X-Git-Url: https://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fyahoo.py;h=b2d8f4b48daddcf734d3a1fb461d1b92736bcfd1;hb=3a686853e1739dfc26548cdc09fe89e693e76a9f;hp=1d9b9875069e481aa0994602c68f7e00d9766f3f;hpb=364ca0582eb1506af049c0e17595509c6bc0e00c;p=youtube-dl.git

diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py
index 1d9b98750..b2d8f4b48 100644
--- a/youtube_dl/extractor/yahoo.py
+++ b/youtube_dl/extractor/yahoo.py
@@ -8,6 +8,7 @@ import re
 from .common import InfoExtractor, SearchInfoExtractor
 from ..compat import (
     compat_urllib_parse,
+    compat_urllib_parse_urlencode,
     compat_urlparse,
 )
 from ..utils import (
@@ -147,6 +148,7 @@ class YahooIE(InfoExtractor):
         }, {
             # Query result is embedded in webpage, but explicit request to video API fails with geo restriction
             'url': 'https://screen.yahoo.com/community/communitary-community-episode-1-ladders-154501237.html',
+            'md5': '4fbafb9c9b6f07aa8f870629f6671b35',
             'info_dict': {
                 'id': '1f32853c-a271-3eef-8cb6-f6d6872cb504',
                 'ext': 'mp4',
@@ -154,11 +156,16 @@ class YahooIE(InfoExtractor):
                 'description': 'md5:8fc39608213295748e1e289807838c97',
                 'duration': 1646,
             },
-            'params': {
-                # m3u8 download
-                'skip_download': True,
+        }, {
+            # it uses an alias to get the video_id
+            'url': 'https://www.yahoo.com/movies/the-stars-of-daddys-home-have-very-different-212843197.html',
+            'info_dict': {
+                'id': '40eda9c8-8e5f-3552-8745-830f67d0c737',
+                'ext': 'mp4',
+                'title': 'Will Ferrell & Mark Wahlberg Are Pro-Spanking',
+                'description': 'While they play feuding fathers in \'Daddy\'s Home,\' star Will Ferrell & Mark Wahlberg share their true feelings on parenthood.',
             },
-        }
+        },
     ]
 
     def _real_extract(self, url):
@@ -202,13 +209,24 @@ class YahooIE(InfoExtractor):
             r'mediaItems: ({.*?})$', webpage, 'items', flags=re.MULTILINE,
             default=None)
         if items_json is None:
-            CONTENT_ID_REGEXES = [
-                r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"',
-                r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"',
-                r'"first_videoid"\s*:\s*"([^"]+)"',
-                r'%s[^}]*"ccm_id"\s*:\s*"([^"]+)"' % re.escape(page_id),
-            ]
-            video_id = self._search_regex(CONTENT_ID_REGEXES, webpage, 'content ID')
+            alias = self._search_regex(
+                r'"aliases":{"video":"(.*?)"', webpage, 'alias', default=None)
+            if alias is not None:
+                alias_info = self._download_json(
+                    'https://www.yahoo.com/_td/api/resource/VideoService.videos;video_aliases=["%s"]' % alias,
+                    display_id, 'Downloading alias info')
+                video_id = alias_info[0]['id']
+            else:
+                CONTENT_ID_REGEXES = [
+                    r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"',
+                    r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"',
+                    r'"first_videoid"\s*:\s*"([^"]+)"',
+                    r'%s[^}]*"ccm_id"\s*:\s*"([^"]+)"' % re.escape(page_id),
+                    r'<article[^>]data-uuid=["\']([^"\']+)',
+                    r'yahoo://article/view\?.*\buuid=([^&"\']+)',
+                ]
+                video_id = self._search_regex(
+                    CONTENT_ID_REGEXES, webpage, 'content ID')
         else:
             items = json.loads(items_json)
             info = items['mediaItems']['query']['results']['mediaObj'][0]
@@ -286,7 +304,7 @@ class YahooIE(InfoExtractor):
         region = self._search_regex(
             r'\\?"region\\?"\s*:\s*\\?"([^"]+?)\\?"',
             webpage, 'region', fatal=False, default='US')
-        data = compat_urllib_parse.urlencode({
+        data = compat_urllib_parse_urlencode({
             'protocol': 'http',
             'region': region,
         })