[youtube] Fix extraction.

[youtube-dl] / youtube_dl / extractor / mediaset.py

diff --git a/youtube_dl/extractor/mediaset.py b/youtube_dl/extractor/mediaset.py
index fcbc064ffd4eec70b512aa70f012fe135375f0ef..933df14952d5cc16857485e306be07f2d32384d3 100644 (file)
--- a/youtube_dl/extractor/mediaset.py
+++ b/youtube_dl/extractor/mediaset.py
@@ -6,7 +6,6 @@ import re
 from .theplatform import ThePlatformBaseIE
 from ..compat import (
     compat_parse_qs,
-    compat_str,
     compat_urllib_parse_urlparse,
 )
 from ..utils import (
@@ -27,7 +26,7 @@ class MediasetIE(ThePlatformBaseIE):
                                 (?:video|on-demand)/(?:[^/]+/)+[^/]+_|
                                 player/index\.html\?.*?\bprogramGuid=
                             )
-                    )(?P<id>[0-9A-Z]{16})
+                    )(?P<id>[0-9A-Z]{16,})
                     '''
     _TESTS = [{
         # full episode
@@ -77,6 +76,18 @@ class MediasetIE(ThePlatformBaseIE):
     }, {
         'url': 'mediaset:FAFU000000665924',
         'only_matching': True,
+    }, {
+        'url': 'https://www.mediasetplay.mediaset.it/video/mediasethaacuoreilfuturo/palmieri-alicudi-lisola-dei-tre-bambini-felici--un-decreto-per-alicudi-e-tutte-le-microscuole_FD00000000102295',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.mediasetplay.mediaset.it/video/cherryseason/anticipazioni-degli-episodi-del-23-ottobre_F306837101005C02',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.mediasetplay.mediaset.it/video/tg5/ambiente-onda-umana-per-salvare-il-pianeta_F309453601079D01',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.mediasetplay.mediaset.it/video/grandefratellovip/benedetta-una-doccia-gelata_F309344401044C135',
+        'only_matching': True,
     }]
 
     @staticmethod
@@ -102,7 +113,7 @@ class MediasetIE(ThePlatformBaseIE):
                 continue
             urlh = ie._request_webpage(
                 embed_url, video_id, note='Following embed URL redirect')
-            embed_url = compat_str(urlh.geturl())
+            embed_url = urlh.geturl()
             program_guid = _program_guid(_qs(embed_url))
             if program_guid:
                 entries.append(embed_url)
@@ -111,7 +122,7 @@ class MediasetIE(ThePlatformBaseIE):
     def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
         for video in smil.findall(self._xpath_ns('.//video', namespace)):
             video.attrib['src'] = re.sub(r'(https?://vod05)t(-mediaset-it\.akamaized\.net/.+?.mpd)\?.+', r'\1\2', video.attrib['src'])
-        return super()._parse_smil_formats(smil, smil_url, video_id, namespace, f4m_params, transform_rtmp_url)
+        return super(MediasetIE, self)._parse_smil_formats(smil, smil_url, video_id, namespace, f4m_params, transform_rtmp_url)
 
     def _real_extract(self, url):
         guid = self._match_id(url)