Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-03-07 04:47:17 +08:00
Code Issues Releases Wiki Activity

[Rai] Fix extraction (Fix #22846)

Browse Source 
Fix for single URL and Playlist like
https://www.raiplay.it/video/2019/08/Ricky-Zoom-S1E1-Collaudato-e-sicuro-1193c631-4c4b-4103-9cbd-110f30c1d5c8.html
and
https://www.raiplay.it/programmi/rickyzoom
This commit is contained in:
akaZ3n0 2020-01-15 19:02:18 +01:00 committed by GitHub
parent 2c482bff7c
commit 5537dbf3fa
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 13 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
youtube_dl/extractor/rai.py
View File

@ -169,15 +169,17 @@ class RaiPlayIE(RaiBaseIE):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
url, video_id = mobj.group('url', 'id') url, video_id = mobj.group('url', 'id')
json_url = url[:-4] + "json"
media = self._download_json( media = self._download_json(
'%s?json' % url, video_id, 'Downloading video JSON') '%s?json' % json_url, video_id, 'Downloading video JSON')
title = media['name'] title = media['name']
video = media['video'] video = media['video']
relinker_info = self._extract_relinker_info(video['contentUrl'], video_id) relinker_info = self._extract_relinker_info(video['content_url'], video_id)
self._sort_formats(relinker_info['formats']) self._sort_formats(relinker_info['formats'])
thumbnails = [] thumbnails = []
@ -274,12 +276,19 @@ class RaiPlayPlaylistIE(InfoExtractor):
('programma', 'nomeProgramma'), webpage, 'title') ('programma', 'nomeProgramma'), webpage, 'title')
description = unescapeHTML(self._html_search_meta( description = unescapeHTML(self._html_search_meta(
('description', 'og:description'), webpage, 'description')) ('description', 'og:description'), webpage, 'description'))
json_url = url + ".json"
media = self._download_json(
'%s?json' % json_url, 'Downloading video JSON')
webpage = media['blocks'][0]['sets'][0]['path_id']
json_url = "https://www.raiplay.it" + webpage
webpage = self._download_webpage(json_url, playlist_id)
entries = [] entries = []
for mobj in re.finditer( for mobj in re.finditer(
r'<a\b[^>]+\bhref=(["\'])(?P<path>/raiplay/video/.+?)\1', r'"weblink"+\s:+\s"(?P<path>/video/.+?.html)"\s?,\s?"sub',
webpage): webpage):
video_url = urljoin(url, mobj.group('path')) video_url = urljoin("https://www.raiplay.it", mobj.group('path'))
entries.append(self.url_result( entries.append(self.url_result(
video_url, ie=RaiPlayIE.ie_key(), video_url, ie=RaiPlayIE.ie_key(),
video_id=RaiPlayIE._match_id(video_url))) video_id=RaiPlayIE._match_id(video_url)))