[已解决]python爬虫问题登录豆瓣客户端

抛弃大学

import re
import urllib.request
from http.cookiejar import CookieJar

loginurl = "https://www.douban.com/accounts/login"
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0;WOW64;rv:23.0) Gecko/20100101 Firefox/74.0'}

cookie = CookieJar()

opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor)

data = {
    "form_email":"your email",
    "form_possword":"your password",
    "source":"index_nav"
}

data = {}
data['form_email'] = '你的账号'
data['form_password'] = '你的密码'
data['source'] = 'index_nav'
       
response = opener.open(loginurl, urllib.parse.urlencode(data).encode('utf-8'))
       
#验证成功跳转至登录页
if response.geturl() == "https://www.douban.com/accounts/login":
    html = response.read().decode()

    imgurl = re.search('<img id="captcha_image" src="(.+?)" alt="captcha" class="captcha_image"/>', html)
    if imgurl:
        url = imgurl.group(1)

        res = urllib.request.urlretrieve(url, 'v.jpg')
       

        captcha = re.search('<input type="hidden" name="captcha-id" value="(.+?)"/>' ,html)
        if captcha:
            vcode = input('请输入图片上的验证码：')
            data["captcha-solution"] = vcode
            data["captcha-id"] = captcha.group(1)
            data["user_login"] = "登录"


            response = opener.open(loginurl, urllib.parse.urlencode(data).encode('utf-8'))


            if response.geturl() == "http://www.douban.com/":
                print('登陆成功!')
-----------------------------------------------------------------------------------------------------错误----------------------------------------------------------------------------------------
Traceback (most recent call last):
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38\豆瓣登录.py", line 23, in <module>
    response = opener.open(loginurl, urllib.parse.urlencode(data).encode('utf-8'))
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 531, in open
    response = meth(req, response)
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 640, in http_response
    response = self.parent.error(
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 569, in error
    return self._call_chain(*args)
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 502, in _call_chain
    result = func(*args)
  File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38\lib\urllib\request.py", line 649, in http_error_default
    raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 418:
这个错误我在网上查了试了好多方法也没有解决 大神帮帮忙

最佳答案

月排行榜 / 总排行榜

Charles未晞

2020-3-31 20:15:47

可以参考这里的代码：https://github.com/CharlesPikachu/DecryptLogin

跳转到最佳答案楼层

qiuyouzhi

加上headers
这个肯定可以百度到

抛弃大学

qiuyouzhi 发表于 2020-3-31 18:25
加上headers
这个肯定可以百度到

我加了。。。上面代码就是加了的。

Charles未晞

可以参考这里的代码：https://github.com/CharlesPikachu/DecryptLogin