From 3aa9176f082e2e2909826a61a80a0923b4bd88d3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?=
 <jaime.marquinez.ferrandiz@gmail.com>
Date: Sun, 21 Dec 2014 12:33:30 +0100
Subject: [PATCH] [yahoo] Improve video id detection (fixes #4521)

---
 youtube_dl/extractor/yahoo.py | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py
index 031226f27..2d9e311b0 100644
--- a/youtube_dl/extractor/yahoo.py
+++ b/youtube_dl/extractor/yahoo.py
@@ -12,6 +12,7 @@
 )
 from ..utils import (
     clean_html,
+    unescapeHTML,
     ExtractorError,
     int_or_none,
 )
@@ -116,6 +117,16 @@ class YahooIE(InfoExtractor):
                 'description': 'md5:1428185051cfd1949807ad4ff6d3686a',
                 'duration': 201,
             }
+        }, {
+            'url': 'https://www.yahoo.com/movies/v/true-story-trailer-173000497.html',
+            'md5': '989396ae73d20c6f057746fb226aa215',
+            'info_dict': {
+                'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1',
+                'ext': 'mp4',
+                'title': '\'True Story\' Trailer',
+                'description': 'True Story',
+                'duration': 150,
+            },
         }, {
             'url': 'https://gma.yahoo.com/pizza-delivery-man-surprised-huge-tip-college-kids-195200785.html',
             'only_matching': True,
@@ -125,6 +136,7 @@ class YahooIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         display_id = mobj.group('display_id')
+        page_id = mobj.group('id')
         url = mobj.group('url')
         host = mobj.group('host')
         webpage = self._download_webpage(url, display_id)
@@ -149,6 +161,7 @@ def _real_extract(self, url):
                 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')
         else:
@@ -211,7 +224,7 @@ def _get_info(self, video_id, display_id, webpage):
         return {
             'id': video_id,
             'display_id': display_id,
-            'title': meta['title'],
+            'title': unescapeHTML(meta['title']),
             'formats': formats,
             'description': clean_html(meta['description']),
             'thumbnail': meta['thumbnail'] if meta.get('thumbnail') else self._og_search_thumbnail(webpage),