diff options
| author | Sergey M․ <dstftw@gmail.com> | 2017-09-06 00:48:37 +0700 | 
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2017-09-06 00:48:37 +0700 | 
| commit | 66c9fa36c10860b380806b9de48f38d628289e03 (patch) | |
| tree | 7d9b1991b5ae9082c3d0ea8e683c7cc7af627442 /youtube_dl/extractor/generic.py | |
| parent | c5c9bf0c120d2c481124a0c3913b981cf061fb95 (diff) | |
[youtube] Separate methods for embeds extraction
Diffstat (limited to 'youtube_dl/extractor/generic.py')
| -rw-r--r-- | youtube_dl/extractor/generic.py | 33 | 
1 files changed, 4 insertions, 29 deletions
| diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index c81efdc00..b83c18380 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -2243,36 +2243,11 @@ class GenericIE(InfoExtractor):          if vid_me_embed_url is not None:              return self.url_result(vid_me_embed_url, 'Vidme') -        # Look for embedded YouTube player -        matches = re.findall(r'''(?x) -            (?: -                <iframe[^>]+?src=| -                data-video-url=| -                <embed[^>]+?src=| -                embedSWF\(?:\s*| -                <object[^>]+data=| -                new\s+SWFObject\( -            ) -            (["\']) -                (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/ -                (?:embed|v|p)/.+?) -            \1''', webpage) -        if matches: +        # Look for YouTube embeds +        youtube_urls = YoutubeIE._extract_urls(webpage) +        if youtube_urls:              return self.playlist_from_matches( -                matches, video_id, video_title, lambda m: unescapeHTML(m[1])) - -        # Look for lazyYT YouTube embed -        matches = re.findall( -            r'class="lazyYT" data-youtube-id="([^"]+)"', webpage) -        if matches: -            return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m)) - -        # Look for Wordpress "YouTube Video Importer" plugin -        matches = re.findall(r'''(?x)<div[^>]+ -            class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+ -            data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage) -        if matches: -            return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1]) +                youtube_urls, video_id, video_title, ie=YoutubeIE.ie_key())          matches = DailymotionIE._extract_urls(webpage)          if matches: | 
