crawler_p5.py

crawler_p5.py

import urllib
import sys
import re
import json

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)
	if table:
		trs = re.findall(r'<tr>(.*?)</tr>', table.group(), re.S)
		#'<td rowspan=1>25/04/2012 17:36</td><td>CDD CACOAL - CACOAL/RO</td><td><FONT COLOR="5F9F9F">Entrega Efetuada</font></td>',
		status = {}
		if len(trs) > 1:
			st = trs[1]
			local = re.search(r'<td>(.*?)</td>', st, re.S).group(1)  #extrai o local
			data = re.search(r'<td rowspan=\d>(.*?)</td>', st, re.S).group(1)  #extrai a data
			situacao = re.search(r'<FONT COLOR="(.*?)">(.*?)</font>', st, re.S).group(2)  #extrai a situacao
		
			status = {'local': local, 'data': data , 'situacao': situacao}
		else:
			status = {'situacao': 'Objeto nao encontrado ou Objeto ainda recem postado'}
	else:
		status = {'situacao': 'Objeto nao encontrado ou Objeto ainda recem postado'}
	return status

def obter_rastreamento(codigo):
	html_data = captura_html(URL % codigo)
	status = extrai_status(html_data)
	return json.dumps(status)

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