yt_dlp/extractor/mediaset.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import functools
   5 import re
   6
   7 from .theplatform import ThePlatformBaseIE
   8 from ..utils import (
   9     ExtractorError,
  10     int_or_none,
  11     OnDemandPagedList,
  12     parse_qs,
  13     try_get,
  14     urljoin,
  15     update_url_query,
  16 )
  17
  18
  19 class MediasetIE(ThePlatformBaseIE):
  20     _TP_TLD = 'eu'
  21     _VALID_URL = r'''(?x)
  22                     (?:
  23                         mediaset:|
  24                         https?://
  25                             (?:(?:www|static3)\.)?mediasetplay\.mediaset\.it/
  26                             (?:
  27                                 (?:video|on-demand|movie)/(?:[^/]+/)+[^/]+_|
  28                                 player/index\.html\?.*?\bprogramGuid=
  29                             )
  30                     )(?P<id>[0-9A-Z]{16,})
  31                     '''
  32     _TESTS = [{
  33         # full episode
  34         'url': 'https://www.mediasetplay.mediaset.it/video/mrwronglezionidamore/episodio-1_F310575103000102',
  35         'md5': 'a7e75c6384871f322adb781d3bd72c26',
  36         'info_dict': {
  37             'id': 'F310575103000102',
  38             'ext': 'mp4',
  39             'title': 'Episodio 1',
  40             'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  41             'thumbnail': r're:^https?://.*\.jpg$',
  42             'duration': 2682.0,
  43             'upload_date': '20210530',
  44             'series': 'Mr Wrong - Lezioni d\'amore',
  45             'timestamp': 1622413946,
  46             'uploader': 'Canale 5',
  47             'uploader_id': 'C5',
  48         },
  49     }, {
  50         'url': 'https://www.mediasetplay.mediaset.it/video/matrix/puntata-del-25-maggio_F309013801000501',
  51         'md5': '1276f966ac423d16ba255ce867de073e',
  52         'info_dict': {
  53             'id': 'F309013801000501',
  54             'ext': 'mp4',
  55             'title': 'Puntata del 25 maggio',
  56             'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  57             'thumbnail': r're:^https?://.*\.jpg$',
  58             'duration': 6565.008,
  59             'upload_date': '20200903',
  60             'series': 'Matrix',
  61             'timestamp': 1599172492,
  62             'uploader': 'Canale 5',
  63             'uploader_id': 'C5',
  64         },
  65     }, {
  66         'url': 'https://www.mediasetplay.mediaset.it/video/cameracafe5/episodio-69-pezzo-di-luna_F303843101017801',
  67         'md5': 'd1650ac9ff944f185556126a736df148',
  68         'info_dict': {
  69             'id': 'F303843101017801',
  70             'ext': 'mp4',
  71             'title': 'Episodio 69 - Pezzo di luna',
  72             'description': '',
  73             'thumbnail': r're:^https?://.*\.jpg$',
  74             'duration': 263.008,
  75             'upload_date': '20200902',
  76             'series': 'Camera Café 5',
  77             'timestamp': 1599064700,
  78             'uploader': 'Italia 1',
  79             'uploader_id': 'I1',
  80         },
  81     }, {
  82         'url': 'https://www.mediasetplay.mediaset.it/video/cameracafe5/episodio-51-tu-chi-sei_F303843107000601',
  83         'md5': '567e9ad375b7a27a0e370650f572a1e3',
  84         'info_dict': {
  85             'id': 'F303843107000601',
  86             'ext': 'mp4',
  87             'title': 'Episodio 51 - Tu chi sei?',
  88             'description': '',
  89             'thumbnail': r're:^https?://.*\.jpg$',
  90             'duration': 367.021,
  91             'upload_date': '20200902',
  92             'series': 'Camera Café 5',
  93             'timestamp': 1599069817,
  94             'uploader': 'Italia 1',
  95             'uploader_id': 'I1',
  96         },
  97     }, {
  98         # clip
  99         'url': 'https://www.mediasetplay.mediaset.it/video/gogglebox/un-grande-classico-della-commedia-sexy_FAFU000000661680',
 100         'only_matching': True,
 101     }, {
 102         # iframe simple
 103         'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665924&id=665924',
 104         'only_matching': True,
 105     }, {
 106         # iframe twitter (from http://www.wittytv.it/se-prima-mi-fidavo-zero/)
 107         'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665104&id=665104',
 108         'only_matching': True,
 109     }, {
 110         'url': 'mediaset:FAFU000000665924',
 111         'only_matching': True,
 112     }, {
 113         'url': 'https://www.mediasetplay.mediaset.it/video/mediasethaacuoreilfuturo/palmieri-alicudi-lisola-dei-tre-bambini-felici--un-decreto-per-alicudi-e-tutte-le-microscuole_FD00000000102295',
 114         'only_matching': True,
 115     }, {
 116         'url': 'https://www.mediasetplay.mediaset.it/video/cherryseason/anticipazioni-degli-episodi-del-23-ottobre_F306837101005C02',
 117         'only_matching': True,
 118     }, {
 119         'url': 'https://www.mediasetplay.mediaset.it/video/tg5/ambiente-onda-umana-per-salvare-il-pianeta_F309453601079D01',
