mirror of
https://github.com/l1ving/youtube-dl
synced 2024-11-26 00:22:58 +08:00
33 lines
1.2 KiB
Python
33 lines
1.2 KiB
Python
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..utils import find_xpath_attr, compat_str
|
|
|
|
|
|
class NBCNewsIE(InfoExtractor):
|
|
_VALID_URL = r'https?://www\.nbcnews\.com/video/.+?/(?P<id>\d+)'
|
|
|
|
_TEST = {
|
|
u'url': u'http://www.nbcnews.com/video/nbc-news/52753292',
|
|
u'file': u'52753292.flv',
|
|
u'md5': u'47abaac93c6eaf9ad37ee6c4463a5179',
|
|
u'info_dict': {
|
|
u'title': u'Crew emerges after four-month Mars food study',
|
|
u'description': u'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
|
|
},
|
|
}
|
|
|
|
def _real_extract(self, url):
|
|
mobj = re.match(self._VALID_URL, url)
|
|
video_id = mobj.group('id')
|
|
all_info = self._download_xml('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
|
|
info = all_info.find('video')
|
|
|
|
return {'id': video_id,
|
|
'title': info.find('headline').text,
|
|
'ext': 'flv',
|
|
'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
|
|
'description': compat_str(info.find('caption').text),
|
|
'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
|
|
}
|