|
|
@ -98,7 +98,12 @@ class CalibreCrawler(threading.Thread):
|
|
|
|
|
|
|
|
|
|
|
|
print "[calibr] Starting crawl on %s ..." % url
|
|
|
|
print "[calibr] Starting crawl on %s ..." % url
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
try:
|
|
|
|
response = urllib2.urlopen(url + "browse/category/allbooks")
|
|
|
|
response = urllib2.urlopen(url + "browse/category/allbooks")
|
|
|
|
|
|
|
|
except URLError:
|
|
|
|
|
|
|
|
print "Skipping %s, as the server could not be successfully reached." % url
|
|
|
|
|
|
|
|
return None
|
|
|
|
|
|
|
|
|
|
|
|
page_contents = response.read()
|
|
|
|
page_contents = response.read()
|
|
|
|
|
|
|
|
|
|
|
|
matcher = re.compile("<div class=\"load_data\" title=\"([\[\]0-9\s,]*)\">")
|
|
|
|
matcher = re.compile("<div class=\"load_data\" title=\"([\[\]0-9\s,]*)\">")
|
|
|
|