Compare commits

...

71 Commits

Author SHA1 Message Date
Philipp Hagemeister
a230068ff7 release 2015.11.02 2015-11-02 16:18:54 +01:00
Jaime Marquínez Ferrándiz
6a75040278 [utils] unified_strdate: Return None if the date format can't be recognized (fixes #7340)
This issue was introduced with ae12bc3ebb, it returned 'None'.
2015-11-02 14:08:38 +01:00
remitamine
c514b0ec65 [videofy.me] fix info extraction
Closes #7339.
2015-11-02 13:55:21 +01:00
Jaime Marquínez Ferrándiz
eb97f46e8b [mitele] Fix extraction and update test checksum (fixes #7343) 2015-11-02 12:46:10 +01:00
Sergey M․
c90d16cf36 [utils:sanitize_path] Disallow trailing whitespace in path segment (Closes #7332) 2015-11-02 04:26:20 +06:00
Philipp Hagemeister
ab6ca04802 release 2015.11.01 2015-11-01 14:20:10 +01:00
Sergey M․
999079b454 [eitb] Improve hds extraction 2015-11-01 15:49:11 +06:00
Sergey M․
8a06999ba0 [eitb] Improve, make more robust and extract f4m formats (Closes #7328) 2015-11-01 01:52:33 +06:00
remitamine
80dcee5cd5 [eitb] fix info extraction 2015-11-01 00:56:16 +06:00
Sergey M
30eecc6a04 Merge pull request #7296 from jaimeMF/xml_attrib_unicode
Use a wrapper around xml.etree.ElementTree.fromstring in python 2.x (…
2015-10-31 18:15:21 +00:00
Sergey M․
dbd82a1d4f [extractor/common] Fix m3u8 extraction on failure 2015-11-01 00:01:34 +06:00
Sergey M․
76f0c50d3d [mdr] Fix failed formats processing 2015-11-01 00:01:08 +06:00
Sergey M․
dc519b5421 [extractor/common] Make ie_key and IE_NAME return unicode string 2015-10-31 23:12:57 +06:00
Sergey M․
ae12bc3ebb [utils] Make unified_strdate always return unicode string 2015-10-31 23:07:37 +06:00
Sergey M․
e327b736ca [generic] Update test 2015-10-31 23:05:30 +06:00
Sergey M․
82b69a5cbb [mdr] PEP 8 2015-10-31 23:00:36 +06:00
Sergey M․
11465da702 [mdr] Simplify xpath 2015-10-31 22:45:45 +06:00
Sergey M․
578c074575 [utils] Support list of xpath in xpath_element 2015-10-31 22:39:44 +06:00
Sergey M․
8cdb5c8453 [mdr] Add audio test 2015-10-31 22:24:21 +06:00
Sergey M․
2b1b2d83ca [mdr] Modernize and include kika.de 2015-10-31 22:17:09 +06:00
Jaime Marquínez Ferrándiz
c3040bd00a [kika] Cleanup
Closes #6957.
2015-10-31 16:32:35 +01:00
Jaime Marquínez Ferrándiz
8c1aa28c27 [kika] Replace non working tests and recognize 'einzelsendung' urls. 2015-10-31 16:14:36 +01:00
Lucas
892015b088 replaced inefficient code 2015-10-31 15:18:23 +01:00
Lucas
47f2d01a5a Add new extractor 2015-10-31 15:18:23 +01:00
Sergey M․
6722ebd437 [anitube] Relax key regex (Closes #7303)
Another variant seen http://anitubebr.xpg.uol.com.br/embed/
2015-10-30 21:00:36 +06:00
Sergey M․
721f5a277c [moniker] Add tests for #7244 2015-10-29 22:47:18 +06:00
Sergey M․
6fb8ace671 [moniker] Add support for builtin embedded videos (Closes #7244) 2015-10-29 22:44:01 +06:00
Jaime Marquínez Ferrándiz
ae37338e68 [compat] compat_etree_fromstring: clarify comment 2015-10-29 13:58:40 +01:00
Sergey M․
03c2c162f9 [clyp] Improve and cleanup (Closes #7194) 2015-10-28 21:42:01 +06:00
Sergey M․
52c3a6e49d [utils] Improve parse_iso8601 2015-10-28 21:40:22 +06:00
Cian Ruane
4e16c1f80b [clyp] Add extractor
Update __init__.py

[clyp.it] Extract ID idiomatically and make duration and description optional
2015-10-28 20:37:19 +06:00
Jaime Marquínez Ferrándiz
7ccb2b84dd [francetv] fix style issues reported by flake8
* Don't redefine variable in list comprehension
* Line missing indentation
2015-10-28 08:22:04 +01:00
Sergey M․
0a192fbea7 [pluzz] Fix mobile support and modernize (Closes #7305) 2015-10-27 21:43:29 +06:00
Pierre Fenoll
a526167d40 [francetv] Accept mobile URLs 2015-10-27 21:39:29 +06:00
Jaime Marquínez Ferrándiz
f78546272c [compat] compat_etree_fromstring: also decode the text attribute
Deletes parse_xml from utils, because it also does it.
2015-10-26 16:41:24 +01:00
Sergey M․
c137cc0d33 [francetv] Add subtitles test 2015-10-26 20:35:45 +06:00
Sergey M․
6e4b8b2891 [francetv] Make subtitles more robust (Closes #7298) 2015-10-26 20:35:28 +06:00
Frans de Jonge
5dadae079b [francetv] Add subtitles support 2015-10-26 20:20:15 +06:00
Sergey M
cd08d806b1 Merge pull request #7297 from lalinsky/vidme-deleted
[vidme] Check for deleted videos
2015-10-26 13:47:42 +00:00
Lukáš Lalinský
5f9f87c06f [vidme] Check for deleted videos 2015-10-26 14:42:17 +01:00
Jaime Marquínez Ferrándiz
387db16a78 [compat] compat_etree_fromstring: only decode bytes objects 2015-10-25 20:30:54 +01:00
Jaime Marquínez Ferrándiz
36e6f62cd0 Use a wrapper around xml.etree.ElementTree.fromstring in python 2.x (#7178)
Attributes aren't unicode objects, so they couldn't be directly used in info_dict fields (for example '--write-description' doesn't work with bytes).
2015-10-25 20:13:16 +01:00
Sergey M․
755ff8d22c [youporn] Extract comment count 2015-10-25 23:41:10 +06:00
Sergey M․
7b3a19e533 [stitcher] Remove origEpisodeURL
It's always 404
2015-10-25 23:17:23 +06:00
Sergey M․
4f13f8f798 [youporn] Improve uploader extraction 2015-10-25 23:12:12 +06:00
Sergey M․
feb7711cf5 [youporn] Make description optional
Some videos does not contain any description
2015-10-25 23:01:12 +06:00
Sergey M․
589c33dade [youporn] Improve and make more robust (Closes #6888, closes #7214) 2015-10-25 22:56:35 +06:00
Erik
e572a1010b [youporn] Fix extraction
[youporn] Added description and thumbnail

[youporn] Added uploader and date

[youporn] Removed Try and Except lines

[youporn] Fixed date, fatal, formats and /s*

[youporn] Undid removing comment about video url components & Undid and fixed removal of encrypted URL detection

