爬虫实战：12306登录

素颜马尾好姑娘i 2022-12-07 12:20 314阅读 0赞

##  爬虫实战：破解点触验证码，实现12306登录 ##

### 1.目标 ###

实现12306登录，获取登录cookies

### 2.技术点 ###

*  1.借用第三方打码平台，进行图片验证码识别
 *  2.破解selenium webdriver反爬

### 3.思路 ###

*  1.输入账号密码
 *  2.获取验证图片
 *  3.识别图片，获取坐标
 *  4.图片验证
 *  5.登录
 *  6.滑动滑块

### 4.环境 ###

python + selenium + 超级鹰

### 5.代码 ###

*  1.12306登录.py

# @author: zly
    # @function: Touch verification code
    # @time: 2020-09-15
    # @copyright: All Rights Reversed
    
    import time
    import random
    
    from selenium import webdriver
    from selenium.webdriver.common.action_chains import ActionChains
    
    from chaojiying import Chaojiying_Client
    from constants import *
    
    
    class MakeTrack:
        """ Track generator, need to pass a distance parameter """
    
        def __init__(self, distance=DISTANCE):
    
            self.distance = distance
    
        def segmentate(self, s):
            """ Track splitter, the size of each piece of track is not divided Returns a list object of a track block :param s --> Tracks to be segmented, int """
    
            if SEGMENTNUM1 <= abs(s) < SEGMENTNUM2:
                s = [round(s / 3) - 3, round(s / 3) + 3]
    
            elif abs(s) >= SEGMENTNUM2:
                s = [
                    round(s / 5) - 5, round(s / 5) - 3,
                    round(s / 5),
                    round(s / 5) + 3, round(s / 5) + 5
                ]
    
            else:
                s = [round(s)]
    
            return s
    
        def make_track(self):
    
            """ Make sliding track to simulate human normal movement Return a list object of sliding track """
    
            track = []
    
            current = v0 = 0
    
            while self.distance > current:
                # 随机事件，随机加速度，生成随机位移
                t = random.randint(1, 4) / 2
                a = random.randint(1, 3)
    
                # 速度、位移
                v0 += a * t
                s = v0 * t + 0.5 * a * t ** 2
    
                # 将不和规则的较大的位移进行分割
                seg = self.segmentate(round(s))
                track.extend(seg)
    
                current += s
    
            # 对不超过目标位移或者不足位移做补偿
            while True:
    
                if sum(track) == self.distance:
                    break
                elif sum(track) > self.distance:
                    track.pop()
                else:
                    track.append(self.distance - sum(track))
    
            if len(track) > TRACKMAXLENGTH:
                self.make_track()
    
            return track
    
    
    class Login12306(Chaojiying_Client):
        """ :param username 12306账号 --> str password 12306密码 --> str cusername 超级鹰账号 --> str cpassword 超级鹰密码 --> str soft_id 软件ID --> str codetype 验证类型 --> int path 验证码图片路径 --> str There are three to config your init configration 1. by set constant 2. by set config dict 3. Direct set init configration """
    
        def __init__(
                self, username=None, password=None,
                cusername=None, cpassword=None, soft_id=None,
                codetype=None, path=None,
                *args, **kwargs
        ):
    
            # 配置优化，可以字典的形式传递参数
            if kwargs.get('configs', 'None'):
    
                # 连接超级鹰，初始化
                super().__init__(
                    username=kwargs['configs'].get('cusername', ''),
                    password=kwargs['configs'].get('cpassword', ''),
                    soft_id=kwargs['configs'].get('soft_id', '')
                )
    
                self.username = kwargs['configs'].get('username', '')
                self.password = kwargs['configs'].get('password', '')
                self.cusername = kwargs['configs'].get('cusername', '')
                self.cpassword = kwargs['configs'].get('cpassword', '')
                self.soft_id = kwargs['configs'].get('soft_id', '')
                self.codetype = kwargs['configs'].get('codetype', '')
                self.path = kwargs['configs'].get('path', '')
    
            elif USERNAME:
                self.username = USERNAME
                self.password = PASSWORD
                self.cusername = CUSERNAME
                self.cpassword = CPASSWORD
                self.soft_id = SOFTID
                self.codetype = CODETIPE
                self.path = PATH
    
