X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fjeuxvideo.py;h=e9f4ed7384225456edf87baf0c24ce5c6ecc4b20;hb=HEAD;hp=d74a1c9b4ee19bcba5f322d23f5e4b8a1412d26e;hpb=943f7f7a399c6fb3006eb2bd68070f28a272171f;p=youtube-dl diff --git a/youtube_dl/extractor/jeuxvideo.py b/youtube_dl/extractor/jeuxvideo.py index d74a1c9b4..e9f4ed738 100644 --- a/youtube_dl/extractor/jeuxvideo.py +++ b/youtube_dl/extractor/jeuxvideo.py @@ -1,33 +1,56 @@ -import json +# coding: utf-8 + +from __future__ import unicode_literals + import re from .common import InfoExtractor + class JeuxVideoIE(InfoExtractor): - _VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm' + _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) - m_download = re.search(r'', webpage) - - xml_link = m_download.group(1) - - id = re.search(r'http://www.jeuxvideo.com/config/\w+/0011/(.*?)/\d+_player\.xml', xml_link).group(1) - - xml_config = self._download_webpage(xml_link, title, - 'Downloading XML config') - info = re.search(r'(.*?)', - xml_config, re.MULTILINE|re.DOTALL).group(1) - info = json.loads(info)['versions'][0] - - video_url = 'http://video720.jeuxvideo.com/' + info['file'] - - track_info = {'id':id, - 'title' : title, - 'ext' : 'mp4', - 'url' : video_url - } - - return [track_info] + 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'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': title, + 'formats': formats, + 'description': self._og_search_description(webpage), + 'thumbnail': config.get('image'), + }