首页 > > 网络编程 > 其它 >

python_爬虫_通过selenium获取人人网cookie值并…

2018-08-17 09:48:42来源：博客园阅读 ()

平台：mac

网站：人人网

最近练习爬虫登陆，方法一是找页面里的js文件，通过解析js文件找到cookie信息再保持。但现在的站点登陆都有验证码，而且最烦的是request时data表单里的值基本上没有不加密的，js学的不好，就别想着破解了。所以想起了用的比较少的selenium模块，用于模拟登陆并获取cookie。

import time,random
from selenium import webdriver
import requests
from urllib import request
from lxml import etree

driver = webdriver.Chrome(executable_path=r'/Applications/Google Chrome.app/chromedriver')
driver.get('http://www.renren.com/PLogin.do')
time.sleep(2)
driver.find_element_by_id('email').clear()
driver.find_element_by_id('email').send_keys('myusername')  # 输入用户名
driver.find_element_by_id('password').clear()
driver.find_element_by_id('password').send_keys('mypassword')  # 输入密码

img_url = 'http://icode.renren.com/getcode.do?t=web_login&rnd='+str(random.random())
request.urlretrieve(img_url,'renren_yzm.jpg')
try:
    driver.find_element_by_id('icode').clear()
    img_res = input('输入验证码：')  # 如果需要输入验证码，可以手工，或者接口给打码平台
    driver.find_element_by_id('icode').send_keys(img_res)
except:
    pass
driver.find_element_by_id('autoLogin').click()  # 自动登陆
driver.find_element_by_id('login').click()  # 登陆
time.sleep(3)
cookie_items = driver.get_cookies()  # 获取cookie值

post = {} # 保存cookie值
for cookie in cookie_items:
    post[cookie['name']] = cookie['value']
print(post['t'])  # 人人网登陆后需要保持登陆的cookie信息
driver.quit()  # 退出selenium
# ------------------------------------------------------------

url = 'http://www.renren.com/265025131/profile'
headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36',
    'Cookie':'t='+post['t'],
}
response = requests.get(url,headers=headers)
print('-'*50)

html = etree.HTML(response.text)
title = html.xpath('//title/text()')
print('目前得到的页面信息',title)
print(response.url)