[youporn] Fix: Add encrypted link to links array only if not already in it

[youporn] Fix: Add encrypted link to links array only if not already in it

[youporn] Fix: cleanup
2015-10-25 20:57:08 +06:00
Sergey M․
7e0dc61334 [njoy] Add support for URLs without display id 2015-10-25 20:48:29 +06:00
Sergey M․
8e82ecfe8f [dailymotion] Extract f4m formats 2015-10-24 21:04:09 +06:00
Sergey M․
ec29539e06 [senateisvp] Pass extra param as query segment without ? 2015-10-24 21:03:45 +06:00
Sergey M․
8cd9614abf [downloader/f4m] More accurate fragment URL construction 2015-10-24 21:02:31 +06:00
remitamine
324ac0a243 [downloader/f4m] get the redirected f4m_url and handle url query string properly 2015-10-24 20:05:46 +06:00
remitamine
3711304510 [extractor/common] get the redirected m3u8_url in _extract_m3u8_formats 2015-10-24 19:01:54 +06:00
Jaime Marquínez Ferrándiz
50b936936d [tutv] Fix test 2015-10-24 14:22:47 +02:00
Jaime Marquínez Ferrándiz
d97da29da2 [abc] Support more URL formats 2015-10-24 12:43:02 +02:00
remitamine
7687b354c5 [abc] add support for audio extraction 2015-10-24 12:42:56 +02:00
Jaime Marquínez Ferrándiz
36d7281037 [spiegeltv] Fix style issue
Use two spaces before comment.
2015-10-24 12:42:08 +02:00
Jaime Marquínez Ferrándiz
865d1fbafc [extractor/common] Remove unused import 2015-10-24 12:39:23 +02:00
Sergey M․
ac21e71968 [spiegeltv] Check formats 2015-10-24 16:25:44 +06:00
Sergey M․
943a1e24b8 [extractor/common] Use more generic URLError in _is_valid_url 2015-10-24 16:25:04 +06:00
Sergey M․
50f01302d3 [spiegeltv] Do not extract m3u8 formats since it's already a format 2015-10-24 16:24:08 +06:00
Christoph Döpmann
0198807ef9 [spiegeltv] Fix Accept-Encoding issue (server chokes on gzip) 2015-10-24 16:21:14 +06:00
Jaime Marquínez Ferrándiz
6856139705 [mitele] Fix test checksum 2015-10-24 12:13:26 +02:00
Jaime Marquínez Ferrándiz
c93153852f [mitele] Don't encode the URL query (closes #7280)
This seems to produce sporadic errors when trying to access the URL, because on python 3.x when you do '%s' % b'somedata' you get "b'somedata'".
2015-10-24 12:10:53 +02:00
Philipp Hagemeister
ab9c7214ee release 2015.10.24 2015-10-24 00:10:41 +02:00
Philipp Hagemeister
dae69640d0 Fix py2exe build (#7276) 2015-10-24 00:10:28 +02:00
Sergey M
edeb3e7cb1 [README.md] Fix typo 2015-10-23 15:58:24 +00:00
Jaime Marquínez Ferrándiz
5c43afd40f [youtube:channel] Support age restricted channels (fixes #7277) 2015-10-23 14:23:45 +02:00
Jaime Marquínez Ferrándiz
9170ca5b16 [youtube:channel] Fix test 2015-10-23 14:16:08 +02:00
Jaime Marquínez Ferrándiz
65d49afa48 [test/test_download] Use extract_flat = 'in_playlist' for playlist items
Some playlist extractors return a 'url' result, which wouldn't be resolved.
2015-10-23 14:12:46 +02:00
38 changed files with 721 additions and 280 deletions

View File

@@ -1,6 +1,6 @@
**Please include the full output of youtube-dl when run with `-v`**.
The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
The output (including the first lines) contains important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist):

View File

@@ -795,7 +795,7 @@ Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/i
**Please include the full output of youtube-dl when run with `-v`**.
The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
The output (including the first lines) contains important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist):

View File

@@ -93,6 +93,7 @@
- **Clipsyndicate**
- **Cloudy**
- **Clubic**
- **Clyp**
- **cmt.com**
- **CNET**
- **CNN**
@@ -281,7 +282,7 @@
- **macgamestore**: MacGameStore trailers
- **mailru**: Видео@Mail.Ru
- **Malemotion**
- **MDR**
- **MDR**: MDR.DE and KiKA
- **media.ccc.de**
- **metacafe**
- **Metacritic**

View File

@@ -28,7 +28,7 @@ py2exe_options = {
"compressed": 1,
"optimize": 2,
"dist_dir": '.',
"dll_excludes": ['w9xpopen.exe'],
"dll_excludes": ['w9xpopen.exe', 'crypt32.dll'],
}
py2exe_console = [{

View File

@@ -13,8 +13,10 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.utils import get_filesystem_encoding
from youtube_dl.compat import (
compat_getenv,
compat_etree_fromstring,
compat_expanduser,
compat_shlex_split,
compat_str,
compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus,
)
@@ -71,5 +73,20 @@ class TestCompat(unittest.TestCase):
def test_compat_shlex_split(self):
self.assertEqual(compat_shlex_split('-option "one two"'), ['-option', 'one two'])
def test_compat_etree_fromstring(self):
xml = '''
<root foo="bar" spam="中文">
<normal>foo</normal>
<chinese>中文</chinese>
<foo><bar>spam</bar></foo>
</root>
'''
doc = compat_etree_fromstring(xml.encode('utf-8'))
self.assertTrue(isinstance(doc.attrib['foo'], compat_str))
self.assertTrue(isinstance(doc.attrib['spam'], compat_str))
self.assertTrue(isinstance(doc.find('normal').text, compat_str))
self.assertTrue(isinstance(doc.find('chinese').text, compat_str))
self.assertTrue(isinstance(doc.find('foo/bar').text, compat_str))
if __name__ == '__main__':
unittest.main()

View File

@@ -102,7 +102,7 @@ def generator(test_case):
params = get_params(test_case.get('params', {}))
if is_playlist and 'playlist' not in test_case:
params.setdefault('extract_flat', True)
params.setdefault('extract_flat', 'in_playlist')
params.setdefault('skip_download', True)
ydl = YoutubeDL(params, auto_init=False)

View File

@@ -68,6 +68,9 @@ from youtube_dl.utils import (
cli_valueless_option,
cli_bool_option,
)
from youtube_dl.compat import (
compat_etree_fromstring,
)
class TestUtil(unittest.TestCase):
@@ -233,6 +236,7 @@ class TestUtil(unittest.TestCase):
unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
'20150202')
self.assertEqual(unified_strdate('25-09-2014'), '20140925')
self.assertEqual(unified_strdate('UNKNOWN DATE FORMAT'), None)
def test_find_xpath_attr(self):
testxml = '''<root>
@@ -242,7 +246,7 @@ class TestUtil(unittest.TestCase):
<node x="b" y="d" />
<node x="" />
</root>'''
doc = xml.etree.ElementTree.fromstring(testxml)
doc = compat_etree_fromstring(testxml)
self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n'), None)
self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None)
@@ -263,7 +267,7 @@ class TestUtil(unittest.TestCase):
<url>http://server.com/download.mp3</url>
</media:song>
</root>'''
doc = xml.etree.ElementTree.fromstring(testxml)
doc = compat_etree_fromstring(testxml)
find = lambda p: doc.find(xpath_with_ns(p, {'media': 'http://example.com/'}))
self.assertTrue(find('media:song') is not None)
self.assertEqual(find('media:song/media:author').text, 'The Author')
@@ -275,9 +279,16 @@ class TestUtil(unittest.TestCase):
p = xml.etree.ElementTree.SubElement(div, 'p')
p.text = 'Foo'
self.assertEqual(xpath_element(doc, 'div/p'), p)
self.assertEqual(xpath_element(doc, ['div/p']), p)
self.assertEqual(xpath_element(doc, ['div/bar', 'div/p']), p)
self.assertEqual(xpath_element(doc, 'div/bar', default='default'), 'default')
self.assertEqual(xpath_element(doc, ['div/bar'], default='default'), 'default')
self.assertTrue(xpath_element(doc, 'div/bar') is None)
self.assertTrue(xpath_element(doc, ['div/bar']) is None)
self.assertTrue(xpath_element(doc, ['div/bar'], 'div/baz') is None)
self.assertRaises(ExtractorError, xpath_element, doc, 'div/bar', fatal=True)
self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar'], fatal=True)
self.assertRaises(ExtractorError, xpath_element, doc, ['div/bar', 'div/baz'], fatal=True)
def test_xpath_text(self):
testxml = '''<root>
@@ -285,7 +296,7 @@ class TestUtil(unittest.TestCase):
<p>Foo</p>
</div>
</root>'''
doc = xml.etree.ElementTree.fromstring(testxml)
doc = compat_etree_fromstring(testxml)
self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
self.assertEqual(xpath_text(doc, 'div/bar', default='default'), 'default')
self.assertTrue(xpath_text(doc, 'div/bar') is None)
@@ -297,7 +308,7 @@ class TestUtil(unittest.TestCase):
<p x="a">Foo</p>
</div>
</root>'''
doc = xml.etree.ElementTree.fromstring(testxml)
doc = compat_etree_fromstring(testxml)
self.assertEqual(xpath_attr(doc, 'div/p', 'x'), 'a')
self.assertEqual(xpath_attr(doc, 'div/bar', 'x'), None)
self.assertEqual(xpath_attr(doc, 'div/p', 'y'), None)
@@ -425,6 +436,8 @@ class TestUtil(unittest.TestCase):
self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
self.assertEqual(parse_iso8601('2015-09-29T08:27:31.727'), 1443515251)
self.assertEqual(parse_iso8601('2015-09-29T08-27-31.727'), None)
def test_strip_jsonp(self):
stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')

