[mediaset] Fix extractor (#2158)

Closes #2149 Authored by: nixxo
2024-12-23 02:26:37 -05:00 · 2022-02-04 06:59:38 +01:00 · 2022-02-04 06:59:38 +01:00 · 22219f2d1f
commit 22219f2d1f
parent 5a13fdd225
1 changed files with 90 additions and 31 deletions
--- a/yt_dlp/extractor/mediaset.py
+++ b/yt_dlp/extractor/mediaset.py
@ -7,6 +7,7 @@ import re
 from .theplatform import ThePlatformBaseIE
 from ..utils import (
    ExtractorError,
+    GeoRestrictedError,
    int_or_none,
    OnDemandPagedList,
    parse_qs,
@ -37,7 +38,7 @@ class MediasetIE(ThePlatformBaseIE):
            'id': 'F310575103000102',
            'ext': 'mp4',
            'title': 'Episodio 1',
-            'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+            'description': 'md5:e8017b7d7194e9bfb75299c2b8d81e02',
            'thumbnail': r're:^https?://.*\.jpg$',
            'duration': 2682.0,
            'upload_date': '20210530',
@ -45,6 +46,11 @@ class MediasetIE(ThePlatformBaseIE):
            'timestamp': 1622413946,
            'uploader': 'Canale 5',
            'uploader_id': 'C5',
+            'season': 'Season 1',
+            'episode': 'Episode 1',
+            'season_number': 1,
+            'episode_number': 1,
+            'chapters': [{'start_time': 0.0, 'end_time': 439.88}, {'start_time': 439.88, 'end_time': 1685.84}, {'start_time': 1685.84, 'end_time': 2682.0}],
        },
    }, {
        'url': 'https://www.mediasetplay.mediaset.it/video/matrix/puntata-del-25-maggio_F309013801000501',
@ -53,7 +59,7 @@ class MediasetIE(ThePlatformBaseIE):
            'id': 'F309013801000501',
            'ext': 'mp4',
            'title': 'Puntata del 25 maggio',
-            'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+            'description': 'md5:ee2e456e3eb1dba5e814596655bb5296',
            'thumbnail': r're:^https?://.*\.jpg$',
            'duration': 6565.008,
            'upload_date': '20200903',
@ -61,6 +67,11 @@ class MediasetIE(ThePlatformBaseIE):
            'timestamp': 1599172492,
            'uploader': 'Canale 5',
            'uploader_id': 'C5',
+            'season': 'Season 5',
+            'episode': 'Episode 5',
+            'season_number': 5,
+            'episode_number': 5,
+            'chapters': [{'start_time': 0.0, 'end_time': 3409.08}, {'start_time': 3409.08, 'end_time': 6565.008}],
        },
    }, {
        'url': 'https://www.mediasetplay.mediaset.it/video/cameracafe5/episodio-69-pezzo-di-luna_F303843101017801',
@ -69,7 +80,7 @@ class MediasetIE(ThePlatformBaseIE):
            'id': 'F303843101017801',
            'ext': 'mp4',
            'title': 'Episodio 69 - Pezzo di luna',
-            'description': '',
+            'description': 'md5:7c32c8ec4118b72588b9412f11353f73',
            'thumbnail': r're:^https?://.*\.jpg$',
            'duration': 263.008,
            'upload_date': '20200902',
@ -77,6 +88,11 @@ class MediasetIE(ThePlatformBaseIE):
            'timestamp': 1599064700,
            'uploader': 'Italia 1',
            'uploader_id': 'I1',
+            'season': 'Season 5',
+            'episode': 'Episode 178',
+            'season_number': 5,
+            'episode_number': 178,
+            'chapters': [{'start_time': 0.0, 'end_time': 261.88}, {'start_time': 261.88, 'end_time': 263.008}],
        },
    }, {
        'url': 'https://www.mediasetplay.mediaset.it/video/cameracafe5/episodio-51-tu-chi-sei_F303843107000601',
@ -85,7 +101,7 @@ class MediasetIE(ThePlatformBaseIE):
            'id': 'F303843107000601',
            'ext': 'mp4',
            'title': 'Episodio 51 - Tu chi sei?',
-            'description': '',
+            'description': 'md5:42ef006e56824cc31787a547590923f4',
            'thumbnail': r're:^https?://.*\.jpg$',
            'duration': 367.021,
            'upload_date': '20200902',
@ -93,6 +109,28 @@ class MediasetIE(ThePlatformBaseIE):
            'timestamp': 1599069817,
            'uploader': 'Italia 1',
            'uploader_id': 'I1',
+            'season': 'Season 5',
+            'episode': 'Episode 6',
+            'season_number': 5,
+            'episode_number': 6,
+            'chapters': [{'start_time': 0.0, 'end_time': 358.68}, {'start_time': 358.68, 'end_time': 367.021}],
+        },
+    }, {
+        # movie
+        'url': 'https://www.mediasetplay.mediaset.it/movie/selvaggi/selvaggi_F006474501000101',
+        'md5': '720440187a2ae26af8148eb9e6b901ed',
+        'info_dict': {
+            'id': 'F006474501000101',
+            'ext': 'mp4',
+            'title': 'Selvaggi',
+            'description': 'md5:cfdedbbfdd12d4d0e5dcf1fa1b75284f',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 5233.01,
+            'upload_date': '20210729',
+            'timestamp': 1627594716,
+            'uploader': 'Cine34',
+            'uploader_id': 'B6',
+            'chapters': [{'start_time': 0.0, 'end_time': 1938.56}, {'start_time': 1938.56, 'end_time': 5233.01}],
        },
    }, {
        # clip
@ -160,6 +198,22 @@ class MediasetIE(ThePlatformBaseIE):
            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 _check_drm_formats(self, tp_formats, video_id):
+        has_nondrm, drm_manifest = False, ''
+        for f in tp_formats:
+            if '_sampleaes/' in (f.get('manifest_url') or ''):
+                drm_manifest = drm_manifest or f['manifest_url']
+                f['has_drm'] = True
+            if not f.get('has_drm') and f.get('manifest_url'):
+                has_nondrm = True
+
+        nodrm_manifest = re.sub(r'_sampleaes/(\w+)_fp_', r'/\1_no_', drm_manifest)
+        if has_nondrm or nodrm_manifest == drm_manifest:
+            return
+
+        tp_formats.extend(self._extract_m3u8_formats(
+            nodrm_manifest, video_id, m3u8_id='hls', fatal=False) or [])
+
    def _real_extract(self, url):
        guid = self._match_id(url)
        tp_path = 'PR1GhC/media/guid/2702976343/' + guid
@ -167,10 +221,10 @@ class MediasetIE(ThePlatformBaseIE):

