Update upstream source from tag 'upstream/2020.05.08'

[youtubedl] / youtube_dl / extractor / mediaset.py

diff --git a/youtube_dl/extractor/mediaset.py b/youtube_dl/extractor/mediaset.py
index df3748798e9f943c16ddd29cead9515b0dd44c57..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,
 from .theplatform import ThePlatformBaseIE
 from ..compat import (
     compat_parse_qs,

-    compat_str,

     compat_urllib_parse_urlparse,
 )
 from ..utils import (
     compat_urllib_parse_urlparse,
 )
 from ..utils import (


@@ -27,7 +26,7 @@ class MediasetIE(ThePlatformBaseIE):
                                 (?:video|on-demand)/(?:[^/]+/)+[^/]+_|
                                 player/index\.html\?.*?\bprogramGuid=
                             )
                                 (?:video|on-demand)/(?:[^/]+/)+[^/]+_|
                                 player/index\.html\?.*?\bprogramGuid=
                             )

-                    )(?P<id>[0-9A-Z]{16})
+                    )(?P<id>[0-9A-Z]{16,})

                     '''
     _TESTS = [{
         # full episode
                     '''
     _TESTS = [{
         # full episode


@@ -62,7 +61,6 @@ class MediasetIE(ThePlatformBaseIE):
             'uploader': 'Canale 5',
             'uploader_id': 'C5',
         },
             'uploader': 'Canale 5',
             'uploader_id': 'C5',
         },

-        'expected_warnings': ['HTTP Error 403: Forbidden'],

     }, {
         # clip
         'url': 'https://www.mediasetplay.mediaset.it/video/gogglebox/un-grande-classico-della-commedia-sexy_FAFU000000661680',
     }, {
         # clip
         'url': 'https://www.mediasetplay.mediaset.it/video/gogglebox/un-grande-classico-della-commedia-sexy_FAFU000000661680',


@@ -78,6 +76,18 @@ class MediasetIE(ThePlatformBaseIE):
     }, {
         'url': 'mediaset:FAFU000000665924',
         'only_matching': True,
     }, {
         '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
     }]
 
     @staticmethod


@@ -103,12 +113,17 @@ class MediasetIE(ThePlatformBaseIE):
                 continue
             urlh = ie._request_webpage(
                 embed_url, video_id, note='Following embed URL redirect')
                 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)
         return entries
 
             program_guid = _program_guid(_qs(embed_url))
             if program_guid:
                 entries.append(embed_url)
         return entries
 

+    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(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)
         tp_path = 'PR1GhC/media/guid/2702976343/' + guid
     def _real_extract(self, url):
         guid = self._match_id(url)
         tp_path = 'PR1GhC/media/guid/2702976343/' + guid


@@ -118,14 +133,15 @@ class MediasetIE(ThePlatformBaseIE):
         subtitles = {}
         first_e = None
         for asset_type in ('SD', 'HD'):
         subtitles = {}
         first_e = None
         for asset_type in ('SD', 'HD'):

-            for f in ('MPEG4', 'MPEG-DASH', 'M3U', 'ISM'):
+            # TODO: fixup ISM+none manifest URLs
+            for f in ('MPEG4', 'MPEG-DASH+none', 'M3U+none'):

                 try:
                     tp_formats, tp_subtitles = self._extract_theplatform_smil(
                         update_url_query('http://link.theplatform.%s/s/%s' % (self._TP_TLD, tp_path), {
                             'mbr': 'true',
                             'formats': f,
                             'assetTypes': asset_type,
                 try:
                     tp_formats, tp_subtitles = self._extract_theplatform_smil(
                         update_url_query('http://link.theplatform.%s/s/%s' % (self._TP_TLD, tp_path), {
                             'mbr': 'true',
                             'formats': f,
                             'assetTypes': asset_type,

-                        }), guid, 'Downloading %s %s SMIL data' % (f, asset_type))
+                        }), guid, 'Downloading %s %s SMIL data' % (f.split('+')[0], asset_type))

                 except ExtractorError as e:
                     if not first_e:
                         first_e = e
                 except ExtractorError as e:
                     if not first_e:
                         first_e = e