准备目标网站 :https://kyfw.12306.cn/otn/login/init安装PIL模块: pip3 install pillow 或 pip3 --default-timeout=100 install -U pillow 第三方图像处理库(图片定位裁剪)准备一个浏览器驱动(版本不要差太多) chromedriver.exe 下载:https://npm.taobao.org/mirrors/chromedriver/验证码识别网站(超级鹰):http://www.chaojiying.com/ 需要注册,使用方法 参考#页面中验证码识别;https://www.cnblogs.com/guokaifeng/p/11536706.html需求分析通过selenium模块来实现模拟登录- 难点:对验证码的自动识别(验证码要一次获取,刷新的话会更改验证码)- 解决方案:对验证码区域进行截取(使用PIL模块的Image),用超级鹰来获取正确验证码的坐标,然后由selenium实现登录 实现代码from PIL import Image #导入Image截图from time import sleep from selenium import webdriverfrom Cjy import Chaojiying_Client # 导入超级鹰验证码识别from selenium.webdriver import ActionChains # 导入ActionChains动作链bro = webdriver.Chrome(executable_path='chromedriver.exe') # 指定浏览器驱动bro.get('https://kyfw.12306.cn/otn/login/init')sleep(3) # 防止网络(慢)原因图片加载失败bro.save_screenshot('main.png') # 截取显示页面# 对页面中的验证码图片做定位code_img_tag = bro.find_element_by_xpath('//*[@id="loginForm"]/div/ul[2]/li[4]/div/div/div[3]/img') # 定位到验证码图片的标签location = code_img_tag.location # 图片坐标(左下,右上) {'x':274,'y':293}size = code_img_tag.size # 图片的宽高 {'height':190,'width':293}# 裁剪的区域范围 (矩获取验证码的图片)rangle = (int(location['x']),int(location['y']),int(location['x']+size['width']),int(location['y']+size['height']))# 使用Image裁剪出验证码图片 code.pngi = Image.open('./main.png')frame = i.crop(rangle)frame.save('code.png')# 调用超级鹰对图片进行识别def get_text(imgPath,imgType): chaojiying = Chaojiying_Client('账户', '密码', '软件id')#超级鹰的账户密码软件码 注意最少要充1元才能使用 im = open(imgPath, 'rb').read() return chaojiying.PostPic(im, imgType)['pic_str']result = get_text('./code.png',9004) # 传入验证码与验证码类型 返回值为正确图片的坐标55,70|267,133 (账户不对或没有余额 会报错)# 把图片坐标转换为 55,70|267,133 ==[[55,70],[267,133]]all_list = []lis = result.split('|') #['55,70', '267,133']all_list.append([int(a) for a in lis[0].split(',')])all_list.append([int(a) for a in lis[-1].split(',')])# 让动作链去指定验证码区域模拟鼠标点击for a in all_list: x = a[0] y = a[1] ActionChains(bro).move_to_element_with_offset(code_img_tag,x,y).click().perform() breakbro.find_element_by_id('username').send_keys('123456') # 输入12306账户bro.find_element_by_id('password').send_keys('67890000000') # 输入密码bro.find_element_by_id('loginSub').click() # 点击登录sleep(5)bro.quit() #退出# 超级鹰代码 import requestsfrom hashlib import md5class 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, 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 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()
|
|
收藏
淘帖
踩