View File

@@ -14,6 +14,7 @@ import socket
import subprocess
import sys
import itertools
import xml.etree.ElementTree
try:
@@ -212,6 +213,43 @@ try:
except ImportError: # Python 2.6
from xml.parsers.expat import ExpatError as compat_xml_parse_error
if sys.version_info[0] >= 3:
compat_etree_fromstring = xml.etree.ElementTree.fromstring
else:
# python 2.x tries to encode unicode strings with ascii (see the
# XMLParser._fixtext method)
etree = xml.etree.ElementTree
try:
_etree_iter = etree.Element.iter
except AttributeError: # Python <=2.6
def _etree_iter(root):
for el in root.findall('*'):
yield el
for sub in _etree_iter(el):
yield sub
# on 2.6 XML doesn't have a parser argument, function copied from CPython
# 2.7 source
def _XML(text, parser=None):
if not parser:
parser = etree.XMLParser(target=etree.TreeBuilder())
parser.feed(text)
return parser.close()
def _element_factory(*args, **kwargs):
el = etree.Element(*args, **kwargs)
for k, v in el.items():
if isinstance(v, bytes):
el.set(k, v.decode('utf-8'))
return el
def compat_etree_fromstring(text):
doc = _XML(text, parser=etree.XMLParser(target=etree.TreeBuilder(element_factory=_element_factory)))
for el in _etree_iter(doc):
if el.text is not None and isinstance(el.text, bytes):
el.text = el.text.decode('utf-8')
return doc
try:
from urllib.parse import parse_qs as compat_parse_qs
@@ -507,6 +545,7 @@ __all__ = [
'compat_chr',
'compat_cookiejar',
'compat_cookies',
'compat_etree_fromstring',
'compat_expanduser',
'compat_get_terminal_size',
'compat_getenv',

View File

@@ -5,12 +5,13 @@ import io
import itertools
import os
import time
import xml.etree.ElementTree as etree
from .fragment import FragmentFD
from ..compat import (
compat_etree_fromstring,
compat_urlparse,
compat_urllib_error,
compat_urllib_parse_urlparse,
)
from ..utils import (
encodeFilename,
@@ -285,9 +286,11 @@ class F4mFD(FragmentFD):
man_url = info_dict['url']
requested_bitrate = info_dict.get('tbr')
self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME)
manifest = self.ydl.urlopen(man_url).read()
urlh = self.ydl.urlopen(man_url)
man_url = urlh.geturl()
manifest = urlh.read()
doc = etree.fromstring(manifest)
doc = compat_etree_fromstring(manifest)
formats = [(int(f.attrib.get('bitrate', -1)), f)
for f in self._get_unencrypted_media(doc)]
if requested_bitrate is None:
@@ -329,20 +332,25 @@ class F4mFD(FragmentFD):
if not live:
write_metadata_tag(dest_stream, metadata)
base_url_parsed = compat_urllib_parse_urlparse(base_url)
self._start_frag_download(ctx)
frags_filenames = []
while fragments_list:
seg_i, frag_i = fragments_list.pop(0)
name = 'Seg%d-Frag%d' % (seg_i, frag_i)
url = base_url + name
query = []
if base_url_parsed.query:
query.append(base_url_parsed.query)
if akamai_pv:
url += '?' + akamai_pv.strip(';')
query.append(akamai_pv.strip(';'))
if info_dict.get('extra_param_to_segment_url'):
url += info_dict.get('extra_param_to_segment_url')
query.append(info_dict['extra_param_to_segment_url'])
url_parsed = base_url_parsed._replace(path=base_url_parsed.path + name, query='&'.join(query))
frag_filename = '%s-%s' % (ctx['tmpfilename'], name)
try:
success = ctx['dl'].download(frag_filename, {'url': url})
success = ctx['dl'].download(frag_filename, {'url': url_parsed.geturl()})
if not success:
return False
(down, frag_sanitized) = sanitize_open(frag_filename, 'rb')

View File

@@ -90,6 +90,7 @@ from .cliphunter import CliphunterIE
from .clipsyndicate import ClipsyndicateIE
from .cloudy import CloudyIE
from .clubic import ClubicIE
from .clyp import ClypIE
from .cmt import CMTIE
from .cnet import CNETIE
from .cnn import (

View File

@@ -12,7 +12,7 @@ from ..utils import (
class ABCIE(InfoExtractor):
IE_NAME = 'abc.net.au'
_VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P<id>\d+)'
_VALID_URL = r'http://www\.abc\.net\.au/news/(?:[^/]+/){1,2}(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
@@ -36,6 +36,18 @@ class ABCIE(InfoExtractor):
'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill',
},
'add_ie': ['Youtube'],
}, {
'url': 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080',
'md5': 'b96eee7c9edf4fc5a358a0252881cc1f',
'info_dict': {
'id': '6880080',
'ext': 'mp3',
'title': 'NAB lifts interest rates, following Westpac and CBA',
'description': 'md5:f13d8edc81e462fce4a0437c7dc04728',
},
}, {
'url': 'http://www.abc.net.au/news/2015-10-19/6866214',
'only_matching': True,
}]
def _real_extract(self, url):
@@ -43,7 +55,7 @@ class ABCIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
mobj = re.search(
r'inline(?P<type>Video|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
r'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);',
webpage)
if mobj is None:
raise ExtractorError('Unable to extract video urls')
@@ -60,11 +72,13 @@ class ABCIE(InfoExtractor):
formats = [{
'url': url_info['url'],
'vcodec': url_info.get('codec') if mobj.group('type') == 'Video' else 'none',
'width': int_or_none(url_info.get('width')),
'height': int_or_none(url_info.get('height')),
'tbr': int_or_none(url_info.get('bitrate')),
'filesize': int_or_none(url_info.get('filesize')),
} for url_info in urls_info]
self._sort_formats(formats)
return {

View File

@@ -26,8 +26,8 @@ class AnitubeIE(InfoExtractor):
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
key = self._html_search_regex(
r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)', webpage, 'key')
key = self._search_regex(
r'src=["\']https?://[^/]+/embed/([A-Za-z0-9_-]+)', webpage, 'key')
config_xml = self._download_xml(
'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, key)

View File

@@ -14,8 +14,8 @@ from ..utils import (
parse_duration,
unified_strdate,
xpath_text,
parse_xml,
)
from ..compat import compat_etree_fromstring
class ARDMediathekIE(InfoExtractor):
@@ -161,7 +161,7 @@ class ARDMediathekIE(InfoExtractor):
raise ExtractorError('This program is only suitable for those aged 12 and older. Video %s is therefore only available between 20 pm and 6 am.' % video_id, expected=True)
if re.search(r'[\?&]rss($|[=&])', url):
doc = parse_xml(webpage)
doc = compat_etree_fromstring(webpage.encode('utf-8'))
if doc.tag == 'rss':
return GenericIE()._extract_rss(url, video_id, doc)

View File

@@ -2,7 +2,6 @@
from __future__ import unicode_literals
import re
import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
@@ -14,7 +13,10 @@ from ..utils import (
remove_end,
unescapeHTML,
)
from ..compat import compat_HTTPError
from ..compat import (
compat_etree_fromstring,
compat_HTTPError,
)
class BBCCoUkIE(InfoExtractor):
@@ -344,7 +346,7 @@ class BBCCoUkIE(InfoExtractor):
url, programme_id, 'Downloading media selection XML')
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8'))
media_selection = compat_etree_fromstring(ee.cause.read().decode('utf-8'))
else:
raise
return self._process_media_selector(media_selection, programme_id)

View File

@@ -4,9 +4,11 @@ from __future__ import unicode_literals
import re
import itertools
import json
import xml.etree.ElementTree as ET
from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
)
from ..utils import (
int_or_none,
unified_strdate,
@@ -88,7 +90,7 @@ class BiliBiliIE(InfoExtractor):
except ValueError:
pass
lq_doc = ET.fromstring(lq_page)
lq_doc = compat_etree_fromstring(lq_page)
lq_durls = lq_doc.findall('./durl')
hq_doc = self._download_xml(

View File

@@ -3,10 +3,10 @@ from __future__ import unicode_literals
import re
import json
import xml.etree.ElementTree
from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
compat_parse_qs,
compat_str,
compat_urllib_parse,
@@ -119,7 +119,7 @@ class BrightcoveIE(InfoExtractor):
object_str = fix_xml_ampersands(object_str)
try:
object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
object_doc = compat_etree_fromstring(object_str.encode('utf-8'))
except compat_xml_parse_error:
return

