diff options
Diffstat (limited to 'yt_dlp/extractor/common.py')
| -rw-r--r-- | yt_dlp/extractor/common.py | 18 |
1 files changed, 12 insertions, 6 deletions
diff --git a/yt_dlp/extractor/common.py b/yt_dlp/extractor/common.py index ebeca4395..6a451c20b 100644 --- a/yt_dlp/extractor/common.py +++ b/yt_dlp/extractor/common.py @@ -1343,7 +1343,7 @@ class InfoExtractor: return self._og_search_property('url', html, **kargs) def _html_extract_title(self, html, name='title', *, fatal=False, **kwargs): - return self._html_search_regex(r'(?s)<title>([^<]+)</title>', html, name, fatal=fatal, **kwargs) + return self._html_search_regex(r'(?s)<title\b[^>]*>([^<]+)</title>', html, name, fatal=fatal, **kwargs) def _html_search_meta(self, name, html, display_name=None, fatal=False, **kwargs): name = variadic(name) @@ -1509,8 +1509,9 @@ class InfoExtractor: 'url': url_or_none(e.get('contentUrl')), 'title': unescapeHTML(e.get('name')), 'description': unescapeHTML(e.get('description')), - 'thumbnails': [{'url': url_or_none(url)} - for url in variadic(traverse_obj(e, 'thumbnailUrl', 'thumbnailURL'))], + 'thumbnails': [{'url': url} + for url in variadic(traverse_obj(e, 'thumbnailUrl', 'thumbnailURL')) + if url_or_none(url)], 'duration': parse_duration(e.get('duration')), 'timestamp': unified_timestamp(e.get('uploadDate')), # author can be an instance of 'Organization' or 'Person' types. @@ -2803,13 +2804,18 @@ class InfoExtractor: mime_type = representation_attrib['mimeType'] content_type = representation_attrib.get('contentType', mime_type.split('/')[0]) - codecs = parse_codecs(representation_attrib.get('codecs', '')) + codec_str = representation_attrib.get('codecs', '') + # Some kind of binary subtitle found in some youtube livestreams + if mime_type == 'application/x-rawcc': + codecs = {'scodec': codec_str} + else: + codecs = parse_codecs(codec_str) if content_type not in ('video', 'audio', 'text'): if mime_type == 'image/jpeg': content_type = mime_type - elif codecs['vcodec'] != 'none': + elif codecs.get('vcodec', 'none') != 'none': content_type = 'video' - elif codecs['acodec'] != 'none': + elif codecs.get('acodec', 'none') != 'none': content_type = 'audio' elif codecs.get('scodec', 'none') != 'none': content_type = 'text' |