diff options
| author | Sergey M․ <dstftw@gmail.com> | 2018-04-09 00:25:44 +0700 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2018-04-09 00:25:44 +0700 |
| commit | d3431dcb90ea72fed502ecfd8f34e7499009a53a (patch) | |
| tree | 9e2ebc6f422c71435a150249c9000e90d41ca019 | |
| parent | 1fc37ca3f181159c98bccf081766abb73b9d344f (diff) | |
| download | youtube-dl-d3431dcb90ea72fed502ecfd8f34e7499009a53a.tar.xz | |
[generic] Restrict share-videos.se embeds regex to filter bogus URLs (#16115)
| -rw-r--r-- | youtube_dl/extractor/generic.py | 21 |
1 files changed, 10 insertions, 11 deletions
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 4b210da72..8922d1914 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -1974,10 +1974,10 @@ class GenericIE(InfoExtractor): 'info_dict': { 'id': '83645793', 'title': 'Lock up and get excited', - 'thumbnail': r're:^https?://.*\.jpg(\?.*)?$', 'ext': 'mp4' - } - } + }, + 'skip': 'TODO: fix nested playlists processing in tests', + }, # { # # TODO: find another test # # http://schema.org/VideoObject @@ -2973,6 +2973,13 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key()) + sharevideos_urls = [mobj.group('url') for mobj in re.finditer( + r'<iframe[^>]+?\bsrc\s*=\s*(["\'])(?P<url>(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1', + webpage)] + if sharevideos_urls: + return self.playlist_from_matches( + sharevideos_urls, video_id, video_title) + def merge_dicts(dict1, dict2): merged = {} for k, v in dict1.items(): @@ -2988,14 +2995,6 @@ class GenericIE(InfoExtractor): merged[k] = v return merged - # Look for Share-Videos.se embeds - sharevideosse_urls = [m.group('url') for m in re.finditer( - r'<iframe[^>]+?src\s*=\s*(["\'])(?P<url>https?://embed\.share-videos\.se/auto/embed/\d+.+?)\1', - webpage)] - if sharevideosse_urls: - return self.playlist_from_matches( - sharevideosse_urls, video_id, video_title) - # Look for HTML5 media entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls') if entries: |