 120         'only_matching': True,
 121     }, {
 122         'url': 'https://www.mediasetplay.mediaset.it/video/grandefratellovip/benedetta-una-doccia-gelata_F309344401044C135',
 123         'only_matching': True,
 124     }, {
 125         'url': 'https://www.mediasetplay.mediaset.it/movie/herculeslaleggendahainizio/hercules-la-leggenda-ha-inizio_F305927501000102',
 126         'only_matching': True,
 127     }]
 128
 129     @staticmethod
 130     def _extract_urls(ie, webpage):
 131         def _qs(url):
 132             return parse_qs(url)
 133
 134         def _program_guid(qs):
 135             return qs.get('programGuid', [None])[0]
 136
 137         entries = []
 138         for mobj in re.finditer(
 139                 r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?video\.mediaset\.it/player/playerIFrame(?:Twitter)?\.shtml.*?)\1',
 140                 webpage):
 141             embed_url = mobj.group('url')
 142             embed_qs = _qs(embed_url)
 143             program_guid = _program_guid(embed_qs)
 144             if program_guid:
 145                 entries.append(embed_url)
 146                 continue
 147             video_id = embed_qs.get('id', [None])[0]
 148             if not video_id:
 149                 continue
 150             urlh = ie._request_webpage(
 151                 embed_url, video_id, note='Following embed URL redirect')
 152             embed_url = urlh.geturl()
 153             program_guid = _program_guid(_qs(embed_url))
 154             if program_guid:
 155                 entries.append(embed_url)
 156         return entries
 157
 158     def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
 159         for video in smil.findall(self._xpath_ns('.//video', namespace)):
 160             video.attrib['src'] = re.sub(r'(https?://vod05)t(-mediaset-it\.akamaized\.net/.+?.mpd)\?.+', r'\1\2', video.attrib['src'])
 161         return super(MediasetIE, self)._parse_smil_formats(smil, smil_url, video_id, namespace, f4m_params, transform_rtmp_url)
 162
 163     def _real_extract(self, url):
 164         guid = self._match_id(url)
 165         tp_path = 'PR1GhC/media/guid/2702976343/' + guid
 166         info = self._extract_theplatform_metadata(tp_path, guid)
 167
 168         formats = []
 169         subtitles = {}
 170         first_e = None
 171         asset_type = 'geoNo:HD,browser,geoIT|geoNo:HD,geoIT|geoNo:SD,browser,geoIT|geoNo:SD,geoIT|geoNo|HD|SD'
 172         # TODO: fixup ISM+none manifest URLs
 173         for f in ('MPEG4', 'MPEG-DASH+none', 'M3U+none'):
 174             try:
 175                 tp_formats, tp_subtitles = self._extract_theplatform_smil(
 176                     update_url_query('http://link.theplatform.%s/s/%s' % (self._TP_TLD, tp_path), {
 177                         'mbr': 'true',
 178                         'formats': f,
 179                         'assetTypes': asset_type,
 180                     }), guid, 'Downloading %s SMIL data' % (f.split('+')[0]))
 181             except ExtractorError as e:
 182                 if not first_e:
 183                     first_e = e
 184                 break
 185             formats.extend(tp_formats)
 186             subtitles = self._merge_subtitles(subtitles, tp_subtitles)
 187         if first_e and not formats:
 188             raise first_e
 189         self._sort_formats(formats)
 190
 191         feed_data = self._download_json(
 192             'https://feed.entertainment.tv.theplatform.eu/f/PR1GhC/mediaset-prod-all-programs-v2/guid/-/' + guid,
 193             guid, fatal=False)
 194         if feed_data:
 195             publish_info = feed_data.get('mediasetprogram$publishInfo') or {}
 196             thumbnails = feed_data.get('thumbnails') or {}
 197             thumbnail = None
 198             for key, value in thumbnails.items():
 199                 if key.startswith('image_keyframe_poster-'):
 200                     thumbnail = value.get('url')
 201                     break
 202
 203             info.update({
 204                 'episode_number': int_or_none(feed_data.get('tvSeasonEpisodeNumber')),
 205                 'season_number': int_or_none(feed_data.get('tvSeasonNumber')),
 206                 'series': feed_data.get('mediasetprogram$brandTitle'),
 207                 'uploader': publish_info.get('description'),
 208                 'uploader_id': publish_info.get('channel'),
 209                 'view_count': int_or_none(feed_data.get('mediasetprogram$numberOfViews')),
 210                 'thumbnail': thumbnail,
 211             })
 212
 213         info.update({
 214             'id': guid,
 215             'formats': formats,
 216             'subtitles': subtitles,
 217         })
 218         return info
 219
 220
 221 class MediasetShowIE(MediasetIE):
 222     _VALID_URL = r'''(?x)
 223                     (?:
 224                         https?://
 225                             (?:(?:www|static3)\.)?mediasetplay\.mediaset\.it/
 226                             (?:
 227                                 (?:fiction|programmi-tv|serie-tv)/(?:.+?/)?
