csbhsh 发表于 2021-2-16 00:22:49

python 54讲 动动手1

复制了答案后还是不行，自己研究了好久又改了一些地方，然后发现人类是有极限的，求大佬帮帮忙
代码↓
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(cookie))
                        
head = {}
head["User-Agent"] = "这里改了"
data = {}
data['form_email'] = '这里填了'
data['form_password'] = '这里也填了'
data['source'] = 'index_nav'

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

#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'), head)

            # 登录成功跳转至首页 '''
            if response.geturl() == "http://www.douban.com/":
                print('登录成功！')
报错↓
Traceback (most recent call last):
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38-32\54.1.py", line 22, in <module>
    response = opener.open(loginurl, urllib.parse.urlencode(data).encode('utf-8'), head)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38-32\lib\urllib\request.py", line 525, in open
    response = self._open(req, data)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38-32\lib\urllib\request.py", line 542, in _open
    result = self._call_chain(self.handle_open, protocol, protocol +
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38-32\lib\urllib\request.py", line 502, in _call_chain
    result = func(*args)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38-32\lib\urllib\request.py", line 1393, in https_open
    return self.do_open(http.client.HTTPSConnection, req,
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38-32\lib\urllib\request.py", line 1350, in do_open
    h.request(req.get_method(), req.selector, req.data, headers,
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38-32\lib\http\client.py", line 1255, in request
    self._send_request(method, url, body, headers, encode_chunked)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38-32\lib\http\client.py", line 1301, in _send_request
    self.endheaders(body, encode_chunked=encode_chunked)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38-32\lib\http\client.py", line 1250, in endheaders
    self._send_output(message_body, encode_chunked=encode_chunked)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38-32\lib\http\client.py", line 1010, in _send_output
    self.send(msg)
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38-32\lib\http\client.py", line 950, in send
    self.connect()
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38-32\lib\http\client.py", line 1417, in connect
    super().connect()
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38-32\lib\http\client.py", line 921, in connect
    self.sock = self._create_connection(
File "C:\Users\Administrator\AppData\Local\Programs\Python\Python38-32\lib\socket.py", line 793, in create_connection
    sock.settimeout(timeout)
TypeError: an integer is required (got type dict)

qq1151985918 发表于 2021-2-16 08:32:10

你 head 和 data 的这里改了 这里填了 到底是改了什么填了什么？

csbhsh 发表于 2021-2-16 13:24:15

qq1151985918 发表于 2021-2-16 08:32
你 head 和 data 的这里改了 这里填了 到底是改了什么填了什么？

就是改了headers和账号密码

csbhsh 发表于 2021-2-16 13:36:57

又改了一下，这回没有报错但还是登录不上，现在连出了什么问题都不知道了，救救我，plz
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(cookie))
                           
head = {}
head["User-Agent"] = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36 Edg/88.0.705.68"
data = {}
data['ck'] = 'Q5m-'
data["remember"] = "true"
data['name'] = '这里是账号（已填）'
data['password'] = '这里是密码（已填）'
data = urllib.parse.urlencode(data).encode('utf-8')
req = urllib.request.Request(loginurl, data, head)
response = opener.open(req)

#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'), head)

            # 登录成功跳转至首页 '''
            if response.geturl() == "http://www.douban.com/":
                print('登录成功！')
页: [1]
查看完整版本: python 54讲 动动手1