youtube-dl

commit 0ae6b019376313bd3dc9fbd4e2784c1aa909e75b
parent def630e523a31145986f0d651d3dde54e52bff30
Author: Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>
Date:   Tue, 11 Feb 2014 14:38:17 +0100

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

Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
5
++++-
M
youtube_dl/extractor/cnn.py
 | 
26
++++++++++++++++++++++++++

2 files changed, 30 insertions(+), 1 deletion(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -32,7 +32,10 @@ from .clipfish import ClipfishIE
 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
diff --git 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(),
+        }