ansol/youtube-dl
7
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-13 16:57:28 +00:00
Code Issues Projects Releases Wiki Activity

[teamcoco] Fix "preload" data extraction (fixes #5179)

Browse Source
This commit is contained in:
Yen Chi Hsuan 2015-04-15 19:56:21 +08:00
parent ae849ca170
commit 9c5335a027
1 changed files with 28 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
youtube_dl/extractor/teamcoco.py
View File

@ -1,3 +1,4 @@
# -*- coding: utf-8 -*-
from __future__ import unicode_literals from __future__ import unicode_literals
import base64 import base64
@ -35,6 +36,17 @@ class TeamcocoIE(InfoExtractor):
'duration': 288, 'duration': 288,
'age_limit': 0, '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 = ( _VIDEO_ID_REGEXES = (
@ -54,10 +66,23 @@ class TeamcocoIE(InfoExtractor):
video_id = self._html_search_regex( video_id = self._html_search_regex(
self._VIDEO_ID_REGEXES, webpage, 'video id') self._VIDEO_ID_REGEXES, webpage, 'video id')
preload = None
preloads = re.findall(r'"preload":\s*"([^"]+)"', webpage) preloads = re.findall(r'"preload":\s*"([^"]+)"', webpage)
if not preloads: if preloads:
raise ExtractorError('Preload information could not be extracted') preload = max([(len(p), p) for p in preloads])[1]
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( data = self._parse_json(
base64.b64decode(preload.encode('ascii')).decode('utf-8'), video_id) base64.b64decode(preload.encode('ascii')).decode('utf-8'), video_id)