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
|
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
determine_ext,
parse_duration,
try_get,
unified_strdate,
)
class MediasetIE(InfoExtractor):
_VALID_URL = r'''(?x)
(?:
mediaset:|
https?://
(?:www\.)?video\.mediaset\.it/
(?:
(?:video|on-demand)/(?:[^/]+/)+[^/]+_|
player/playerIFrame(?:Twitter)?\.shtml\?.*?\bid=
)
)(?P<id>[0-9]+)
'''
_TESTS = [{
# full episode
'url': 'http://www.video.mediaset.it/video/hello_goodbye/full/quarta-puntata_661824.html',
'md5': '9b75534d42c44ecef7bf1ffeacb7f85d',
'info_dict': {
'id': '661824',
'ext': 'mp4',
'title': 'Quarta puntata',
'description': 'md5:7183696d6df570e3412a5ef74b27c5e2',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 1414,
'creator': 'mediaset',
'upload_date': '20161107',
'series': 'Hello Goodbye',
'categories': ['reality'],
},
'expected_warnings': ['is not a supported codec'],
}, {
'url': 'http://www.video.mediaset.it/video/matrix/full_chiambretti/puntata-del-25-maggio_846685.html',
'md5': '1276f966ac423d16ba255ce867de073e',
'info_dict': {
'id': '846685',
'ext': 'mp4',
'title': 'Puntata del 25 maggio',
'description': 'md5:ee2e456e3eb1dba5e814596655bb5296',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 6565,
'creator': 'mediaset',
'upload_date': '20180525',
'series': 'Matrix',
'categories': ['infotainment'],
},
'expected_warnings': ['HTTP Error 403: Forbidden'],
}, {
# clip
'url': 'http://www.video.mediaset.it/video/gogglebox/clip/un-grande-classico-della-commedia-sexy_661680.html',
'only_matching': True,
}, {
# iframe simple
'url': 'http://www.video.mediaset.it/player/playerIFrame.shtml?id=665924&autoplay=true',
'only_matching': True,
}, {
# iframe twitter (from http://www.wittytv.it/se-prima-mi-fidavo-zero/)
'url': 'https://www.video.mediaset.it/player/playerIFrameTwitter.shtml?id=665104&playrelated=false&autoplay=false&related=true&hidesocial=true',
'only_matching': True,
}, {
'url': 'mediaset:661824',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return [
mobj.group('url')
for mobj in re.finditer(
r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>https?://(?:www\.)?video\.mediaset\.it/player/playerIFrame(?:Twitter)?\.shtml\?.*?\bid=\d+.*?)\1',
webpage)]
def _real_extract(self, url):
video_id = self._match_id(url)
video = self._download_json(
'https://www.video.mediaset.it/html/metainfo.sjson',
video_id, 'Downloading media info', query={
'id': video_id
})['video']
title = video['title']
media_id = video.get('guid') or video_id
video_list = self._download_json(
'http://cdnsel01.mediaset.net/GetCdn2018.aspx',
video_id, 'Downloading video CDN JSON', query={
'streamid': media_id,
'format': 'json',
})['videoList']
formats = []
for format_url in video_list:
ext = determine_ext(format_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
format_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
elif ext == 'mpd':
formats.extend(self._extract_mpd_formats(
format_url, video_id, mpd_id='dash', fatal=False))
elif ext == 'ism' or '.ism' in format_url:
formats.extend(self._extract_ism_formats(
format_url, video_id, ism_id='mss', fatal=False))
else:
formats.append({
'url': format_url,
'format_id': determine_ext(format_url),
})
self._sort_formats(formats)
creator = try_get(
video, lambda x: x['brand-info']['publisher'], compat_str)
category = try_get(
video, lambda x: x['brand-info']['category'], compat_str)
categories = [category] if category else None
return {
'id': video_id,
'title': title,
'description': video.get('short-description'),
'thumbnail': video.get('thumbnail'),
'duration': parse_duration(video.get('duration')),
'creator': creator,
'upload_date': unified_strdate(video.get('production-date')),
'webpage_url': video.get('url'),
'series': video.get('brand-value'),
'season': video.get('season'),
'categories': categories,
'formats': formats,
}
|
