]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/tudou.py
3 from __future__
import unicode_literals
8 from .common
import InfoExtractor
11 class TudouIE(InfoExtractor
):
12 _VALID_URL
= r
'https?://(?:www\.)?tudou\.com/(?:listplay|programs(?:/view)?|albumplay)/?.*/(?P<id>[^/?#]+?)(?:\.html)?/?(?:$|[?#])'
14 'url': 'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html',
15 'md5': '140a49ed444bd22f93330985d8475fcb',
19 'title': '卡马乔国足开大脚长传冲吊集锦',
20 'thumbnail': 're:^https?://.*\.jpg$',
23 'url': 'http://www.tudou.com/programs/view/ajX3gyhL0pc/',
27 'title': 'La Sylphide-Bolshoi-Ekaterina Krysanova & Vyacheslav Lopatin 2012',
28 'thumbnail': 're:^https?://.*\.jpg$',
31 'url': 'http://www.tudou.com/albumplay/cJAHGih4yYg.html',
32 'only_matching': True,
35 _PLAYER_URL
= 'http://js.tudouui.com/bin/lingtong/PortalPlayer_177.swf'
37 def _url_for_id(self
, id, quality
=None):
38 info_url
= "http://v2.tudou.com/f?id=" + str(id)
40 info_url
+= '&hd' + quality
41 webpage
= self
._download
_webpage
(info_url
, id, "Opening the info webpage")
42 final_url
= self
._html
_search
_regex
('>(.+?)</f>', webpage
, 'video url')
45 def _real_extract(self
, url
):
46 video_id
= self
._match
_id
(url
)
47 webpage
= self
._download
_webpage
(url
, video_id
)
49 m
= re
.search(r
'vcode:\s*[\'"](.+?)[\'"]', webpage)
53 'url
': 'youku
:' + m.group(1),
57 title = self._search_regex(
58 r",kw:\s*['\"](.+?
)[\"']", webpage, 'title
')
59 thumbnail_url = self._search_regex(
60 r",pic:\s*[\"'](.+?
)[\"']", webpage, 'thumbnail URL
', fatal=False)
62 player_url = self._search_regex(
63 r"playerUrl\s*:\s*['\"](.+?\
.swf
)[\"']",
64 webpage, 'player URL
', default=self._PLAYER_URL)
66 segs_json = self._search_regex(r'segs
: \'(.*)\'', webpage, 'segments
')
67 segments = json.loads(segs_json)
68 # It looks like the keys are the arguments that have to be passed as
69 # the hd field in the request url, we pick the higher
70 # Also, filter non-number qualities (see issue #3643).
71 quality = sorted(filter(lambda k: k.isdigit(), segments.keys()),
72 key=lambda k: int(k))[-1]
73 parts = segments[quality]
75 len_parts = len(parts)
77 self.to_screen('%s: found
%s parts
' % (video_id, len_parts))
80 final_url = self._url_for_id(part_id, quality)
81 ext = (final_url.split('?
')[0]).split('.')[-1]
87 'thumbnail
': thumbnail_url,
89 'Referer
': player_url,
92 result.append(part_info)
95 '_type
': 'multi_video
',