fenix
/
ytdl-nightly
mirror of https://github.com/ytdl-org/ytdl-nightly.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[aljazeera] fix extraction(closes #20911)(closes #27779)

This commit is contained in:
Remita Amine 2021-01-17 17:35:10 +01:00
parent 58f6c2112d
commit 26499ba823
1 changed files with 32 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
youtube_dl/extractor/aljazeera.py
View File

@ -1,13 +1,16 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor from .common import InfoExtractor
class AlJazeeraIE(InfoExtractor): class AlJazeeraIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?aljazeera\.com/(?:programmes|video)/.*?/(?P<id>[^/]+)\.html' _VALID_URL = r'https?://(?:www\.)?aljazeera\.com/(?P<type>program/[^/]+|(?:feature|video)s)/\d{4}/\d{1,2}/\d{1,2}/(?P<id>[^/?&#]+)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html', 'url': 'https://www.aljazeera.com/program/episode/2014/9/19/deliverance',
'info_dict': { 'info_dict': {
'id': '3792260579001', 'id': '3792260579001',
'ext': 'mp4', 'ext': 'mp4',
@ -20,14 +23,34 @@ class AlJazeeraIE(InfoExtractor):
'add_ie': ['BrightcoveNew'], 'add_ie': ['BrightcoveNew'],
'skip': 'Not accessible from Travis CI server', 'skip': 'Not accessible from Travis CI server',
}, { }, {
'url': 'http://www.aljazeera.com/video/news/2017/05/sierra-leone-709-carat-diamond-auctioned-170511100111930.html', 'url': 'https://www.aljazeera.com/videos/2017/5/11/sierra-leone-709-carat-diamond-to-be-auctioned-off',
'only_matching': True,
}, {
'url': 'https://www.aljazeera.com/features/2017/8/21/transforming-pakistans-buses-into-art',
'only_matching': True, 'only_matching': True,
}] }]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/665003303001/default_default/index.html?videoId=%s' BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
def _real_extract(self, url): def _real_extract(self, url):
program_name = self._match_id(url) post_type, name = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, program_name) post_type = {
brightcove_id = self._search_regex( 'features': 'post',
r'RenderPagesVideo\(\'(.+?)\'', webpage, 'brightcove id') 'program': 'episode',
return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id) 'videos': 'video',
}[post_type.split('/')[0]]
video = self._download_json(
'https://www.aljazeera.com/graphql', name, query={
'operationName': 'SingleArticleQuery',
'variables': json.dumps({
'name': name,
'postType': post_type,
}),
}, headers={
'wp-site': 'aje',
})['data']['article']['video']
video_id = video['id']
account_id = video.get('accountId') or '665003303001'
player_id = video.get('playerId') or 'BkeSH5BDb'
return self.url_result(
self.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, video_id),
'BrightcoveNew', video_id)