]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tube8.py
1 from __future__
import unicode_literals
9 from .keezmovies
import KeezMoviesIE
12 class Tube8IE(KeezMoviesIE
):
13 _VALID_URL
= r
'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/(?P<id>\d+)'
15 'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
16 'md5': '65e20c48e6abff62ed0c3965fff13a39',
19 'display_id': 'kasia-music-video',
21 'description': 'hot teen Kasia grinding',
22 'uploader': 'unknown',
23 'title': 'Kasia music video',
26 'categories': ['Teen'],
30 'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/',
31 'only_matching': True,
35 def _extract_urls(webpage
):
37 r
'<iframe[^>]+\bsrc=["\']((?
:https?
:)?
//(?
:www\
.)?tube8\
.com
/embed
/(?
:[^
/]+/)+\d
+)',
40 def _real_extract(self, url):
41 webpage, info = self._extract_info(url)
44 info['title
'] = self._html_search_regex(
45 r'videoTitle\s
*=\s
*"([^"]+)', webpage, 'title
')
47 description = self._html_search_regex(
48 r'>Description
:</strong
>\s
*(.+?
)\s
*<', webpage, 'description
', fatal=False)
49 uploader = self._html_search_regex(
50 r'<span
class="username">\s
*(.+?
)\s
*<',
51 webpage, 'uploader
', fatal=False)
53 like_count = int_or_none(self._search_regex(
54 r'rupVar\s
*=\s
*"(\d+)"', webpage, 'like count
', fatal=False))
55 dislike_count = int_or_none(self._search_regex(
56 r'rdownVar\s
*=\s
*"(\d+)"', webpage, 'dislike count
', fatal=False))
57 view_count = str_to_int(self._search_regex(
58 r'<strong
>Views
: </strong
>([\d
,\
.]+)\s
*</li
>',
59 webpage, 'view count
', fatal=False))
60 comment_count = str_to_int(self._search_regex(
61 r'<span
id="allCommentsCount">(\d
+)</span
>',
62 webpage, 'comment count
', fatal=False))
64 category = self._search_regex(
65 r'Category
:\s
*</strong
>\s
*<a
[^
>]+href
=[^
>]+>([^
<]+)',
66 webpage, 'category
', fatal=False)
67 categories = [category] if category else None
69 tags_str = self._search_regex(
70 r'(?s
)Tags
:\s
*</strong
>(.+?
)</(?
!a
)',
71 webpage, 'tags
', fatal=False)
72 tags = [t for t in re.findall(
73 r'<a
[^
>]+href
=[^
>]+>([^
<]+)', tags_str)] if tags_str else None
76 'description
': description,
78 'view_count
': view_count,
79 'like_count
': like_count,
80 'dislike_count
': dislike_count,
81 'comment_count
': comment_count,
82 'categories
': categories,