Scrape Z*** Faktury Loop 4

#!/usr/bin/python
# -*- coding: utf-8 -*-
import scraperwiki
import sys
from bs4 import BeautifulSoup
import re
import urllib2
import time
import string

lastinvoicenumber = scraperwiki.sqlite.get_var("lastnumber")
if not lastinvoicenumber:
    lastinvoicenumber = 1

checknumber = lastinvoicenumber
counter_bad = 0
counter_good = 0
while counter_bad<15:
    try:
        checknumber = str(checknumber)
        checkurl= 'http://www.zvjs.sk/index.php?fa_obj&type=fa&id=' + checknumber
        checkpage = urllib2.urlopen(checkurl)
        checksoup = BeautifulSoup(checkpage.read(), from_encoding="windows-1252")
        price_val = checksoup.find_all('td')[9].text[:-1].replace(",", ".").replace(" ", "") or "null"
        print checknumber
        print checkurl
        print price_val
        if price_val == "0.00":
            counter_bad = counter_bad + 1
            print "BAD :" , counter_bad
        else:
            counter_good = counter_good + 1
            print "GOOD :" , counter_good
        checknumber = int(checknumber)
        checknumber = checknumber + 1
        #time.sleep(1)
    except:
        print ("Error checking available sites : "), checkurl
        counter_bad = counter_bad + 1
        print "BAD : " , counter_bad

newmax_val = counter_good
print "NEW MAX INVOICE NO :"
print newmax_val
print "####################"

number = lastinvoicenumber
maxval = lastinvoicenumber + newmax_val
while number<maxval:
    try:
        print number
            number = str(number)
            url= 'http://www.zvjs.sk/index.php?fa_obj&type=fa&id=' + number
            page = urllib2.urlopen(url)
            soup = BeautifulSoup(page.read(), from_encoding="windows-1252")

            evidence_no_val = soup.find_all('td')[3].text.strip() or "null"
            paired_with_val = soup.find_all('td')[5].text.strip() or "null"
        invoice_desc_val = soup.find_all('td')[7].text.replace('\"', '' ) or "null"
        invoice_price_val = soup.find_all('td')[9].text[:-1].replace(",", ".").replace(" ", "") or "null"
            date_received_val = soup.find_all('td')[11].text or "null"
            date_payment_val = soup.find_all('td')[13].text or "null"
            pay_form_val = soup.find_all('td')[15].text or "null"
            trade_name_val = soup.find_all('td')[17].text or "null"
            company_location_val = soup.find_all('td')[19].text or "null"
            trade_form_val = soup.find_all('td')[21].text or "null"
            court_val = soup.find_all('td')[23].text or "null"
            ico_val = soup.find_all('td')[25].text or "null"
            dic_val = soup.find_all('td')[27].text or "null"
            accout_no_val = soup.find_all('td')[29].text or "null"
            for link in soup.find_all("a", limit=1):
                attachment_url = (link.get('href'))
            if ( attachment_url == '/index.php?fa_obj'):
                             attachment_url="null"
                    else:
                             attachment_url = "http://www.zvjs.sk" + attachment_url
            number = int(number)
            scraperwiki.sqlite.save_var('lastnumber', number)
        output = trade_name_val + " | " + invoice_price_val + " | " + date_received_val + " | " + date_payment_val
        print output.encode("utf-8")
        scraperwiki.sqlite.save(unique_keys=["invoice_id"],
                        data={  "invoice_id":number,
                            "invoice_price":invoice_price_val,
                            "evidence_no":evidence_no_val,
                            "paired_with":paired_with_val,
                            "invoice_desc":invoice_desc_val,
                            "date_received":date_received_val,
                            "date_payment":date_payment_val,
                            "pay_form":pay_form_val,
                            "trade_name":trade_name_val,
                            "trade_form":trade_form_val,
                            "company_location":company_location_val,
                            "court":court_val,
                            "ico":ico_val,
                            "dic":dic_val,
                            "accout_no":accout_no_val,
                            "invoice_attachment":attachment_url,
                            "invoice_url":url})
            number = number +1
            time.sleep(1)
    except:
        print ("Error Scraping Data")
        number = int(number)
        number = number + 1

sys.exit()