]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/hellporno.py
1 from .common
import InfoExtractor
10 class HellPornoIE(InfoExtractor
):
11 _VALID_URL
= r
'https?://(?:www\.)?hellporno\.(?:com/videos|net/v)/(?P<id>[^/]+)'
13 'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
14 'md5': 'f0a46ebc0bed0c72ae8fe4629f7de5f3',
17 'display_id': 'dixie-is-posing-with-naked-ass-very-erotic',
19 'title': 'Dixie is posing with naked ass very erotic',
20 'description': 'md5:9a72922749354edb1c4b6e540ad3d215',
22 'thumbnail': r
're:https?://.*\.jpg$',
24 'timestamp': 1398762720,
25 'upload_date': '20140429',
30 'url': 'http://hellporno.net/v/186271/',
31 'only_matching': True,
34 def _real_extract(self
, url
):
35 display_id
= self
._match
_id
(url
)
37 webpage
= self
._download
_webpage
(url
, display_id
)
39 title
= remove_end(self
._html
_extract
_title
(webpage
), ' - Hell Porno')
41 info
= self
._parse
_html
5_media
_entries
(url
, webpage
, display_id
)[0]
42 self
._sort
_formats
(info
['formats'])
44 video_id
= self
._search
_regex
(
45 (r
'chs_object\s*=\s*["\'](\d
+)',
46 r'params\
[["\']video_id["\']\
]\s
*=\s
*(\d
+)'), webpage, 'video
id',
48 description = self._search_regex(
49 r'class=["\']desc_video_view_v2[^>]+>([^<]+)', webpage,
50 'description', fatal=False)
53 for c in self._html_search_meta(
54 'keywords', webpage, 'categories', default='').split(',')
56 duration = int_or_none(self._og_search_property(
57 'video:duration', webpage, fatal=False))
58 timestamp = unified_timestamp(self._og_search_property(
59 'video:release_date', webpage, fatal=False))
60 view_count = int_or_none(self._search_regex(
61 r'>Views\s+(\d+)', webpage, 'view count', fatal=False))
63 return merge_dicts(info, {
65 'display_id': display_id,
67 'description': description,
68 'categories': categories,
70 'timestamp': timestamp,
71 'view_count': view_count,