[cbnc] fix extraction

youtube_dl/extractor/cnbc.py

@@ -1,13 +1,15 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import smuggle_url
 
 
 class CNBCIE(InfoExtractor):
-    _VALID_URL = r'https?://video\.cnbc\.com/gallery/\?video=(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www|video)?\.cnbc\.com/(?:gallery|video)/(?:\?video=(?P<id>[0-9]+)|.*/(?P<display_id>[^.]+))'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://video.cnbc.com/gallery/?video=3000503714',
         'info_dict': {
             'id': '3000503714',
@@ -22,10 +24,33 @@ class CNBCIE(InfoExtractor):
             # m3u8 download
             'skip_download': True,
         },
-    }
+    }, {
+        'url': 'https://www.cnbc.com/video/2018/07/19/trump-i-dont-necessarily-agree-with-raising-rates.html',
+        'info_dict': {
+            'id': '7000033068',
+            'ext': 'mp4',
+            'title': 'Full interview with Brian Belski and Tobias Levkovich',
+            'description': 'md5:958012776b16f68bad3008587dd0a03a',
+            'timestamp': 1532908800,
+            'upload_date': '20180730',
+            'uploader': 'NBCU-CNBC',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        if not video_id:
+            display_id = mobj.group('display_id')
+            webpage = self._download_webpage(url, display_id)
+            video_id = self._html_search_regex(
+                r'<a[^>]+?data-VideoID=[\'"]\s*([0-9]+)\s*',
+                webpage, display_id
+            )
         return {
             '_type': 'url_transparent',
             'ie_key': 'ThePlatform',