]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/c56.py
2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
7 from ..utils
import js_to_json
10 class C56IE(InfoExtractor
):
11 _VALID_URL
= r
'https?://(?:(?:www|player)\.)?56\.com/(?:.+?/)?(?:v_|(?:play_album.+-))(?P<textid>.+?)\.(?:html|swf)'
14 'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html',
15 'md5': 'e59995ac63d0457783ea05f93f12a866',
19 'title': '网事知多少 第32期:车怒',
23 'url': 'http://www.56.com/u47/v_MTM5NjQ5ODc2.html',
33 def _real_extract(self
, url
):
34 mobj
= re
.match(self
._VALID
_URL
, url
, flags
=re
.VERBOSE
)
35 text_id
= mobj
.group('textid')
37 webpage
= self
._download
_webpage
(url
, text_id
)
38 sohu_video_info_str
= self
._search
_regex
(
39 r
'var\s+sohuVideoInfo\s*=\s*({[^}]+});', webpage
, 'Sohu video info', default
=None)
40 if sohu_video_info_str
:
41 sohu_video_info
= self
._parse
_json
(
42 sohu_video_info_str
, text_id
, transform_source
=js_to_json
)
43 return self
.url_result(sohu_video_info
['url'], 'Sohu')
45 page
= self
._download
_json
(
46 'http://vxml.56.com/json/%s/' % text_id
, text_id
, 'Downloading video info')
52 'format_id': f
['type'],
53 'filesize': int(f
['filesize']),
55 } for f
in info
['rfiles']
57 self
._sort
_formats
(formats
)
61 'title': info
['Subject'],
62 'duration': int(info
['duration']) / 1000.0,
64 'thumbnail': info
.get('bimg') or info
.get('img'),