aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/cnn.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/cnn.py')
-rw-r--r--youtube_dl/extractor/cnn.py26
1 files changed, 26 insertions, 0 deletions
diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py
index 80bf59ade..b32cb8980 100644
--- a/youtube_dl/extractor/cnn.py
+++ b/youtube_dl/extractor/cnn.py
@@ -6,6 +6,7 @@ from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_duration,
+ url_basename,
)
@@ -98,3 +99,28 @@ class CNNIE(InfoExtractor):
'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(),
+ }