模拟登陆知乎并批量下载问题关注者的头像、ID、签名

import re
import requests
import http.cookiejar as cookielib
from PIL import Image
import time
import os
import json

登录内容

login_url = 'https://www.zhihu.com/#signin'
meizi_url = 'https://www.zhihu.com/topic/19565769/followers'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36'
}
session = requests.session()
session.cookies = cookielib.LWPCookieJar(filename='zhihucookies')
try:
session.cookies.load(ignore_discard=True)
except:
print('Cookie未加载')

def get_xsrf():
index_url = 'https://www.zhihu.com/topic/19565769/followers'
index_page = session.get(index_url, headers=headers).text
_xsrf = re.findall('name="_xsrf" value="(.*?)"', index_page)
return _xsrf[0]
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()
try:
im = Image.open('captcha.jpg')
im.show()
im.close()
except:
print(u'请到 %s 目录找到captcha.jpg 手动输入' % os.path.abspath('captcha.jpg'))
captcha = input('请输入验证码\n> ')
return captcha

def isLogin():
url1 = 'https://www.zhihu.com/settings/profile'
html = session.get(url1, headers=headers, allow_redirects=False)
login_code = html.status_code
if login_code == 200:
return True
else:
return False
def login(secret, account):
_xsrf = get_xsrf()
if re.match(r'^1\d{10}$', account):
print('login by phone! \n')
post_url = 'https://www.zhihu.com/login/phone_num'
postdata = {
'_xsrf': _xsrf,
'password': secret,
'phone_num': account
}
else:
if '@' in account:
print('login by mail! \n')
else:
print('你的账号输入有问题，请重新登录')
return 0
post_url = 'https://www.zhihu.com/login/email'
postdata = {
'_xsrf': _xsrf,
'password': secret,
'email': account
}
login_page = session.post(post_url, data=postdata, headers=headers)
login_code = login_page.json()
if login_code['r'] == 1:
postdata['captcha'] = get_captcha()
login_page = session.post(post_url, data=postdata, headers=headers)
login_code = login_page.json()
print(login_code['msg'])
print(login_code)
session.cookies.save()

获取美女头像和ID

def getMzUrl(page):
startime = int(time.time())
pages = page * 20
count = 1
for off in range(0, pages+20, 20):
formdata = {
"start": startime,
"offset": off
}
headers1 = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36',
'Host': 'www.zhihu.com',
'Origin': 'https://www.zhihu.com',
'Referer': 'https://ww.zhihu.com/topic/19565769/followers',
'X-Requested-With': 'XMLHttpRequest',
'X-Xsrftoken': get_xsrf()
}
meizi_page = json.loads(session.post(meizi_url, data=formdata, headers=headers1).text)
print(meizi_page)
userinfos = re.findall(r'avatar-img-50.?src="(.?)".??author-link">(.*?)', str(meizi_page), re.S)
print(userinfos)
for userinfo in userinfos:
os.chdir('E:/pylearn/rsa/知乎妹子头像和id和签名')
image = requests.get(userinfo[0])
with open(userinfo[1]+'.jpg', 'wb') as file:
file.write(image.content)
count += 1
print("用户头像下载地址：" + userinfo[0])
print("用户名：" + userinfo[1])
print('图片总数：' + str(count))
print(startime)

if name == 'main':
if isLogin():
print('已登录.')
getMzUrl(10)
else:
account = input('请输入用户名\n> ')
secret = input('请输入密码\n> ')
login(secret, account)