            else:
                # 连接超级鹰，初始化
                super().__init__(
                    username=cusername,
                    password=cpassword,
                    soft_id=soft_id
                )
    
                self.username = username
                self.password = password
                self.cusername = cusername
                self.cpassword = cpassword
                self.soft_id = soft_id
                self.codetype = codetype
                self.path = path
    
            self.run
    
        @property
        def run(self):
            """ You can call the run method directly for login verification, or you can also call other methods to achieve this function :return Return false means login verification failed Return true means login verification success """
    
            self.driver = self.prepares()
    
            self.driver.get('https://kyfw.12306.cn/otn/resources/login.html')
    
            self.driver.implicitly_wait(IMPLICITLYWAIT)
            self.driver.maximize_window()
    
            time.sleep(1)
    
            # 1.输入账号密码
            self.input_user_pwd(username=self.username, password=self.password)
    
            # 2.获取验证图片
            self.get_pic()
    
            while True:
                # 3.识别图片，获取坐标
                position, pic_id = self.get_position(codetype=self.codetype)
    
                if not position:
                    position, pic_id = self.get_position(codetype=self.codetype)
    
                # 4.图片验证
                self.img_click(position)
    
                # 5.登录
                login = self.login(pic_id)
                if not login:
    
                    self.driver.refresh()
                    self.input_user_pwd(username=self.username, password=self.password)
                    self.get_pic()
    
                    continue
    
                # 6.滑动滑块
                return True if self.slide() else False
    
        def prepares(self):
            """ Break through 12306 webriver Returns a webdrive after anti pickling """
    
            # 12306通过图片验证之后依然登陆不上，其中的原因是有webdriver反扒
            # 要想突破反扒，就必须修改带有webdrive的标志，我们用selenium打开的浏览器
            # 上面往往都会显示 Chrome正受到自动测试软件的控制
            # 因此我们需要修改Options和selenium浏览器的js标志navigator
            # selenium控制的浏览器默认是true/false，正常的是undefined
    
            options = webdriver.ChromeOptions()
            options.add_experimental_option("excludeSwitches", ["enable-automation"])
            options.add_experimental_option('useAutomationExtension', False)
            driver = webdriver.Chrome(options=options)
            driver.execute_cdp_cmd(
                "Page.addScriptToEvaluateOnNewDocument",
                { 
                    "source": "Object.defineProperty("
                              "navigator, 'webdriver', "
                              "{get: () => undefined})"
                }
            )
    
            return driver
    
        def input_user_pwd(self, username=None, password=None):
            """ Enter 12306 account and password @username: 12306账号 --> str, defalut is None @password: 12306密码 --> str, defalut is None The return 0 here has no effect, it just means the end of the function """
    
            # 切换至账号密码登录
            self.driver.find_element_by_xpath('//li[@class="login-hd-account"]/a').click()
    
            # 这里需要睡1-2秒，否则会报错，加载js，浏览器js没有代码快
            time.sleep(2)
    
            # 输入账号密码
            self.driver.find_element_by_id('J-userName').send_keys(username)
            self.driver.find_element_by_id('J-password').send_keys(password)
    
            return 0
    
        def get_pic(self):
            """ Get touch captcha image The return 0 here has no effect, it just means the end of the function """
    
            # 截图
            self.driver.find_element_by_id('J-loginImg').screenshot(self.path)
    
            return 0
    
        def get_position(self, codetype=None):
            """ Get the touch coordinates of super Eagle verification @soft_id: 软件ID --> str, defalut is None @codetype: 验证类型 --> int, defalut is None :return a list object [position, pic_id] """
    
            # 发送图片，获取坐标是
            verify_data = self.PostPic(self.path, codetype)
            print(verify_data)
    
            # 如果成功获取坐标则格式化，否则return None
            if verify_data['err_no'] == 0:
    
                temp = verify_data['pic_str'].split('|')
                position = [i.split(',') for i in temp]
    
                return [position, verify_data['pic_id']]
    
            else:
    
                self.ReportError(verify_data['pic_id'])
                return [None, verify_data['pic_id']]
    
        def img_click(self, position):
            """ Get the touch coordinates of super Eagle verification @position: 点触坐标 --> Nested list, [['55', '55'], ['88', '88']...] The return 0 here has no effect, it just means the end of the function """
    
