python3爬虫开发实践崔庆才——练习模拟登陆爬取Github

#coding:utf-8

import requests
from lxml import etree

class Login(object):

 def __init__(self):
 
    self.headers = {
        'Referer': 'https://github.com/',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
        'Host': 'github.com'
    }
    self.login_url = 'https://github.com/login'
    self.post_url = 'https://github.com/session'
    self.logined_url = 'https://github.com/settings/profile'
    # requests 库的Session ，它可以帮助我们维持一个会话;自动处理cookies;
    self.session = requests.Session()   

def token(self):
"""
获取初始页面的cookies;获取到authenticity_token;
"""
    response = self.session.get(self.login_url, headers=self.headers)
    selector = etree.HTML(response.text)
    token = selector.xpath('//div//input[2]/@value'