diff --git a/youtube_dl/extractor/jeuxvideo.py b/youtube_dl/extractor/jeuxvideo.py index ae2e37a708..6bb54b9322 100644 --- a/youtube_dl/extractor/jeuxvideo.py +++ b/youtube_dl/extractor/jeuxvideo.py @@ -6,6 +6,7 @@ from .common import InfoExtractor + class JeuxVideoIE(InfoExtractor): _VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm' @@ -23,25 +24,29 @@ def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) title = re.match(self._VALID_URL, url).group(1) webpage = self._download_webpage(url, title) - m_download = re.search(r'', webpage) - - xml_link = m_download.group(1) + xml_link = self._html_search_regex( + r'', + webpage, u'config URL') - id = re.search(r'http://www.jeuxvideo.com/config/\w+/0011/(.*?)/\d+_player\.xml', xml_link).group(1) + 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, - 'Downloading XML config') + xml_config = self._download_webpage( + xml_link, title, u'Downloading XML config') config = xml.etree.ElementTree.fromstring(xml_config.encode('utf-8')) - info = re.search(r'(.*?)', - xml_config, re.MULTILINE|re.DOTALL).group(1) - info = json.loads(info)['versions'][0] + 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'] - return {'id': id, - 'title' : config.find('titre_video').text, - 'ext' : 'mp4', - 'url' : video_url, - 'description': self._og_search_description(webpage), - 'thumbnail': config.find('image').text, - } + return { + 'id': video_id, + 'title': config.find('titre_video').text, + 'ext': 'mp4', + 'url': video_url, + 'description': self._og_search_description(webpage), + 'thumbnail': config.find('image').text, + }