X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fyahoo.py;h=bf4e659ac6981c77f7e5f3c77578c4808634d766;hb=1ed34f3dd6f534a3a5a3d6808d8d3466a9e5dea2;hp=6e72f1e5552d38d4a2baf8d2b14f3ce01ae3342c;hpb=a28ccbabc60c81016c851ae46365be377ea83795;p=youtube-dl

diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py
index 6e72f1e55..bf4e659ac 100644
--- a/youtube_dl/extractor/yahoo.py
+++ b/youtube_dl/extractor/yahoo.py
@@ -17,10 +17,12 @@ from ..utils import (
     int_or_none,
 )
 
+from .nbc import NBCSportsVPlayerIE
+
 
 class YahooIE(InfoExtractor):
     IE_DESC = 'Yahoo screen and movies'
-    _VALID_URL = r'(?P<url>(?P<host>https?://(?:[a-zA-Z]{2}\.)?[\da-zA-Z_-]+\.yahoo\.com)/(?:[^/]+/)*(?P<display_id>.+?)-(?P<id>[0-9]+)(?:-[a-z]+)?\.html)'
+    _VALID_URL = r'(?P<url>(?P<host>https?://(?:[a-zA-Z]{2}\.)?[\da-zA-Z_-]+\.yahoo\.com)/(?:[^/]+/)*(?P<display_id>.+)?-(?P<id>[0-9]+)(?:-[a-z]+)?\.html)'
     _TESTS = [
         {
             'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
@@ -138,12 +140,15 @@ class YahooIE(InfoExtractor):
                 'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d',
                 'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson',
             }
+        }, {
+            'url': 'https://tw.news.yahoo.com/-100120367.html',
+            'only_matching': True,
         }
     ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        display_id = mobj.group('display_id')
+        display_id = mobj.group('display_id') or self._match_id(url)
         page_id = mobj.group('id')
         url = mobj.group('url')
         host = mobj.group('host')
@@ -161,10 +166,9 @@ class YahooIE(InfoExtractor):
                 video_id = items[0]['id']
                 return self._get_info(video_id, display_id, webpage)
         # Look for NBCSports iframes
-        iframe_m = re.search(
-            r'<iframe[^>]+src="(?P<url>https?://vplayer\.nbcsports\.com/[^"]+)"', webpage)
-        if iframe_m:
-            return self.url_result(iframe_m.group('url'), 'NBCSports')
+        nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
+        if nbc_sports_url:
+            return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
 
         items_json = self._search_regex(
             r'mediaItems: ({.*?})$', webpage, 'items', flags=re.MULTILINE,