Python——使用代码平台进行识别验证码

打码平台介绍

一般使用超级鹰或打码兔的打码平台。

超级鹰介绍

打开http://www.chaojiying.com/contact.html注册用户，生成软件ID

下载python的demo文件

使用方法

from chaojiying import Chaojiying

CHAOJIYING_USERNAME = 'xxxxxx' # 账号
CHAOJIYING_PASSWORD = '123456' # 密码
CHAOJIYING_SOFT_ID = 894611 # 生成的唯一key
CHAOJIYING_KIND = 9004 # 题型

cjy = Chaojiying(CHAOJIYING_USERNAME, CHAOJIYING_PASSWORD, CHAOJIYING_SOFT_ID) # 创建实例
result = cjy.post_pic(bytes_array.getvalue(), CHAOJIYING_KIND) # 上传图片

逻辑实现

1.获取需要识别的图片

在获取需要的识别的图片时，一般需要讲图片以及文字提示。通过selenium的截图方法,获取到所需的信息。

self.browser.save_screenshot('aa.png') # 先把整个屏幕截图
element = self.browser.find_element_by_xpath('/html/body/div[2]/div/div[2]/div[2]/div[3]/div/div[2]/div[3]/div/div') # 获取图片所在的div

left = element.location['x']
top = element.location['y'] - 100
right = element.location['x'] + element.size['width']
bottom = element.location['y'] + element.size['height']

im = Image.open('aa.png')
captcha = im.crop((left, top, right, bottom)) # 根据div的长宽在整个屏幕上面截图
captcha.save('captcha.png')

2.识别需要点击的坐标

 把需要识别的图片和提示一起上传 返回坐标

result = self.chaojiying.post_pic(bytes_array.getvalue(), CHAOJIYING_KIND) # 提交图片进行验证
groups = result.get('pic_str').split('|') # 对返回的数据进行解析 获取x坐标和y坐标
locations = [[int(number) for number in group.split(',')] for group in groups]

3.根据坐标顺序依次页面进行点击

根据x和y坐标依次点击图片当中的文字self.get_touclick_element() 获取图片的位置

move_to_element_with_offset 将鼠标移动到距某个元素多少距离的位置

for location in locations:
　　ActionChains(self.browser).move_to_element_with_offset(self.get_touclick_element(), location[0],location[1]).click().perform()
　　time.sleep(1)

识别案例

conf 目录

[DEFAULT]
CODE_USERNAME = xxxxxxxxx
CODE_PASSWORD = 1111111
CODE_SOFT_ID = 894611
CODE_KIND = 9004
TRACK_TICKET_USERNAME = uuuuuu
TRACK_TICKET_PASSWORD = ya1111

[OTHER]
image=1

check_config.ini

import logging
import os
from logging import handlers

# 日志格式
c_format = '[%(asctime)s] [%(levelname)s] [%(filename)s:%(lineno)d] [%(message)s]'
f_format = '[%(asctime)s]-[%(levelname)s]-[%(filename)s:%(lineno)d]-[%(message)s]'
# log文件目录
logfile_dir = r'%s\log'%os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
log_name = 'scrapy.log'

# 文件绝对路径
logfile_path = os.path.join(logfile_dir, log_name)


def get_mylogger(name):
    """
    get log
    :param name: 
    :return: 
    """
    logger = logging.getLogger(name)
    logger.setLevel('DEBUG')

    console_handler = logging.StreamHandler()
    console_handler.setLevel('INFO')

    file_handler = logging.FileHandler(logfile_path)
    file_handler.setLevel('WARNING')

    file_size_handler = handlers.RotatingFileHandler(logfile_path, maxBytes=5 * 1024*1024, backupCount=5)
    file_time_handler = handlers.TimedRotatingFileHandler(logfile_path,when="W0",backupCount=5)

    logger.addHandler(console_handler)
    logger.addHandler(file_handler)

    file_format = logging.Formatter(fmt=f_format)
    console_format = logging.Formatter(fmt=c_format, datefmt='%Y-%m-%d %H:%M:%S ')

    console_handler.setFormatter(console_format)
    file_handler.setFormatter(file_format)

    return logger

if __name__ == '__main__':
    log = get_mylogger('test')

my_logset.py

import os
config_path = r'%s\%s' %(os.path.dirname(os.path.abspath(__file__)),'check_config.ini')

settings.py

lib目录

#!/usr/local/bin/python3
# -*- coding: utf-8 -*-
import configparser
import os



class Read_Ini(object):

    def __init__(self,config_file):
        self.config = configparser.ConfigParser()
        self.config.read(filenames=config_file)



    def get_value(self, name,section='DEFAULT'):
        """
         得到section下的属性name的值
        :param section: 
        :param name: 
        :return: 
        """
        return  self.config.get(section,name)

    def get_section_dict(self,section='DEFAULT'):
        """
         得到section下所有属性值
        :param section: 
        :return: 
        """
        return self.config.options(section)

if __name__ == '__main__':
    path = r'%s\conf\%s' % (os.path.dirname(os.path.dirname(os.path.abspath(__file__))), 'check_config.ini')
    print(path)
    a = Read_Ini(path)
    print(a.get_value('CODE_USERNAME'))

read_ini.py

import requests
from hashlib import md5


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/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)',
        }


