kopia lustrzana https://github.com/yt-dlp/yt-dlp
[Yahoo/NBCSports] Generalize NBC sports info extractor
rodzic
a28ccbabc6
commit
a2a4d5fa31
|
@ -310,6 +310,7 @@ from .naver import NaverIE
|
|||
from .nba import NBAIE
|
||||
from .nbc import (
|
||||
NBCIE,
|
||||
NBCSportsVPlayerIE,
|
||||
NBCSportsIE,
|
||||
NBCNewsIE,
|
||||
)
|
||||
|
|
|
@ -50,7 +50,7 @@ class NBCIE(InfoExtractor):
|
|||
return self.url_result(theplatform_url)
|
||||
|
||||
|
||||
class NBCSportsIE(InfoExtractor):
|
||||
class NBCSportsVPlayerIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://vplayer\.nbcsports\.com/(?:[^/]+/)+(?P<id>[0-9a-zA-Z]+)'
|
||||
|
||||
_TEST = {
|
||||
|
@ -64,6 +64,13 @@ class NBCSportsIE(InfoExtractor):
|
|||
}
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def _extract_url(webpage):
|
||||
iframe_m = re.search(
|
||||
r'<iframe[^>]+src="(?P<url>https?://vplayer\.nbcsports\.com/[^"]+)"', webpage)
|
||||
if iframe_m:
|
||||
return iframe_m.group('url')
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
@ -71,6 +78,28 @@ class NBCSportsIE(InfoExtractor):
|
|||
return self.url_result(theplatform_url, 'ThePlatform')
|
||||
|
||||
|
||||
class NBCSportsIE(InfoExtractor):
|
||||
# Does not include https becuase its certificate is invalid
|
||||
_VALID_URL = r'http://www\.nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
|
||||
|
||||
_TEST = {
|
||||
'url': 'http://www.nbcsports.com//college-basketball/ncaab/tom-izzo-michigan-st-has-so-much-respect-duke',
|
||||
'md5': 'ba6c93f96b67bf05344f78bd523dac0f',
|
||||
'info_dict': {
|
||||
'id': 'PHJSaFWbrTY9',
|
||||
'ext': 'flv',
|
||||
'title': 'Tom Izzo, Michigan St. has \'so much respect\' for Duke',
|
||||
'description': 'md5:ecb459c9d59e0766ac9c7d5d0eda8113',
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
return self.url_result(
|
||||
NBCSportsVPlayerIE._extract_url(webpage), 'NBCSportsVPlayer')
|
||||
|
||||
|
||||
class NBCNewsIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)https?://(?:www\.)?nbcnews\.com/
|
||||
(?:video/.+?/(?P<id>\d+)|
|
||||
|
|
|
@ -17,6 +17,8 @@ from ..utils import (
|
|||
int_or_none,
|
||||
)
|
||||
|
||||
from .nbc import NBCSportsVPlayerIE
|
||||
|
||||
|
||||
class YahooIE(InfoExtractor):
|
||||
IE_DESC = 'Yahoo screen and movies'
|
||||
|
@ -132,6 +134,7 @@ class YahooIE(InfoExtractor):
|
|||
}, {
|
||||
'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',
|
||||
'md5': 'ceae8dced5c14a1c1ffcb7a32194cca5',
|
||||
'info_dict': {
|
||||
'id': '9CsDKds0kvHI',
|
||||
'ext': 'flv',
|
||||
|
@ -161,10 +164,9 @@ class YahooIE(InfoExtractor):
|
|||
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')
|
||||
nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
|
||||
if nbc_sports_url:
|
||||
return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
|
||||
|
||||
items_json = self._search_regex(
|
||||
r'mediaItems: ({.*?})$', webpage, 'items', flags=re.MULTILINE,
|
||||
|
|
Ładowanie…
Reference in New Issue