requests登录csdn

最新推荐文章于 2024-03-16 23:59:22 发布

不才陈某

最新推荐文章于 2024-03-16 23:59:22 发布

阅读量1.9k

点赞数

文章标签： csdn python爬虫

文章首发于微信公众号【码猿技术专栏】，欢迎关注！！！

本文链接：https://blog.csdn.net/qq_34162294/article/details/53876689

版权

# -*-coding:utf-8 -*-
import requests
from bs4 import BeautifulSoup
import lxml
import codecs
import os

class CSDN():
    def __init__(self,url):
        self.url = url
        self.header = {'Referer': 'https://passport.csdn.net/account/login',
                   "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36", }
        self.s = requests.session()

    #登录csdn
    def login(self):
        re=self.s.get(self.url,headers=self.header)
        html = re.text
        soup = BeautifulSoup(html, 'lxml')
        all_input = soup.find_all('input')
        lt_value = all_input[3].get('value')
        execution_value = all_input[4].get('value')
        _eventId_value = all_input[5].get('value')
        payload = {   #表单
            "username": "18796327106@163.com",
            "password": "as676767as",
            "lt": lt_value,
            "execution": execution_value,
            "_eventId": _eventId_value
        }
        r2 = self.s.post(url, headers=self.header, data=payload)

     #下面的代码是爬取我自己的博客上的代码
    def get_text(self):
        url="http://blog.csdn.net/qq_34162294/article/details/53872170"
        re=self.s.get(url,headers=self.header)
        html=re.text
        soup=BeautifulSoup(html,'lxml')
        code=soup.find('code')
        filename='g:\\file\\code.cpp'
        path=os.path.normpath(filename)    #将代码写入cpp文件
        with codecs.open(path,'w',encoding='utf-8') as f:
            f.write(code.text)









if __name__=="__main__":
    url='https://passport.csdn.net/account/login'
    app=CSDN(url)
    app.login()
    app.get_text()