[spankbang] Detect unavailable videos (closes #14644)
[youtube-dl] / youtube_dl / extractor / spankbang.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..utils import ExtractorError
7
8
9 class SpankBangIE(InfoExtractor):
10     _VALID_URL = r'https?://(?:(?:www|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video'
11     _TESTS = [{
12         'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
13         'md5': '1cc433e1d6aa14bc376535b8679302f7',
14         'info_dict': {
15             'id': '3vvn',
16             'ext': 'mp4',
17             'title': 'fantasy solo',
18             'description': 'Watch fantasy solo free HD porn video - 05 minutes - dillion harper masturbates on a bed free adult movies.',
19             'thumbnail': r're:^https?://.*\.jpg$',
20             'uploader': 'silly2587',
21             'age_limit': 18,
22         }
23     }, {
24         # 480p only
25         'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
26         'only_matching': True,
27     }, {
28         # no uploader
29         'url': 'http://spankbang.com/lklg/video/sex+with+anyone+wedding+edition+2',
30         'only_matching': True,
31     }]
32
33     def _real_extract(self, url):
34         video_id = self._match_id(url)
35         webpage = self._download_webpage(url, video_id)
36
37         if re.search(r'<[^>]+\bid=["\']video_removed', webpage):
38             raise ExtractorError(
39                 'Video %s is not available' % video_id, expected=True)
40
41         stream_key = self._html_search_regex(
42             r'''var\s+stream_key\s*=\s*['"](.+?)['"]''',
43             webpage, 'stream key')
44
45         formats = [{
46             'url': 'http://spankbang.com/_%s/%s/title/%sp__mp4' % (video_id, stream_key, height),
47             'ext': 'mp4',
48             'format_id': '%sp' % height,
49             'height': int(height),
50         } for height in re.findall(r'<(?:span|li|p)[^>]+[qb]_(\d+)p', webpage)]
51         self._check_formats(formats, video_id)
52         self._sort_formats(formats)
53
54         title = self._html_search_regex(
55             r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title')
56         description = self._og_search_description(webpage)
57         thumbnail = self._og_search_thumbnail(webpage)
58         uploader = self._search_regex(
59             r'class="user"[^>]*><img[^>]+>([^<]+)',
60             webpage, 'uploader', default=None)
61
62         age_limit = self._rta_search(webpage)
63
64         return {
65             'id': video_id,
66             'title': title,
67             'description': description,
68             'thumbnail': thumbnail,
69             'uploader': uploader,
70             'formats': formats,
71             'age_limit': age_limit,
72         }