X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/575f75429e2e479957d006a26940f4a5a51347ce..2dbb05e5969fc6d6b5d51b6bb9576b03fb63d936:/youtube_dl/extractor/chaturbate.py?ds=inline diff --git a/youtube_dl/extractor/chaturbate.py b/youtube_dl/extractor/chaturbate.py index 8fbc91c..a459dcb 100644 --- a/youtube_dl/extractor/chaturbate.py +++ b/youtube_dl/extractor/chaturbate.py @@ -3,11 +3,15 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ExtractorError +from ..utils import ( + ExtractorError, + lowercase_escape, + url_or_none, +) class ChaturbateIE(InfoExtractor): - _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?P[^/?#]+)' + _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?:fullvideo/?\?.*?\bb=)?(?P[^/?&#]+)' _TESTS = [{ 'url': 'https://www.chaturbate.com/siswet19/', 'info_dict': { @@ -21,6 +25,9 @@ class ChaturbateIE(InfoExtractor): 'skip_download': True, }, 'skip': 'Room is offline', + }, { + 'url': 'https://chaturbate.com/fullvideo/?b=caylin', + 'only_matching': True, }, { 'url': 'https://en.chaturbate.com/siswet19/', 'only_matching': True, @@ -31,12 +38,40 @@ class ChaturbateIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage( + 'https://chaturbate.com/%s/' % video_id, video_id, + headers=self.geo_verification_headers()) + + found_m3u8_urls = [] + + data = self._parse_json( + self._search_regex( + r'initialRoomDossier\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', + webpage, 'data', default='{}', group='value'), + video_id, transform_source=lowercase_escape, fatal=False) + if data: + m3u8_url = url_or_none(data.get('hls_source')) + if m3u8_url: + found_m3u8_urls.append(m3u8_url) + + if not found_m3u8_urls: + for m in re.finditer( + r'(\\u002[27])(?Phttp.+?\.m3u8.*?)\1', webpage): + found_m3u8_urls.append(lowercase_escape(m.group('url'))) + + if not found_m3u8_urls: + for m in re.finditer( + r'(["\'])(?Phttp.+?\.m3u8.*?)\1', webpage): + found_m3u8_urls.append(m.group('url')) - m3u8_formats = [(m.group('id').lower(), m.group('url')) for m in re.finditer( - r'hlsSource(?P.+?)\s*=\s*(?P["\'])(?Phttp.+?)(?P=q)', webpage)] + m3u8_urls = [] + for found_m3u8_url in found_m3u8_urls: + m3u8_fast_url, m3u8_no_fast_url = found_m3u8_url, found_m3u8_url.replace('_fast', '') + for m3u8_url in (m3u8_fast_url, m3u8_no_fast_url): + if m3u8_url not in m3u8_urls: + m3u8_urls.append(m3u8_url) - if not m3u8_formats: + if not m3u8_urls: error = self._search_regex( [r']+class=(["\'])desc_span\1[^>]*>(?P[^<]+)', r']+id=(["\'])defchat\1[^>]*>\s*

(?P[^<]+)<'], @@ -50,7 +85,13 @@ class ChaturbateIE(InfoExtractor): raise ExtractorError('Unable to find stream URL') formats = [] - for m3u8_id, m3u8_url in m3u8_formats: + for m3u8_url in m3u8_urls: + for known_id in ('fast', 'slow'): + if '_%s' % known_id in m3u8_url: + m3u8_id = known_id + break + else: + m3u8_id = None formats.extend(self._extract_m3u8_formats( m3u8_url, video_id, ext='mp4', # ffmpeg skips segments for fast m3u8