You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
youtube-dl/youtube_dl/extractor/nbc.py

37 lines
1.2 KiB
Python

11 years ago
from __future__ import unicode_literals
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 = {
11 years ago
'url': 'http://www.nbcnews.com/video/nbc-news/52753292',
'md5': '47abaac93c6eaf9ad37ee6c4463a5179',
'info_dict': {
'id': '52753292',
'ext': 'flv',
'title': 'Crew emerges after four-month Mars food study',
'description': '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')
11 years ago
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,
}