X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/54477c858fa2504360964e675faf953d78ac57e6..712213a489c35dbaf5120268f1a309dc457cea29:/youtube_dl/extractor/jeuxvideo.py
diff --git a/youtube_dl/extractor/jeuxvideo.py b/youtube_dl/extractor/jeuxvideo.py
index 6bb54b9..e9f4ed7 100644
--- a/youtube_dl/extractor/jeuxvideo.py
+++ b/youtube_dl/extractor/jeuxvideo.py
@@ -1,52 +1,56 @@
# coding: utf-8
-import json
+from __future__ import unicode_literals
+
import re
-import xml.etree.ElementTree
from .common import InfoExtractor
class JeuxVideoIE(InfoExtractor):
- _VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm'
-
- _TEST = {
- u'url': u'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
- u'file': u'5182.mp4',
- u'md5': u'046e491afb32a8aaac1f44dd4ddd54ee',
- u'info_dict': {
- u'title': u'GC 2013 : Tearaway nous présente ses papiers d\'identité',
- u'description': u'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.\n',
+ _VALID_URL = r'https?://.*?\.jeuxvideo\.com/.*/(.*?)\.htm'
+
+ _TESTS = [{
+ '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',
+ 'info_dict': {
+ 'id': '114765',
+ 'ext': 'mp4',
+ '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.',
},
- }
+ }, {
+ 'url': 'http://www.jeuxvideo.com/videos/chroniques/434220/l-histoire-du-jeu-video-la-saturn.htm',
+ 'only_matching': True,
+ }]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- title = re.match(self._VALID_URL, url).group(1)
+ title = mobj.group(1)
webpage = self._download_webpage(url, title)
- xml_link = self._html_search_regex(
- r'',
- webpage, u'config URL')
-
+ title = self._html_search_meta('name', webpage) or self._og_search_title(webpage)
+ config_url = self._html_search_regex(
+ r'data-src(?:set-video)?="(/contenu/medias/video\.php.*?)"',
+ webpage, 'config URL')
+ config_url = 'http://www.jeuxvideo.com' + config_url
+
video_id = self._search_regex(
- r'http://www\.jeuxvideo\.com/config/\w+/\d+/(.*?)/\d+_player\.xml',
- xml_link, u'video ID')
-
- xml_config = self._download_webpage(
- xml_link, title, u'Downloading XML config')
- config = xml.etree.ElementTree.fromstring(xml_config.encode('utf-8'))
- info_json = self._search_regex(
- r'(?sm)(.*?)',
- xml_config, u'JSON information')
- info = json.loads(info_json)['versions'][0]
-
- video_url = 'http://video720.jeuxvideo.com/' + info['file']
+ r'id=(\d+)',
+ config_url, 'video ID')
+
+ config = self._download_json(
+ config_url, title, 'Downloading JSON config')
+
+ formats = [{
+ 'url': source['file'],
+ 'format_id': source['label'],
+ 'resolution': source['label'],
+ } for source in reversed(config['sources'])]
return {
'id': video_id,
- 'title': config.find('titre_video').text,
- 'ext': 'mp4',
- 'url': video_url,
+ 'title': title,
+ 'formats': formats,
'description': self._og_search_description(webpage),
- 'thumbnail': config.find('image').text,
+ 'thumbnail': config.get('image'),
}