]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/chaturbate.py
e3eba4be94660759537e969701f9e043fff5b73d
[youtubedl] / youtube_dl / extractor / chaturbate.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 ChaturbateIE(InfoExtractor):
10 _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?P<id>[^/?#]+)'
11 _TESTS = [{
12 'url': 'https://www.chaturbate.com/siswet19/',
13 'info_dict': {
14 'id': 'siswet19',
15 'ext': 'mp4',
16 'title': 're:^siswet19 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
17 'age_limit': 18,
18 'is_live': True,
19 },
20 'params': {
21 'skip_download': True,
22 },
23 'skip': 'Room is offline',
24 }, {
25 'url': 'https://en.chaturbate.com/siswet19/',
26 'only_matching': True,
27 }]
28
29 _ROOM_OFFLINE = 'Room is currently offline'
30
31 def _real_extract(self, url):
32 video_id = self._match_id(url)
33
34 webpage = self._download_webpage(url, video_id)
35
36 m3u8_urls = []
37
38 for m in re.finditer(
39 r'(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage):
40 m3u8_fast_url, m3u8_no_fast_url = m.group('url'), m.group(
41 'url').replace('_fast', '')
42 for m3u8_url in (m3u8_fast_url, m3u8_no_fast_url):
43 if m3u8_url not in m3u8_urls:
44 m3u8_urls.append(m3u8_url)
45
46 if not m3u8_urls:
47 error = self._search_regex(
48 [r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>',
49 r'<div[^>]+id=(["\'])defchat\1[^>]*>\s*<p><strong>(?P<error>[^<]+)<'],
50 webpage, 'error', group='error', default=None)
51 if not error:
52 if any(p in webpage for p in (
53 self._ROOM_OFFLINE, 'offline_tipping', 'tip_offline')):
54 error = self._ROOM_OFFLINE
55 if error:
56 raise ExtractorError(error, expected=True)
57 raise ExtractorError('Unable to find stream URL')
58
59 formats = []
60 for m3u8_url in m3u8_urls:
61 m3u8_id = 'fast' if '_fast' in m3u8_url else 'slow'
62 formats.extend(self._extract_m3u8_formats(
63 m3u8_url, video_id, ext='mp4',
64 # ffmpeg skips segments for fast m3u8
65 preference=-10 if m3u8_id == 'fast' else None,
66 m3u8_id=m3u8_id, fatal=False, live=True))
67 self._sort_formats(formats)
68
69 return {
70 'id': video_id,
71 'title': self._live_title(video_id),
72 'thumbnail': 'https://roomimg.stream.highwebmedia.com/ri/%s.jpg' % video_id,
73 'age_limit': self._rta_search(webpage),
74 'is_live': True,
75 'formats': formats,
76 }