View File

@@ -0,0 +1,57 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
float_or_none,
parse_iso8601,
)
class ClypIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?clyp\.it/(?P<id>[a-z0-9]+)'
_TEST = {
'url': 'https://clyp.it/ojz2wfah',
'md5': '1d4961036c41247ecfdcc439c0cddcbb',
'info_dict': {
'id': 'ojz2wfah',
'ext': 'mp3',
'title': 'Krisson80 - bits wip wip',
'description': '#Krisson80BitsWipWip #chiptune\n#wip',
'duration': 263.21,
'timestamp': 1443515251,
'upload_date': '20150929',
},
}
def _real_extract(self, url):
audio_id = self._match_id(url)
metadata = self._download_json(
'https://api.clyp.it/%s' % audio_id, audio_id)
formats = []
for secure in ('', 'Secure'):
for ext in ('Ogg', 'Mp3'):
format_id = '%s%s' % (secure, ext)
format_url = metadata.get('%sUrl' % format_id)
if format_url:
formats.append({
'url': format_url,
'format_id': format_id,
'vcodec': 'none',
})
self._sort_formats(formats)
title = metadata['Title']
description = metadata.get('Description')
duration = float_or_none(metadata.get('Duration'))
timestamp = parse_iso8601(metadata.get('DateCreated'))
return {
'id': audio_id,
'title': title,
'description': description,
'duration': duration,
'timestamp': timestamp,
'formats': formats,
}

View File

@@ -10,13 +10,11 @@ import re
import socket
import sys
import time
import xml.etree.ElementTree
from ..compat import (
compat_cookiejar,
compat_cookies,
compat_getpass,
compat_HTTPError,
compat_http_client,
compat_urllib_error,
compat_urllib_parse,
@@ -24,6 +22,7 @@ from ..compat import (
compat_urllib_request,
compat_urlparse,
compat_str,
compat_etree_fromstring,
)
from ..utils import (
NO_DEFAULT,
@@ -311,11 +310,11 @@ class InfoExtractor(object):
@classmethod
def ie_key(cls):
"""A string for getting the InfoExtractor with get_info_extractor"""
return cls.__name__[:-2]
return compat_str(cls.__name__[:-2])
@property
def IE_NAME(self):
return type(self).__name__[:-2]
return compat_str(type(self).__name__[:-2])
def _request_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
""" Returns the response handle """
@@ -462,7 +461,7 @@ class InfoExtractor(object):
return xml_string
if transform_source:
xml_string = transform_source(xml_string)
return xml.etree.ElementTree.fromstring(xml_string.encode('utf-8'))
return compat_etree_fromstring(xml_string.encode('utf-8'))
def _download_json(self, url_or_request, video_id,
note='Downloading JSON metadata',
@@ -842,7 +841,7 @@ class InfoExtractor(object):
self._request_webpage(url, video_id, 'Checking %s URL' % item)
return True
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError):
if isinstance(e.cause, compat_urllib_error.URLError):
self.to_screen(
'%s: %s URL is invalid, skipping' % (video_id, item))
return False
@@ -944,13 +943,15 @@ class InfoExtractor(object):
if re.match(r'^https?://', u)
else compat_urlparse.urljoin(m3u8_url, u))
m3u8_doc = self._download_webpage(
res = self._download_webpage_handle(
m3u8_url, video_id,
note=note or 'Downloading m3u8 information',
errnote=errnote or 'Failed to download m3u8 information',
fatal=fatal)
if m3u8_doc is False:
return m3u8_doc
if res is False:
return res
m3u8_doc, urlh = res
m3u8_url = urlh.geturl()
last_info = None
last_media = None
kv_rex = re.compile(

View File

@@ -5,12 +5,12 @@ import re
import json
import base64
import zlib
import xml.etree.ElementTree
from hashlib import sha1
from math import pow, sqrt, floor
from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
compat_urllib_parse,
compat_urllib_parse_unquote,
compat_urllib_request,
@@ -234,7 +234,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
return output
def _extract_subtitles(self, subtitle):
sub_root = xml.etree.ElementTree.fromstring(subtitle)
sub_root = compat_etree_fromstring(subtitle)
return [{
'ext': 'srt',
'data': self._convert_subtitles_to_srt(sub_root),

View File

@@ -141,9 +141,17 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
type_ = media.get('type')
if type_ == 'application/vnd.lumberjack.manifest':
continue
if type_ == 'application/x-mpegURL' or determine_ext(media_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
media_url, video_id, 'mp4', m3u8_id='hls'))
ext = determine_ext(media_url)
if type_ == 'application/x-mpegURL' or ext == 'm3u8':
m3u8_formats = self._extract_m3u8_formats(
media_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
if m3u8_formats:
formats.extend(m3u8_formats)
elif type_ == 'application/f4m' or ext == 'f4m':
f4m_formats = self._extract_f4m_formats(
media_url, video_id, preference=-1, f4m_id='hds', fatal=False)
if f4m_formats:
formats.extend(f4m_formats)
else:
f = {
'url': media_url,

View File

@@ -1,39 +1,92 @@
# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .brightcove import BrightcoveIE
from ..utils import ExtractorError
from ..compat import compat_urllib_request
from ..utils import (
float_or_none,
int_or_none,
parse_iso8601,
)
class EitbIE(InfoExtractor):
IE_NAME = 'eitb.tv'
_VALID_URL = r'https?://www\.eitb\.tv/(eu/bideoa|es/video)/[^/]+/(?P<playlist_id>\d+)/(?P<chapter_id>\d+)'
_VALID_URL = r'https?://(?:www\.)?eitb\.tv/(?:eu/bideoa|es/video)/[^/]+/\d+/(?P<id>\d+)'
_TEST = {
'add_ie': ['Brightcove'],
'url': 'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/2677100210001/2743577154001/lasa-y-zabala-30-anos/',
'url': 'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/4104995148001/4090227752001/lasa-y-zabala-30-anos/',
'md5': 'edf4436247185adee3ea18ce64c47998',
'info_dict': {
'id': '2743577154001',
'id': '4090227752001',
'ext': 'mp4',
'title': '60 minutos (Lasa y Zabala, 30 años)',
# All videos from eitb has this description in the brightcove info
'description': '.',
'uploader': 'Euskal Telebista',
'description': 'Programa de reportajes de actualidad.',
'duration': 3996.76,
'timestamp': 1381789200,
'upload_date': '20131014',
'tags': list,
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
chapter_id = mobj.group('chapter_id')
webpage = self._download_webpage(url, chapter_id)
bc_url = BrightcoveIE._extract_brightcove_url(webpage)
if bc_url is None:
raise ExtractorError('Could not extract the Brightcove url')
# The BrightcoveExperience object doesn't contain the video id, we set
# it manually
bc_url += '&%40videoPlayer={0}'.format(chapter_id)
return self.url_result(bc_url, BrightcoveIE.ie_key())
video_id = self._match_id(url)
video = self._download_json(
'http://mam.eitb.eus/mam/REST/ServiceMultiweb/Video/MULTIWEBTV/%s/' % video_id,
video_id, 'Downloading video JSON')
media = video['web_media'][0]
formats = []
for rendition in media['RENDITIONS']:
video_url = rendition.get('PMD_URL')
if not video_url:
continue
tbr = float_or_none(rendition.get('ENCODING_RATE'), 1000)
format_id = 'http'
if tbr:
format_id += '-%d' % int(tbr)
formats.append({
'url': rendition['PMD_URL'],
'format_id': format_id,
'width': int_or_none(rendition.get('FRAME_WIDTH')),
'height': int_or_none(rendition.get('FRAME_HEIGHT')),
'tbr': tbr,
})
hls_url = media.get('HLS_SURL')
if hls_url:
request = compat_urllib_request.Request(
'http://mam.eitb.eus/mam/REST/ServiceMultiweb/DomainRestrictedSecurity/TokenAuth/',
headers={'Referer': url})
token_data = self._download_json(
request, video_id, 'Downloading auth token', fatal=False)
if token_data:
token = token_data.get('token')
if token:
m3u8_formats = self._extract_m3u8_formats(
'%s?hdnts=%s' % (hls_url, token), video_id, m3u8_id='hls', fatal=False)
if m3u8_formats:
formats.extend(m3u8_formats)
hds_url = media.get('HDS_SURL')
if hds_url:
f4m_formats = self._extract_f4m_formats(
'%s?hdcore=3.7.0' % hds_url.replace('euskalsvod', 'euskalvod'),
video_id, f4m_id='hds', fatal=False)
if f4m_formats:
formats.extend(f4m_formats)
self._sort_formats(formats)
return {
'id': video_id,
'title': media.get('NAME_ES') or media.get('name') or media['NAME_EU'],
'description': media.get('SHORT_DESC_ES') or video.get('desc_group') or media.get('SHORT_DESC_EU'),
'thumbnail': media.get('STILL_URL') or media.get('THUMBNAIL_URL'),
'duration': float_or_none(media.get('LENGTH'), 1000),
'timestamp': parse_iso8601(media.get('BROADCST_DATE'), ' '),
'tags': media.get('TAGS'),
'formats': formats,
}

