Python爬虫实战 | (17) 破解微博登录图片验证码

在本篇博客中，我们将使用selenium模拟登录新浪微博，破解其登陆时的图片验证码。微博和简书、b站登录有所不同，后两个每次登录都会有验证码，微博有时有有时可能没有，所以写法稍有不同。

我们需要使用验证码识别服务平台。超级鹰，来帮助我们破解图片验证码。下面的chaojiying.py文件用于调用超级鹰服务，帮助我们破解点触或图片验证码，直接照搬就好了：

import requests
from hashlib import md5
 
 
#使用超级鹰来进行图片验证码和点触验证码的识别
class Chaojiying(object):
 
    def __init__(self, username, password, soft_id):
        self.username = username
        self.password = md5(password.encode('utf-8')).hexdigest()
        self.soft_id = soft_id
        self.base_params = {
            'user': self.username,
            'pass2': self.password,
            'softid': self.soft_id,
        }
        self.headers = {
            'Connection': 'Keep-Alive',
            'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36',
        }
 
    def post_pic(self, im, codetype):
        """
        im: 图片字节
        codetype: 题目类型 参考 http://www.chaojiying.com/price.html
        """
        params = {
            'codetype': codetype,
        }
        params.update(self.base_params)
        files = {'userfile': ('ccc.jpg', im)}
        r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, files=files,
                          headers=self.headers)
        return r.json()
 
    def report_error(self, im_id):
        """
        im_id:报错题目的图片ID
        """
        params = {
            'id': im_id,
        }
        params.update(self.base_params)
        r = requests.post('http://upload.chaojiying.net/Upload/ReportError.php', data=params, headers=self.headers)
        return r.json()

程序主体框架：

from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
from selenium.common.exceptions import TimeoutException,NoSuchElementException
from WeiBoLogin.chaojiying import Chaojiying
import requests
from requests import RequestException
#微博用户名和密码
USERNAME = ''
PASSWORD = ''

#超级鹰用户名、密码、软件ID(需要注册)
CHAOJIYING_USERNAME = ''
CHAOJIYING_PASSWORD = ''
CHAOJIYING_SOFT_ID = 
CHAOJIYING_KIND = 1902 #验证码类型 4-6位英文数字组合 破解图片验证码 具体可见官网

#破解图片验证码 登陆微博
class WeiboLogin():

    def __init__(self):
        self.url = 'https://www.weibo.com'
        self.browser = webdriver.Chrome()
        self.wait = WebDriverWait(self.browser, 20)
        self.username = USERNAME
        self.passward = PASSWORD
        self.chaojiying = Chaojiying(CHAOJIYING_USERNAME, CHAOJIYING_PASSWORD, CHAOJIYING_SOFT_ID)

    def __del__(self):
        self.browser.close()

    def get_click_image(self,name='captcha_weibo.png'):
        pass

    def login_successfully(self):
        pass

    def get_click_button(self):
        pass

    def open(self):
        pass

    def login(self):
        # 打开登陆界面 输入用户名和密码
        self.open()
        #找到并点击登陆按钮
        button = self.get_click_button()
        button.click()

        if self.login_successfully():  # 有时可能不需要验证码
            print("登陆成功")
        else:
            # 获取图片验证码 图片
            image = self.get_click_image()
            # 识别图片验证码
            result = self.chaojiying.post_pic(image, CHAOJIYING_KIND)
            print(result)
            # 判断是否成功
            # 找到验证码输入框
            verifycode = self.wait.until(EC.presence_of_element_located((By.NAME, 'verifycode')))
            # 输入验证码
            verifycode.send_keys(result['pic_str'])
            # 找到并点击登陆按钮
            button = self.get_click_button()
            button.click()
            if self.login_successfully():
                print('登录成功')
            else:
                self.chaojiying.report_error(result['pic_id'])
                self.login()

if __name__ == '__main__':
    login = WeiboLogin()
    login.login()

打开登录界面，输入用户名和密码：

    def open(self):
        """
        打开登陆界面 输入用户名和密码
        :return:
        """
        self.browser.get(self.url)
        # 找到用户名和密码输入框
        '''
        <input id="loginname" type="text" class="W_input" maxlength="128" autocomplete="off" action-data="text=邮箱/会员帐号/手机号" action-type="text_copy" name="username" node-type="username" tabindex="1">
        '''
        username = self.wait.until(EC.presence_of_element_located((By.ID,'loginname')))
        '''
        <input type="password" class="W_input" maxlength="24" autocomplete="off" value="" action-type="text_copy" name="password" node-type="password" tabindex="2">
        '''
        password = self.wait.until(EC.presence_of_element_located((By.NAME,'password')))
        # 输入用户名和密码
        username.send_keys(self.username)
        password.send_keys(self.passward)

找到登录按钮：

  def get_click_button(self):
        """
        找到登陆按钮
        :return:
        """
        '''
        <a href="javascript:void(0)" class="W_btn_a btn_32px" action-type="btn_submit" node-type="submitBtn" suda-data="key=tblog_weibologin3&amp;value=click_sign" tabindex="6"><span node-type="submitStates">登录</span></a>
        '''
        button = self.wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,'.W_btn_a')))
        return button

判断登录是否成功，如果成功会有消息提示：

  def login_successfully(self):
        """
        判断登陆是否成功
        :return:
        """
        '''
        <em class="W_ficon ficon_mail S_ficon">I</em>
        '''
        try:
            return bool(
                WebDriverWait(self.browser,5).until(EC.presence_of_element_located((By.CSS_SELECTOR,'.ficon_mail')))
            )
        except TimeoutException:
            return  False

如果登录不成功，则获取图片验证码：

   def get_click_image(self,name='captcha_weibo.png'):
        '''
        :param name:
        :return:
        '''
        '''
        <img width="95" height="34" action-type="btn_change_verifycode" node-type="verifycode_image" src="https://login.sina.com.cn/cgi/pin.php?r=88815771&amp;s=0&amp;p=gz-66c0488ef9191010d88bea8c9f3a09fdf3bf">
        '''
        try:
            element = self.wait.until(EC.presence_of_element_located((By.XPATH,'//img[@node-type="verifycode_image"]')))
            verifycode_image = element.get_attribute('src')  # 得到图片链接
            verifycode_image = get_html(verifycode_image).content #获取图片内容
            with open(name, 'wb') as f:
                f.write(verifycode_image)
            return verifycode_image
        except NoSuchElementException:
            print("")
        return None

完整项目