爬取人人网个人主页

import requests from lxml import etree class Renrenlogin(object): def __init__(self): #post_url: form表单中action中的url地址 self.post_url='http://www.renren.com/PLogin.do' #真正要抓取的页面url地址：人人网的个人主页 self.get_url='http://www.renren.com/974686948/profile' #实例化session对象 self.session=requests.session() #提取数据—先post在get def parse_html(self): user=input("请输入人人网用户名：") password=input("请输入人人网密码：") data={ "email":user, "password":password } #先post,把cookies保存session对象中-会话保持 self.session.post(url=self.post_url,data=data) #在get,正常抓取数据 html=self.session.get(url=self.get_url).text parse_obj=etree.HTML(html) xpath_bds='//*[@id="operate_area"]/div[1]/ul/li[1]/span/text()' school=parse_obj.xpath(xpath_bds) print(school) def run(self): self.parse_html() if __name__ == '__main__': spider=Renrenlogin() spider.run()