rendered paste body#! /usr/bin/env pythonfrom urllib2 import urlopenfrom BeautifulSoup import BeautifulSoupimport rebase_url = 'http://www.irs.gov/businesses/small/article/0,,id=104696,00.html'base = 'http://www.irs.gov'def get_state_urls(base_url): soup = BeautifulSoup(urlopen(base_url)) links = soup.fetch("table")[2].fetch("a") #stringsss = "state", "url" for link in links: return [a['href'] for a in links if a.string != "Alphabetical"] # title = link.string.replace("\n", " ") # url = link['href'] # stringsss += title, url #return title, urldef get_states(base_url): soup = BeautifulSoup(urlopen(base_url)) links = soup.fetch("table")[2].fetch("a") for link in links: return [a.string.replace("\n", " ") for a in links if a.string]def get_count_info(state_url): soup = BeautifulSoup(urlopen(state_url))# tables = soup.fetch('table')[2] county = []# num1 = ""# num2 = ""# num3 = "" soup.prettify()# for table in tables: for tests in soup.fetch('table')[2].fetch('td'): county += tests.contents[0] + "," return county# county += table.fetch('td')[0]# num1 += table.fetch('td')[1]# num2 += table.fetch('td')[2]# num3 += table.fetch('td')[3]# table1 = county, num1, num2, num3# return table1# for table in tables:# return table# return [a.string.replace("\n", " ") for a in tables]# print table.find('_1')# print table.find('_2')# print table.find('_3')# return [a['td'] for a in tables]links_print = get_state_urls(base_url)state_print = get_states(base_url)for a,b in zip(links_print, state_print): url = base + a for tables in get_count_info(url): print u,'tables'# print tables[1]# print tables[2]# print tables[3] print url, b