[youtube] Fix extraction.

[youtube-dl] / youtube_dl / extractor / inc.py

diff --git a/youtube_dl/extractor/inc.py b/youtube_dl/extractor/inc.py
index 279e53c154ee5c626710dcc9b2f3f11b7762dbd7..d5b258a0fcf514d5f7cd19d615fc6aef5d404575 100644 (file)
--- a/youtube_dl/extractor/inc.py
+++ b/youtube_dl/extractor/inc.py
@@ -1,10 +1,11 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from .kaltura import KalturaIE
 
 
 class IncIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?inc\.com(?:/[\w-]+)+/(?P<id>[\w-]+)(?:\.html)?'
+    _VALID_URL = r'https?://(?:www\.)?inc\.com/(?:[^/]+/)+(?P<id>[^.]+).html'
     _TESTS = [{
         'url': 'http://www.inc.com/tip-sheet/bill-gates-says-these-5-books-will-make-you-smarter.html',
         'md5': '7416739c9c16438c09fa35619d6ba5cb',
@@ -17,6 +18,24 @@ class IncIE(InfoExtractor):
             'upload_date': '20160920',
             'uploader_id': 'video@inc.com',
         },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # div with id=kaltura_player_1_kqs38cgm
+        'url': 'https://www.inc.com/oscar-raymundo/richard-branson-young-entrepeneurs.html',
+        'info_dict': {
+            'id': '1_kqs38cgm',
+            'ext': 'mp4',
+            'title': 'Branson: "In the end, you have to say, Screw it. Just do it."',
+            'description': 'md5:21b832d034f9af5191ca5959da5e9cb6',
+            'timestamp': 1364403232,
+            'upload_date': '20130327',
+            'uploader_id': 'incdigital@inc.com',
+        },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         'url': 'http://www.inc.com/video/david-whitford/founders-forum-tripadvisor-steve-kaufer-most-enjoyable-moment-for-entrepreneur.html',
         'only_matching': True,
@@ -27,14 +46,14 @@ class IncIE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
 
         partner_id = self._search_regex(
-            r'var\s+_bizo_data_partner_id\s*=\s*"(\d+)";',
-            webpage,
-            'partner id')
+            r'var\s+_?bizo_data_partner_id\s*=\s*["\'](\d+)', webpage,
+            'partner id', default='1034971')
 
-        kaltura_id = self._parse_json(self._search_regex(
-            r'pageInfo\.videos\s*=\s*\[(.+)\];',
-            webpage,
-            'kaltura id'),
+        kaltura_id = self._search_regex(
+            r'id=(["\'])kaltura_player_(?P<id>.+?)\1', webpage, 'kaltura id',
+            default=None, group='id') or self._parse_json(self._search_regex(
+                r'pageInfo\.videos\s*=\s*\[(.+)\];', webpage, 'kaltura id'),
             display_id)['vid_kaltura_id']
 
-        return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura')
+        return self.url_result(
+            'kaltura:%s:%s' % (partner_id, kaltura_id), KalturaIE.ie_key())