102
103
104
105
106
107
108
109
110
111
112
113
114
115
116 | 102
103
104
105
106
107
108
109
110
111
112
113
114
115
116 |
-
+
| href="(?:https?://www.liveradio.ie)?/stations/([\w-]+) .*?
<img\s+src="/(files/images/[^"]+)" .*?
="country">([^<]+)< .*?
itemprop="name"><a[^>]+>([^<]+)</a> .*?
class="genre">([^<]+)<
""", html, re.X|re.S)
for row in ls:
log.DATA(row)
#log.DATA(row)
id, img, country, title, genre = row
r.append(dict(
homepage = self.base + "stations/" + id,
url = "urn:liveradio:" + id,
playing = unhtml(country),
title = unhtml(title),
genre = unhtml(genre), |
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 | 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 |
+
-
-
+
+
-
+
| <span class="country">United Kingdom</span>
</a>
<div class="name" itemprop="name"><a href="http://www.liveradio.ie/stations/soulconnexion-radio">Soulconnexion Radio</a></div>
<div class="genre">Funk, Soul</div>
"""
def pq_extract(self, html):
r = []
html = pq(html).make_links_absolute(self.base)
for radio in pq(html).find("*[itemscope][itemtype='http://schema.org/RadioStation']"):
log.DATA(radio)
for radio in html.find("*[itemscope][itemtype='http://schema.org/RadioStation']"):
#log.DATA(radio)
radio = pq(radio)
href = radio.find("*[itemprop='name'] a").attr("href")
id = re.search("/([\w-]+)$", href).group(1)
r.append(dict(
homepage = self.base + "stations/" + id,
url = "urn:liveradio:" + id,
playing = radio.find("*.country").text(),
title = radio.find("*[itemprop='name']").text(),
genre = radio.find("*.genre").text(),
img = self.base + re.sub("^/", "", radio.find("img[itemprop='image']").attr("src"))
img = radio.find("img[itemprop='image']").attr("src")
))
return r
# Update `url` on station data access (incurs a delay for playing or recording)
#
# · utilizes action.handler["urn:liveradio"] → urn_resolve hook |