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
|
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
|
-
+
-
+
+
+
+
+
-
-
+
+
+
+
-
+
-
-
+
+
+
-
+
-
-
+
+
+
+
+
-
-
+
+
+
+
+
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
-
-
-
-
+
+
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
-
+
|
import re
from config import *
from channels import *
import ahttp
import action
# hook special JSON format in to avoid grepping images by generic handler
# obsolete: hook special JSON format in to avoid grepping images by generic handler
action.playlist_fmt_prio.insert(5, "rnjs")
action.playlist_content_map.insert(7, ("rnjs", r'"logo175x175rounded"'))
action.extract_playlist.extr_urls["rnjs"] = dict(
url = r" (?x) \"streamUrl\" \s*:\s* \"(\w+:\\?/\\?/[^\"]+)\" ",
title = r" (?x) \"(?:description|seoTitle)\" \s*:\s* \"([^\"]+)\" ",
unesc = "json",
)
# Radio.net
#
# · Uses HTML block-wise regex extraction.
# → <a href="stationname.radio.net"> <img…> <strong>…</strong> <small>…</small>
# → <div class="sc-1crnfmg-11 sc-1crnfmg-12 cYzyuZ"><a href="/s/kissfmuk">
# → basically just title/url, images in a separate json blob
#
# · Currently using an urn: to resolve stream urls at play time.
#
# previously:
# · There's an API key in each page listing, contained in a script block
# as `apiKey: '…'?`
#
#
html = ahttp.get("http://www.radio.net/")
html = ahttp.get("http://www.radio.net/genre")
self.set_key(html)
ls = re.findall("""<li><a class="language-info".*?>([\w\s']+)</a>""", html)
self.categories = [i for i in ls][0:-18]
ls = re.findall("""<a class="[^"]+" href="/genre/(\w+)">([^<]+)</a>""", html)
self.categories = ["Top 40 and Charts"] + [i[1] for i in ls]
# Fetch entries
def update_streams(self, cat, search=None):
# category page, get key
urlcat = cat.replace(" ", "-").lower()
html = ahttp.get(self.genre_url.format(cat))
html = ahttp.get(self.genre_url.format(urlcat))
for p in range(2, 4):
if html.find('"?p={}">'.format(p)) >= 0:
html += ahttp.get(self.genre_url.format(cat) + "?p={}".format(p))
if html.find('?p={}"'.format(p)) >= 0:
html += ahttp.get(self.genre_url.format(urlcat) + "?p={}".format(p))
self.set_key(html)
r = []
# prefetch images from embedded json (genres and location would also be sourceable from "playables":[…])
imgs = dict(re.findall('\],"id":"(\w+)","logo100x100":"(htt[^"]+)",', html))
#log.DATA(imgs)
# split station blocks
for row in re.findall("""<div class="stationinfo(.+?)</div>""", html, re.S):
log.FOR_rOW(1)
# extract text fields
d = re.findall("""
<a\s+href="(?:https?:)?(//(?:[\w-]+)\.radio\.net/s/([^"]+)/?)" .*?
<img[^>]+ src="([^<">]+)" .*?
<strong[^>]*>(.*?)</strong> .*?
<small[^>]*>\s*(.*?)\s*</small>
""", row, re.X|re.S)
# log.DATA_ROW(d)
if d and len(d) and len(d[0]) == 5:
href, name, img, title, desc = d[0]
r.append(dict(
name = name,
genre = cat,
title = unhtml(title),
playing = unhtml(desc),
url = "urn:radionet:"+name, #self._url(name),
homepage = "http:{}".format(href),
img = img,
));
|