]>
Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/drtuber.py
1 from __future__
import unicode_literals
5 from .common
import InfoExtractor
14 class DrTuberIE(InfoExtractor
):
15 _VALID_URL
= r
'https?://(?:(?:www|m)\.)?drtuber\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[\w-]+))?'
17 'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
18 'md5': '93e680cf2536ad0dfb7e74d94a89facd',
21 'display_id': 'hot-perky-blonde-naked-golf',
23 'title': 'hot perky blonde naked golf',
26 'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
27 'thumbnail': r
're:https?://.*\.jpg$',
31 'url': 'http://www.drtuber.com/embed/489939',
32 'only_matching': True,
34 'url': 'http://m.drtuber.com/video/3893529/lingerie-blowjob-from-beautiful-teen',
35 'only_matching': True,
39 def _extract_urls(webpage
):
41 r
'<iframe[^>]+?src=["\'](?P
<url
>(?
:https?
:)?
//(?
:www\
.)?drtuber\
.com
/embed
/\d
+)',
44 def _real_extract(self, url):
45 mobj = re.match(self._VALID_URL, url)
46 video_id = mobj.group('id')
47 display_id = mobj.group('display_id
') or video_id
49 webpage = self._download_webpage(
50 'http
://www
.drtuber
.com
/video
/%s' % video_id, display_id)
52 video_data = self._download_json(
53 'http
://www
.drtuber
.com
/player_config_json
/', video_id, query={
61 for format_id, video_url in video_data['files
'].items():
64 'format_id
': format_id,
65 'quality
': 2 if format_id == 'hq
' else 1,
68 self._sort_formats(formats)
70 duration = int_or_none(video_data.get('duration
')) or parse_duration(
71 video_data.get('duration_format
'))
73 title = self._html_search_regex(
74 (r'<h1
[^
>]+class=["\']title[^>]+>([^<]+)',
75 r'<title>([^<]+)\s*@\s+DrTuber',
76 r'class="title_watch
"[^>]*><(?:p|h\d+)[^>]*>([^<]+)<',
77 r'<p[^>]+class="title_substrate
">([^<]+)</p>',
78 r'<title>([^<]+) - \d+'),
81 thumbnail = self._html_search_regex(
83 webpage, 'thumbnail
', fatal=False)
85 def extract_count(id_, name, default=NO_DEFAULT):
86 return str_to_int(self._html_search_regex(
87 r'<span
[^
>]+(?
:class|
id)="%s"[^
>]*>([\d
,\
.]+)</span
>' % id_,
88 webpage, '%s count
' % name, default=default, fatal=False))
90 like_count = extract_count('rate_likes
', 'like
')
91 dislike_count = extract_count('rate_dislikes
', 'dislike
', default=None)
92 comment_count = extract_count('comments_count
', 'comment
')
94 cats_str = self._search_regex(
95 r'<div
[^
>]+class="categories_list">(.+?
)</div
>',
96 webpage, 'categories
', fatal=False)
97 categories = [] if not cats_str else re.findall(
98 r'<a title
="([^"]+)"', cats_str)
102 'display_id': display_id,
105 'thumbnail': thumbnail,
106 'like_count': like_count,
107 'dislike_count': dislike_count,
108 'comment_count': comment_count,
109 'categories': categories,
110 'age_limit': self._rta_search(webpage),
111 'duration': duration,