import requestsfrom bs4 import BeautifulSoupimport lxmlheaders = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:61.0) Gecko/20100101 Firefox/61.0", "Cookie": "xq_a_token=b02adfc63102d5b06db993fb32
import requestsimport jsonheaders = { 'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36"}url = 'https://xueqiu.com/statuses/hot/listV2.json?'
以下将从处理cookie的两种方式来分析爬取雪球网的新闻数据, 一个是手动处理cookie,到源码去抓包,找到他的request header里面的cookie,复制出来封装到headers内; 另一个是自动处理cookie,引入模块requests的session,这个方法和requests一样可以发送get和post请求,但是他在发送请求
# -*- coding: utf-8 -*- # file_name: xq_get_cookie.py # author: lwh from selenium import webdriver from selenium.webdriver import ActionChains from io import BytesIO import json import base64 import time from selenium.webdriver.common.by import By f
