1 from __future__ import unicode_literals
3 from .common import InfoExtractor
14 class BeegIE(InfoExtractor):
15 _VALID_URL = r'https?://(?:www\.)?beeg\.(?:com|porn(?:/video)?)/(?P<id>\d+)'
18 'url': 'http://beeg.com/5416503',
19 'md5': 'a1a1b1a8bc70a89e49ccfd113aed0820',
23 'title': 'Sultry Striptease',
24 'description': 'md5:d22219c09da287c14bed3d6c37ce4bc2',
25 'timestamp': 1391813355,
26 'upload_date': '20140207',
33 'url': 'https://beeg.com/1941093077?t=911-1391',
34 'only_matching': True,
37 'url': 'https://beeg.com/1277207756',
38 'only_matching': True,
40 'url': 'https://beeg.porn/video/5416503',
41 'only_matching': True,
43 'url': 'https://beeg.porn/5416503',
44 'only_matching': True,
47 def _real_extract(self, url):
48 video_id = self._match_id(url)
50 webpage = self._download_webpage(url, video_id)
52 beeg_version = self._search_regex(
53 r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version',
54 default='1546225636701')
56 if len(video_id) >= 10:
60 qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
61 t = qs.get('t', [''])[0].split('-')
70 for api_path in ('', 'api.'):
71 video = self._download_json(
72 'https://%sbeeg.com/api/v6/%s/video/%s'
73 % (api_path, beeg_version, video_id), video_id,
74 fatal=api_path == 'api.', query=query)
79 for format_id, video_url in video.items():
82 height = self._search_regex(
83 r'^(\d+)[pP]$', format_id, 'height', default=None)
87 'url': self._proto_relative_url(
88 video_url.replace('{DATA_MARKERS}', 'data=pc_XX__%s_0' % beeg_version), 'https:'),
89 'format_id': format_id,
90 'height': int(height),
92 self._sort_formats(formats)
94 title = video['title']
95 video_id = compat_str(video.get('id') or video_id)
96 display_id = video.get('code')
97 description = video.get('desc')
98 series = video.get('ps_name')
100 timestamp = unified_timestamp(video.get('date'))
101 duration = int_or_none(video.get('duration'))
103 tags = [tag.strip() for tag in video['tags'].split(',')] if video.get('tags') else None
107 'display_id': display_id,
109 'description': description,
111 'timestamp': timestamp,
112 'duration': duration,
115 'age_limit': self._rta_search(webpage),