fenix/ytdl-nightly
1
0
Fork 0
mirror of https://github.com/ytdl-org/ytdl-nightly.git synced 2024-12-23 13:32:08 +01:00
Code Issues Packages Projects Releases Wiki Activity

[jeuxvideo] Fix extraction (fixes #5190)

Browse Source
This commit is contained in:
Jaime Marquínez Ferrándiz 2015-03-12 22:33:59 +01:00
parent 3946864c8a
commit 054b99a330
1 changed files with 19 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
youtube_dl/extractor/jeuxvideo.py
View File

@ -2,7 +2,6 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import json
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -15,10 +14,10 @@ class JeuxVideoIE(InfoExtractor):
'url': 'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm', 'url': 'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
'md5': '046e491afb32a8aaac1f44dd4ddd54ee', 'md5': '046e491afb32a8aaac1f44dd4ddd54ee',
'info_dict': { 'info_dict': {
'id': '5182', 'id': '114765',
'ext': 'mp4', 'ext': 'mp4',
'title': 'GC 2013 : Tearaway nous présente ses papiers d\'identité', 'title': 'Tearaway : GC 2013 : Tearaway nous présente ses papiers d\'identité',
'description': 'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.\n', 'description': 'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.',
}, },
} }
@ -26,26 +25,29 @@ class JeuxVideoIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
title = mobj.group(1) title = mobj.group(1)
webpage = self._download_webpage(url, title) webpage = self._download_webpage(url, title)
xml_link = self._html_search_regex( title = self._html_search_meta('name', webpage)
r'<param name="flashvars" value="config=(.*?)" />', config_url = self._html_search_regex(
r'data-src="(/contenu/medias/video.php.*?)"',
webpage, 'config URL') webpage, 'config URL')
config_url = 'http://www.jeuxvideo.com' + config_url
video_id = self._search_regex( video_id = self._search_regex(
r'http://www\.jeuxvideo\.com/config/\w+/\d+/(.*?)/\d+_player\.xml', r'id=(\d+)',
xml_link, 'video ID') config_url, 'video ID')
config = self._download_xml( config = self._download_json(
xml_link, title, 'Downloading XML config') config_url, title, 'Downloading JSON config')
info_json = config.find('format.json').text
info = json.loads(info_json)['versions'][0]
video_url = 'http://video720.jeuxvideo.com/' + info['file'] formats = [{
'url': source['file'],
'format_id': source['label'],
'resolution': source['label'],
} for source in reversed(config['sources'])]
return { return {
'id': video_id, 'id': video_id,
'title': config.find('titre_video').text, 'title': title,
'ext': 'mp4', 'formats': formats,
'url': video_url,
'description': self._og_search_description(webpage), 'description': self._og_search_description(webpage),
'thumbnail': config.find('image').text, 'thumbnail': config.get('image'),
} }