From f856816b940d95e995c2b9995d01097ab144a1af Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 23 May 2019 23:52:11 +0700 Subject: [PATCH] [extractor/common] Strip src attribute for HTML5 entries code (closes #18485, closes #21169) --- youtube_dl/extractor/common.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 937237b3f..9c3e9eec6 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -67,6 +67,7 @@ from ..utils import ( sanitized_Request, sanitize_filename, str_or_none, + strip_or_none, unescapeHTML, unified_strdate, unified_timestamp, @@ -2480,7 +2481,7 @@ class InfoExtractor(object): 'subtitles': {}, } media_attributes = extract_attributes(media_tag) - src = media_attributes.get('src') + src = strip_or_none(media_attributes.get('src')) if src: _, formats = _media_formats(src, media_type) media_info['formats'].extend(formats) @@ -2490,7 +2491,7 @@ class InfoExtractor(object): s_attr = extract_attributes(source_tag) # data-video-src and data-src are non standard but seen # several times in the wild - src = dict_get(s_attr, ('src', 'data-video-src', 'data-src')) + src = strip_or_none(dict_get(s_attr, ('src', 'data-video-src', 'data-src'))) if not src: continue f = parse_content_type(s_attr.get('type')) @@ -2533,7 +2534,7 @@ class InfoExtractor(object): track_attributes = extract_attributes(track_tag) kind = track_attributes.get('kind') if not kind or kind in ('subtitles', 'captions'): - src = track_attributes.get('src') + src = strip_or_none(track_attributes.get('src')) if not src: continue lang = track_attributes.get('srclang') or track_attributes.get('lang') or track_attributes.get('label')