X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9d6a3ba754469c85b7f0f88714203f99ac69087a..39393b81acfaf4045fb7f20454a0226f0dc9142e:/youtube_dl/extractor/chaturbate.py?ds=inline diff --git a/youtube_dl/extractor/chaturbate.py b/youtube_dl/extractor/chaturbate.py index e2b828d..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<id>[^/?#]+)' + _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?:fullvideo/?\?.*?\bb=)?(?P<id>[^/?&#]+)' _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, @@ -32,14 +39,34 @@ class ChaturbateIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage( - url, video_id, headers=self.geo_verification_headers()) + 'https://chaturbate.com/%s/' % video_id, video_id, + headers=self.geo_verification_headers()) - m3u8_urls = [] + found_m3u8_urls = [] + + data = self._parse_json( + self._search_regex( + r'initialRoomDossier\s*=\s*(["\'])(?P<value>(?:(?!\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) - for m in re.finditer( - r'(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage): - m3u8_fast_url, m3u8_no_fast_url = m.group('url'), m.group( - 'url').replace('_fast', '') + if not found_m3u8_urls: + for m in re.finditer( + r'(\\u002[27])(?P<url>http.+?\.m3u8.*?)\1', webpage): + found_m3u8_urls.append(lowercase_escape(m.group('url'))) + + if not found_m3u8_urls: + for m in re.finditer( + r'(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage): + found_m3u8_urls.append(m.group('url')) + + 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) @@ -59,7 +86,12 @@ class ChaturbateIE(InfoExtractor): formats = [] for m3u8_url in m3u8_urls: - m3u8_id = 'fast' if '_fast' in m3u8_url else 'slow' + 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