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
215
216
217
218
219
220
221
222
223
224
|
import base64
import re
import urllib.parse
from .common import InfoExtractor
from ..utils import (
ExtractorError,
clean_html,
time_seconds,
try_call,
unified_timestamp,
update_url_query,
)
class RadikoBaseIE(InfoExtractor):
_FULL_KEY = None
def _auth_client(self):
_, auth1_handle = self._download_webpage_handle(
'https://radiko.jp/v2/api/auth1', None, 'Downloading authentication page',
headers={
'x-radiko-app': 'pc_html5',
'x-radiko-app-version': '0.0.1',
'x-radiko-device': 'pc',
'x-radiko-user': 'dummy_user',
})
auth1_header = auth1_handle.info()
auth_token = auth1_header['X-Radiko-AuthToken']
kl = int(auth1_header['X-Radiko-KeyLength'])
ko = int(auth1_header['X-Radiko-KeyOffset'])
raw_partial_key = self._extract_full_key()[ko:ko + kl]
partial_key = base64.b64encode(raw_partial_key).decode()
area_id = self._download_webpage(
'https://radiko.jp/v2/api/auth2', None, 'Authenticating',
headers={
'x-radiko-device': 'pc',
'x-radiko-user': 'dummy_user',
'x-radiko-authtoken': auth_token,
'x-radiko-partialkey': partial_key,
}).split(',')[0]
auth_data = (auth_token, area_id)
self.cache.store('radiko', 'auth_data', auth_data)
return auth_data
def _extract_full_key(self):
if self._FULL_KEY:
return self._FULL_KEY
jscode = self._download_webpage(
'https://radiko.jp/apps/js/playerCommon.js', None,
note='Downloading player js code')
full_key = self._search_regex(
(r"RadikoJSPlayer\([^,]*,\s*(['\"])pc_html5\1,\s*(['\"])(?P<fullkey>[0-9a-f]+)\2,\s*{"),
jscode, 'full key', fatal=False, group='fullkey')
if full_key:
full_key = full_key.encode()
else: # use full key ever known
full_key = b'bcd151073c03b352e1ef2fd66c32209da9ca0afa'
self._FULL_KEY = full_key
return full_key
def _find_program(self, video_id, station, cursor):
station_program = self._download_xml(
'https://radiko.jp/v3/program/station/weekly/%s.xml' % station, video_id,
note='Downloading radio program for %s station' % station)
prog = None
for p in station_program.findall('.//prog'):
ft_str, to_str = p.attrib['ft'], p.attrib['to']
ft = unified_timestamp(ft_str, False)
to = unified_timestamp(to_str, False)
if ft <= cursor and cursor < to:
prog = p
break
if not prog:
raise ExtractorError('Cannot identify radio program to download!')
assert ft, to
return prog, station_program, ft, ft_str, to_str
def _extract_formats(self, video_id, station, is_onair, ft, cursor, auth_token, area_id, query):
m3u8_playlist_data = self._download_xml(
f'https://radiko.jp/v3/station/stream/pc_html5/{station}.xml', video_id,
note='Downloading stream information')
m3u8_urls = m3u8_playlist_data.findall('.//url')
formats = []
found = set()
for url_tag in m3u8_urls:
pcu = url_tag.find('playlist_create_url')
url_attrib = url_tag.attrib
playlist_url = update_url_query(pcu.text, {
'station_id': station,
**query,
'l': '15',
'lsid': '88ecea37e968c1f17d5413312d9f8003',
'type': 'b',
})
if playlist_url in found:
continue
else:
found.add(playlist_url)
time_to_skip = None if is_onair else cursor - ft
domain = urllib.parse.urlparse(playlist_url).netloc
subformats = self._extract_m3u8_formats(
playlist_url, video_id, ext='m4a',
live=True, fatal=False, m3u8_id=domain,
note=f'Downloading m3u8 information from {domain}',
headers={
'X-Radiko-AreaId': area_id,
'X-Radiko-AuthToken': auth_token,
})
for sf in subformats:
if re.fullmatch(r'[cf]-radiko\.smartstream\.ne\.jp', domain):
# Prioritize live radio vs playback based on extractor
sf['preference'] = 100 if is_onair else -100
if not is_onair and url_attrib['timefree'] == '1' and time_to_skip:
sf['downloader_options'] = {'ffmpeg_args': ['-ss', time_to_skip]}
formats.extend(subformats)
return formats
class RadikoIE(RadikoBaseIE):
_VALID_URL = r'https?://(?:www\.)?radiko\.jp/#!/ts/(?P<station>[A-Z0-9-]+)/(?P<id>\d+)'
_TESTS = [{
# QRR (文化放送) station provides <desc>
'url': 'https://radiko.jp/#!/ts/QRR/20210425101300',
'only_matching': True,
}, {
# FMT (TOKYO FM) station does not provide <desc>
'url': 'https://radiko.jp/#!/ts/FMT/20210810150000',
'only_matching': True,
}, {
'url': 'https://radiko.jp/#!/ts/JOAK-FM/20210509090000',
'only_matching': True,
}]
def _real_extract(self, url):
station, video_id = self._match_valid_url(url).groups()
vid_int = unified_timestamp(video_id, False)
prog, station_program, ft, radio_begin, radio_end = self._find_program(video_id, station, vid_int)
auth_cache = self.cache.load('radiko', 'auth_data')
for attempt in range(2):
auth_token, area_id = (not attempt and auth_cache) or self._auth_client()
formats = self._extract_formats(
video_id=video_id, station=station, is_onair=False,
ft=ft, cursor=vid_int, auth_token=auth_token, area_id=area_id,
query={
'start_at': radio_begin,
'ft': radio_begin,
'end_at': radio_end,
'to': radio_end,
'seek': video_id,
})
if formats:
break
return {
'id': video_id,
'title': try_call(lambda: prog.find('title').text),
'description': clean_html(try_call(lambda: prog.find('info').text)),
'uploader': try_call(lambda: station_program.find('.//name').text),
'uploader_id': station,
'timestamp': vid_int,
'formats': formats,
'is_live': True,
}
class RadikoRadioIE(RadikoBaseIE):
_VALID_URL = r'https?://(?:www\.)?radiko\.jp/#!/live/(?P<id>[A-Z0-9-]+)'
_TESTS = [{
# QRR (文化放送) station provides <desc>
'url': 'https://radiko.jp/#!/live/QRR',
'only_matching': True,
}, {
# FMT (TOKYO FM) station does not provide <desc>
'url': 'https://radiko.jp/#!/live/FMT',
'only_matching': True,
}, {
'url': 'https://radiko.jp/#!/live/JOAK-FM',
'only_matching': True,
}]
def _real_extract(self, url):
station = self._match_id(url)
self.report_warning('Downloader will not stop at the end of the program! Press Ctrl+C to stop')
auth_token, area_id = self._auth_client()
# get current time in JST (GMT+9:00 w/o DST)
vid_now = time_seconds(hours=9)
prog, station_program, ft, _, _ = self._find_program(station, station, vid_now)
title = prog.find('title').text
description = clean_html(prog.find('info').text)
station_name = station_program.find('.//name').text
formats = self._extract_formats(
video_id=station, station=station, is_onair=True,
ft=ft, cursor=vid_now, auth_token=auth_token, area_id=area_id,
query={})
return {
'id': station,
'title': title,
'description': description,
'uploader': station_name,
'uploader_id': station,
'timestamp': ft,
'formats': formats,
'is_live': True,
}
|
