]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/sohu.py
6 from .common
import InfoExtractor
7 from ..utils
import ExtractorError
10 class SohuIE(InfoExtractor
):
11 _VALID_URL
= r
'https?://(?P<mytv>my\.)?tv\.sohu\.com/.+?/(?(mytv)|n)(?P<id>\d+)\.shtml.*?'
14 u
'url': u
'http://tv.sohu.com/20130724/n382479172.shtml#super',
15 u
'file': u
'382479172.mp4',
16 u
'md5': u
'bde8d9a6ffd82c63a1eefaef4eeefec7',
18 u
'title': u
'MV:Far East Movement《The Illest》',
20 u
'skip': u
'Only available from China',
23 def _real_extract(self
, url
):
25 def _fetch_data(vid_id
, mytv
=False):
27 base_data_url
= 'http://my.tv.sohu.com/play/videonew.do?vid='
29 base_data_url
= u
'http://hot.vrs.sohu.com/vrs_flash.action?vid='
30 data_url
= base_data_url
+ str(vid_id
)
31 data_json
= self
._download
_webpage
(
33 note
=u
'Downloading JSON data for ' + str(vid_id
))
34 return json
.loads(data_json
)
36 mobj
= re
.match(self
._VALID
_URL
, url
)
37 video_id
= mobj
.group('id')
38 mytv
= mobj
.group('mytv') is not None
40 webpage
= self
._download
_webpage
(url
, video_id
)
41 raw_title
= self
._html
_search
_regex
(r
'(?s)<title>(.+?)</title>',
42 webpage
, u
'video title')
43 title
= raw_title
.partition('-')[0].strip()
45 vid
= self
._html
_search
_regex
(r
'var vid ?= ?["\'](\d
+)["\']', webpage,
47 data = _fetch_data(vid, mytv)
49 QUALITIES = ('ori', 'super', 'high', 'nor')
50 vid_ids = [data['data'][q + 'Vid']
52 if data['data'][q + 'Vid'] != 0]
54 raise ExtractorError(u'No formats available for this video')
56 # For now, we just pick the highest available quality
59 format_data = data if vid == vid_id else _fetch_data(vid_id, mytv)
60 part_count = format_data['data']['totalBlocks']
61 allot = format_data['allot']
62 prot = format_data['prot']
63 clipsURL = format_data['data']['clipsURL']
64 su = format_data['data']['su']
67 for i in range(part_count):
68 part_url = ('http://%s/?prot=%s&file=%s&new=%s' %
69 (allot, prot, clipsURL[i], su[i]))
70 part_str = self._download_webpage(
72 note=u'Downloading part %d of %d' % (i+1, part_count))
74 part_info = part_str.split('|')
75 video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3])
78 'id': '%s_part%02d' % (video_id, i + 1),
83 playlist.append(video_info)
85 if len(playlist) == 1: