crawler_p3.py

crawler_p3.py

import urllib
import sys
import re

URL = 'http://websro.correios.com.br/sro_bin/txect01$.QueryList?P_ITEMCODE=&P_LINGUA=001&P_TESTE=&P_TIPO=001&P_COD_UNI=%s'

def captura_html(url):
	html_data = urllib.urlopen(url).read()
	return html_data


def extrai_status(html):
	table = re.search(r'<table.*</TABLE>', html, re.S).group()
	print table

def obter_rastreamento(codigo):
	html_data = captura_html(URL % codigo)
	status = extrai_status(html_data)

if __name__ == '__main__':
	codigo = sys.argv[1]
	status = obter_rastreamento(codigo)
	print 'status', status