由于一些论坛不登录验证,就不能查看帖子的内容和附件,所以需要登录验证,如果在代码中添加登录验证,那就增加了代码的复杂度,所以可以结合cookie来登录然后爬取需要的资料
cookie的获取
- 使用chrome,登录后在开发工具里查取
#!/usr/bin/env python
# -*- coding:utf-8 -*-
"""
@author:Aiker Zhao
@file:jianli.py
@time:下午10:50
"""
import os
import re
import requests
from bs4 import BeautifulSoup
from requests.exceptions import RequestException
from hashlib import md5
headers = {
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36',
'Cookie': 'PHPSESSID=ui7unwxc3yf4glbdaqmat2ee00; __cfduid=de4fa38a23ad640f0bcdb4313560af62e1543723208; ape__Session=ui7uxxxxdfd4glbdaqmat2ee00; _ga=GA1.2.176343230234.1552443854'
}
def get_con