View File

@@ -83,6 +83,14 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
if subtitle:
title += ' - %s' % subtitle
subtitles = {}
subtitles_list = [{
'url': subformat['url'],
'ext': subformat.get('format'),
} for subformat in info.get('subtitles', []) if subformat.get('url')]
if subtitles_list:
subtitles['fr'] = subtitles_list
return {
'id': video_id,
'title': title,
@@ -91,20 +99,27 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']),
'timestamp': int_or_none(info['diffusion']['timestamp']),
'formats': formats,
'subtitles': subtitles,
}
class PluzzIE(FranceTVBaseInfoExtractor):
IE_NAME = 'pluzz.francetv.fr'
_VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'
_VALID_URL = r'https?://(?:m\.)?pluzz\.francetv\.fr/videos/(?P<id>.+?)\.html'
# Can't use tests, videos expire in 7 days
def _real_extract(self, url):
title = re.match(self._VALID_URL, url).group(1)
webpage = self._download_webpage(url, title)
video_id = self._search_regex(
r'data-diffusion="(\d+)"', webpage, 'ID')
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_meta(
'id_video', webpage, 'video id', default=None)
if not video_id:
video_id = self._search_regex(
r'data-diffusion=["\'](\d+)', webpage, 'video id')
return self._extract_video(video_id, 'Pluzz')
@@ -120,6 +135,9 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
'title': 'Soir 3',
'upload_date': '20130826',
'timestamp': 1377548400,
'subtitles': {
'fr': 'mincount:2',
},
},
}, {
'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',

View File

@@ -9,6 +9,7 @@ import sys
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..compat import (
compat_etree_fromstring,
compat_urllib_parse_unquote,
compat_urllib_request,
compat_urlparse,
@@ -21,7 +22,6 @@ from ..utils import (
HEADRequest,
is_html,
orderedSet,
parse_xml,
smuggle_url,
unescapeHTML,
unified_strdate,
@@ -141,6 +141,7 @@ class GenericIE(InfoExtractor):
'ext': 'mp4',
'title': 'Automatics, robotics and biocybernetics',
'description': 'md5:815fc1deb6b3a2bff99de2d5325be482',
'upload_date': '20130627',
'formats': 'mincount:16',
'subtitles': 'mincount:1',
},
@@ -1237,7 +1238,7 @@ class GenericIE(InfoExtractor):
# Is it an RSS feed, a SMIL file or a XSPF playlist?
try:
doc = parse_xml(webpage)
doc = compat_etree_fromstring(webpage.encode('utf-8'))
if doc.tag == 'rss':
return self._extract_rss(url, video_id, doc)
elif re.match(r'^(?:{[^}]+})?smil$', doc.tag):

View File

@@ -1,64 +1,169 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
determine_ext,
int_or_none,
parse_duration,
parse_iso8601,
xpath_text,
)
class MDRIE(InfoExtractor):
_VALID_URL = r'^(?P<domain>https?://(?:www\.)?mdr\.de)/(?:.*)/(?P<type>video|audio)(?P<video_id>[^/_]+)(?:_|\.html)'
IE_DESC = 'MDR.DE and KiKA'
_VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z]+(?P<id>\d+)(?:_.+?)?\.html'
# No tests, MDR regularily deletes its videos
_TEST = {
_TESTS = [{
# MDR regularily deletes its videos
'url': 'http://www.mdr.de/fakt/video189002.html',
'only_matching': True,
}
}, {
# audio
'url': 'http://www.mdr.de/kultur/audio1312272_zc-15948bad_zs-86171fdd.html',
'md5': '64c4ee50f0a791deb9479cd7bbe9d2fa',
'info_dict': {
'id': '1312272',
'ext': 'mp3',
'title': 'Feuilleton vom 30. Oktober 2015',
'duration': 250,
'uploader': 'MITTELDEUTSCHER RUNDFUNK',
},
}, {
'url': 'http://www.kika.de/baumhaus/videos/video19636.html',
'md5': '4930515e36b06c111213e80d1e4aad0e',
'info_dict': {
'id': '19636',
'ext': 'mp4',
'title': 'Baumhaus vom 30. Oktober 2015',
'duration': 134,
'uploader': 'KIKA',
},
}, {
'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/videos/video8182.html',
'md5': '5fe9c4dd7d71e3b238f04b8fdd588357',
'info_dict': {
'id': '8182',
'ext': 'mp4',
'title': 'Beutolomäus und der geheime Weihnachtswunsch',
'description': 'md5:b69d32d7b2c55cbe86945ab309d39bbd',
'timestamp': 1419047100,
'upload_date': '20141220',
'duration': 4628,
'uploader': 'KIKA',
},
}, {
'url': 'http://www.kika.de/baumhaus/sendungen/video19636_zc-fea7f8a0_zs-4bf89c60.html',
'only_matching': True,
}, {
'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/einzelsendung2534.html',
'only_matching': True,
}]
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('video_id')
domain = m.group('domain')
video_id = self._match_id(url)
# determine title and media streams from webpage
html = self._download_webpage(url, video_id)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h[12]>(.*?)</h[12]>', html, 'title')
xmlurl = self._search_regex(
r'dataURL:\'(/(?:.+)/(?:video|audio)[0-9]+-avCustom.xml)', html, 'XML URL')
data_url = self._search_regex(
r'dataURL\s*:\s*(["\'])(?P<url>/.+/(?:video|audio)[0-9]+-avCustom\.xml)\1',
webpage, 'data url', group='url')
doc = self._download_xml(
compat_urlparse.urljoin(url, data_url), video_id)
title = xpath_text(doc, ['./title', './broadcast/broadcastName'], 'title', fatal=True)
doc = self._download_xml(domain + xmlurl, video_id)
formats = []
for a in doc.findall('./assets/asset'):
url_el = a.find('./progressiveDownloadUrl')
if url_el is None:
continue
abr = int(a.find('bitrateAudio').text) // 1000
media_type = a.find('mediaType').text
format = {
'abr': abr,
'filesize': int(a.find('fileSize').text),
'url': url_el.text,
}
processed_urls = []
for asset in doc.findall('./assets/asset'):
for source in (
'progressiveDownload',
'dynamicHttpStreamingRedirector',
'adaptiveHttpStreamingRedirector'):
url_el = asset.find('./%sUrl' % source)
if url_el is None:
continue
video_url = url_el.text
if video_url in processed_urls:
continue
processed_urls.append(video_url)
vbr = int_or_none(xpath_text(asset, './bitrateVideo', 'vbr'), 1000)
abr = int_or_none(xpath_text(asset, './bitrateAudio', 'abr'), 1000)
ext = determine_ext(url_el.text)
if ext == 'm3u8':
url_formats = self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
preference=0, m3u8_id='HLS', fatal=False)
elif ext == 'f4m':
url_formats = self._extract_f4m_formats(
video_url + '?hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id,
preference=0, f4m_id='HDS', fatal=False)
else:
media_type = xpath_text(asset, './mediaType', 'media type', default='MP4')
vbr = int_or_none(xpath_text(asset, './bitrateVideo', 'vbr'), 1000)
abr = int_or_none(xpath_text(asset, './bitrateAudio', 'abr'), 1000)
filesize = int_or_none(xpath_text(asset, './fileSize', 'file size'))
f = {
'url': video_url,
'format_id': '%s-%d' % (media_type, vbr or abr),
'filesize': filesize,
'abr': abr,
'preference': 1,
}
if vbr:
width = int_or_none(xpath_text(asset, './frameWidth', 'width'))
height = int_or_none(xpath_text(asset, './frameHeight', 'height'))
f.update({
'vbr': vbr,
'width': width,
'height': height,
})
url_formats = [f]
if not url_formats:
continue
if not vbr:
for f in url_formats:
abr = f.get('tbr') or abr
if 'tbr' in f:
del f['tbr']
f.update({
'abr': abr,
'vcodec': 'none',
})
formats.extend(url_formats)
vbr_el = a.find('bitrateVideo')
if vbr_el is None:
format.update({
'vcodec': 'none',
'format_id': '%s-%d' % (media_type, abr),
})
else:
vbr = int(vbr_el.text) // 1000
format.update({
'vbr': vbr,
'width': int(a.find('frameWidth').text),
'height': int(a.find('frameHeight').text),
'format_id': '%s-%d' % (media_type, vbr),
})
formats.append(format)
self._sort_formats(formats)
description = xpath_text(doc, './broadcast/broadcastDescription', 'description')
timestamp = parse_iso8601(
xpath_text(
doc, [
'./broadcast/broadcastDate',
'./broadcast/broadcastStartDate',
'./broadcast/broadcastEndDate'],
'timestamp', default=None))
duration = parse_duration(xpath_text(doc, './duration', 'duration'))
uploader = xpath_text(doc, './rights', 'uploader')
return {
'id': video_id,
'title': title,
'description': description,
'timestamp': timestamp,
'duration': duration,
'uploader': uploader,
'formats': formats,
}

