mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-09-06 10:59:36 +02:00
[wsj:article] Add extractor
This commit is contained in:
parent
0254f93b08
commit
3266d08af2
@ -1233,7 +1233,10 @@
|
|||||||
WrzutaIE,
|
WrzutaIE,
|
||||||
WrzutaPlaylistIE,
|
WrzutaPlaylistIE,
|
||||||
)
|
)
|
||||||
from .wsj import WSJIE
|
from .wsj import (
|
||||||
|
WSJIE,
|
||||||
|
WSJArticleIE,
|
||||||
|
)
|
||||||
from .xbef import XBefIE
|
from .xbef import XBefIE
|
||||||
from .xboxclips import XboxClipsIE
|
from .xboxclips import XboxClipsIE
|
||||||
from .xfileshare import XFileShareIE
|
from .xfileshare import XFileShareIE
|
||||||
|
@ -10,10 +10,11 @@
|
|||||||
|
|
||||||
|
|
||||||
class WSJIE(InfoExtractor):
|
class WSJIE(InfoExtractor):
|
||||||
_VALID_URL = r'''(?x)https?://
|
_VALID_URL = r'''(?x)
|
||||||
(?:
|
(?:
|
||||||
video-api\.wsj\.com/api-video/player/iframe\.html\?guid=|
|
https?://video-api\.wsj\.com/api-video/player/iframe\.html\?guid=|
|
||||||
(?:www\.)?wsj\.com/video/[^/]+/
|
https?://(?:www\.)?wsj\.com/video/[^/]+/|
|
||||||
|
wsj:
|
||||||
)
|
)
|
||||||
(?P<id>[a-zA-Z0-9-]+)'''
|
(?P<id>[a-zA-Z0-9-]+)'''
|
||||||
IE_DESC = 'Wall Street Journal'
|
IE_DESC = 'Wall Street Journal'
|
||||||
@ -87,3 +88,24 @@ def _real_extract(self, url):
|
|||||||
'title': title,
|
'title': title,
|
||||||
'categories': info.get('keywords'),
|
'categories': info.get('keywords'),
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
class WSJArticleIE(InfoExtractor):
|
||||||
|
_VALID_URL = r'(?i)https?://(?:www\.)?wsj\.com/articles/(?P<id>\w[^/]+)'
|
||||||
|
_TESTS = [{
|
||||||
|
'url': 'https://www.wsj.com/articles/dont-like-china-no-pandas-for-you-1490366939?',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '4B13FA62-1D8C-45DB-8EA1-4105CB20B362',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'upload_date': '20170221',
|
||||||
|
'uploader_id': 'ralcaraz',
|
||||||
|
'title': 'Bao Bao the Panda Leaves for China',
|
||||||
|
}
|
||||||
|
}]
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
article_id = self._match_id(url)
|
||||||
|
webpage = self._download_webpage(url, article_id)
|
||||||
|
video_id = self._search_regex(r'data-src=["\']([A-Z0-9\-]+)',
|
||||||
|
webpage, 'video id')
|
||||||
|
return self.url_result('wsj:%s' % video_id, WSJIE.ie_key(), video_id)
|
||||||
|
Loading…
Reference in New Issue
Block a user