def main():
table = Datasheet()
tel = ''
street = ''
locality = ''
title = ''
for i in range(3):
page = i+1
url = URL("http://torino.paginegialle.it/pgol/4-veterinari/3-torino/p-%s?mr=50" % page)
print "collecting from %s" % url
connection = url.open()
doc = Document( connection.read() )
items = doc.by_class('item_sx')
row = []
for j, item in enumerate(items):
divs = item.by_class('address')
try:
title = item.by_class('item_head')[0].by_tag('a')[0].content
except IndexError, e:
print >> sys.stderr, "%s" % j, e
pass
for z, div in enumerate(divs):
if div != None:
try:
street = div.by_class('street-address')[0].content
locality = div.by_class('locality')[0].content
tel = div.by_class('tel')[0].by_class('value')[0].content
except IndexError, e:
print >> sys.stderr, "%s" % z, e
pass
save = "%s, %s %s, %s \n" % ( plaintext(title), plaintext(street).replace(",", ""), plaintext(locality).replace('(TO)', ''), plaintext(tel).replace(",", "") )
print >> sys.stderr, save
row.append(save)
def main():
table = Datasheet()
url = URL("http://www.comuniecitta.it/torino/elenco-ospedali-di-torino.html")
connection = url.open()
doc = Document( connection.read() )
items = doc.by_class('ulamm')[1:]
row = []
for ul in items:
li = ul.by_tag('li')
kind = plaintext(ul.previous.content)
for el in li:
if el != None:
save = "%s, %s \n" % ( plaintext(el.content).replace('\n', ','), kind, )
row.append(save)
table.append( row )
table.save("files/h_torino.txt")
