爬虫用户登陆

案例网站：https://www.yaozh.com/

自行先注册一个账号登陆，从后台拿到cookie信息（需要先解析成字典）。用requests带着cookie请求页面：

import requests
from fake_useragent import UserAgent

ua =UserAgent(verify_ssl=False)
url = 'https://www.yaozh.com'

headers = {'User-Agent' : ua.chrome}
cookies = {
            "acw_tc" : "2f624a4915517019851723054e594f26ab0e94b2dac89e5553a58be6820866",
            "PHPSESSID" : "thn69c47mbv6mnh8b80su209d5",
            "_ga" : "GA1.2.64439649.1551701987",
            "_gid" : "GA1.2.1552323367.1551701987",
            "Hm_lvt_65968db3ac154c3089d7f9a4cbb98c94" : "1551701987",
            "MEIQIA_VISIT_ID" : "1HzPWocm0CUcs9riBBRYZKTslGD",
            "yaozh_logintime" : "1551702120",
            "yaozh_user" : "704072%09%E7%90%B4%E4%BC%BC%E7%9A%91%",
            "yaozh_userId" : "704072",
            "_gat" : "1",
            "yaozh_uidhas" : "1",
            "yaozh_mylogin" : "1551702126",
            "acw_tc" : "2f624a4915517019851723054e594f26ab0e94b2dac89e5553a58be6820866",
            "MEIQIA_VISIT_ID" : "1HzPWocm0CUcs9riBBRYZKTslGD",
            "Hm_lpvt_65968db3ac154c3089d7f9a4cbb98c94" : "1551702127",
        }
response = requests.get(url=url,headers=headers,cookies=cookies,verify=False)

print(response.text)

用户名密码登陆

用session来接收并保存cookie，然后用session请求该网站的其他页面，即为登陆后的用户访问：

import requests
from fake_useragent import UserAgent

ua =UserAgent(verify_ssl=False)
url = 'https://www.yaozh.com'
url_login = 'https://www.yaozh.com/login/'
headers = {'User-Agent' : ua.chrome}

formdata = {
    "username" : "琴似皑患者炉",
    "pwd" : "zcb167+-",
    "formhash" : "DBEB84DA5B",
    "backurl" : "%2F%2Fwww.yaozh.com%2F",
}

session = requests.session()

response = session.post(url=url_login,headers=headers,data=formdata,verify=False)

data = session.get(url=url,headers=headers).content.decode()
print(data)