From 3d2729514f432ac4d80b8dffbacb893b603f6d68 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 12 Nov 2016 23:08:05 +0700 Subject: [PATCH] [plays] Improve extraction and add support for embed URLs --- youtube_dl/extractor/plays.py | 25 +++++++++++++++---------- 1 file 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 @@ class PlaysTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?plays\.tv/video/(?P[0-9a-f]{18})' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?plays\.tv/(?:video|embeds)/(?P[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)]+data-mpd="([^"]+)"[^>]*>(.+?)', webpage).groups() @@ -39,10 +43,11 @@ def _real_extract(self, url): }) 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