diff options
author | Yen Chi Hsuan <[email protected]> | 2015-04-15 19:56:21 +0800 |
---|---|---|
committer | Yen Chi Hsuan <[email protected]> | 2015-04-15 19:56:21 +0800 |
commit | 9c5335a0270042b7e84f02e550676447ccf603b1 (patch) | |
tree | fb7fa81838aba16773cb0d8d4a90ef6f25dbd928 /youtube_dl/extractor/teamcoco.py | |
parent | ae849ca1701dc5bdf25e648a57a1e6ec64f2f968 (diff) | |
download | youtube-dl-9c5335a0270042b7e84f02e550676447ccf603b1.tar.gz youtube-dl-9c5335a0270042b7e84f02e550676447ccf603b1.zip |
[teamcoco] Fix "preload" data extraction (fixes #5179)
Diffstat (limited to 'youtube_dl/extractor/teamcoco.py')
-rw-r--r-- | youtube_dl/extractor/teamcoco.py | 31 |
1 files changed, 28 insertions, 3 deletions
diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py index 1caf08cb7..2381676b4 100644 --- a/youtube_dl/extractor/teamcoco.py +++ b/youtube_dl/extractor/teamcoco.py @@ -1,3 +1,4 @@ +# -*- coding: utf-8 -*- from __future__ import unicode_literals import base64 @@ -35,6 +36,17 @@ class TeamcocoIE(InfoExtractor): 'duration': 288, 'age_limit': 0, } + }, { + 'url': 'http://teamcoco.com/video/timothy-olyphant-drinking-whiskey', + 'info_dict': { + 'id': '88748', + 'ext': 'mp4', + 'title': 'Timothy Olyphant Raises A Toast To “Justified”', + 'description': 'md5:15501f23f020e793aeca761205e42c24', + }, + 'params': { + 'skip_download': True, # m3u8 downloads + } } ] _VIDEO_ID_REGEXES = ( @@ -54,10 +66,23 @@ class TeamcocoIE(InfoExtractor): video_id = self._html_search_regex( self._VIDEO_ID_REGEXES, webpage, 'video id') + preload = None preloads = re.findall(r'"preload":\s*"([^"]+)"', webpage) - if not preloads: - raise ExtractorError('Preload information could not be extracted') - preload = max([(len(p), p) for p in preloads])[1] + if preloads: + preload = max([(len(p), p) for p in preloads])[1] + + if not preload: + preload = ''.join(re.findall(r'this\.push\("([^"]+)"\);', webpage)) + + if not preload: + preload = self._html_search_regex([ + r'player,\[?"([^"]+)"\]?', r'player.init\(\[?"([^"]+)"\]?\)' + ], webpage.replace('","', ''), 'preload data', default=None) + + if not preload: + raise ExtractorError( + 'Preload information could not be extracted', expected=True) + data = self._parse_json( base64.b64decode(preload.encode('ascii')).decode('utf-8'), video_id) |