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
|
# coding: utf-8
from __future__ import unicode_literals
import time
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
js_to_json,
try_get,
update_url_query,
urlencode_postdata,
)
class PicartoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www.)?picarto\.tv/(?P<id>[a-zA-Z0-9]+)'
_TEST = {
'url': 'https://picarto.tv/Setz',
'info_dict': {
'id': 'Setz',
'ext': 'mp4',
'title': 're:^Setz [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'timestamp': int,
'is_live': True
},
'skip': 'Stream is offline',
}
@classmethod
def suitable(cls, url):
return False if PicartoVodIE.suitable(url) else super(PicartoIE, cls).suitable(url)
def _real_extract(self, url):
channel_id = self._match_id(url)
stream_page = self._download_webpage(url, channel_id)
if '>This channel does not exist' in stream_page:
raise ExtractorError(
'Channel %s does not exist' % channel_id, expected=True)
player = self._parse_json(
self._search_regex(
r'(?s)playerSettings\[\d+\]\s*=\s*(\{.+?\}\s*\n)', stream_page,
'player settings'),
channel_id, transform_source=js_to_json)
if player.get('online') is False:
raise ExtractorError('Stream is offline', expected=True)
cdn_data = self._download_json(
'https://picarto.tv/process/channel', channel_id,
data=urlencode_postdata({'loadbalancinginfo': channel_id}),
note='Downloading load balancing info')
def get_event(key):
return try_get(player, lambda x: x['event'][key], compat_str) or ''
params = {
'token': player.get('token') or '',
'ticket': get_event('ticket'),
'con': int(time.time() * 1000),
'type': get_event('ticket'),
'scope': get_event('scope'),
}
prefered_edge = cdn_data.get('preferedEdge')
default_tech = player.get('defaultTech')
formats = []
for edge in cdn_data['edges']:
edge_ep = edge.get('ep')
if not edge_ep or not isinstance(edge_ep, compat_str):
continue
edge_id = edge.get('id')
for tech in cdn_data['techs']:
tech_label = tech.get('label')
tech_type = tech.get('type')
preference = 0
if edge_id == prefered_edge:
preference += 1
if tech_type == default_tech:
preference += 1
format_id = []
if edge_id:
format_id.append(edge_id)
if tech_type == 'application/x-mpegurl' or tech_label == 'HLS':
format_id.append('hls')
formats.extend(self._extract_m3u8_formats(
update_url_query(
'https://%s/hls/%s/index.m3u8'
% (edge_ep, channel_id), params),
channel_id, 'mp4', preference=preference,
m3u8_id='-'.join(format_id), fatal=False))
continue
elif tech_type == 'video/mp4' or tech_label == 'MP4':
format_id.append('mp4')
formats.append({
'url': update_url_query(
'https://%s/mp4/%s.mp4' % (edge_ep, channel_id),
params),
'format_id': '-'.join(format_id),
'preference': preference,
})
else:
# rtmp format does not seem to work
continue
self._sort_formats(formats)
mature = player.get('mature')
if mature is None:
age_limit = None
else:
age_limit = 18 if mature is True else 0
return {
'id': channel_id,
'title': self._live_title(channel_id),
'is_live': True,
'thumbnail': player.get('vodThumb'),
'age_limit': age_limit,
'formats': formats,
}
class PicartoVodIE(InfoExtractor):
_VALID_URL = r'https?://(?:www.)?picarto\.tv/videopopout/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://picarto.tv/videopopout/ArtofZod_2017.12.12.00.13.23.flv',
'md5': '3ab45ba4352c52ee841a28fb73f2d9ca',
'info_dict': {
'id': 'ArtofZod_2017.12.12.00.13.23.flv',
'ext': 'mp4',
'title': 'ArtofZod_2017.12.12.00.13.23.flv',
'thumbnail': r're:^https?://.*\.jpg'
},
}, {
'url': 'https://picarto.tv/videopopout/Plague',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
vod_info = self._parse_json(
self._search_regex(
r'(?s)#vod-player["\']\s*,\s*(\{.+?\})\s*\)', webpage,
video_id),
video_id, transform_source=js_to_json)
formats = self._extract_m3u8_formats(
vod_info['vod'], video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls')
self._sort_formats(formats)
return {
'id': video_id,
'title': video_id,
'thumbnail': vod_info.get('vodThumb'),
'formats': formats,
}
|
