debian/{compat,control}: Relutanctly update compat to 11.

[youtubedl] / youtube_dl / extractor / prosiebensat1.py

diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py
index 5091d8456faf3a4841ba770ea408aa75be806f83..7efff45662906b7a861ba6e22fc1a840f82635f6 100644 (file)
--- a/youtube_dl/extractor/prosiebensat1.py
+++ b/youtube_dl/extractor/prosiebensat1.py
@@ -129,6 +129,7 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
                     https?://
                         (?:www\.)?
                         (?:
                     https?://
                         (?:www\.)?
                         (?:

+                            (?:beta\.)?

                             (?:
                                 prosieben(?:maxx)?|sixx|sat1(?:gold)?|kabeleins(?:doku)?|the-voice-of-germany|7tv|advopedia
                             )\.(?:de|at|ch)|
                             (?:
                                 prosieben(?:maxx)?|sixx|sat1(?:gold)?|kabeleins(?:doku)?|the-voice-of-germany|7tv|advopedia
                             )\.(?:de|at|ch)|


@@ -300,6 +301,21 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
                 'skip_download': True,
             },
         },
                 'skip_download': True,
             },
         },

+        {
+            # 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',
         {
             # geo restricted to Germany
             'url': 'http://www.kabeleinsdoku.de/tv/mayday-alarm-im-cockpit/video/102-notlandung-im-hudson-river-ganze-folge',


@@ -329,6 +345,8 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
         r'clip[iI]d=(\d+)',
         r'clip[iI]d\s*=\s*["\'](\d+)',
         r"'itemImageUrl'\s*:\s*'/dynamic/thumbnails/full/\d+/(\d+)",
         r'clip[iI]d=(\d+)',
         r'clip[iI]d\s*=\s*["\'](\d+)',
         r"'itemImageUrl'\s*:\s*'/dynamic/thumbnails/full/\d+/(\d+)",

+        r'proMamsId&quot;\s*:\s*&quot;(\d+)',
+        r'proMamsId"\s*:\s*"(\d+)',

     ]
     _TITLE_REGEXES = [
         r'<h2 class="subtitle" itemprop="name">\s*(.+?)</h2>',
     ]
     _TITLE_REGEXES = [
         r'<h2 class="subtitle" itemprop="name">\s*(.+?)</h2>',


@@ -338,6 +356,7 @@ 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'<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>',
     ]
     _DESCRIPTION_REGEXES = [
         r'<p itemprop="description">\s*(.+?)</p>',


@@ -369,7 +388,9 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
     def _extract_clip(self, url, webpage):
         clip_id = self._html_search_regex(
             self._CLIPID_REGEXES, webpage, 'clip id')
     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')
+        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)
         info = self._extract_video_info(url, clip_id)
         description = self._html_search_regex(
             self._DESCRIPTION_REGEXES, webpage, 'description', default=None)


@@ -424,3 +445,6 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
             return self._extract_clip(url, webpage)
         elif page_type == 'playlist':
             return self._extract_playlist(url, webpage)
             return self._extract_clip(url, webpage)
         elif page_type == 'playlist':
             return self._extract_playlist(url, webpage)

+        else:
+            raise ExtractorError(
+                'Unsupported page type %s' % page_type, expected=True)