 228                                     (?:[a-z]+)_SE(?P<id>\d{12})
 229                                     (?:,ST(?P<st>\d{12}))?
 230                                     (?:,sb(?P<sb>\d{9}))?$
 231                             )
 232                     )
 233                     '''
 234     _TESTS = [{
 235         # TV Show webpage (with a single playlist)
 236         'url': 'https://www.mediasetplay.mediaset.it/serie-tv/fireforce/episodi_SE000000001556',
 237         'info_dict': {
 238             'id': '000000001556',
 239             'title': 'Fire Force',
 240         },
 241         'playlist_count': 1,
 242     }, {
 243         # TV Show webpage (with multiple playlists)
 244         'url': 'https://www.mediasetplay.mediaset.it/programmi-tv/leiene/leiene_SE000000000061,ST000000002763',
 245         'info_dict': {
 246             'id': '000000002763',
 247             'title': 'Le Iene',
 248         },
 249         'playlist_count': 7,
 250     }, {
 251         # TV Show specific playlist (single page)
 252         'url': 'https://www.mediasetplay.mediaset.it/serie-tv/fireforce/episodi_SE000000001556,ST000000002738,sb100013107',
 253         'info_dict': {
 254             'id': '100013107',
 255             'title': 'Episodi',
 256         },
 257         'playlist_count': 4,
 258     }, {
 259         # TV Show specific playlist (with multiple pages)
 260         'url': 'https://www.mediasetplay.mediaset.it/programmi-tv/leiene/iservizi_SE000000000061,ST000000002763,sb100013375',
 261         'info_dict': {
 262             'id': '100013375',
 263             'title': 'I servizi',
 264         },
 265         'playlist_count': 53,
 266     }]
 267
 268     _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'
 269     _PAGE_SIZE = 25
 270
 271     def _fetch_page(self, sb, page):
 272         lower_limit = page * self._PAGE_SIZE + 1
 273         upper_limit = lower_limit + self._PAGE_SIZE - 1
 274         content = self._download_json(
 275             self._BY_SUBBRAND % (sb, lower_limit, upper_limit), sb)
 276         for entry in content.get('entries') or []:
 277             yield self.url_result(
 278                 'mediaset:' + entry['guid'],
 279                 playlist_title=entry['mediasetprogram$subBrandDescription'])
 280
 281     def _real_extract(self, url):
 282         playlist_id, st, sb = self._match_valid_url(url).group('id', 'st', 'sb')
 283         if not sb:
 284             page = self._download_webpage(url, playlist_id)
 285             entries = [self.url_result(urljoin('https://www.mediasetplay.mediaset.it', url))
 286                        for url in re.findall(r'href="([^<>=]+SE\d{12},ST\d{12},sb\d{9})">[^<]+<', page)]
 287             title = (self._html_search_regex(r'(?s)<h1[^>]*>(.+?)</h1>', page, 'title', default=None)
 288                      or self._og_search_title(page))
 289             return self.playlist_result(entries, st or playlist_id, title)
 290
 291         entries = OnDemandPagedList(
 292             functools.partial(self._fetch_page, sb),
 293             self._PAGE_SIZE)
 294         title = try_get(entries, lambda x: x[0]['playlist_title'])
 295
 296         return self.playlist_result(entries, sb, title)