        formats = []
        subtitles = {}
-        first_e = None
+        first_e = geo_e = None
        asset_type = 'geoNo:HD,browser,geoIT|geoNo:HD,geoIT|geoNo:SD,browser,geoIT|geoNo:SD,geoIT|geoNo|HD|SD'
        # TODO: fixup ISM+none manifest URLs
-        for f in ('MPEG4', 'MPEG-DASH+none', 'M3U+none'):
+        for f in ('MPEG4', 'M3U'):
            try:
                tp_formats, tp_subtitles = self._extract_theplatform_smil(
                    update_url_query('http://link.theplatform.%s/s/%s' % (self._TP_TLD, tp_path), {
@ -179,13 +233,19 @@ class MediasetIE(ThePlatformBaseIE):
                        'assetTypes': asset_type,
                    }), guid, 'Downloading %s SMIL data' % (f.split('+')[0]))
            except ExtractorError as e:
+                if not geo_e and isinstance(e, GeoRestrictedError):
+                    geo_e = e
                if not first_e:
                    first_e = e
-                break
+                continue
+            self._check_drm_formats(tp_formats, guid)
            formats.extend(tp_formats)
            subtitles = self._merge_subtitles(subtitles, tp_subtitles)
-        if first_e and not formats:
-            raise first_e
+
+        # check for errors and report them
+        if (first_e or geo_e) and not formats:
+            raise geo_e or first_e
+
        self._sort_formats(formats)

        feed_data = self._download_json(
@ -201,15 +261,22 @@ class MediasetIE(ThePlatformBaseIE):
                    break

            info.update({
-                'episode_number': int_or_none(feed_data.get('tvSeasonEpisodeNumber')),
-                'season_number': int_or_none(feed_data.get('tvSeasonNumber')),
-                'series': feed_data.get('mediasetprogram$brandTitle'),
+                'description': info.get('description') or feed_data.get('description') or feed_data.get('longDescription'),
                'uploader': publish_info.get('description'),
                'uploader_id': publish_info.get('channel'),
                'view_count': int_or_none(feed_data.get('mediasetprogram$numberOfViews')),
                'thumbnail': thumbnail,
            })

