]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/aparat.py
   2 from __future__ 
import unicode_literals
 
   6 from .common 
import InfoExtractor
 
  13 class AparatIE(InfoExtractor
): 
  14     _VALID_URL 
= r
'^https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)' 
  17         'url': 'http://www.aparat.com/v/wP8On', 
  18         'md5': '6714e0af7e0d875c5a39c4dc4ab46ad1', 
  22             'title': 'تیم گلکسی 11 - زومیت', 
  24         # 'skip': 'Extremely unreliable', 
  27     def _real_extract(self
, url
): 
  28         video_id 
= self
._match
_id
(url
) 
  30         # Note: There is an easier-to-parse configuration at 
  31         # http://www.aparat.com/video/video/config/videohash/%video_id 
  32         # but the URL in there does not work 
  33         embed_url 
= ('http://www.aparat.com/video/video/embed/videohash/' + 
  34                      video_id 
+ '/vt/frame') 
  35         webpage 
= self
._download
_webpage
(embed_url
, video_id
) 
  37         video_urls 
= re
.findall(r
'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage
) 
  38         for i
, video_url 
in enumerate(video_urls
): 
  39             req 
= HEADRequest(video_url
) 
  40             res 
= self
._request
_webpage
( 
  41                 req
, video_id
, note
='Testing video URL %d' % i
, errnote
=False) 
  45             raise ExtractorError('No working video URLs found') 
  47         title 
= self
._search
_regex
(r
'\s+title:\s*"([^"]+)"', webpage
, 'title') 
  48         thumbnail 
= self
._search
_regex
( 
  49             r
'\s+image:\s*"([^"]+)"', webpage
, 'thumbnail', fatal
=False) 
  56             'thumbnail': thumbnail
,