1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-27 19:36:50 +01:00

[Yahoo/NBCSports] Fix #5226

This commit is contained in:
Yen Chi Hsuan 2015-03-31 02:21:27 +08:00
parent edd7344820
commit a28ccbabc6
3 changed files with 36 additions and 0 deletions

View File

@ -310,6 +310,7 @@ from .naver import NaverIE
from .nba import NBAIE
from .nbc import (
NBCIE,
NBCSportsIE,
NBCNewsIE,
)
from .ndr import NDRIE

View File

@ -50,6 +50,27 @@ class NBCIE(InfoExtractor):
return self.url_result(theplatform_url)
class NBCSportsIE(InfoExtractor):
_VALID_URL = r'https?://vplayer\.nbcsports\.com/(?:[^/]+/)+(?P<id>[0-9a-zA-Z]+)'
_TEST = {
'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_share/select/9CsDKds0kvHI',
'md5': 'ceae8dced5c14a1c1ffcb7a32194cca5',
'info_dict': {
'id': '9CsDKds0kvHI',
'ext': 'flv',
'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d',
'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
theplatform_url = self._og_search_video_url(webpage)
return self.url_result(theplatform_url, 'ThePlatform')
class NBCNewsIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://(?:www\.)?nbcnews\.com/
(?:video/.+?/(?P<id>\d+)|

View File

@ -129,6 +129,15 @@ class YahooIE(InfoExtractor):
}, {
'url': 'https://gma.yahoo.com/pizza-delivery-man-surprised-huge-tip-college-kids-195200785.html',
'only_matching': True,
}, {
'note': 'NBC Sports embeds',
'url': 'http://sports.yahoo.com/blogs/ncaab-the-dagger/tyler-kalinoski-s-buzzer-beater-caps-davidson-s-comeback-win-185609842.html?guid=nbc_cbk_davidsonbuzzerbeater_150313',
'info_dict': {
'id': '9CsDKds0kvHI',
'ext': 'flv',
'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d',
'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson',
}
}
]
@ -151,6 +160,11 @@ class YahooIE(InfoExtractor):
items = json.loads(items_json)
video_id = items[0]['id']
return self._get_info(video_id, display_id, webpage)
# Look for NBCSports iframes
iframe_m = re.search(
r'<iframe[^>]+src="(?P<url>https?://vplayer\.nbcsports\.com/[^"]+)"', webpage)
if iframe_m:
return self.url_result(iframe_m.group('url'), 'NBCSports')
items_json = self._search_regex(
r'mediaItems: ({.*?})$', webpage, 'items', flags=re.MULTILINE,