1
2
3
4
5
6
7
8
9
10
11
12
13
|
# api: streamtuner2
# title: RCast
# description: Streaming server provider and station directory
# type: channel
# category: radio
# version: 0.2
# url: http://www.rcast.net/dir
# png:
# iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAABH0lEQVR42mPgZWXkNxdhsScH87Iw8DOAGHcDBf6Tg02FmW1RDPj97cvf/0BwJ4D/HyHNGAbc9uUBawaBf0BASDOGASBNIM1fHt34BaKRFd4CGg4C
# eA0Agd9fPv255c39F90AXC6DG3ArSOwP1O9wDTc92cA23gqR/g3i3yvz/IFuMNgAeyBANx0Enk7M+Qlig5wO0wgCt1yZwepuBQj8sQUCsAG/3r74g+7k318//oWxYYaDwM/3r//A2GADsKUDGICxH7XG/wK75s8f
# cEB/vnwU7C2MdADDn2+d+4VsADCKIc72ZPsHM/zvn99/cRpw050Z7O+nvVkYUfpmx4KfMDGcBiB7A90AZIzXgJ9vX4D9eceP9x9ZBhCDwQZQmp0BVv4354bQNGwAAAAASUVORK5CYII=
# priority: extra
# extraction-method: regex
|
>
|
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
|
# encoding: utf-8
# api: streamtuner2
# title: RCast
# description: Streaming server provider and station directory
# type: channel
# category: radio
# version: 0.3
# url: http://www.rcast.net/dir
# png:
# iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAABH0lEQVR42mPgZWXkNxdhsScH87Iw8DOAGHcDBf6Tg02FmW1RDPj97cvf/0BwJ4D/HyHNGAbc9uUBawaBf0BASDOGASBNIM1fHt34BaKRFd4CGg4C
# eA0Agd9fPv255c39F90AXC6DG3ArSOwP1O9wDTc92cA23gqR/g3i3yvz/IFuMNgAeyBANx0Enk7M+Qlig5wO0wgCt1yZwepuBQj8sQUCsAG/3r74g+7k318//oWxYYaDwM/3r//A2GADsKUDGICxH7XG/wK75s8f
# cEB/vnwU7C2MdADDn2+d+4VsADCKIc72ZPsHM/zvn99/cRpw050Z7O+nvVkYUfpmx4KfMDGcBiB7A90AZIzXgJ9vX4D9eceP9x9ZBhCDwQZQmp0BVv4354bQNGwAAAAASUVORK5CYII=
# priority: extra
# extraction-method: regex
|
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
|
break
# extract
ls = re.findall("""
<tr> .*?
<audio\s+id="jp_audio_(\d+)" .*? src="([^"]+?);?"> .*?
<h4.*?>([^<>]+)</a></h4> .*?
<b>([^<>]*)</b> .*?
<b\s+class[^>]+>([^<>]*)</b> .*?
Genre:(.+?)</td> .*?
</i>\s*(\d+)\s*Kbps<br>\s*(audio/[\w.-]+)
""", html, re.X|re.S)
#log.DATA(re.findall("(<audio.*?>)", html))
# blocks
for row in ls:
try:
log.UI(row)
r.append(dict(
id = row[0],
url = row[1],
title = unhtml(row[2]),
playing = unhtml(row[3]),
homepage = unhtml(row[4]),
genre = unhtml(row[5]),
bitrate = to_int(row[6]),
format = row[7],
#listeners = to_int(listeners[5])
))
except:
pass #some field missing
# done
return r
|
|
|
|
|
|
|
|
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
|
break
# extract
ls = re.findall("""
<tr> .*?
<audio\s+id="jp_audio_(\d+)" .*? src="([^"]+?);?"> .*?
<h4.*?>([^<>]+)</a></h4> .*?
<b\\b[^>]*>([^<>]*)</b> .*?
<small\s+class[^>]+>([^<>]*)</small> .*?
Genres?:(.+?)<br> .*?
<p[^>]*>\s*(\d+)\s*Kbps
""", html, re.X|re.S)
#log.DATA(re.findall("(<audio.*?>)", html))
# blocks
for row in ls:
try:
log.UI(row)
r.append(dict(
id = row[0],
url = row[1],
title = unhtml(row[2]),
playing = unhtml(row[3]),
homepage = unhtml(row[4]),
genre = unhtml(strip_tags(row[5])),
bitrate = to_int(row[6]),
#format = row[7],
#listeners = to_int(listeners[5])
))
except:
pass #some field missing
# done
return r
|