diff options
| author | Sergey M․ <dstftw@gmail.com> | 2016-11-12 23:08:05 +0700 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2016-11-12 23:08:05 +0700 |
| commit | 3d2729514f432ac4d80b8dffbacb893b603f6d68 (patch) | |
| tree | 0040f752092baf3fe9eb9f7d2ae85a5f0975658d | |
| parent | f076d7972c80ad7db9909fef0f34f0c579ebee1b (diff) | |
| download | youtube-dl-3d2729514f432ac4d80b8dffbacb893b603f6d68.tar.xz | |
[plays] Improve extraction and add support for embed URLs
| -rw-r--r-- | youtube_dl/extractor/plays.py | 25 |
1 files changed, 15 insertions, 10 deletions
diff --git a/youtube_dl/extractor/plays.py b/youtube_dl/extractor/plays.py index 5ac0292fa..ddfc6f148 100644 --- a/youtube_dl/extractor/plays.py +++ b/youtube_dl/extractor/plays.py @@ -8,8 +8,8 @@ from ..utils import int_or_none class PlaysTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?plays\.tv/video/(?P<id>[0-9a-f]{18})' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?plays\.tv/(?:video|embeds)/(?P<id>[0-9a-f]{18})' + _TESTS = [{ 'url': 'https://plays.tv/video/56af17f56c95335490/when-you-outplay-the-azir-wall', 'md5': 'dfeac1198506652b5257a62762cec7bc', 'info_dict': { @@ -18,14 +18,18 @@ class PlaysTVIE(InfoExtractor): 'title': 'Bjergsen - When you outplay the Azir wall', 'description': 'Posted by Bjergsen', } - } + }, { + 'url': 'https://plays.tv/embeds/56af17f56c95335490', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage( + 'https://plays.tv/video/%s' % video_id, video_id) + + info = self._search_json_ld(webpage, video_id,) - content = self._search_json_ld(webpage, video_id) - title = content['title'] mpd_url, sources = re.search( r'(?s)<video[^>]+data-mpd="([^"]+)"[^>]*>(.+?)</video>', webpage).groups() @@ -39,10 +43,11 @@ class PlaysTVIE(InfoExtractor): }) self._sort_formats(formats) - return { + info.update({ 'id': video_id, - 'title': title, 'description': self._og_search_description(webpage), - 'thumbnail': self._og_search_thumbnail(webpage), + 'thumbnail': info.get('thumbnail') or self._og_search_thumbnail(webpage), 'formats': formats, - } + }) + + return info |