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
|
# api: streamtuner2
# title: Internet-Radio
# description: Broad list of webradios from all genres.
# type: channel
# category: radio
# version: 1.5
# url: http://www.internet-radio.com/
# config:
# { name: internetradio_max_pages, type: int, value: 5, category: limit, description: How many pages to fetch and read. }
# priority: standard
# png:
# iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAABHNCSVQICAgIfAhkiAAAAaZJREFUOI2N0j1PlEEUBeBnlsVoRJcCPwINxIJGAoWVFbVK4g8w
# oUUTFRNbG3+FhVErK36BhcYCrTR8FS4mRGUXFEKCUizRwLXgnfV1Awk3mUzmnHPvPXNnUkSE40RKFYxhHKMYxFb1GIlnMLVN/etBUjuGWDm6wEHHyQbLW/Qd
# JTu8QEq9mJlnogz3sHOJV3iHz2iKzuDiH+bm+J3XD74EU5Gc7pSn/4aYUi14s8BIhkZ5puKhvdgpNFVccaA5oaP7TO66SCuYKnG9weMmjaz5yadqqfvkPE/z
# 8TLTIp4U3I01ljY5f/gQu1LPGvWS7Rel5NtLzOzRlfk+Ngd4i48Ke9PZVpNGUCvwawvsZm6db8GtoLt9s4iIFotZFEwXybU1VjO+z4egv/MVKlIaqTMMJ2nh
# eeH0wQYX4BwbiQkRTSmdktJ1KY3lGYznuw3zWsS2lLo2WMl4P49ycjCbn3k0pfuVg5m1432e4zr9UGMbLwv8avmP/OJOBQOlAsvF3hYNMititzg2Kuxn7iyr
# VbSG/tltFHt3CVvATRBRH0lpEvfwXXL3L9zE/NEe0EfHAAAAAElFTkSuQmCC
# extraction-method: regex, dom
#
# Internet-Radio.co.uk/.com is one of the largest stream directories.
# Available music genre classifications are mirrored verbatim and flatly.
#
# The new version of this plugin alternates between PyQuery and Regex
# station extraction. Both overlook some paid or incomplete entries.
# HTTP retrieval happens in one batch, determined by the number of pages
# setting, rather than the global max_streams option.
#
from channels import *
import re
from config import *
import ahttp
from pq import pq
# streams and gui
class internet_radio (ChannelPlugin):
# control data
listformat = "pls"
categories = []
base_url = "https://www.internet-radio.com/"
has_search = True
# load genres
def update_categories(self):
html = ahttp.get(self.base_url)
rx = re.compile("""="/stations/[-+&.\w\s%]+/">([^<]+)<""")
cats = rx.findall(html)
cats = list(set(cats))
cats = [s.capitalize() for s in cats]
self.categories = sorted(list(set(cats)))
# fetch station lists
def update_streams(self, cat, search=None):
entries = []
if not search and cat not in self.categories:
return []
rx_pages = re.compile('href="/stations/[-+\w%\d\s]+/page(\d+)">\d+</a>')
# Fetch multiple pages at once
html = []
max_pages = max(int(conf.internetradio_max_pages), 1)
for page in range(1, max_pages):
# Append HTML source
if search:
html.append(
ahttp.get("%ssearch/?radio=%s%s" % (self.base_url, search, "&page=%s" % page if page>1 else ""))
)
else:
html.append(
ahttp.get("%sstations/%s/%s" % (self.base_url, cat.lower().replace(" ", "%20"), "page%s" % page if page>1 else ""))
)
# Is there a next page?
if str(page+1) not in rx_pages.findall(html[-1]):
break
self.parent.status(float(page)/float(max_pages+1), timeout=1)
# Alternatively try regex or pyquery parsing
#log.HTTP(html)
entries = self.from_html(html)
# fin
log.FINISHED("internet_radio.update_streams")
return entries
# Switch update method
@use_rx
def from_html(self, html, use_rx):
if use_rx:
return self.with_regex(html)
else:
return self.with_dom(html)
# Regex extraction
def with_regex(self, html):
log.PROC("internet-radio, regex")
r = []
html = "\n".join(html)
# Break up into <tr> blocks before extracting bits
rx_tr = re.compile("""<tr[^>]*>(.+?)</tr>""", re.S)
rx_data = re.compile(r"""
playjp',\s*'(https?://[^'">]+)
.*? <h4.*?>([^<>]+)</
.*? <b>([^<>]*)</b>
(?: .*? href="(.*?)" )?
(?: .*? Genres:((?:</?a[^>]+>|\w+|\s+)+) )?
.*? (\d+)\s*Listeners
.*? (\d+)\s*Kbps
""", re.S|re.X)
for div in rx_tr.findall(html):
if div.find('id="pagination"') < 0:
#log.DATA(len(div))
uu = rx_data.search(div)
if uu:
(url, title, playing, homepage, genres, listeners, bitrate) = uu.groups()
# transform data
r.append({
"url": url,
"genre": strip_tags(genres or ""),
"homepage": ahttp.fix_url(homepage or ""),
"title": nl(title or ""),
"playing": nl(playing or ""),
"bitrate": int(bitrate or 0),
"listeners": int(listeners or 0),
"format": "audio/mpeg", # there is no stream info on that, but internet-radio.org.uk doesn't seem very ogg-friendly anyway, so we assume the default here
})
else:
log.DATA("Regex couldn't decipher entry:", div)
return r
# DOM traversing
def with_dom(self, html_list):
log.PROC("internet-radio, dom")
rx_numbers = re.compile("(\d+)")
r = []
for html in html_list:
# the streams are arranged in table rows
doc = pq(html)
for dir in (pq(e) for e in doc("tr")):
#log.HTML(dir)
# bitrate/listeners
bl = dir.find("p")
if bl:
bl = rx_numbers.findall(str(bl.text()) + " 0 0")
else:
bl = [0, 0]
# stream url
url = dir.find("i").eq(0).parent().attr("onclick")
if url:
url = re.search("(http://[^\'\"\>]+)", url)
if url:
url = url.group(0)
else:
url = ""
else:
url = ""
row = {
"title": dir.find("h4").text(),
"homepage": ahttp.fix_url(dir.find("a.small").attr("href") or ""),
"url": url,
"genre": dir.find("a[href^='/stations/']").text() or "",
"listeners": int(bl[0]),
"bitrate": int(bl[1]),
"format": "audio/mpeg",
"playing": dir.find("b").text(),
}
#log.DATA(row)
r.append(row)
return r
|
