[nfl] Add support for URLs without id (Closes #6907)

This commit is contained in:
Sergey M․ 2015-09-20 23:45:01 +06:00
parent 5b4c54631a
commit 4423eba49b

View file

@ -60,7 +60,7 @@ class NFLIE(InfoExtractor):
) )
)/ )/
(?:.+?/)* (?:.+?/)*
(?P<id>(?:[a-z0-9]{16}|\w{8}\-(?:\w{4}\-){3}\w{12})) (?P<id>[^/#?&]+)
''' '''
_TESTS = [{ _TESTS = [{
'url': 'http://www.nfl.com/videos/nfl-game-highlights/0ap3000000398478/Week-3-Redskins-vs-Eagles-highlights', 'url': 'http://www.nfl.com/videos/nfl-game-highlights/0ap3000000398478/Week-3-Redskins-vs-Eagles-highlights',
@ -96,6 +96,17 @@ class NFLIE(InfoExtractor):
'timestamp': 1422850320, 'timestamp': 1422850320,
'upload_date': '20150202', 'upload_date': '20150202',
}, },
}, {
'url': 'http://www.patriots.com/video/2015/09/18/10-days-gillette',
'md5': '4c319e2f625ffd0b481b4382c6fc124c',
'info_dict': {
'id': 'n-238346',
'ext': 'mp4',
'title': '10 Days at Gillette',
'description': 'md5:8cd9cd48fac16de596eadc0b24add951',
'timestamp': 1442618809,
'upload_date': '20150918',
},
}, { }, {
'url': 'http://www.nfl.com/videos/nfl-network-top-ten/09000d5d810a6bd4/Top-10-Gutsiest-Performances-Jack-Youngblood', 'url': 'http://www.nfl.com/videos/nfl-network-top-ten/09000d5d810a6bd4/Top-10-Gutsiest-Performances-Jack-Youngblood',
'only_matching': True, 'only_matching': True,
@ -135,13 +146,14 @@ def _real_extract(self, url):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
config_url = NFLIE.prepend_host(host, self._search_regex( config_url = NFLIE.prepend_host(host, self._search_regex(
r'(?:config|configURL)\s*:\s*"([^"]+)"', webpage, 'config URL', r'(?:(?:config|configURL)\s*:\s*|<nflcs:avplayer[^>]+data-config\s*=\s*)(["\'])(?P<config>.+?)\1',
default='static/content/static/config/video/config.json')) webpage, 'config URL', default='static/content/static/config/video/config.json',
group='config'))
# For articles, the id in the url is not the video id # For articles, the id in the url is not the video id
video_id = self._search_regex( video_id = self._search_regex(
r'contentId\s*:\s*"([^"]+)"', webpage, 'video id', default=video_id) r'(?:<nflcs:avplayer[^>]+data-contentId\s*=\s*|contentId\s*:\s*)(["\'])(?P<id>.+?)\1',
config = self._download_json(config_url, video_id, webpage, 'video id', default=video_id, group='id')
note='Downloading player config') config = self._download_json(config_url, video_id, 'Downloading player config')
url_template = NFLIE.prepend_host( url_template = NFLIE.prepend_host(
host, '{contentURLTemplate:}'.format(**config)) host, '{contentURLTemplate:}'.format(**config))
video_data = self._download_json( video_data = self._download_json(