diff options
| author | Sergey M․ <dstftw@gmail.com> | 2017-04-09 01:39:40 +0700 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2017-04-09 01:39:40 +0700 |
| commit | a6f7263cf421d9156048596cca0552e027e70788 (patch) | |
| tree | fc9f5c9fd850ccbe3406ae4892f01680ccf9952b | |
| parent | 43724365048755adbea8bbff05708903ea52e1a8 (diff) | |
[chaturbate] Fix extraction (closes #12665)
| -rw-r--r-- | youtube_dl/extractor/chaturbate.py | 16 |
1 files changed, 12 insertions, 4 deletions
diff --git a/youtube_dl/extractor/chaturbate.py b/youtube_dl/extractor/chaturbate.py index 8fbc91c1f..e3eba4be9 100644 --- a/youtube_dl/extractor/chaturbate.py +++ b/youtube_dl/extractor/chaturbate.py @@ -33,10 +33,17 @@ class ChaturbateIE(InfoExtractor): webpage = self._download_webpage(url, video_id) - m3u8_formats = [(m.group('id').lower(), m.group('url')) for m in re.finditer( - r'hlsSource(?P<id>.+?)\s*=\s*(?P<q>["\'])(?P<url>http.+?)(?P=q)', webpage)] + m3u8_urls = [] - if not m3u8_formats: + 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', '') + 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_urls: error = self._search_regex( [r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>', r'<div[^>]+id=(["\'])defchat\1[^>]*>\s*<p><strong>(?P<error>[^<]+)<'], @@ -50,7 +57,8 @@ 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: + m3u8_id = 'fast' if '_fast' in m3u8_url else 'slow' formats.extend(self._extract_m3u8_formats( m3u8_url, video_id, ext='mp4', # ffmpeg skips segments for fast m3u8 |