View File

@@ -1,7 +1,10 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urllib_parse
from ..compat import (
compat_urllib_parse,
compat_urlparse,
)
from ..utils import (
encode_dict,
get_element_by_attribute,
@@ -15,7 +18,7 @@ class MiTeleIE(InfoExtractor):
_TESTS = [{
'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/',
'md5': 'ace7635b2a0b286aaa37d3ff192d2a8a',
'md5': '0ff1a13aebb35d9bc14081ff633dd324',
'info_dict': {
'id': '0NF1jJnxS1Wu3pHrmvFyw2',
'display_id': 'programa-144',
@@ -34,6 +37,7 @@ class MiTeleIE(InfoExtractor):
config_url = self._search_regex(
r'data-config\s*=\s*"([^"]+)"', webpage, 'data config url')
config_url = compat_urlparse.urljoin(url, config_url)
config = self._download_json(
config_url, display_id, 'Downloading config JSON')
@@ -56,7 +60,7 @@ class MiTeleIE(InfoExtractor):
'sta': '0',
}
media = self._download_json(
'%s/?%s' % (gat, compat_urllib_parse.urlencode(encode_dict(token_data)).encode('utf-8')),
'%s/?%s' % (gat, compat_urllib_parse.urlencode(encode_dict(token_data))),
display_id, 'Downloading %s JSON' % location['loc'])
file_ = media.get('file')
if not file_:

View File

@@ -17,7 +17,7 @@ from ..utils import (
class MonikerIE(InfoExtractor):
IE_DESC = 'allmyvideos.net and vidspot.net'
_VALID_URL = r'https?://(?:www\.)?(?:allmyvideos|vidspot)\.net/(?P<id>[a-zA-Z0-9_-]+)'
_VALID_URL = r'https?://(?:www\.)?(?:allmyvideos|vidspot)\.net/(?:(?:2|v)/v-)?(?P<id>[a-zA-Z0-9_-]+)'
_TESTS = [{
'url': 'http://allmyvideos.net/jih3nce3x6wn',
@@ -46,6 +46,18 @@ class MonikerIE(InfoExtractor):
}, {
'url': 'https://www.vidspot.net/l2ngsmhs8ci5',
'only_matching': True,
}, {
'url': 'http://vidspot.net/2/v-ywDf99',
'md5': '5f8254ce12df30479428b0152fb8e7ba',
'info_dict': {
'id': 'ywDf99',
'ext': 'mp4',
'title': 'IL FAIT LE MALIN EN PORSHE CAYENNE ( mais pas pour longtemps)',
'description': 'IL FAIT LE MALIN EN PORSHE CAYENNE.',
},
}, {
'url': 'http://allmyvideos.net/v/v-HXZm5t',
'only_matching': True,
}]
def _real_extract(self, url):
@@ -64,18 +76,30 @@ class MonikerIE(InfoExtractor):
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, error), expected=True)
fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage)
data = dict(fields)
builtin_url = self._search_regex(
r'<iframe[^>]+src=(["\'])(?P<url>.+?/builtin-.+?)\1',
orig_webpage, 'builtin URL', default=None, group='url')
post = compat_urllib_parse.urlencode(data)
headers = {
b'Content-Type': b'application/x-www-form-urlencoded',
}
req = compat_urllib_request.Request(url, post, headers)
webpage = self._download_webpage(
req, video_id, note='Downloading video page ...')
if builtin_url:
req = compat_urllib_request.Request(builtin_url)
req.add_header('Referer', url)
webpage = self._download_webpage(req, video_id, 'Downloading builtin page')
title = self._og_search_title(orig_webpage).strip()
description = self._og_search_description(orig_webpage).strip()
else:
fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage)
data = dict(fields)
title = os.path.splitext(data['fname'])[0]
post = compat_urllib_parse.urlencode(data)
headers = {
b'Content-Type': b'application/x-www-form-urlencoded',
}
req = compat_urllib_request.Request(url, post, headers)
webpage = self._download_webpage(
req, video_id, note='Downloading video page ...')
title = os.path.splitext(data['fname'])[0]
description = None
# Could be several links with different quality
links = re.findall(r'"file" : "?(.+?)",', webpage)
@@ -89,5 +113,6 @@ class MonikerIE(InfoExtractor):
return {
'id': video_id,
'title': title,
'description': description,
'formats': formats,
}

View File

@@ -14,7 +14,8 @@ from ..utils import (
class NDRBaseIE(InfoExtractor):
def _real_extract(self, url):
display_id = self._match_id(url)
mobj = re.match(self._VALID_URL, url)
display_id = next(group for group in mobj.groups() if group)
webpage = self._download_webpage(url, display_id)
return self._extract_embed(webpage, display_id)
@@ -101,7 +102,7 @@ class NDRIE(NDRBaseIE):
class NJoyIE(NDRBaseIE):
IE_NAME = 'njoy'
IE_DESC = 'N-JOY'
_VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)+(?P<id>[^/?#]+),[\da-z]+\.html'
_VALID_URL = r'https?://www\.n-joy\.de/(?:[^/]+/)+(?:(?P<display_id>[^/?#]+),)?(?P<id>[\da-z]+)\.html'
_TESTS = [{
# httpVideo, same content id
'url': 'http://www.n-joy.de/entertainment/comedy/comedy_contest/Benaissa-beim-NDR-Comedy-Contest,comedycontest2480.html',
@@ -136,6 +137,9 @@ class NJoyIE(NDRBaseIE):
'params': {
'skip_download': True,
},
}, {
'url': 'http://www.n-joy.de/radio/webradio/morningshow209.html',
'only_matching': True,
}]
def _extract_embed(self, webpage, display_id):

View File

@@ -121,9 +121,9 @@ class SenateISVPIE(InfoExtractor):
'url': compat_urlparse.urljoin(domain, filename) + '?v=3.1.0&fp=&r=&g=',
}]
else:
hdcore_sign = '?hdcore=3.1.0'
hdcore_sign = 'hdcore=3.1.0'
url_params = (domain, video_id, stream_num)
f4m_url = '%s/z/%s_1@%s/manifest.f4m' % url_params + hdcore_sign
f4m_url = '%s/z/%s_1@%s/manifest.f4m?' % url_params + hdcore_sign
m3u8_url = '%s/i/%s_1@%s/master.m3u8' % url_params
for entry in self._extract_f4m_formats(f4m_url, video_id, f4m_id='f4m'):
# URLs without the extra param induce an 404 error

View File

@@ -77,17 +77,21 @@ class SpiegeltvIE(InfoExtractor):
'rtmp_live': True,
})
elif determine_ext(endpoint) == 'm3u8':
m3u8_formats = self._extract_m3u8_formats(
endpoint.replace('[video]', play_path),
video_id, 'm4v',
preference=1, # Prefer hls since it allows to workaround georestriction
m3u8_id='hls', fatal=False)
if m3u8_formats is not False:
formats.extend(m3u8_formats)
formats.append({
'url': endpoint.replace('[video]', play_path),
'ext': 'm4v',
'format_id': 'hls', # Prefer hls since it allows to workaround georestriction
'protocol': 'm3u8',
'preference': 1,
'http_headers': {
'Accept-Encoding': 'deflate', # gzip causes trouble on the server side
},
})
else:
formats.append({
'url': endpoint,
})
self._check_formats(formats, video_id)
thumbnails = []
for image in media_json['images']:

View File

@@ -64,7 +64,7 @@ class StitcherIE(InfoExtractor):
'url': episode[episode_key],
'ext': determine_ext(episode[episode_key]) or 'mp3',
'vcodec': 'none',
} for episode_key in ('origEpisodeURL', 'episodeURL') if episode.get(episode_key)]
} for episode_key in ('episodeURL',) if episode.get(episode_key)]
description = self._search_regex(
r'Episode Info:\s*</span>([^<]+)<', webpage, 'description', fatal=False)
duration = int_or_none(episode.get('duration'))

