def _parseRestaurantPage(self, pool, queue, url, name, base=False):
utils.log('[%s] parsing restaurant page %s (%s)' % (self, name, url))
try:
soup = utils.getSoup(url)
except:
#utils.printException()
utils.log("[%s] error downloading page %s (%s)" % (self, name, url))
return
content = soup.find('div', { 'id' : 'content'})
if content is None:
return
entity = Entity()
entity.title = content.find('h1').getText()
entity.subcategory = "restaurant"
entity.seattletimes = {}
details = content.find('div', {'id' : 'edbtext'})
desc = details.find('p').getText()
if desc is not None:
entity.desc = desc
details = details.findAll('p', {'class' : 'list'})
address = details[0].renderContents().strip().replace('<br />', '')
address = re.sub('[ \n\t]+', ' ', address)
entity.address = address
if len(details) > 1:
site = details[1].get('href')
if site is not None:
entity.site = site
if len(details) > 2:
hoursOfOperation = details[2].getText()
if hoursOfOperation is not None:
entity.hoursOfOperation = hoursOfOperation
key = (entity.title, entity.address)
if key in self.seen or '(closed)' in entity.title.lower():
return
self.seen.add(key)
self._output.put(entity)
