]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/radiojavan.py
1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
12 class RadioJavanIE(InfoExtractor
):
13 _VALID_URL
= r
'https?://(?:www\.)?radiojavan\.com/videos/video/(?P<id>[^/]+)/?'
15 'url': 'http://www.radiojavan.com/videos/video/chaartaar-ashoobam',
16 'md5': 'e85208ffa3ca8b83534fca9fe19af95b',
18 'id': 'chaartaar-ashoobam',
20 'title': 'Chaartaar - Ashoobam',
21 'thumbnail': r
're:^https?://.*\.jpe?g$',
22 'upload_date': '20150215',
29 def _real_extract(self
, url
):
30 video_id
= self
._match
_id
(url
)
32 webpage
= self
._download
_webpage
(url
, video_id
)
35 'url': 'https://media.rdjavan.com/media/music_video/%s' % video_path
,
36 'format_id': '%sp' % height
,
37 'height': int(height
),
38 } for height
, video_path
in re
.findall(r
"RJ\.video(\d+)p\s*=\s*'/?([^']+)'", webpage
)]
39 self
._sort
_formats
(formats
)
41 title
= self
._og
_search
_title
(webpage
)
42 thumbnail
= self
._og
_search
_thumbnail
(webpage
)
44 upload_date
= unified_strdate(self
._search
_regex
(
45 r
'class="date_added">Date added: ([^<]+)<',
46 webpage
, 'upload date', fatal
=False))
48 view_count
= str_to_int(self
._search
_regex
(
49 r
'class="views">Plays: ([\d,]+)',
50 webpage
, 'view count', fatal
=False))
51 like_count
= str_to_int(self
._search
_regex
(
52 r
'class="rating">([\d,]+) likes',
53 webpage
, 'like count', fatal
=False))
54 dislike_count
= str_to_int(self
._search
_regex
(
55 r
'class="rating">([\d,]+) dislikes',
56 webpage
, 'dislike count', fatal
=False))
61 'thumbnail': thumbnail
,
62 'upload_date': upload_date
,
63 'view_count': view_count
,
64 'like_count': like_count
,
65 'dislike_count': dislike_count
,