1 from __future__ import unicode_literals
5 from .common import InfoExtractor
12 class DrTuberIE(InfoExtractor):
13 _VALID_URL = r'https?://(?:www\.)?drtuber\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[\w-]+))?'
15 'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
16 'md5': '93e680cf2536ad0dfb7e74d94a89facd',
19 'display_id': 'hot-perky-blonde-naked-golf',
21 'title': 'hot perky blonde naked golf',
24 'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
25 'thumbnail': 're:https?://.*\.jpg$',
29 'url': 'http://www.drtuber.com/embed/489939',
30 'only_matching': True,
33 def _real_extract(self, url):
34 mobj = re.match(self._VALID_URL, url)
35 video_id = mobj.group('id')
36 display_id = mobj.group('display_id') or video_id
38 webpage = self._download_webpage(
39 'http://www.drtuber.com/video/%s' % video_id, display_id)
41 video_url = self._html_search_regex(
42 r'<source src="([^"]+)"', webpage, 'video URL')
44 title = self._html_search_regex(
45 (r'class="title_watch"[^>]*><p>([^<]+)<',
46 r'<p[^>]+class="title_substrate">([^<]+)</p>',
47 r'<title>([^<]+) - \d+'),
50 thumbnail = self._html_search_regex(
52 webpage, 'thumbnail', fatal=False)
54 def extract_count(id_, name, default=NO_DEFAULT):
55 return str_to_int(self._html_search_regex(
56 r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
57 webpage, '%s count' % name, default=default, fatal=False))
59 like_count = extract_count('rate_likes', 'like')
60 dislike_count = extract_count('rate_dislikes', 'dislike', default=None)
61 comment_count = extract_count('comments_count', 'comment')
63 cats_str = self._search_regex(
64 r'<div[^>]+class="categories_list">(.+?)</div>',
65 webpage, 'categories', fatal=False)
66 categories = [] if not cats_str else re.findall(
67 r'<a title="([^"]+)"', cats_str)
71 'display_id': display_id,
74 'thumbnail': thumbnail,
75 'like_count': like_count,
76 'dislike_count': dislike_count,
77 'comment_count': comment_count,
78 'categories': categories,
79 'age_limit': self._rta_search(webpage),