利用request模拟登录知乎

最新推荐文章于 2021-03-15 22:02:19 发布

Y_momo

最新推荐文章于 2021-03-15 22:02:19 发布

阅读量644

点赞数 2

分类专栏：爬虫文章标签：模拟登录

本文链接：https://blog.csdn.net/qq_39689483/article/details/77370991

版权

爬虫专栏收录该内容

0 篇文章 0 订阅

订阅专栏

# -*- coding: utf-8 -*-

import requests
import json

try:
    import cookielib
except:
    import http.cookiejar as cookielib

import re
from bs4 import BeautifulSoup
import os, time
import cv2

try:
    from PIL import Image
except:
    pass


session = requests.session()
session.cookies = cookielib.LWPCookieJar(filename="cookies.txt")
try:
    session.cookies.load(ignore_discard=True)
except:
    print ("cookie未能加载")

agent = "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:51.0) Gecko/20100101 Firefox/51.0"
header = {
    "HOST":"www.zhihu.com",
    "Referer": "https://www.zhizhu.com",
    'User-Agent': agent
}
push = []
def is_login():
    #通过个人中心页面返回状态码来判断是否为登录状态
    inbox_url = "https://www.zhihu.com/question/56250357/answer/148534773"
    response = session.get(inbox_url, headers=header, allow_redirects=False)
    if response.status_code  != 200:
        return False
    else:
        return True


def get_xsrf():
    homeurl = 'https://www.zhihu.com/#signin'
    homeresponse = session.get(url=homeurl, headers=header)
    homesoup = BeautifulSoup(homeresponse.text, 'html.parser')
    xsrfinput = homesoup.find('input', {'name': '_xsrf'})
    xsrf_token = xsrfinput['value']
    return xsrf_token
    print(xsrf_token)

def left(event,x,y,flags,param):
        if event == cv2.EVENT_LBUTTONDOWN:
            a = [x*0.5,y*0.5]
            push.append(a)


randomtime = str(int(time.time() * 1000))
captchaurl = 'https://www.zhihu.com/captcha.gif?r='+\
             randomtime+"&type=login&lang=cn"
captcharesponse = session.get(url=captchaurl, headers=header)
with open(r'G:\linuxShare\ArticleSpider\ArticleSpider\utils\captcha.gif', 'wb') as f:
   f.write(captcharesponse.content)
   f.close()
im = Image.open(r'G:\linuxShare\ArticleSpider\ArticleSpider\utils\captcha.gif')
im = im.convert('RGB')
im.save(r'G:\linuxShare\ArticleSpider\ArticleSpider\utils\captcha.jpg', 'jpeg')
img = cv2.imread(r"G:\linuxShare\ArticleSpider\ArticleSpider\utils\captcha.jpg")
print(type(img))
cv2.namedWindow('Image')
cv2.setMouseCallback('Image',left)
cv2.imshow('Image', img)
cv2.waitKey(0)



def get_index():
    response = session.get("https://www.zhihu.com/#signin", headers=header)
    with open("index_page.html", "wb") as f:
        f.write(response.text.encode("utf-8"))
    print ("ok")

def zhihu_login(account, password):
    #知乎登录
    if re.match("^1\d{10}",account):
        print ("手机号码登录")
        post_url = "https://www.zhihu.com/login/phone_num"
        post_data = {
            "_xsrf": get_xsrf(),
            "phone_num": account,
            "password": password,
            "captcha_type": "cn ",
            "captcha" : {"img_size":[200,44],"input_points":push}
        }
    else:
        if "@" in account:
            #判断用户名是否为邮箱
            print("邮箱方式登录")
            post_url = "https://www.zhihu.com/login/email"
            post_data = {
                "_xsrf": get_xsrf(),
                "email": account,
                "password": password,
                "captcha_type": "cn",
                "captcha": {"img_size": [200, 44], "input_points": push}
            }
    print(post_data)
    print(push)
    response_text = session.post(post_url, data=json.dumps(post_data), headers=header)
    session.cookies.save()