View File

@@ -10,10 +10,10 @@ class TutvIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tu\.tv/videos/(?P<id>[^/?]+)'
_TEST = {
'url': 'http://tu.tv/videos/robots-futbolistas',
'md5': '627c7c124ac2a9b5ab6addb94e0e65f7',
'md5': '0cd9e28ad270488911b0d2a72323395d',
'info_dict': {
'id': '2973058',
'ext': 'flv',
'ext': 'mp4',
'title': 'Robots futbolistas',
},
}

View File

@@ -1,10 +1,10 @@
from __future__ import unicode_literals
import re
import xml.etree.ElementTree
from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
compat_urllib_request,
)
from ..utils import (
@@ -97,7 +97,7 @@ class VevoIE(InfoExtractor):
if last_version['version'] == -1:
raise ExtractorError('Unable to extract last version of the video')
renditions = xml.etree.ElementTree.fromstring(last_version['data'])
renditions = compat_etree_fromstring(last_version['data'])
formats = []
# Already sorted from worst to best quality
for rend in renditions.findall('rendition'):
@@ -114,7 +114,7 @@ class VevoIE(InfoExtractor):
def _formats_from_smil(self, smil_xml):
formats = []
smil_doc = xml.etree.ElementTree.fromstring(smil_xml.encode('utf-8'))
smil_doc = compat_etree_fromstring(smil_xml.encode('utf-8'))
els = smil_doc.findall('.//{http://www.w3.org/2001/SMIL20/Language}video')
for el in els:
src = el.attrib['src']

View File

@@ -2,8 +2,8 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
find_xpath_attr,
int_or_none,
parse_iso8601,
)
@@ -18,33 +18,35 @@ class VideofyMeIE(InfoExtractor):
'id': '1100701',
'ext': 'mp4',
'title': 'This is VideofyMe',
'description': None,
'description': '',
'upload_date': '20130326',
'timestamp': 1364288959,
'uploader': 'VideofyMe',
'uploader_id': 'thisisvideofyme',
'view_count': int,
'likes': int,
'comment_count': int,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
config = self._download_xml('http://sunshine.videofy.me/?videoId=%s' % video_id,
video_id)
video = config.find('video')
sources = video.find('sources')
url_node = next(node for node in [find_xpath_attr(sources, 'source', 'id', 'HQ %s' % key)
for key in ['on', 'av', 'off']] if node is not None)
video_url = url_node.find('url').text
view_count = int_or_none(self._search_regex(
r'([0-9]+)', video.find('views').text, 'view count', fatal=False))
config = self._download_json('http://vf-player-info-loader.herokuapp.com/%s.json' % video_id, video_id)['videoinfo']
video = config.get('video')
blog = config.get('blog', {})
return {
'id': video_id,
'title': video.find('title').text,
'url': video_url,
'thumbnail': video.find('thumb').text,
'description': video.find('description').text,
'uploader': config.find('blog/name').text,
'uploader_id': video.find('identifier').text,
'view_count': view_count,
'title': video['title'],
'url': video['sources']['source']['url'],
'thumbnail': video.get('thumb'),
'description': video.get('description'),
'timestamp': parse_iso8601(video.get('date')),
'uploader': blog.get('name'),
'uploader_id': blog.get('identifier'),
'view_count': int_or_none(self._search_regex(r'([0-9]+)', video.get('views'), 'view count', fatal=False)),
'likes': int_or_none(video.get('likes')),
'comment_count': int_or_none(video.get('nrOfComments')),
}

View File

@@ -101,6 +101,10 @@ class VidmeIE(InfoExtractor):
# suspended
'url': 'https://vid.me/Ox3G',
'only_matching': True,
}, {
# deleted
'url': 'https://vid.me/KTPm',
'only_matching': True,
}, {
# no formats in the API response
'url': 'https://vid.me/e5g',
@@ -143,6 +147,11 @@ class VidmeIE(InfoExtractor):
video = response['video']
if video.get('state') == 'deleted':
raise ExtractorError(
'Vidme said: Sorry, this video has been deleted.',
expected=True)
if video.get('state') in ('user-disabled', 'suspended'):
raise ExtractorError(
'Vidme said: This video has been suspended either due to a copyright claim, '

View File

@@ -1,121 +1,171 @@
from __future__ import unicode_literals
import json
import re
import sys
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlparse,
compat_urllib_request,
)
from ..compat import compat_urllib_request
from ..utils import (
ExtractorError,
int_or_none,
str_to_int,
unescapeHTML,
unified_strdate,
)
from ..aes import (
aes_decrypt_text
)
from ..aes import aes_decrypt_text
class YouPornIE(InfoExtractor):
_VALID_URL = r'^(?P<proto>https?://)(?:www\.)?(?P<url>youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+))'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?youporn\.com/watch/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
'md5': '71ec5fcfddacf80f495efa8b6a8d9a89',
'info_dict': {
'id': '505835',
'display_id': 'sex-ed-is-it-safe-to-masturbate-daily',
'ext': 'mp4',
'upload_date': '20101221',
'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
'uploader': 'Ask Dan And Jennifer',
'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': 'Ask Dan And Jennifer',
'upload_date': '20101221',
'average_rating': int,
'view_count': int,
'comment_count': int,
'categories': list,
'tags': list,
'age_limit': 18,
}
}
},
}, {
# Anonymous User uploader
'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
'info_dict': {
'id': '561726',
'display_id': 'big-tits-awesome-brunette-on-amazing-webcam-show',
'ext': 'mp4',
'title': 'Big Tits Awesome Brunette On amazing webcam show',
'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': 'Anonymous User',
'upload_date': '20111125',
'average_rating': int,
'view_count': int,
'comment_count': int,
'categories': list,
'tags': list,
'age_limit': 18,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid')
url = mobj.group('proto') + 'www.' + mobj.group('url')
video_id = mobj.group('id')
display_id = mobj.group('display_id')
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
age_limit = self._rta_search(webpage)
request = compat_urllib_request.Request(url)
request.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(request, display_id)
# Get JSON parameters
json_params = self._search_regex(
[r'videoJa?son\s*=\s*({.+})',
r'var\s+currentVideo\s*=\s*new\s+Video\((.+?)\)[,;]'],
webpage, 'JSON parameters')
try:
params = json.loads(json_params)
except ValueError:
raise ExtractorError('Invalid JSON')
title = self._search_regex(
[r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P<title>.+?)\1',
r'<h1[^>]+class=["\']heading\d?["\'][^>]*>([^<])<'],
webpage, 'title', group='title')
self.report_extraction(video_id)
try:
video_title = params['title']
upload_date = unified_strdate(params['release_date_f'])
video_description = params['description']
video_uploader = params['submitted_by']
thumbnail = params['thumbnails'][0]['image']
except KeyError:
raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
links = []
# Get all of the links from the page
DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
download_list_html = self._search_regex(DOWNLOAD_LIST_RE,
webpage, 'download list').strip()
LINK_RE = r'<a href="([^"]+)">'
links = re.findall(LINK_RE, download_list_html)
sources = self._search_regex(
r'sources\s*:\s*({.+?})', webpage, 'sources', default=None)
if sources:
for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources):
links.append(link)
# Get all encrypted links
encrypted_links = re.findall(r'var encryptedQuality[0-9]{3}URL = \'([a-zA-Z0-9+/]+={0,2})\';', webpage)
for encrypted_link in encrypted_links:
link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8')
# Fallback #1
for _, link in re.findall(
r'(?:videoUrl|videoSrc|videoIpadUrl|html5PlayerSrc)\s*[:=]\s*(["\'])(http.+?)\1', webpage):
links.append(link)
# Fallback #2, this also contains extra low quality 180p format
for _, link in re.findall(r'<a[^>]+href=(["\'])(http.+?)\1[^>]+title=["\']Download [Vv]ideo', webpage):
links.append(link)
# Fallback #3, encrypted links
for _, encrypted_link in re.findall(
r'encryptedQuality\d{3,4}URL\s*=\s*(["\'])([\da-zA-Z+/=]+)\1', webpage):
links.append(aes_decrypt_text(encrypted_link, title, 32).decode('utf-8'))
formats = []
for link in links:
# A link looks like this:
# http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0
# A path looks like this:
# /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
video_url = unescapeHTML(link)
path = compat_urllib_parse_urlparse(video_url).path
format_parts = path.split('/')[4].split('_')[:2]
dn = compat_urllib_parse_urlparse(video_url).netloc.partition('.')[0]
resolution = format_parts[0]
height = int(resolution[:-len('p')])
bitrate = int(format_parts[1][:-len('k')])
format = '-'.join(format_parts) + '-' + dn
formats.append({
for video_url in set(unescapeHTML(link) for link in links):
f = {
'url': video_url,
'format': format,
'format_id': format,
'height': height,
'tbr': bitrate,
'resolution': resolution,
})
}
# Video URL's path looks like this:
# /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.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)
if mobj:
height = int(mobj.group('height'))
bitrate = int(mobj.group('bitrate'))
f.update({
'format_id': '%dp-%dk' % (height, bitrate),
'height': height,
'tbr': bitrate,
})
formats.append(f)
self._sort_formats(formats)
if not formats:
raise ExtractorError('ERROR: no known formats available for video')
description = self._html_search_regex(
r'(?s)<div[^>]+class=["\']video-description["\'][^>]*>(.+?)</div>',
webpage, 'description', default=None)
thumbnail = self._search_regex(
r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
webpage, 'thumbnail', fatal=False, group='thumbnail')
uploader = self._html_search_regex(
r'(?s)<div[^>]+class=["\']videoInfoBy["\'][^>]*>\s*By:\s*</div>(.+?)</(?:a|div)>',
webpage, 'uploader', fatal=False)
upload_date = unified_strdate(self._html_search_regex(
r'(?s)<div[^>]+class=["\']videoInfoTime["\'][^>]*>(.+?)</div>',
webpage, 'upload date', fatal=False))
age_limit = self._rta_search(webpage)
average_rating = int_or_none(self._search_regex(
r'<div[^>]+class=["\']videoInfoRating["\'][^>]*>\s*<div[^>]+class=["\']videoRatingPercentage["\'][^>]*>(\d+)%</div>',
webpage, 'average rating', fatal=False))
view_count = str_to_int(self._search_regex(
r'(?s)<div[^>]+class=["\']videoInfoViews["\'][^>]*>.*?([\d,.]+)\s*</div>',
webpage, 'view count', fatal=False))
comment_count = str_to_int(self._search_regex(
r'>All [Cc]omments? \(([\d,.]+)\)',
webpage, 'comment count', fatal=False))
def extract_tag_box(title):
tag_box = self._search_regex(
(r'<div[^>]+class=["\']tagBoxTitle["\'][^>]*>\s*%s\b.*?</div>\s*'
'<div[^>]+class=["\']tagBoxContent["\']>(.+?)</div>') % re.escape(title),
webpage, '%s tag box' % title, default=None)
if not tag_box:
return []
return re.findall(r'<a[^>]+href=[^>]+>([^<]+)', tag_box)
categories = extract_tag_box('Category')
tags = extract_tag_box('Tags')
return {
'id': video_id,
'uploader': video_uploader,
'upload_date': upload_date,
'title': video_title,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'description': video_description,
'uploader': uploader,
'upload_date': upload_date,
'average_rating': average_rating,
'view_count': view_count,
'comment_count': comment_count,
'categories': categories,
'tags': tags,
'age_limit': age_limit,
'formats': formats,
}

