youtube-dl

commit 76bee08fe72f154ad3754428eb80413ad0a3aa19
parent 2913821723c826a0d2bfc16427592bf2b9d6d31c
Author: Sergey M․ <dstftw@gmail.com>
Date:   Thu,  9 Mar 2017 23:42:07 +0700

[prosiebensat1] Improve title extraction and add test

Diffstat:
M
youtube_dl/extractor/prosiebensat1.py
 | 
22
+++++++++++++++++++---

1 file changed, 19 insertions(+), 3 deletions(-)
diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py
@@ -301,6 +301,21 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
             },
         },
         {
+            # title in <h2 class="subtitle">
+            'url': 'http://www.prosieben.de/stars/oscar-award/videos/jetzt-erst-enthuellt-das-geheimnis-von-emma-stones-oscar-robe-clip',
+            'info_dict': {
+                'id': '4895826',
+                'ext': 'mp4',
+                'title': 'Jetzt erst enthüllt: Das Geheimnis von Emma Stones Oscar-Robe',
+                'description': 'md5:e5ace2bc43fadf7b63adc6187e9450b9',
+                'upload_date': '20170302',
+            },
+            'params': {
+                'skip_download': True,
+            },
+            'skip': 'geo restricted to Germany',
+        },
+        {
             # geo restricted to Germany
             'url': 'http://www.kabeleinsdoku.de/tv/mayday-alarm-im-cockpit/video/102-notlandung-im-hudson-river-ganze-folge',
             'only_matching': True,
@@ -338,6 +353,7 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
         r'<header class="module_header">\s*<h2>([^<]+)</h2>\s*</header>',
         r'<h2 class="video-title" itemprop="name">\s*(.+?)</h2>',
         r'<div[^>]+id="veeseoTitle"[^>]*>(.+?)</div>',
+        r'<h2[^>]+class="subtitle"[^>]*>([^<]+)</h2>',
     ]
     _DESCRIPTION_REGEXES = [
         r'<p itemprop="description">\s*(.+?)</p>',
@@ -369,9 +385,9 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
     def _extract_clip(self, url, webpage):
         clip_id = self._html_search_regex(
             self._CLIPID_REGEXES, webpage, 'clip id')
-        title = self._html_search_regex(self._TITLE_REGEXES, webpage, 'title', default=None)
-        if title is None:
-            title = self._og_search_title(webpage)
+        title = self._html_search_regex(
+            self._TITLE_REGEXES, webpage, 'title',
+            default=None) or self._og_search_title(webpage)
         info = self._extract_video_info(url, clip_id)
         description = self._html_search_regex(
             self._DESCRIPTION_REGEXES, webpage, 'description', default=None)