Created
May 29, 2015 00:09
-
-
Save DiegoQueiroz/04f4f08b07321a7f99d3 to your computer and use it in GitHub Desktop.
Download a single page of CNPq Lattes
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# -*- coding: utf-8 -*- | |
import sys | |
if sys.version_info.major >= 3: | |
# usando Python 3.x ou superior | |
from urllib.request import Request, build_opener, HTTPCookieProcessor | |
from urllib.parse import urlencode | |
else: | |
# usando Python 2.x ou anterior | |
from urllib2 import Request, build_opener, HTTPCookieProcessor | |
from urllib import urlencode | |
url = 'http://buscatextual.cnpq.br/buscatextual/visualizacv.do' | |
opener = build_opener(HTTPCookieProcessor()) | |
opener.open(url) # esse primeiro acesso serve apenas para criar uma sessão | |
# e receber as cookies do servidor | |
# Para cada currículo, é necessário criar uma nova requisição | |
# e utilizar o Opener para abrir a página | |
# O mesmo Opener pode ser utilizado para abrir vários currículos | |
id_curriculo = 'K4212066D0' | |
data = urlencode({'id' : id_curriculo, 'metodo' : 'visualizarCV'}) | |
data = data.encode('ISO-8859-1') # essencial no Python 3 | |
req = Request(url, data) | |
pagina = opener.open(req) | |
print(pagina.read()) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment