.add_option('-a', '--batch-file',
|
||||||
dest='batchfile', metavar='F', help='file containing URLs to download')
|
dest='batchfile', metavar='F', help='file containing URLs to download')
|
||||||
parser.add_option('-w', '--no-overwrites',
|
filesystem.add_option('-w', '--no-overwrites',
|
||||||
action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
|
action='store_true', dest='nooverwrites', help='do not overwrite files', default=False)
|
||||||
|
filesystem.add_option('-c', '--continue',
|
||||||
|
action='store_true', dest='continue_dl', help='resume partially downloaded files', default=False)
|
||||||
|
parser.add_option_group(filesystem)
|
||||||
|
|
||||||
(opts, args) = parser.parse_args()
|
(opts, args) = parser.parse_args()
|
||||||
|
|
||||||
# Batch file verification
|
# Batch file verification
|
||||||
batchurls = []
|
batchurls = []
|
||||||
if opts.batchfile is not None:
|
if opts.batchfile is not None:
|
||||||
try:
|
try:
|
||||||
batchurls = [line.strip() for line in open(opts.batchfile, 'r')]
|
batchurls = open(opts.batchfile, 'r').readlines()
|
||||||
|
batchurls = [x.strip() for x in batchurls]
|
||||||
|
batchurls = [x for x in batchurls if len(x) > 0]
|
||||||
except IOError:
|
except IOError:
|
||||||
sys.exit(u'ERROR: batch file could not be read')
|
sys.exit(u'ERROR: batch file could not be read')
|
||||||
all_urls = batchurls + args
|
all_urls = batchurls + args
|
||||||
|
|
||||||
# Conflicting, missing and erroneous options
|
# Conflicting, missing and erroneous options
|
||||||
if len(all_urls) < 1:
|
if len(all_urls) < 1:
|
||||||
sys.exit(u'ERROR: you must provide at least one URL')
|
parser.error(u'you must provide at least one URL')
|
||||||
if opts.usenetrc and (opts.username is not None or opts.password is not None):
|
if opts.usenetrc and (opts.username is not None or opts.password is not None):
|
||||||
sys.exit(u'ERROR: using .netrc conflicts with giving username/password')
|
parser.error(u'using .netrc conflicts with giving username/password')
|
||||||
if opts.password is not None and opts.username is None:
|
if opts.password is not None and opts.username is None:
|
||||||
sys.exit(u'ERROR: account username missing')
|
parser.error(u'account username missing')
|
||||||
if opts.outtmpl is not None and (opts.useliteral or opts.usetitle):
|
if opts.outtmpl is not None and (opts.useliteral or opts.usetitle):
|
||||||
sys.exit(u'ERROR: using output template conflicts with using title or literal title')
|
parser.error(u'using output template conflicts with using title or literal title')
|
||||||
if opts.usetitle and opts.useliteral:
|
if opts.usetitle and opts.useliteral:
|
||||||
sys.exit(u'ERROR: using title conflicts with using literal title')
|
parser.error(u'using title conflicts with using literal title')
|
||||||
if opts.username is not None and opts.password is None:
|
if opts.username is not None and opts.password is None:
|
||||||
opts.password = getpass.getpass(u'Type account password and press return:')
|
opts.password = getpass.getpass(u'Type account password and press return:')
|
||||||
if opts.ratelimit is not None:
|
if opts.ratelimit is not None:
|
||||||
numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
|
numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
|
||||||
if numeric_limit is None:
|
if numeric_limit is None:
|
||||||
sys.exit(u'ERROR: invalid rate limit specified')
|
parser.error(u'invalid rate limit specified')
|
||||||
opts.ratelimit = numeric_limit
|
opts.ratelimit = numeric_limit
|
||||||
|
|
||||||
# Information extractors
|
# Information extractors
|
||||||
@@ -1044,6 +1198,7 @@ if __name__ == '__main__':
|
|||||||
'ignoreerrors': opts.ignoreerrors,
|
'ignoreerrors': opts.ignoreerrors,
|
||||||
'ratelimit': opts.ratelimit,
|
'ratelimit': opts.ratelimit,
|
||||||
'nooverwrites': opts.nooverwrites,
|
'nooverwrites': opts.nooverwrites,
|
||||||
|
'continuedl': opts.continue_dl,
|
||||||
})
|
})
|
||||||
fd.add_info_extractor(youtube_search_ie)
|
fd.add_info_extractor(youtube_search_ie)
|
||||||
fd.add_info_extractor(youtube_pl_ie)
|
fd.add_info_extractor(youtube_pl_ie)
|
||||||
|
|||||||
Reference in New Issue
Block a user