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': r're:https?://.*\.jpg$',
29 'url': 'http://www.drtuber.com/embed/489939',
30 'only_matching': True,
34 def _extract_urls(webpage):
36 r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?drtuber\.com/embed/\d+)',
39 def _real_extract(self, url):
40 mobj = re.match(self._VALID_URL, url)
41 video_id = mobj.group('id')
42 display_id = mobj.group('display_id') or video_id
44 webpage = self._download_webpage(
45 'http://www.drtuber.com/video/%s' % video_id, display_id)
47 video_data = self._download_json(
48 'http://www.drtuber.com/player_config_json/', video_id, query={
56 for format_id, video_url in video_data['files'].items():
59 'format_id': format_id,
60 'quality': 2 if format_id == 'hq' else 1,
63 self._sort_formats(formats)
65 title = self._html_search_regex(
66 (r'class="title_watch"[^>]*><(?:p|h\d+)[^>]*>([^<]+)<',
67 r'<p[^>]+class="title_substrate">([^<]+)</p>',
68 r'<title>([^<]+) - \d+'),
71 thumbnail = self._html_search_regex(
73 webpage, 'thumbnail', fatal=False)
75 def extract_count(id_, name, default=NO_DEFAULT):
76 return str_to_int(self._html_search_regex(
77 r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
78 webpage, '%s count' % name, default=default, fatal=False))
80 like_count = extract_count('rate_likes', 'like')
81 dislike_count = extract_count('rate_dislikes', 'dislike', default=None)
82 comment_count = extract_count('comments_count', 'comment')
84 cats_str = self._search_regex(
85 r'<div[^>]+class="categories_list">(.+?)</div>',
86 webpage, 'categories', fatal=False)
87 categories = [] if not cats_str else re.findall(
88 r'<a title="([^"]+)"', cats_str)
92 'display_id': display_id,
95 'thumbnail': thumbnail,
96 'like_count': like_count,
97 'dislike_count': dislike_count,
98 'comment_count': comment_count,
99 'categories': categories,
100 'age_limit': self._rta_search(webpage),