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
|
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_urllib_parse,
compat_urllib_parse_unquote,
)
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
parse_iso8601,
sanitized_Request,
HEADRequest,
url_basename,
)
class ViewsterIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?viewster\.com/(?:serie|movie)/(?P<id>\d+-\d+-\d+)'
_TESTS = [{
# movie, Type=Movie
'url': 'http://www.viewster.com/movie/1140-11855-000/the-listening-project/',
'md5': 'e642d1b27fcf3a4ffa79f194f5adde36',
'info_dict': {
'id': '1140-11855-000',
'ext': 'mp4',
'title': 'The listening Project',
'description': 'md5:bac720244afd1a8ea279864e67baa071',
'timestamp': 1214870400,
'upload_date': '20080701',
'duration': 4680,
},
}, {
# series episode, Type=Episode
'url': 'http://www.viewster.com/serie/1284-19427-001/the-world-and-a-wall/',
'md5': '9243079a8531809efe1b089db102c069',
'info_dict': {
'id': '1284-19427-001',
'ext': 'mp4',
'title': 'The World and a Wall',
'description': 'md5:24814cf74d3453fdf5bfef9716d073e3',
'timestamp': 1428192000,
'upload_date': '20150405',
'duration': 1500,
},
}, {
# serie, Type=Serie
'url': 'http://www.viewster.com/serie/1303-19426-000/',
'info_dict': {
'id': '1303-19426-000',
'title': 'Is It Wrong to Try to Pick up Girls in a Dungeon?',
'description': 'md5:eeda9bef25b0d524b3a29a97804c2f11',
},
'playlist_count': 13,
}, {
# unfinished serie, no Type
'url': 'http://www.viewster.com/serie/1284-19427-000/baby-steps-season-2/',
'info_dict': {
'id': '1284-19427-000',
'title': 'Baby Steps—Season 2',
'description': 'md5:e7097a8fc97151e25f085c9eb7a1cdb1',
},
'playlist_mincount': 16,
}, {
# geo restricted series
'url': 'https://www.viewster.com/serie/1280-18794-002/',
'only_matching': True,
}, {
# geo restricted video
'url': 'https://www.viewster.com/serie/1280-18794-002/what-is-extraterritoriality-lawo/',
'only_matching': True,
}]
_ACCEPT_HEADER = 'application/json, text/javascript, */*; q=0.01'
def _download_json(self, url, video_id, note='Downloading JSON metadata', fatal=True):
request = sanitized_Request(url)
request.add_header('Accept', self._ACCEPT_HEADER)
request.add_header('Auth-token', self._AUTH_TOKEN)
return super(ViewsterIE, self)._download_json(request, video_id, note, fatal=fatal)
def _real_extract(self, url):
video_id = self._match_id(url)
# Get 'api_token' cookie
self._request_webpage(HEADRequest('http://www.viewster.com/'), video_id)
cookies = self._get_cookies('http://www.viewster.com/')
self._AUTH_TOKEN = compat_urllib_parse_unquote(cookies['api_token'].value)
info = self._download_json(
'https://public-api.viewster.com/search/%s' % video_id,
video_id, 'Downloading entry JSON')
entry_id = info.get('Id') or info['id']
# unfinished serie has no Type
if info.get('Type') in ('Serie', None):
try:
episodes = self._download_json(
'https://public-api.viewster.com/series/%s/episodes' % entry_id,
video_id, 'Downloading series JSON')
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
self.raise_geo_restricted()
else:
raise
entries = [
self.url_result(
'http://www.viewster.com/movie/%s' % episode['OriginId'], 'Viewster')
for episode in episodes]
title = (info.get('Title') or info['Synopsis']['Title']).strip()
description = info.get('Synopsis', {}).get('Detailed')
return self.playlist_result(entries, video_id, title, description)
formats = []
manifest_url = None
for media_type in ('application/f4m+xml', 'application/x-mpegURL', 'video/mp4'):
media = self._download_json(
'https://public-api.viewster.com/movies/%s/video?mediaType=%s'
% (entry_id, compat_urllib_parse.quote(media_type)),
video_id, 'Downloading %s JSON' % media_type, fatal=False)
if not media:
continue
video_url = media.get('Uri')
if not video_url:
continue
ext = determine_ext(video_url)
if ext == 'f4m':
manifest_url = video_url
video_url += '&' if '?' in video_url else '?'
video_url += 'hdcore=3.2.0&plugin=flowplayer-3.2.0.1'
formats.extend(self._extract_f4m_formats(
video_url, video_id, f4m_id='hds'))
elif ext == 'm3u8':
manifest_url = video_url
m3u8_formats = self._extract_m3u8_formats(
video_url, video_id, 'mp4', m3u8_id='hls',
fatal=False) # m3u8 sometimes fail
if m3u8_formats:
formats.extend(m3u8_formats)
else:
qualities_basename = self._search_regex(
'/([^/]+)(?:.csmil/manifest.f4m|.csmil/master.m3u8)',
manifest_url, 'qualities basename', default=None)
if qualities_basename:
QUALITIES_RE = r'((,\d+k)+,?)'
qualities = self._search_regex(
QUALITIES_RE, qualities_basename,
'qualities').strip(',').split(',')
http_template = re.sub(QUALITIES_RE, r'%s', qualities_basename)
http_url_basename = url_basename(video_url)
for q in qualities:
formats.append({
'url': video_url.replace(http_url_basename, http_template % q),
'ext': 'mp4',
'format_id': 'http-%s' % q,
'tbr': int_or_none(self._search_regex(
r'(\d+)k', q, 'bitrate', default=None)),
})
if not formats and not info.get('LanguageSets') and not info.get('VODSettings'):
self.raise_geo_restricted()
self._sort_formats(formats)
synopsis = info.get('Synopsis') or {}
# Prefer title outside synopsis since it's less messy
title = (info.get('Title') or synopsis['Title']).strip()
description = synopsis.get('Detailed') or (info.get('Synopsis') or {}).get('Short')
duration = int_or_none(info.get('Duration'))
timestamp = parse_iso8601(info.get('ReleaseDate'))
return {
'id': video_id,
'title': title,
'description': description,
'timestamp': timestamp,
'duration': duration,
'formats': formats,
}
|
