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 | "string": "",
"cat": cat,
"order": "listeners",
"amount": conf.max_streams,
}
referer = "http://www.shoutcast.com/?action=sub&cat="+cat
html = http.get(url, params=params, referer=referer, ajax=1)
#__print__(dbg.DATA, html)
#__print__(re.compile("id=(\d+)").findall(html));
# new html
"""
<tr>
<td width="6%"><a href="#" onClick="window.open('player/?radname=Schlagerhoelle%20%2D%20das%20Paradies%20fr%20Schlager%20%20und%20Discofox&stationid=14687&coding=MP3','radplayer','height=232,width=776')"><img class="icon transition" src="/img/icon-play.png" alt="Play"></a></td>
<td width="30%"><a class="transition" href="http://yp.shoutcast.com/sbin/tunein-station.pls?id=14687">Schlagerhoelle - das Paradies fr Schlager und Discofox</a></td>
<td width="12%" style="text-align:left;" width="10%">Oldies</td>
<td width="12%" style="text-align:left;" width="10%">955</td>
<td width="12%" style="text-align:left;" width="10%">128</td>
<td width="12%" style="text-align:left;" width="10%">MP3</td>
</tr>
"""
# With the new shallow <td> lists it doesn't make much sense to use
# the pyquery DOM traversal. There aren't any sensible selectors to
# extract values; it's just counting the tags.
# And there's a bug in PyQuery 1.2.4 and CssSelector. So make two
# attempts, alternate between regex and DOM; user preference first.
entries = []
use_regex = not conf.get("pyquery") or not pq
retry = 2
while retry and not entries:
retry -= 1
try:
if use_regex:
entries = self.with_regex(html)
else:
entries = self.with_dom(html)
except Exception as e:
__print__(dbg.ERR, e)
use_regex ^= 1
return entries
# Extract using regex
def with_regex(self, html):
__print__(dbg.PROC, "channels.shoutcast.update_streams: regex scraping mode")
rx_stream = re.compile( |
>
>
<
>
|
<
<
<
|
<
|
<
|
>
|
|
<
>
| 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 | "string": "",
"cat": cat,
"order": "listeners",
"amount": conf.max_streams,
}
referer = "http://www.shoutcast.com/?action=sub&cat="+cat
html = http.get(url, params=params, referer=referer, ajax=1)
self.parent.status(0.75)
#__print__(dbg.DATA, html)
#__print__(re.compile("id=(\d+)").findall(html));
# new html
"""
<tr>
<td width="6%"><a href="#" onClick="window.open('player/?radname=Schlagerhoelle%20%2D%20das%20Paradies%20fr%20Schlager%20%20und%20Discofox&stationid=14687&coding=MP3','radplayer','height=232,width=776')"><img class="icon transition" src="/img/icon-play.png" alt="Play"></a></td>
<td width="30%"><a class="transition" href="http://yp.shoutcast.com/sbin/tunein-station.pls?id=14687">Schlagerhoelle - das Paradies fr Schlager und Discofox</a></td>
<td width="12%" style="text-align:left;" width="10%">Oldies</td>
<td width="12%" style="text-align:left;" width="10%">955</td>
<td width="12%" style="text-align:left;" width="10%">128</td>
<td width="12%" style="text-align:left;" width="10%">MP3</td>
</tr>
"""
# With the new shallow <td> lists it doesn't make much sense to use
# the pyquery DOM traversal. There aren't any sensible selectors to
# extract values; it's just counting the tags.
#
# And there's a bug in PyQuery 1.2.4 and CssSelector. So make two
# attempts, alternate between regex and DOM; user preference first.
#
for use_rx in [not conf.pyquery or not pq, conf.pyquery]:
try:
entries = (self.with_regex(html) if use_rx else self.with_dom(html))
if len(entries):
break
except Exception as e:
__print__(dbg.ERR, e)
continue
return entries
# Extract using regex
def with_regex(self, html):
__print__(dbg.PROC, "channels.shoutcast.update_streams: regex scraping mode")
rx_stream = re.compile( |
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190 | "format": self.mime_fmt(fmt),
}]
return entries
# Iterate over DOM instead
def with_dom(self, html):
__print__(dbg.PROC, "channels.shoutcast.update_streams: attempt DOM/PyQuery processing")
entries = []
for div in (pq(e) for e in pq(html).find("tr")):
entries.append({
"title": div.find("a.transition").text(),
"url": div.find("a.transition").attr("href"),
"homepage": "",
"listeners": int(div.find("td:eq(3)").text()), |
|
| 174
175
176
177
178
179
180
181
182
183
184
185
186
187
188 | "format": self.mime_fmt(fmt),
}]
return entries
# Iterate over DOM instead
def with_dom(self, html):
__print__(dbg.PROC, "channels.shoutcast.update_streams: attempt PyQuery/DOM traversal")
entries = []
for div in (pq(e) for e in pq(html).find("tr")):
entries.append({
"title": div.find("a.transition").text(),
"url": div.find("a.transition").attr("href"),
"homepage": "",
"listeners": int(div.find("td:eq(3)").text()), |