yt-dlp/youtube_dl/extractor/nba.py

40 lines
1.4 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
2013-06-23 15:18:00 -04:00
import re
from .common import InfoExtractor
class NBAIE(InfoExtractor):
2014-03-29 09:54:45 -04:00
_VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?:nba/)?video(?P<id>/[^?]*?)(?:/index\.html)?(?:\?.*)?$'
2013-06-27 14:46:46 -04:00
_TEST = {
'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
'md5': u'c0edcfc37607344e2ff8f13c378c88a4',
'info_dict': {
2014-03-29 09:54:45 -04:00
'id': '0021200253-okc-bkn-recap.nba',
'ext': 'mp4',
'description': 'Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.',
'title': 'Thunder vs. Nets',
},
2013-06-27 14:46:46 -04:00
}
2013-06-23 15:18:00 -04:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
2014-03-29 09:54:45 -04:00
video_id = mobj.group('id')
2013-06-23 15:18:00 -04:00
webpage = self._download_webpage(url, video_id)
video_url = 'http://ht-mobile.cdn.turner.com/nba/big' + video_id + '_nba_1280x720.mp4'
2013-06-23 15:18:00 -04:00
shortened_video_id = video_id.rpartition('/')[2]
title = self._og_search_title(webpage, default=shortened_video_id).replace('NBA.com: ', '')
2013-06-23 15:18:00 -04:00
description = self._html_search_regex(r'<meta name="description" (?:content|value)="(.*?)" />', webpage, 'description', fatal=False)
return {
2013-06-23 15:18:00 -04:00
'id': shortened_video_id,
'url': video_url,
'title': title,
'description': description,
}