diff options
Diffstat (limited to 'youtube_dl/extractor/generic.py')
| -rw-r--r-- | youtube_dl/extractor/generic.py | 16 |
1 files changed, 12 insertions, 4 deletions
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index c1792c534..489b3c7c1 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2332,12 +2332,23 @@ class GenericIE(InfoExtractor): info_dict.update(json_ld) return info_dict + # Look for HTML5 media + entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls') + if entries: + for entry in entries: + entry.update({ + 'id': video_id, + 'title': video_title, + }) + self._sort_formats(entry['formats']) + return self.playlist_result(entries) + def check_video(vurl): if YoutubeIE.suitable(vurl): return True vpath = compat_urlparse.urlparse(vurl).path vext = determine_ext(vpath) - return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml') + return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js') def filter_video(urls): return list(filter(check_video, urls)) @@ -2388,9 +2399,6 @@ class GenericIE(InfoExtractor): if m_video_type is not None: found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)) if not found: - # HTML5 video - found = re.findall(r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage) - if not found: REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)' found = re.search( r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")' |