豆瓣url的登录问题

zy8818

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

# 豆瓣的登录url 
loginurl = 'https://www.douban.com/accounts/login'
cookie = CookieJar()
opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor)
 
data = {
    "form_email":"your email",
    "form_password":"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()
    
    #验证码图片地址
    imgurl = re.search('<img id="captcha_image" src="(.+?)" alt="captcha" class="captcha_image"/>', html)
    if imgurl:
        url = imgurl.group(1)
        # 将验证码图片保存至同目录下
        res = urllib.request.urlretrieve(url, 'v.jpg')

        # 获取captcha-id参数
        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"

            # 提交验证码验证
            response = opener.open(loginurl, urllib.parse.urlencode(data).encode('utf-8'))

            # 登录成功跳转至首页 '''
            if response.geturl() == "http://www.douban.com/":
                print('登录成功！')

Traceback (most recent call last):
  File "C:/Users/Administrator/AppData/Local/Programs/Python/Python38/111.py", line 20, 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:
一大堆的红字

suchocolate

得加header。你的教程有点老了，建议用requests学爬虫。

from urllib import request

url = 'https://www.douban.com/accounts/login'
headers = {'User-Agent': 'Firefox'}
req = request.Request(url, headers=headers)
r = request.urlopen(req)
print(r.read().decode('utf-8'))

或

from urllib import request
url = 'https://www.douban.com/accounts/login'
opener = request.build_opener()
opener.addheaders = [('User-agent', 'Firefox')]
response = opener.open(url)
r = response.read().decode('utf-8')
print(r)