+            if feed_data.get('programType') == 'episode':
+                info.update({
+                    'episode_number': int_or_none(
+                        feed_data.get('tvSeasonEpisodeNumber')),
+                    'season_number': int_or_none(
+                        feed_data.get('tvSeasonNumber')),
+                    'series': feed_data.get('mediasetprogram$brandTitle'),
+                })
+
        info.update({
            'id': guid,
            'formats': formats,
@ -224,37 +291,29 @@ class MediasetShowIE(MediasetIE):
                        https?://
                            (?:(?:www|static3)\.)?mediasetplay\.mediaset\.it/
                            (?:
-                                (?:fiction|programmi-tv|serie-tv)/(?:.+?/)?
-                                    (?:[a-z]+)_SE(?P<id>\d{12})
+                                (?:fiction|programmi-tv|serie-tv|kids)/(?:.+?/)?
+                                    (?:[a-z-]+)_SE(?P<id>\d{12})
                                    (?:,ST(?P<st>\d{12}))?
                                    (?:,sb(?P<sb>\d{9}))?$
                            )
                    )
                    '''
    _TESTS = [{
-        # TV Show webpage (with a single playlist)
-        'url': 'https://www.mediasetplay.mediaset.it/serie-tv/fireforce/episodi_SE000000001556',
+        # TV Show webpage (general webpage)
+        'url': 'https://www.mediasetplay.mediaset.it/programmi-tv/leiene/leiene_SE000000000061',
        'info_dict': {
-            'id': '000000001556',
-            'title': 'Fire Force',
+            'id': '000000000061',
+            'title': 'Le Iene',
        },
-        'playlist_count': 1,
+        'playlist_mincount': 7,
    }, {
-        # TV Show webpage (with multiple playlists)
+        # TV Show webpage (specific season)
        'url': 'https://www.mediasetplay.mediaset.it/programmi-tv/leiene/leiene_SE000000000061,ST000000002763',
        'info_dict': {
            'id': '000000002763',
            'title': 'Le Iene',
        },
-        'playlist_count': 7,
-    }, {
-        # TV Show specific playlist (single page)
-        'url': 'https://www.mediasetplay.mediaset.it/serie-tv/fireforce/episodi_SE000000001556,ST000000002738,sb100013107',
-        'info_dict': {
-            'id': '100013107',
-            'title': 'Episodi',
-        },
-        'playlist_count': 4,
+        'playlist_mincount': 7,
    }, {
        # TV Show specific playlist (with multiple pages)
        'url': 'https://www.mediasetplay.mediaset.it/programmi-tv/leiene/iservizi_SE000000000061,ST000000002763,sb100013375',
@ -262,7 +321,7 @@ class MediasetShowIE(MediasetIE):
            'id': '100013375',
            'title': 'I servizi',
        },
-        'playlist_count': 53,
+        'playlist_mincount': 50,
    }]

    _BY_SUBBRAND = 'https://feed.entertainment.tv.theplatform.eu/f/PR1GhC/mediaset-prod-all-programs-v2?byCustomValue={subBrandId}{%s}&sort=:publishInfo_lastPublished|desc,tvSeasonEpisodeNumber|desc&range=%d-%d'
@ -281,7 +340,7 @@ class MediasetShowIE(MediasetIE):
    def _real_extract(self, url):
        playlist_id, st, sb = self._match_valid_url(url).group('id', 'st', 'sb')
        if not sb:
-            page = self._download_webpage(url, playlist_id)
+            page = self._download_webpage(url, st or playlist_id)
            entries = [self.url_result(urljoin('https://www.mediasetplay.mediaset.it', url))
                       for url in re.findall(r'href="([^<>=]+SE\d{12},ST\d{12},sb\d{9})">[^<]+<', page)]
            title = (self._html_search_regex(r'(?s)<h1[^>]*>(.+?)</h1>', page, 'title', default=None)