#!/usr/bin/python
from BeautifulSoup import BeautifulSoup
import requests
from urlparse import urljoin
import requests_cache
from re import escape
requests_cache.configure('/tmp/data')
 
def get_places():
	i = 1;
	while True: 
		url = 'http://www.sw.gov.pl/pl/jednostki/index,%s,0.html' % (i,)
		r = requests.get(url)
		print "Requests URL: ",url
		s = BeautifulSoup(r.text)
		rows = s.findAll('div',{'class':'praca-margines'})[1:]
		if rows: #Result found 
			for row in rows:
				yield urljoin(url,row.find('a')['href'])
		else: # No more result
			break;
		i+=1
 
def get_text(url):
	r = requests.get(url)
	print "Requests URL: ",url
	s = BeautifulSoup(r.text)
	return  [x.text for x in s.find('div',{'class':'jednostka'}).findChildren()]
dataset = ([x]+get_text(x) for x in get_places())
dataset_clean = (('"'+y.replace('"','\"')+'"' for y in x) for x in dataset)
open('b.csv','wb').write("\n".join(";".join(x) for x in dataset_clean).encode('utf-8'))

Wynik działania