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
|
# downloads stream list from shoutcast for given category
def update_streams(self, cat, search=""):
if (not cat or cat == self.empty):
__print__("nocat")
return []
ucat = urllib.quote(cat)
# new extraction regex
if not conf.get("pyquery") or not pq:
rx_stream = re.compile("""
<a\s+class="?playbutton\d?[^>]+id="(\d+)".+?
<a\s+class="[\w\s]*title[\w\s]*"[^>]+href="(http://[^">]+)"[^>]*>([^<>]+)</a>.+?
(?:Recently\s*played|Coming\s*soon|Now\s*playing):\s*([^<]*).+?
ners">(\d*)<.+?
bitrate">(\d*)<.+?
type">([MP3AAC]*)
""", re.S|re.I|re.X)
rx_next = re.compile("""onclick="showMoreGenre""")
for uu in rx_stream.findall(html):
(id, homepage, title, playing, ls, bit, fmt) = uu
__print__(uu)
entries += [{
"title": self.entity_decode(title),
"url": "http://yp.shoutcast.com/sbin/tunein-station.pls?id=" + id,
"homepage": http.fix_url(homepage),
"playing": self.entity_decode(playing),
"genre": cat, #self.strip_tags(uu[4]),
|
<
<
<
<
<
<
<
<
<
<
<
<
<
<
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
|
|
|
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
|
# downloads stream list from shoutcast for given category
def update_streams(self, cat, search=""):
if (not cat or cat == self.empty):
__print__("nocat")
return []
ucat = urllib.quote(cat)
# loop
entries = []
next = 0
max = int(conf.max_streams)
count = max
rx_stream = None
rx_next = re.compile("""onclick="showMoreGenre""")
while (next < max):
# page
url = "http://www.shoutcast.com/genre-ajax/" + ucat
referer = url.replace("/genre-ajax", "/radio")
params = { "strIndex":"0", "count":str(count), "ajax":"true", "mode":"listeners", "order":"desc" }
html = http.ajax(url, params, referer) #,feedback=self.parent.status)
__print__(html)
# regular expressions
if not conf.get("pyquery") or not pq:
# new extraction regex
if not rx_stream:
rx_stream = re.compile(
"""
<a\s+class="?playbutton\d?[^>]+id="(\d+)".+?
<a\s+class="[\w\s]*title[\w\s]*"[^>]+href="(http://[^">]+)"[^>]*>([^<>]+)</a>.+?
(?:Recently\s*played|Coming\s*soon|Now\s*playing):\s*([^<]*).+?
ners">(\d*)<.+?
bitrate">(\d*)<.+?
type">([MP3AAC]*)
""",
re.S|re.I|re.X
)
# extract entries
self.parent.status("parsing document...")
__print__("loop-rx")
for m in rx_stream.findall(html):
(id, homepage, title, playing, ls, bit, fmt) = m
__print__(uu)
entries += [{
"title": self.entity_decode(title),
"url": "http://yp.shoutcast.com/sbin/tunein-station.pls?id=" + id,
"homepage": http.fix_url(homepage),
"playing": self.entity_decode(playing),
"genre": cat, #self.strip_tags(uu[4]),
|