[cnn] Add an extractor for blogs (closes #2361)

This commit is contained in:
Jaime Marquínez Ferrándiz 2014-02-11 14:38:17 +01:00
parent def630e523
commit 0ae6b01937
2 changed files with 30 additions and 1 deletions

View file

@ -32,7 +32,10 @@
from .cliphunter import CliphunterIE
from .clipsyndicate import ClipsyndicateIE
from .cmt import CMTIE
from .cnn import CNNIE
from .cnn import (
CNNIE,
CNNBlogsIE,
)
from .collegehumor import CollegeHumorIE
from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
from .condenast import CondeNastIE

View file

@ -6,6 +6,7 @@
from ..utils import (
int_or_none,
parse_duration,
url_basename,
)
@ -98,3 +99,28 @@ def _real_extract(self, url):
'duration': duration,
'upload_date': upload_date,
}
class CNNBlogsIE(InfoExtractor):
_VALID_URL = r'https?://[^\.]+\.blogs\.cnn\.com/.+'
_TEST = {
'url': 'http://reliablesources.blogs.cnn.com/2014/02/09/criminalizing-journalism/',
'md5': '3e56f97b0b6ffb4b79f4ea0749551084',
'info_dict': {
'id': 'bestoftv/2014/02/09/criminalizing-journalism.cnn',
'ext': 'mp4',
'title': 'Criminalizing journalism?',
'description': 'Glenn Greenwald responds to comments made this week on Capitol Hill that journalists could be criminal accessories.',
'upload_date': '20140209',
},
'add_ie': ['CNN'],
}
def _real_extract(self, url):
webpage = self._download_webpage(url, url_basename(url))
cnn_url = self._html_search_regex(r'data-url="(.+?)"', webpage, 'cnn url')
return {
'_type': 'url',
'url': cnn_url,
'ie_key': CNNIE.ie_key(),
}