View File

@@ -1644,8 +1644,18 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
'playlist_mincount': 91,
'info_dict': {
'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
'title': 'Uploads from lex will',
}
}, {
'note': 'Age restricted channel',
# from https://www.youtube.com/user/DeusExOfficial
'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
'playlist_mincount': 64,
'info_dict': {
'id': 'UUs0ifCMCm1icqRbqhUINa0w',
'title': 'Uploads from Deus Ex',
},
}]
def _real_extract(self, url):
@@ -1666,7 +1676,7 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
'channelId', channel_page, 'channel id', default=None)
if not channel_playlist_id:
channel_playlist_id = self._search_regex(
r'data-channel-external-id="([^"]+)"',
r'data-(?:channel-external-|yt)id="([^"]+)"',
channel_page, 'channel id', default=None)
if channel_playlist_id and channel_playlist_id.startswith('UC'):
playlist_id = 'UU' + channel_playlist_id[2:]

View File

@@ -36,6 +36,7 @@ import zlib
from .compat import (
compat_basestring,
compat_chr,
compat_etree_fromstring,
compat_html_entities,
compat_http_client,
compat_kwargs,
@@ -178,10 +179,19 @@ def xpath_with_ns(path, ns_map):
def xpath_element(node, xpath, name=None, fatal=False, default=NO_DEFAULT):
if sys.version_info < (2, 7): # Crazy 2.6
xpath = xpath.encode('ascii')
def _find_xpath(xpath):
if sys.version_info < (2, 7): # Crazy 2.6
xpath = xpath.encode('ascii')
return node.find(xpath)
if isinstance(xpath, (str, compat_str)):
n = _find_xpath(xpath)
else:
for xp in xpath:
n = _find_xpath(xp)
if n is not None:
break
n = node.find(xpath)
if n is None:
if default is not NO_DEFAULT:
return default
@@ -356,7 +366,7 @@ def sanitize_path(s):
if drive_or_unc:
norm_path.pop(0)
sanitized_path = [
path_part if path_part in ['.', '..'] else re.sub('(?:[/<>:"\\|\\\\?\\*]|\.$)', '#', path_part)
path_part if path_part in ['.', '..'] else re.sub('(?:[/<>:"\\|\\\\?\\*]|[\s.]$)', '#', path_part)
for path_part in norm_path]
if drive_or_unc:
sanitized_path.insert(0, drive_or_unc + os.path.sep)
@@ -814,9 +824,11 @@ def parse_iso8601(date_str, delimiter='T', timezone=None):
if date_str is None:
return None
date_str = re.sub(r'\.[0-9]+', '', date_str)
if timezone is None:
m = re.search(
r'(\.[0-9]+)?(?:Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$)',
r'(?:Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$)',
date_str)
if not m:
timezone = datetime.timedelta()
@@ -829,9 +841,12 @@ def parse_iso8601(date_str, delimiter='T', timezone=None):
timezone = datetime.timedelta(
hours=sign * int(m.group('hours')),
minutes=sign * int(m.group('minutes')))
date_format = '%Y-%m-%d{0}%H:%M:%S'.format(delimiter)
dt = datetime.datetime.strptime(date_str, date_format) - timezone
return calendar.timegm(dt.timetuple())
try:
date_format = '%Y-%m-%d{0}%H:%M:%S'.format(delimiter)
dt = datetime.datetime.strptime(date_str, date_format) - timezone
return calendar.timegm(dt.timetuple())
except ValueError:
pass
def unified_strdate(date_str, day_first=True):
@@ -896,7 +911,8 @@ def unified_strdate(date_str, day_first=True):
timetuple = email.utils.parsedate_tz(date_str)
if timetuple:
upload_date = datetime.datetime(*timetuple[:6]).strftime('%Y%m%d')
return upload_date
if upload_date is not None:
return compat_str(upload_date)
def determine_ext(url, default_ext='unknown_video'):
@@ -1651,29 +1667,6 @@ def encode_dict(d, encoding='utf-8'):
return dict((k.encode(encoding), v.encode(encoding)) for k, v in d.items())
try:
etree_iter = xml.etree.ElementTree.Element.iter
except AttributeError: # Python <=2.6
etree_iter = lambda n: n.findall('.//*')
def parse_xml(s):
class TreeBuilder(xml.etree.ElementTree.TreeBuilder):
def doctype(self, name, pubid, system):
pass # Ignore doctypes
parser = xml.etree.ElementTree.XMLParser(target=TreeBuilder())
kwargs = {'parser': parser} if sys.version_info >= (2, 7) else {}
tree = xml.etree.ElementTree.XML(s.encode('utf-8'), **kwargs)
# Fix up XML parser in Python 2.x
if sys.version_info < (3, 0):
for n in etree_iter(tree):
if n.text is not None:
if not isinstance(n.text, compat_str):
n.text = n.text.decode('utf-8')
return tree
US_RATINGS = {
'G': 0,
'PG': 10,
@@ -1974,7 +1967,7 @@ def dfxp2srt(dfxp_data):
return out
dfxp = xml.etree.ElementTree.fromstring(dfxp_data.encode('utf-8'))
dfxp = compat_etree_fromstring(dfxp_data.encode('utf-8'))
out = []
paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall(_x('.//ttaf1:p')) or dfxp.findall('.//p')

View File

@@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2015.10.23'
__version__ = '2015.11.02'