]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/drtuber.py
1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
6 from ..utils
import str_to_int
9 class DrTuberIE(InfoExtractor
):
10 _VALID_URL
= r
'https?://(?:www\.)?drtuber\.com/video/(?P<id>\d+)/(?P<display_id>[\w-]+)'
12 'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
13 'md5': '93e680cf2536ad0dfb7e74d94a89facd',
16 'display_id': 'hot-perky-blonde-naked-golf',
18 'title': 'Hot Perky Blonde Naked Golf',
22 'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
23 'thumbnail': 're:https?://.*\.jpg$',
28 def _real_extract(self
, url
):
29 mobj
= re
.match(self
._VALID
_URL
, url
)
30 video_id
= mobj
.group('id')
31 display_id
= mobj
.group('display_id')
33 webpage
= self
._download
_webpage
(url
, display_id
)
35 video_url
= self
._html
_search
_regex
(
36 r
'<source src="([^"]+)"', webpage
, 'video URL')
38 title
= self
._html
_search
_regex
(
39 r
'<title>([^<]+)\s*-\s*Free', webpage
, 'title')
41 thumbnail
= self
._html
_search
_regex
(
43 webpage
, 'thumbnail', fatal
=False)
45 like_count
= str_to_int(self
._html
_search
_regex
(
46 r
'<span id="rate_likes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
47 webpage
, 'like count', fatal
=False))
48 dislike_count
= str_to_int(self
._html
_search
_regex
(
49 r
'<span id="rate_dislikes">\s*<img[^>]+>\s*<span>([\d,\.]+)</span>',
50 webpage
, 'like count', fatal
=False))
51 comment_count
= str_to_int(self
._html
_search
_regex
(
52 r
'<span class="comments_count">([\d,\.]+)</span>',
53 webpage
, 'comment count', fatal
=False))
55 cats_str
= self
._search
_regex
(
56 r
'<span>Categories:</span><div>(.+?)</div>', webpage
, 'categories', fatal
=False)
57 categories
= [] if not cats_str
else re
.findall(r
'<a title="([^"]+)"', cats_str
)
61 'display_id': display_id
,
64 'thumbnail': thumbnail
,
65 'like_count': like_count
,
66 'dislike_count': dislike_count
,
67 'comment_count': comment_count
,
68 'categories': categories
,
69 'age_limit': self
._rta
_search
(webpage
),