Roxedus/ytdl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[jeuxvideo] Extract more information and add test

Browse Source
This commit is contained in:
Jaime Marquínez Ferrándiz 2013-08-22 12:37:34 +02:00
parent 8403612258
commit 063fcc9676
1 changed files with 21 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
youtube_dl/extractor/jeuxvideo.py
View File

@ -1,11 +1,24 @@
# coding: utf-8
import json import json
import re import re
import xml.etree.ElementTree
from .common import InfoExtractor from .common import InfoExtractor
class JeuxVideoIE(InfoExtractor): class JeuxVideoIE(InfoExtractor):
_VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm' _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'e0fdb0cd3ce98713ef9c1e1e025779d0',
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): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
title = re.match(self._VALID_URL, url).group(1) title = re.match(self._VALID_URL, url).group(1)
@ -18,16 +31,17 @@ class JeuxVideoIE(InfoExtractor):
xml_config = self._download_webpage(xml_link, title, xml_config = self._download_webpage(xml_link, title,
'Downloading XML config') 'Downloading XML config')
config = xml.etree.ElementTree.fromstring(xml_config.encode('utf-8'))
info = re.search(r'<format\.json>(.*?)</format\.json>', info = re.search(r'<format\.json>(.*?)</format\.json>',
xml_config, re.MULTILINE|re.DOTALL).group(1) xml_config, re.MULTILINE|re.DOTALL).group(1)
info = json.loads(info)['versions'][0] info = json.loads(info)['versions'][0]
video_url = 'http://video720.jeuxvideo.com/' + info['file'] video_url = 'http://video720.jeuxvideo.com/' + info['file']
track_info = {'id':id, return {'id': id,
'title' : title, 'title' : config.find('titre_video').text,
'ext' : 'mp4', 'ext' : 'mp4',
'url' : video_url 'url' : video_url,
} 'description': self._og_search_description(webpage),
'thumbnail': config.find('image').text,
return [track_info] }