Skrypt pobierający wszystkie dane PKW ze strony http://klk.kbw.gov.pl/kalkulator/20141116/000000/SMD/

getpkw.py

import requests
import re
import time
import sys

def URL(teryt):
	while teryt[-2:] == "00":
		teryt = teryt[:-2]
	url = "http://klk.kbw.gov.pl/kalkulator/20141116/000000/SMD"
	if len(teryt) > 0:
		url += "/" + teryt[0:2] + "0000"
	if len(teryt) > 2:
		url += "/" + teryt[0:4] + "00"
	if len(teryt) > 4:
		url += "/" + teryt

	return url

def getOKW(teryt, okw):
	url = "http://klk.kbw.gov.pl/TMP/" + teryt + "/" + okw + "/" + teryt + "-" + okw + ".zip"
	print(url)
	sys.stdout.flush()

	MAX = 100
	while MAX:
		MAX -= 1
		try:
			requests.get(URL(teryt) + "/" + okw)
			res = requests.get(url)
			if res.ok:
				print(res)
				sys.stdout.flush()
				return res.content
		except:
			pass
		print("Error, sleeping 1s")
		sys.stdout.flush()
		time.sleep(1)

def saveOKW(teryt, okw):
	if teryt < "026401":
		return

	data = getOKW(teryt, okw)

	with open(teryt + "-" + okw + ".zip", "wb") as f:
		f.write(data)

def ls(teryt):
	url = URL(teryt)
	data = requests.get(url)
	if not data.ok:
		print(data)
		sys.stdout.flush()

	list = re.findall(b'href="([^"]*)"', data.content)
	return [e.decode().split("/")[-1] for e in list]

for woj in ls(""):
	for powiat in ls(woj):
		for gmina in ls(powiat):
			for okw in ls(gmina):
				saveOKW(gmina, okw)