python实现登录抓取_python使用selenium和requests.session登录抓取

#Author:song

from selenium importwebdriverfrom selenium.webdriver.common.keys importKeysfrom requests importsessionimportrequestsdefget_cookies():

driver=webdriver.Chrome()

driver.get('https://www.zhihu.com/signup?next=%2F')

locad_butter= driver.find_element_by_css_selector('#root > div > main > div > div > div > div.SignContainer-inner > div.SignContainer-switch > span')

locad_butter.click()importtime

time.sleep(2)

username= driver.find_element_by_css_selector('#root > div > main > div > div > div > div.SignContainer-inner > div.Login-content > form > div.SignFlow-account > div.SignFlowInput.SignFlow-accountInputContainer > div.SignFlow-accountInput.Input-wrapper > input')

username.send_keys('username')

passwd= driver.find_element_by_css_selector('#root > div > main > div > div > div > div.SignContainer-inner > div.Login-content > form > div.SignFlow-password > div > div.Input-wrapper > input')

passwd.send_keys('passwd')

#passwd.send_keys(Keys.RETURN)

driver.find_element_by_css_selector('#root > div > main > div > div > div > div.SignContainer-inner > div.Login-content > form > button').click()

time.sleep(10)

cookies=driver.get_cookies()

c={item['name']:item['value'] for item incookies}

cookies_value= 'aliyungf_tc={}; _xsrf={}; q_c1={}; capsion_ticket={}; _zap={}; z_c0={}; d_c0={}'.format(c['aliyungf_tc'], c['_xsrf'],c['q_c1'], c['capsion_ticket'],c['_zap'], c['z_c0'], c['d_c0'])returncookies_valuedefcrawer_page(cookies_value):

headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36',

}

cookies_dict={'Cookie':cookies_value

}

cookies= requests.utils.cookiejar_from_dict(cookies_dict)#用requests的session方法保持cookie的时候发现requests不能保持手动构建的cookie,手动构建的cookie是dict类型的。要把dict转为 cookiejar类型。

session =session()

session.cookies=cookies

response= session.get('https://www.zhihu.com/api/v4/search_v3?t=general&q=python&correction=1&offset=5&limit=10&search_hash_id=42cde34da2dc8ae359c5402be499b867',headers=headers)print(response.status_code)

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值