X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fjeuxvideo.py;h=0020c47cfd53a05eb4c719a2d8c203783e97d4e2;hb=3f8ced5144a76a3f9ab7ee8cd06cc79bb75dc564;hp=d74a1c9b4ee19bcba5f322d23f5e4b8a1412d26e;hpb=8403612258afb1897b82bd789cfb64ea76017688;p=youtube-dl
diff --git a/youtube_dl/extractor/jeuxvideo.py b/youtube_dl/extractor/jeuxvideo.py
index d74a1c9b4..0020c47cf 100644
--- a/youtube_dl/extractor/jeuxvideo.py
+++ b/youtube_dl/extractor/jeuxvideo.py
@@ -1,33 +1,52 @@
+# coding: utf-8
+
import json
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',
+ },
+ }
+
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)
+ 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')
- info = re.search(r'(.*?)',
- xml_config, re.MULTILINE|re.DOTALL).group(1)
- info = json.loads(info)['versions'][0]
+ 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']
- track_info = {'id':id,
- 'title' : title,
- 'ext' : 'mp4',
- 'url' : video_url
- }
-
- return [track_info]
+ 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,
+ }