            # 要点触的图片
            element = self.driver.find_element_by_id('J-loginImg')
    
            # 按照坐标值点击
            for k in position:
    
                # x、y需要int的原因：move_to_element_with_offset中x、y只能是int型
                x = int(k[0])
                y = int(k[1])
    
                ActionChains(self.driver).move_to_element_with_offset(element, x, y).click().perform()
    
            return 0
    
        def login(self, pic_id=None):
            """ Its role is to log in and get cookies Return true means the verification is successful, otherwise it fails """
    
            # 登录，获取cookies
            self.driver.find_element_by_id('J-login').click()
    
            # 判断图片验证是否验证成功
            verify_tag = self.driver.find_element_by_xpath('//*[@class="lgcode-error"]')
    
            # 看verify_tag的display属性是否可见，可见则表示验证失败
            if verify_tag.is_displayed():
    
                # 别浪费钱，向超级鹰报个错
                self.ReportError(pic_id)
                print("图片验证失败，报错成功")
    
                return False
    
            print("图片验证成功")
            time.sleep(3)
    
            return True
    
        def slide(self):
    
            """ Sliding verification, if it's successful return cookies, or return False """
    
            try:
    
                # 定位滑块
                element = self.driver.find_element_by_id('nc_1_n1z')
                # 生成轨迹
                track = MakeTrack().make_track()
    
                # 滑动
                ActionChains(self.driver).click_and_hold(element).perform()
                [ActionChains(self.driver).move_by_offset(i, 0).perform() for i in track]
                ActionChains(self.driver).release(element).perform()
    
                # 时间取决于网速
                time.sleep(5)
    
            except Exception as e:
    
                # stale element reference: element is not attached to the page document
                # 页面刷新导致获取不到元素，若能够滑动通过此错误无需再管，不是每次都会发生
    
                print(str(e))
                time.sleep(10)
                self.driver.quit()
    
                return False
    
            # 判断是否登陆成功
            try:
    
                self.driver.find_element_by_xpath('//*[@class="btn btn-primary ok"]').click()
                cookies = self.driver.get_cookies()
    
                print("恭喜您登陆成功")
                print(cookies)
                time.sleep(10)
    
                self.driver.quit()
    
                return True
    
            except Exception as e:
    
                print(str(e))
                print("恭喜您登陆失败，再来一次吧")
    
                time.sleep(10)
                self.driver.quit()
    
                return False
    
    
    configs = { 
        'username': '',      # 12306账号
        'password': '',      # 12306密码
        'cusername': '',     # 超级鹰账号
        'cpassword': '',     # 超级鹰密码
        'soft_id': '',       # 软件ID
        'codetype': 9004,    # 验证类型
        'path': ''           # 验证码图片路径
    }
    
    
    Login12306(configs=configs)

*  2、chaojiying.py

import requests
    from hashlib import md5
    
    class Chaojiying_Client(object):
    
        def __init__(self, username, password, soft_id):
    
            self.username = username
            password = password.encode('utf8')
            self.password = md5(password).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/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)',
            }
    
        def PostPic(self, path, codetype):
            """ path: 图片路径 codetype: 题目类型 参考 http://www.chaojiying.com/price.html """
    
            with open(path, 'rb') as f:
                imagecontent = f.read()
    
            params = { 
                'codetype': codetype,
            }
            params.update(self.base_params)
            files = { 'userfile': ('ccc.jpg', imagecontent)}
    
            r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, files=files, headers=self.headers)
    
            return r.json()
    
        def ReportError(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()

*  3、contants.py

# 12306账号
    USERNAME = ''
    
    # 12306密码
    PASSWORD = ''
    
    # 超级鹰账号
    CUSERNAME = ''
    
    # 超级鹰密码
    CPASSWORD = ''
    
    # 软件ID
    SOFTID = ''
    
    # 验证类型
    CODETIPE = ''
    
    # 验证码图片路径
    PATH = ''
    
    # 滑块滑动的距离，单位：px
    DISTANCE = 425
    
    # 轨迹分割规定大小
    SEGMENTNUM1 = 30
    SEGMENTNUM2 = 50
    
    # 轨迹最大段数
    TRACKMAXLENGTH = 30
    
    # # 显性等待时间，单位：s
    IMPLICITLYWAIT = 10

### 温馨提示：千万不要干坏事喲~~，否则抓进局里后果自负… ###