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
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
|
# Break up into <tr> blocks before extracting bits
rx_tr = re.compile("""<tr[^>]*>(.+?)</tr>""", re.S)
rx_data = re.compile(r"""
\?u=(https?://[^'">]+/listen\.pls)
.*?
<div[^>]+10px[^>]+>(.+?)</div>
.*?
(?:href="/station/[^>]+|<b)>\s*([^<>]+)\s*</[ab]>
.*?
(?:<br>\s*([^<>]+)\s*<br>)+?
.*?
<a[^>]+class="url"[^>]+href="([^<">]+)"
.*?
(?:(\d+)\s+Kbps \s*<br>\s*)+?
(?:(\d+)\s+Listeners \s*<br>\s*)+?
""", re.S|re.X)
for div in rx_tr.findall(html):
#__print__(dbg.DATA, len(div))
uu = rx_data.search(div)
if uu:
(url, genres, title, playing, homepage, bitrate, listeners) = uu.groups()
# transform data
r.append({
"url": url,
"genre": self.strip_tags(genres),
"homepage": http.fix_url(homepage),
"title": title.strip(),
"playing": playing.strip(),
"bitrate": int(bitrate if bitrate else 0),
"listeners": int(listeners if listeners else 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:
__print__(dbg.ERR, "rx missed", div)
return r
# DOM traversing
def with_dom(self, html_list):
__print__(dbg.PROC, "internet-radio, dom")
rx_numbers = re.compile("(\d+)")
|
|
>
>
|
|
>
>
|
|
>
>
>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
|
# Break up into <tr> blocks before extracting bits
rx_tr = re.compile("""<tr[^>]*>(.+?)</tr>""", re.S)
rx_data = re.compile(r"""
\?u=(https?://[^'">]+/listen\.pls)
.*?
<div[^>]+10px[^>]+>(.+?)</div>
.*?
listing2
.*?
(?:href="/station/[^>]+> | <b>) ([^<>]+) </[ab]>
(?:\s*</span>\s*)*
(?:<br>\s*([^<>]+)\s*<br>)?
.*?
(?:<a[^>]+class="url"[^>]+href="([^<">]+)")?
.+
listing1
.*?
(?:(\d+)\s+Kbps \s*<br>\s*)?
(?:(\d+)\s+Listeners)?
(?:\s*<br>\s*)?
\s*</td>
""", re.S|re.X)
for div in rx_tr.findall(html):
if div.find('id="pagination"') < 0:
#__print__(dbg.DATA, len(div))
uu = rx_data.search(div)
if uu:
(url, genres, title, playing, homepage, bitrate, listeners) = uu.groups()
# transform data
r.append({
"url": url,
"genre": self.strip_tags(genres),
"homepage": http.fix_url(homepage),
"title": (title if title else "").strip(),
"playing": (playing if playing else "").strip(),
"bitrate": int(bitrate if bitrate else 0),
"listeners": int(listeners if listeners else 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:
__print__(dbg.ERR, "rx missed", div)
return r
# DOM traversing
def with_dom(self, html_list):
__print__(dbg.PROC, "internet-radio, dom")
rx_numbers = re.compile("(\d+)")
|