]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/drtuber.py
Start new release.
[youtubedl] / youtube_dl / extractor / drtuber.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..utils import (
7 NO_DEFAULT,
8 str_to_int,
9 )
10
11
12 class DrTuberIE(InfoExtractor):
13 _VALID_URL = r'https?://(?:(?:www|m)\.)?drtuber\.com/(?:video|embed)/(?P<id>\d+)(?:/(?P<display_id>[\w-]+))?'
14 _TESTS = [{
15 'url': 'http://www.drtuber.com/video/1740434/hot-perky-blonde-naked-golf',
16 'md5': '93e680cf2536ad0dfb7e74d94a89facd',
17 'info_dict': {
18 'id': '1740434',
19 'display_id': 'hot-perky-blonde-naked-golf',
20 'ext': 'mp4',
21 'title': 'hot perky blonde naked golf',
22 'like_count': int,
23 'comment_count': int,
24 'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
25 'thumbnail': r're:https?://.*\.jpg$',
26 'age_limit': 18,
27 }
28 }, {
29 'url': 'http://www.drtuber.com/embed/489939',
30 'only_matching': True,
31 }, {
32 'url': 'http://m.drtuber.com/video/3893529/lingerie-blowjob-from-beautiful-teen',
33 'only_matching': True,
34 }]
35
36 @staticmethod
37 def _extract_urls(webpage):
38 return re.findall(
39 r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?drtuber\.com/embed/\d+)',
40 webpage)
41
42 def _real_extract(self, url):
43 mobj = re.match(self._VALID_URL, url)
44 video_id = mobj.group('id')
45 display_id = mobj.group('display_id') or video_id
46
47 webpage = self._download_webpage(
48 'http://www.drtuber.com/video/%s' % video_id, display_id)
49
50 video_data = self._download_json(
51 'http://www.drtuber.com/player_config_json/', video_id, query={
52 'vid': video_id,
53 'embed': 0,
54 'aid': 0,
55 'domain_id': 0,
56 })
57
58 formats = []
59 for format_id, video_url in video_data['files'].items():
60 if video_url:
61 formats.append({
62 'format_id': format_id,
63 'quality': 2 if format_id == 'hq' else 1,
64 'url': video_url
65 })
66 self._sort_formats(formats)
67
68 title = self._html_search_regex(
69 (r'<h1[^>]+class=["\']title[^>]+>([^<]+)',
70 r'<title>([^<]+)\s*@\s+DrTuber',
71 r'class="title_watch"[^>]*><(?:p|h\d+)[^>]*>([^<]+)<',
72 r'<p[^>]+class="title_substrate">([^<]+)</p>',
73 r'<title>([^<]+) - \d+'),
74 webpage, 'title')
75
76 thumbnail = self._html_search_regex(
77 r'poster="([^"]+)"',
78 webpage, 'thumbnail', fatal=False)
79
80 def extract_count(id_, name, default=NO_DEFAULT):
81 return str_to_int(self._html_search_regex(
82 r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
83 webpage, '%s count' % name, default=default, fatal=False))
84
85 like_count = extract_count('rate_likes', 'like')
86 dislike_count = extract_count('rate_dislikes', 'dislike', default=None)
87 comment_count = extract_count('comments_count', 'comment')
88
89 cats_str = self._search_regex(
90 r'<div[^>]+class="categories_list">(.+?)</div>',
91 webpage, 'categories', fatal=False)
92 categories = [] if not cats_str else re.findall(
93 r'<a title="([^"]+)"', cats_str)
94
95 return {
96 'id': video_id,
97 'display_id': display_id,
98 'formats': formats,
99 'title': title,
100 'thumbnail': thumbnail,
101 'like_count': like_count,
102 'dislike_count': dislike_count,
103 'comment_count': comment_count,
104 'categories': categories,
105 'age_limit': self._rta_search(webpage),
106 }