    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()

chaojiying.py

core目录

#!/usr/local/bin/python3
# -*- coding: utf-8 -*-
# @Time    : 2018/4/22 20:16
# @Author  : hyang
# @File    : demo.py
# @Software: 

import time
from io import BytesIO
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait # 等待元素加载的
from selenium.webdriver.common.action_chains import ActionChains  #拖拽
from selenium.webdriver.support import expected_conditions as EC
# from selenium.common.exceptions import TimeoutException, NoSuchElementException
from selenium.webdriver.common.by import By
from PIL import Image
from lib import chaojiying
from lib import read_ini
from conf import settings
from conf import my_logset as mylog




class Check_Code_Click_Demo(object):

    def __init__(self):
        self.url = 'https://kyfw.12306.cn/otn/login/init'
        self.driver = webdriver.Chrome()
        self.wait = WebDriverWait(self.driver,10)
        # print(settings.config_path)
        self.config = read_ini.Read_Ini(settings.config_path)
        self.logger = mylog.get_mylogger('demo')
        '''
        使用超级鹰打码平台-用户名，密码，软件ID
        '''
        self.chaojiying = chaojiying.Chaojiying(self.config.get_value('CODE_USERNAME'), self.config.get_value('CODE_PASSWORD'), self.config.get_value('CODE_SOFT_ID'))

    def __del__(self):
        self.driver.close() # 当对象销毁后，执行关闭

    def open_url(self):
        '''
        打开网页，最大化，操作滚动条
        :return: 
        '''
        self.driver.get(self.url)
        time.sleep(1)
        # self.driver.maximize_window()  # 最大化
        self.driver.set_window_size(1920, 1080)  # 分辨率 1920*1080
        self.logger.info('打开url，输入用户名，密码')
        self.driver.find_element_by_id('username').send_keys(self.config.get_value('TRACK_TICKET_USERNAME'))
        time.sleep(1)
        self.driver.find_element_by_id('password').send_keys(self.config.get_value('TRACK_TICKET_PASSWORD'))
        time.sleep(1)
        # js = 'var q=document.documentElement.scrollTop=280'  # 操作滚动条
        # self.driver.execute_script(js)


    # 区域截图(对指定的区域/元素截图)
    def element_screenshot(self,element):
        # 截取全屏图片
        self.driver.save_screenshot("full.png")
        # 获取element的顶点坐标
        x_point = element.location['x']+120
        y_point = element.location['y']+50
        # 获取element的宽、高
        element_width = x_point + element.size['width']+100
        element_height = y_point + element.size['height']+100
        # 开始截取指定区域
        picture = Image.open("full.png")

        ''''' 
        crop()--  一个显式的参数：一个4元组 
          Image.crop(box=None):图像返回一个矩形区域,box是一个四元组 限定所述左，上，右，和下像素坐标 
          参数：box--裁剪矩形，作为（左，上，右，下）-tuple;返回类型：Image；返回：一个Image对象 
          所以你应该重写它： 
          #        ^    4-tuple    ^ 
        '''
        picture = picture.crop((x_point, y_point, element_width, element_height))
        picture.save("fullcrop.png")

        return picture

    def get_touclick_image(self):
        """
        得到要点击的图像
        :return: 
        """
        element = self.wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.touclick-img-par.touclick-bgimg')))
        return element

    def get_image(self,name='captcha.png',num = 100):
        """
         得到要识别的图片
        :param name: 
        :param num: 
        :return: 
        """
        time.sleep(5)
        image_element = self.wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.touclick-img-par.touclick-bgimg')))
        captcha = self.element_screenshot(image_element)
        self.logger.info('得到要识别的图片')
        return captcha

    def get_click_words(self, location):
        """
         根据返回坐标的位置，点击图像中识别字的坐标
        :param location: 
        :return: 
        """
        for loc in location:
            im_element = self.get_touclick_image()
            # print(im_element.location['x'], im_element.location['y'], im_element.size)
            #print('loc=',loc)
            # 将鼠标移动到距某个元素多少距离的位置点击
            ActionChains(self.driver).move_to_element_with_offset(im_element,loc[0]-40,
                                                                  loc[1]-40).click().perform()
            self.driver.save_screenshot('check.png')
            time.sleep(3)


    def get_points(self,res):
        """
         解析坐标的位置
        :param res: 
        :return: 
        """
        groups = res.get('pic_str').split('|')  # 解析返回的坐标
        location = [[int(num) for num in group.split(',')] for
 group in groups]

        return location


    def login(self):
        time.sleep(1)
        login_element = self.driver.find_element_by_id('loginSub')
        self.logger.info('开始点击登录')
        login_element.click()


    def main(self):
        image = self.get_image()
        #time.sleep(10)
        byte_array = BytesIO()
        image.save(byte_array, format('png'))  # 把图片转换为二进制格式保存到内存中
        try:
            res = self.chaojiying.post_pic(byte_array.getvalue(), self.config.get_value('CODE_KIND'))  # 获取图像二进制数据,把数据提交到打码平台
            self.logger.info('得到打码平台' % res)
            # 解析坐标
            location = self.get_points(res)
            if location:
                self.logger.info('得到识别的坐标'%location)
                self.get_click_words(location)
                self.login()
                time.sleep(6)
                for handle in self.driver.window_handles:
                    print(handle)
                    self.driver.switch_to.window(handle)

                check_error = self.driver.find_element_by_id('error_msgmypasscode1')
                check_style = check_error.get_attribute('style')
                print('style=',check_style)
                if 'none' in check_style:
                    self.logger.info('验证成功')
                    self.driver.save_screenshot('True.png')
                else:
                    self.logger.error('验证失败!!!')
                    self.main()
        except Exception as e:
            self.logger.error('返回异常!!!%s'% e)

if __name__ == '__main__':
    c = Check_Code_Click_Demo()
    c.open_url()
    c.main()

demo.py

bin目录

import sys,os

BASE_DIR=os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
sys.path.append(BASE_DIR)  # 加入环境变量

from core import demo
from conf import my_log_settings

if __name__ == '__main__':
    # my_log_settings.load_my_logging_cfg(__name__)
    de = demo.Check_Code_Click_Demo()
    de.open_url()
    de.main()

start.py