[yahoo] restore support for cbs suffixed URLs

diff --git a/test/test_all_urls.py b/test/test_all_urls.py
index 465ce005097d246d6b77ae8c04b47fa94889dc41..81056a999d2014506b589ea4b31ab67951486f1b 100644 (file)
--- a/test/test_all_urls.py
+++ b/test/test_all_urls.py
@@ -123,12 +123,6 @@ class TestAllURLsMatching(unittest.TestCase):
         self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['pbs'])
         self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['pbs'])
 
-    def test_yahoo_https(self):
-        # https://github.com/ytdl-org/youtube-dl/issues/2701
-        self.assertMatch(
-            'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html',
-            ['Yahoo'])
-
     def test_no_duplicated_ie_names(self):
         name_accu = collections.defaultdict(list)
         for ie in self.ies:

diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py
index 6c6bd76e879edbef50e8839549efc7326edd485b..f041cf5de1136999efd0c795bb7847f3696587c0 100644 (file)
--- a/youtube_dl/extractor/yahoo.py
+++ b/youtube_dl/extractor/yahoo.py
@@ -25,7 +25,7 @@ from .brightcove import BrightcoveNewIE
 
 class YahooIE(InfoExtractor):
     IE_DESC = 'Yahoo screen and movies'
-    _VALID_URL = r'(?P<url>https?://(?:(?P<country>[a-zA-Z]{2}(?:-[a-zA-Z]{2})?|malaysia)\.)?(?:[\da-zA-Z_-]+\.)?yahoo\.com/(?:[^/]+/)*(?P<id>[^?&#]*-[0-9]+)\.html)'
+    _VALID_URL = r'(?P<url>https?://(?:(?P<country>[a-zA-Z]{2}(?:-[a-zA-Z]{2})?|malaysia)\.)?(?:[\da-zA-Z_-]+\.)?yahoo\.com/(?:[^/]+/)*(?P<id>[^?&#]*-[0-9]+)(?:-[a-z]+)?\.html)'
     _TESTS = [{
         'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
         'info_dict': {
@@ -171,6 +171,9 @@ class YahooIE(InfoExtractor):
     }, {
         'url': 'https://es-us.noticias.yahoo.com/es-la-puerta-irrompible-que-110539379.html',
         'only_matching': True,
+    }, {
+        'url': 'https://www.yahoo.com/entertainment/v/longtime-cbs-news-60-minutes-032036500-cbs.html',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):