def _parseDetailPage(self, name, href, subcategory):
try:
soup = utils.getSoup(href)
except urllib2.HTTPError:
utils.log("[%s] error parsing %s (%s)" % (self, name, href))
return
summ = soup.find('div', {'class' : 'summary-address'})
try:
addrp = summ.find('p', {'class' : 'adr'})
street_addr = addrp.find('span', {'class' : 'street-address'}).getText().strip()
locality = addrp.find('span', {'class' : 'locality'}).getText().strip()
region = addrp.find('span', {'class' : 'region'}).getText().strip()
try:
postal_code = addrp.find('span', {'class' : 'postal-code'}).getText().strip()
except AttributeError:
postal_code = ""
addr = "%s, %s, %s %s" % (street_addr, locality, region, postal_code)
except AttributeError:
try:
p = summ.find('p').getText()
r = re.compile('(.*)nr\. ', re.DOTALL)
m = r.match(p)
if m is None:
r = re.compile('(.*)at[. ]', re.DOTALL)
m = r.match(p)
addr = m.groups()[0].replace('\n', ' ').strip()
except AttributeError:
utils.log("[%s] error parsing %s (%s)" % (self, name, href))
return
entity = Entity()
entity.subcategory = subcategory
entity.title = name
entity.address = addr
entity.nymag = { }
self._output.put(entity)
