Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/mediaset.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .theplatform import ThePlatformBaseIE
   7 from ..compat import (
   8     compat_parse_qs,
   9     compat_str,
  10     compat_urllib_parse_urlparse,
  11 )
  12 from ..utils import (
  13     ExtractorError,
  14     int_or_none,
  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)/(?:[^/]+/)+[^/]+_|
  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/hellogoodbye/quarta-puntata_FAFU000000661824',
  35         'md5': '9b75534d42c44ecef7bf1ffeacb7f85d',
  36         'info_dict': {
  37             'id': 'FAFU000000661824',
  38             'ext': 'mp4',
  39             'title': 'Quarta puntata',
  40             'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  41             'thumbnail': r're:^https?://.*\.jpg$',
  42             'duration': 1414.26,
  43             'upload_date': '20161107',
  44             'series': 'Hello Goodbye',
  45             'timestamp': 1478532900,
  46             'uploader': 'Rete 4',
  47             'uploader_id': 'R4',
  48         },
  49     }, {
  50         'url': 'https://www.mediasetplay.mediaset.it/video/matrix/puntata-del-25-maggio_F309013801000501',
  51         'md5': '288532f0ad18307705b01e581304cd7b',
  52         'info_dict': {
  53             'id': 'F309013801000501',
  54             'ext': 'mp4',
  55             'title': 'Puntata del 25 maggio',
  56             'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  57             'thumbnail': r're:^https?://.*\.jpg$',
  58             'duration': 6565.007,
  59             'upload_date': '20180526',
  60             'series': 'Matrix',
  61             'timestamp': 1527326245,
  62             'uploader': 'Canale 5',
  63             'uploader_id': 'C5',
  64         },
  65     }, {
  66         # clip
  67         'url': 'https://www.mediasetplay.mediaset.it/video/gogglebox/un-grande-classico-della-commedia-sexy_FAFU000000661680',
  68         'only_matching': True,
  69     }, {
  70         # iframe simple
  71         'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665924&id=665924',
  72         'only_matching': True,
  73     }, {
  74         # iframe twitter (from http://www.wittytv.it/se-prima-mi-fidavo-zero/)
  75         'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665104&id=665104',
  76         'only_matching': True,
  77     }, {
  78         'url': 'mediaset:FAFU000000665924',
  79         'only_matching': True,
  80     }, {
  81         'url': 'https://www.mediasetplay.mediaset.it/video/mediasethaacuoreilfuturo/palmieri-alicudi-lisola-dei-tre-bambini-felici--un-decreto-per-alicudi-e-tutte-le-microscuole_FD00000000102295',
  82         'only_matching': True,
  83     }, {
  84         'url': 'https://www.mediasetplay.mediaset.it/video/cherryseason/anticipazioni-degli-episodi-del-23-ottobre_F306837101005C02',
  85         'only_matching': True,
  86     }, {
  87         'url': 'https://www.mediasetplay.mediaset.it/video/tg5/ambiente-onda-umana-per-salvare-il-pianeta_F309453601079D01',
  88         'only_matching': True,
  89     }, {
  90         'url': 'https://www.mediasetplay.mediaset.it/video/grandefratellovip/benedetta-una-doccia-gelata_F309344401044C135',
  91         'only_matching': True,
  92     }]
  93
  94     @staticmethod
  95     def _extract_urls(ie, webpage):
  96         def _qs(url):
  97             return compat_parse_qs(compat_urllib_parse_urlparse(url).query)
  98
  99         def _program_guid(qs):
 100             return qs.get('programGuid', [None])[0]
 101
 102         entries = []
 103         for mobj in re.finditer(
 104                 r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?video\.mediaset\.it/player/playerIFrame(?:Twitter)?\.shtml.*?)\1',
 105                 webpage):
 106             embed_url = mobj.group('url')
 107             embed_qs = _qs(embed_url)
 108             program_guid = _program_guid(embed_qs)
 109             if program_guid:
 110                 entries.append(embed_url)
 111                 continue
 112             video_id = embed_qs.get('id', [None])[0]
 113             if not video_id:
 114                 continue
 115             urlh = ie._request_webpage(
 116                 embed_url, video_id, note='Following embed URL redirect')
 117             embed_url = compat_str(urlh.geturl())
 118             program_guid = _program_guid(_qs(embed_url))
 119             if program_guid:
 120                 entries.append(embed_url)
 121         return entries
 122
 123     def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
 124         for video in smil.findall(self._xpath_ns('.//video', namespace)):
 125             video.attrib['src'] = re.sub(r'(https?://vod05)t(-mediaset-it\.akamaized\.net/.+?.mpd)\?.+', r'\1\2', video.attrib['src'])
 126         return super(MediasetIE, self)._parse_smil_formats(smil, smil_url, video_id, namespace, f4m_params, transform_rtmp_url)
 127
 128     def _real_extract(self, url):
 129         guid = self._match_id(url)
 130         tp_path = 'PR1GhC/media/guid/2702976343/' + guid
 131         info = self._extract_theplatform_metadata(tp_path, guid)
 132
 133         formats = []
 134         subtitles = {}
 135         first_e = None
 136         for asset_type in ('SD', 'HD'):
 137             # TODO: fixup ISM+none manifest URLs
 138             for f in ('MPEG4', 'MPEG-DASH+none', 'M3U+none'):
 139                 try:
 140                     tp_formats, tp_subtitles = self._extract_theplatform_smil(
 141                         update_url_query('http://link.theplatform.%s/s/%s' % (self._TP_TLD, tp_path), {
 142                             'mbr': 'true',
 143                             'formats': f,
 144                             'assetTypes': asset_type,
 145                         }), guid, 'Downloading %s %s SMIL data' % (f.split('+')[0], asset_type))
 146                 except ExtractorError as e:
 147                     if not first_e:
 148                         first_e = e
 149                     break
 150                 for tp_f in tp_formats:
 151                     tp_f['quality'] = 1 if asset_type == 'HD' else 0
 152                 formats.extend(tp_formats)
 153                 subtitles = self._merge_subtitles(subtitles, tp_subtitles)
 154         if first_e and not formats:
 155             raise first_e
 156         self._sort_formats(formats)
 157
 158         fields = []
 159         for templ, repls in (('tvSeason%sNumber', ('', 'Episode')), ('mediasetprogram$%s', ('brandTitle', 'numberOfViews', 'publishInfo'))):
 160             fields.extend(templ % repl for repl in repls)
 161         feed_data = self._download_json(
 162             'https://feed.entertainment.tv.theplatform.eu/f/PR1GhC/mediaset-prod-all-programs/guid/-/' + guid,
 163             guid, fatal=False, query={'fields': ','.join(fields)})
 164         if feed_data:
 165             publish_info = feed_data.get('mediasetprogram$publishInfo') or {}
 166             info.update({
 167                 'episode_number': int_or_none(feed_data.get('tvSeasonEpisodeNumber')),
 168                 'season_number': int_or_none(feed_data.get('tvSeasonNumber')),
 169                 'series': feed_data.get('mediasetprogram$brandTitle'),
 170                 'uploader': publish_info.get('description'),
 171                 'uploader_id': publish_info.get('channel'),
 172                 'view_count': int_or_none(feed_data.get('mediasetprogram$numberOfViews')),
 173             })
 174
 175         info.update({
 176             'id': guid,
 177             'formats': formats,
 178             'subtitles': subtitles,
 179         })
 180         return info