[plays] Fix extraction

This commit is contained in:
cpm 2016-11-11 15:48:19 -05:00 committed by Sergey M․
parent bc40b3a5ba
commit 8b1aeadc33
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D

View File

@ -10,12 +10,12 @@ from ..utils import int_or_none
class PlaysTVIE(InfoExtractor): class PlaysTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?plays\.tv/video/(?P<id>[0-9a-f]{18})' _VALID_URL = r'https?://(?:www\.)?plays\.tv/video/(?P<id>[0-9a-f]{18})'
_TEST = { _TEST = {
'url': 'http://plays.tv/video/56af17f56c95335490/when-you-outplay-the-azir-wall', 'url': 'https://plays.tv/video/56af17f56c95335490/when-you-outplay-the-azir-wall',
'md5': 'dfeac1198506652b5257a62762cec7bc', 'md5': 'dfeac1198506652b5257a62762cec7bc',
'info_dict': { 'info_dict': {
'id': '56af17f56c95335490', 'id': '56af17f56c95335490',
'ext': 'mp4', 'ext': 'mp4',
'title': 'When you outplay the Azir wall', 'title': 'Bjergsen - When you outplay the Azir wall',
'description': 'Posted by Bjergsen', 'description': 'Posted by Bjergsen',
} }
} }
@ -24,14 +24,11 @@ class PlaysTVIE(InfoExtractor):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
title = self._og_search_title(webpage) content = self._search_json_ld(webpage, video_id)
content = self._parse_json( title = content['title']
self._search_regex(
r'R\.bindContent\(({.+?})\);', webpage,
'content'), video_id)['content']
mpd_url, sources = re.search( mpd_url, sources = re.search(
r'(?s)<video[^>]+data-mpd="([^"]+)"[^>]*>(.+?)</video>', r'(?s)<video[^>]+data-mpd="([^"]+)"[^>]*>(.+?)</video>',
content).groups() webpage).groups()
formats = self._extract_mpd_formats( formats = self._extract_mpd_formats(
self._proto_relative_url(mpd_url), video_id, mpd_id='DASH') self._proto_relative_url(mpd_url), video_id, mpd_id='DASH')
for format_id, height, format_url in re.findall(r'<source\s+res="((\d+)h?)"\s+src="([^"]+)"', sources): for format_id, height, format_url in re.findall(r'<source\s+res="((\d+)h?)"\s+src="([^"]+)"', sources):