1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
|
# coding: utf-8
from __future__ import unicode_literals
import re
from .theplatform import ThePlatformBaseIE
from ..utils import (
ExtractorError,
int_or_none,
parse_qs,
update_url_query,
)
class MediasetIE(ThePlatformBaseIE):
_TP_TLD = 'eu'
_VALID_URL = r'''(?x)
(?:
mediaset:|
https?://
(?:(?:www|static3)\.)?mediasetplay\.mediaset\.it/
(?:
(?:video|on-demand|movie)/(?:[^/]+/)+[^/]+_|
player/index\.html\?.*?\bprogramGuid=
)
)(?P<id>[0-9A-Z]{16,})
'''
_TESTS = [{
# full episode
'url': 'https://www.mediasetplay.mediaset.it/video/mrwronglezionidamore/episodio-1_F310575103000102',
'md5': 'a7e75c6384871f322adb781d3bd72c26',
'info_dict': {
'id': 'F310575103000102',
'ext': 'mp4',
'title': 'Episodio 1',
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 2682.0,
'upload_date': '20210530',
'series': 'Mr Wrong - Lezioni d\'amore',
'timestamp': 1622413946,
'uploader': 'Canale 5',
'uploader_id': 'C5',
},
}, {
'url': 'https://www.mediasetplay.mediaset.it/video/matrix/puntata-del-25-maggio_F309013801000501',
'md5': '1276f966ac423d16ba255ce867de073e',
'info_dict': {
'id': 'F309013801000501',
'ext': 'mp4',
'title': 'Puntata del 25 maggio',
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 6565.008,
'upload_date': '20200903',
'series': 'Matrix',
'timestamp': 1599172492,
'uploader': 'Canale 5',
'uploader_id': 'C5',
},
}, {
'url': 'https://www.mediasetplay.mediaset.it/video/cameracafe5/episodio-69-pezzo-di-luna_F303843101017801',
'md5': 'd1650ac9ff944f185556126a736df148',
'info_dict': {
'id': 'F303843101017801',
'ext': 'mp4',
'title': 'Episodio 69 - Pezzo di luna',
'description': '',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 263.008,
'upload_date': '20200902',
'series': 'Camera Café 5',
'timestamp': 1599064700,
'uploader': 'Italia 1',
'uploader_id': 'I1',
},
}, {
'url': 'https://www.mediasetplay.mediaset.it/video/cameracafe5/episodio-51-tu-chi-sei_F303843107000601',
'md5': '567e9ad375b7a27a0e370650f572a1e3',
'info_dict': {
'id': 'F303843107000601',
'ext': 'mp4',
'title': 'Episodio 51 - Tu chi sei?',
'description': '',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 367.021,
'upload_date': '20200902',
'series': 'Camera Café 5',
'timestamp': 1599069817,
'uploader': 'Italia 1',
'uploader_id': 'I1',
},
}, {
# clip
'url': 'https://www.mediasetplay.mediaset.it/video/gogglebox/un-grande-classico-della-commedia-sexy_FAFU000000661680',
'only_matching': True,
}, {
# iframe simple
'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665924&id=665924',
'only_matching': True,
}, {
# iframe twitter (from http://www.wittytv.it/se-prima-mi-fidavo-zero/)
'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665104&id=665104',
'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,
}, {
'url': 'https://www.mediasetplay.mediaset.it/movie/herculeslaleggendahainizio/hercules-la-leggenda-ha-inizio_F305927501000102',
'only_matching': True,
}]
@staticmethod
def _extract_urls(ie, webpage):
def _qs(url):
return parse_qs(url)
def _program_guid(qs):
return qs.get('programGuid', [None])[0]
entries = []
for mobj in re.finditer(
r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?video\.mediaset\.it/player/playerIFrame(?:Twitter)?\.shtml.*?)\1',
webpage):
embed_url = mobj.group('url')
embed_qs = _qs(embed_url)
program_guid = _program_guid(embed_qs)
if program_guid:
entries.append(embed_url)
continue
video_id = embed_qs.get('id', [None])[0]
if not video_id:
continue
urlh = ie._request_webpage(
embed_url, video_id, note='Following embed URL redirect')
embed_url = urlh.geturl()
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
info = self._extract_theplatform_metadata(tp_path, guid)
formats = []
subtitles = {}
first_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'):
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 SMIL data' % (f.split('+')[0]))
except ExtractorError as e:
if not first_e:
first_e = e
break
formats.extend(tp_formats)
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
if first_e and not formats:
raise first_e
self._sort_formats(formats)
feed_data = self._download_json(
'https://feed.entertainment.tv.theplatform.eu/f/PR1GhC/mediaset-prod-all-programs-v2/guid/-/' + guid,
guid, fatal=False)
if feed_data:
publish_info = feed_data.get('mediasetprogram$publishInfo') or {}
thumbnails = feed_data.get('thumbnails') or {}
thumbnail = None
for key, value in thumbnails.items():
if key.startswith('image_keyframe_poster-'):
thumbnail = value.get('url')
break
info.update({
'episode_number': int_or_none(feed_data.get('tvSeasonEpisodeNumber')),
'season_number': int_or_none(feed_data.get('tvSeasonNumber')),
'series': feed_data.get('mediasetprogram$brandTitle'),
'uploader': publish_info.get('description'),
'uploader_id': publish_info.get('channel'),
'view_count': int_or_none(feed_data.get('mediasetprogram$numberOfViews')),
'thumbnail': thumbnail,
})
info.update({
'id': guid,
'formats': formats,
'subtitles': subtitles,
})
return info
|
