R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[PlaysTV] Fix for plays.tv extractor, adding additional tests

Browse Source
This commit is contained in:
cpm 2016-11-11 15:48:19 -05:00
parent bc40b3a5ba
commit 4dcba52fed
1 changed files with 36 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
youtube_dl/extractor/plays.py
View File

@ -9,29 +9,55 @@ 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 = { _TESTS = [{
'url': 'http://plays.tv/video/56af17f56c95335490/when-you-outplay-the-azir-wall', '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',
}
}, {
'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',
} }
} }, {
'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): def _real_extract(self, url):
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_regex(
content = self._parse_json( r'<script class=\"linked_data\" type=\"application\/ld\+json\">{(.+?)}<\/script>', webpage, 'content')
self._search_regex( content = self._parse_json("{" + content + "}", video_id)
r'R\.bindContent\(({.+?})\);', webpage, title = content['name']
'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):