python爬虫-知乎登录

时间:2022-08-04 11:02:12
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
'''
Required
- requests (必须)
- pillow (可选)
''' import requests
try:
import cookielib
except:
import http.cookiejar as cookielib
import re
import time
import os.path
try:
from PIL import Image
except:
pass
#使用验证码识别库
#import pytesseract # 构造 Request headers
agent = 'Mozilla/5.0 (Windows NT 5.1; rv:33.0) Gecko/20100101 Firefox/33.0'
headers = {
'User-Agent': agent
} # 使用登录cookie信息
session = requests.session()
session.cookies = cookielib.LWPCookieJar(filename='cookies')
try:
session.cookies.load(ignore_discard=True)
except:
print("Cookie 未能加载") def get_xsrf():
'''_xsrf 是一个动态变化的参数'''
index_url = 'https://www.zhihu.com'
# 获取登录时需要用到的_xsrf
index_page = session.get(index_url, headers=headers)
html = index_page.text
pattern = r'name="_xsrf" value="(.*?)"'
# 这里的_xsrf 返回的是一个list
_xsrf = re.findall(pattern, html)
return _xsrf[0] # 获取验证码
def get_captcha():
t = str(int(time.time()*1000))
captcha_url = 'https://www.zhihu.com/captcha.gif?r=' + t + "&type=login"
r = session.get(captcha_url, headers=headers)
with open('captcha.jpg', 'wb') as f:
f.write(r.content)
f.close()
# 用pillow 的 Image 显示验证码
# 如果没有安装 pillow 到源代码所在的目录去找到验证码然后手动输入
try:
im = Image.open('captcha.jpg')
#使用验证码识别,系统需要安装tesseract-ocr软件
#下载地址:https://jaist.dl.sourceforge.net/project/tesseract-ocr-alt/tesseract-ocr-setup-3.02.02.exe
#由于验证码识别,测试识别率不高,因此暂时不使用,寻找更好的识别方法再加
#code = pytesseract.image_to_string(im)
#print(code)
im.show()
im.close()
#if len(code)!=4:
# print('自动识别不出验证码,请手动输入验证码!')
#else:
# captcha = code
# return captchac
except:
print(u'请到 %s 目录找到captcha.jpg 手动输入' % os.path.abspath('captcha.jpg'))
captcha = input("please input the captcha\n>")
return captcha def isLogin():
# 通过查看用户个人信息来判断是否已经登录
url = "https://www.zhihu.com/settings/profile"
login_code = session.get(url,allow_redirects=False).status_code
if int(x=login_code) == 200:
return True
else:
return False def login(secret, account):
# 通过输入的用户名判断是否是手机号
if re.match(r"^1\d{10}$", account):
print("手机号登录 \n")
post_url = 'https://www.zhihu.com/login/phone_num'
postdata = {
'_xsrf': get_xsrf(),
'password': secret,
'remember_me': 'true',
'phone_num': account,
}
#可加上邮箱的判断,这里不加了
else:
print("邮箱登录 \n")
post_url = 'https://www.zhihu.com/login/email'
postdata = {
'_xsrf': get_xsrf(),
'password': secret,
'remember_me': 'true',
'email': account,
}
try:
# 不需要验证码直接登录成功
login_page = session.post(post_url, data=postdata, headers=headers)
login_code = login_page.text
print(login_page.status)
print(login_code)
except:
# 需要输入验证码后才能登录成功
postdata["captcha"] = get_captcha()
login_page = session.post(post_url, data=postdata, headers=headers)
login_code = eval(login_page.text)
print(login_code['msg'])
return login_code['r']
session.cookies.save() try:
input = raw_input
except:
pass if __name__ == '__main__':
while True:
if isLogin():
print('您已经登录')
else:
account = input('请输入你的用户名\n> ')
secret = input("请输入你的密码\n> ")
result = login(secret, account)
if result == 0:
#爬取登录成功后的网站内容
conf_url = "https://www.zhihu.com/settings/profile"
text = session.get(conf_url,headers=headers).text
print(text)
break

以上代码在python 2.*中运行时,只需修改代码的print处即可

代码部分参考网友,代码持续更新优化中,如有错误或更优的方法欢迎大家的留言!