[tudou] Add support for youku links (Closes #1571)

This commit is contained in:
Philipp Hagemeister 2013-10-15 01:20:04 +02:00
parent 7394b8db3b
commit 9ed3bdc64d

View File

@ -7,15 +7,25 @@
class TudouIE(InfoExtractor): class TudouIE(InfoExtractor):
_VALID_URL = r'(?:http://)?(?:www\.)?tudou\.com/(?:listplay|programs)/(?:view|(.+?))/(?:([^/]+)|([^/]+))(?:\.html)?' _VALID_URL = r'(?:http://)?(?:www\.)?tudou\.com/(?:listplay|programs|albumplay)/(?:view|(.+?))/(?:([^/]+)|([^/]+))(?:\.html)?'
_TEST = { _TESTS = [{
u'url': u'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html', u'url': u'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html',
u'file': u'159448201.f4v', u'file': u'159448201.f4v',
u'md5': u'140a49ed444bd22f93330985d8475fcb', u'md5': u'140a49ed444bd22f93330985d8475fcb',
u'info_dict': { u'info_dict': {
u"title": u"卡马乔国足开大脚长传冲吊集锦" u"title": u"卡马乔国足开大脚长传冲吊集锦"
} }
} },
{
u'url': u'http://www.tudou.com/albumplay/TenTw_JgiPM/PzsAs5usU9A.html',
u'file': u'todo.mp4',
u'md5': u'todo.mp4',
u'info_dict': {
u'title': u'todo.mp4',
},
u'add_ie': [u'Youku'],
u'skip': u'Only works from China'
}]
def _url_for_id(self, id, quality = None): def _url_for_id(self, id, quality = None):
info_url = "http://v2.tudou.com/f?id="+str(id) info_url = "http://v2.tudou.com/f?id="+str(id)
@ -29,14 +39,18 @@ def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(2) video_id = mobj.group(2)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = re.search(",kw:\"(.+)\"",webpage)
if title is None: m = re.search(r'vcode:\s*[\'"](.+?)[\'"]', webpage)
title = re.search(",kw: \'(.+)\'",webpage) if m and m.group(1):
title = title.group(1) return {
thumbnail_url = re.search(",pic: \'(.+?)\'",webpage) '_type': 'url',
if thumbnail_url is None: 'url': u'youku:' + m.group(1),
thumbnail_url = re.search(",pic:\"(.+?)\"",webpage) 'ie_key': 'Youku'
thumbnail_url = thumbnail_url.group(1) }
title = self._search_regex(r",kw:['\"](.+?)[\"']", webpage, u'title')
thumbnail_url = self._search_regex(
r",pic:\s*[\"'](.+?)[\"']", webpage, u'thumbnail URL', fatal=False)
segs_json = self._search_regex(r'segs: \'(.*)\'', webpage, 'segments') segs_json = self._search_regex(r'segs: \'(.*)\'', webpage, 'segments')
segments = json.loads(segs_json) segments = json.loads(segs_json)