Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-03-13 08:47:15 +08:00
Code Issues Releases Wiki Activity

[PlaysTVIE] Replaced regex with json_ld

Browse Source
This commit is contained in:
cpm 2016-11-11 23:14:58 -05:00
parent 4dcba52fed
commit 5f31a5e783
1 changed files with 4 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

37
youtube_dl/extractor/plays.py
View File

@ -9,16 +9,7 @@ from ..utils import int_or_none
class PlaysTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?plays\.tv/video/(?P<id>[0-9a-f]{18})'
_TESTS = [{
'url': 'https://plays.tv/video/57698d69e6c84884a2/just-a-typical-reaper-potg',
'md5': 'c4bdc35a0c9ca1f95c6ecad2f99c0e76',
'info_dict': {
'id': '57698d69e6c84884a2',
'ext': 'mp4',
'title': 'Solfect - Just a typical Reaper POTG',
'description': 'Posted by Solfect',
}
}, {
_TEST = {
'url': 'https://plays.tv/video/56af17f56c95335490/when-you-outplay-the-azir-wall',
'md5': 'dfeac1198506652b5257a62762cec7bc',
'info_dict': {
@ -27,34 +18,14 @@ class PlaysTVIE(InfoExtractor):
'title': 'Bjergsen - When you outplay the Azir wall',
'description': 'Posted by Bjergsen',
}
}, {
'url': 'https://plays.tv/video/58236095d388d140aa/-?from=user',
'md5': '09535d1d157f679e6446fb39ce51645a',
'info_dict': {
'id': '58236095d388d140aa',
'ext': 'mp4',
'title': 'akn3ex - \u63a7\u3048\u3081\u306b\u8a00\u3063\u3066\u9811\u5f35\u3063\u3066\u308b',
'description': 'Posted by akn3ex',
}
}, {
'url': 'http://plays.tv/video/56d77f74866aa25854/pro-abortion-propaganda?from=search&search=dota+2',
'md5': '3e3fc1d5c20cb373eb3143bbb4ca5070',
'info_dict': {
'id': '56d77f74866aa25854',
'ext': 'mp4',
'title': 'SavageIs - pro abortion propaganda',
'description': 'Posted by SavageIs',
}
}]
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
content = self._search_regex(
r'<script class=\"linked_data\" type=\"application\/ld\+json\">{(.+?)}<\/script>', webpage, 'content')
content = self._parse_json("{" + content + "}", video_id)
title = content['name']
content = self._search_json_ld(webpage, video_id)
title = content['title']
mpd_url, sources = re.search(
r'(?s)<video[^>]+data-mpd="([^"]+)"[^>]*>(.+?)</video>',
webpage).groups()