• 解析图形验证码登录系统


    windows 10 下pip install 报错【PermissionError: [WinError 32] 另一个程序正在使用此文件,进程无法访问。】

    C:UsershaseePython36Libsite-packagespipcompat_init_.py
    第75行改为 return s.decode('cp936')
    原因:
    编码问题,虽然py3统一用utf-8了。但win下的终端显示用的还是gbk编码。
    CP936其实就是GBK,IBM在发明Code Page的时候将GBK放在第936页,所以叫CP936。

    下载whl包后安装

    下载对应python、tesseract版本的teserocr包:
    https://github.com/simonflueckiger/tesserocr-windows_build/releases
    pip install XXX.whl 安装下载包

    # -*- coding: utf-8 -*-
    # @Time       : 2018/11/20 13:30
    # @Author     : Philly
    # @File       : crackImage.py
    # @Description: 实时获取并解析图片验证码进行登录系统
    import tesserocr
    from PIL import Image
    from urllib import request
    from selenium import webdriver
    from time import sleep
    import pyautogui
    from selenium.webdriver.common.action_chains import ActionChains
    import os
    import re
    
    
    
    
    # 把验证码另存为图片
    def image_save_as():
        image = driver.find_element_by_id("valiCode")
        actions = ActionChains(driver)
        actions.context_click(image)
        actions.perform()
        pyautogui.typewrite(['down', 'down', 'enter', 'enter']) # 右键找到图片另存为
        sleep(2)
        pyautogui.typewrite(['enter'])
        sleep(2)
    
    def get_newest_image(image_path):
    
        lists = os.listdir(image_path)
        lists.sort(key=lambda fn:os.path.getmtime(image_path + "\" + fn))  # 按时间排序
        image_new = os.path.join(image_path, lists[-1])
    
        return image_new
    
    
    """
    driver.save_screenshot("all.png")
    print(image.location, image.size)
    left = image.location['x']
    top = image.location['y']
    right = image.location['x'] + image.size['width']
    bottom = image.location['y'] + image.size['height']
    
    im = Image.open('all.png')
    im = im.crop((left, top, right, bottom))
    im.save('code9.png')
    
    imageUrl = url2 + "/GetValidateCode"
    request.urlretrieve(imageUrl, "code8.jpg")  # 把图片保存到本地code8.jpg
    
    """
    # 转换验证码图片为文字
    def image_to_txt(image_new):
        image = Image.open(image_new)
        image = image.convert('L')
        threshold = 80  # 设置阈值
        table = []
        for i in range(256):
            if i < threshold:
                table.append(0)
            else:
                table.append(1)
    
        image = image.point(table, '1')
        result = tesserocr.image_to_text(image)
        f = open('result.txt', 'w')
        f.write(result)
        f.close()
        # 去掉中间空格
        result_e = ''.join(result.split())
        # 只取数字
        result_w = re.findall('d+', result_e)[0]
    
        return result_w
    
    def login(result_w):
        driver.find_element_by_id("LoginAccount").send_keys("zbsqy")
        sleep(1)
        driver.find_element_by_id("Password").send_keys("admin")
        sleep(1)
        driver.find_element_by_id("verifyCode").send_keys(result_w)
        sleep(1)
        driver.find_element_by_id("btnLogin").click()
        sleep(3)
    
    
    if __name__ == "__main__":
        driver = webdriver.Chrome()
        driver.maximize_window()
        driver.get("http://192.168.14.38:88/User/Login")
        sleep(2)
    
        image_path = r"C:UsershaseeDownloads"    # 验证码另存为的路径
    
        image_save_as()
        image_new = get_newest_image(image_path)
        result_w = image_to_txt(image_new)
        login(result_w)
    
    

    报错

    File "tesserocr.pyx", line 2445, in tesserocr._tesserocr.image_to_text
    RuntimeError: Failed to init API, possibly an invalid tessdata path: C:

    把对应的 tessdata 文件夹放到报错路径即可

  • 相关阅读:
    python开发必备:virtualenv虚拟环境(自用)
    JavaScript经典实例
    javascript事件驱动及事件处理
    在HTML网页中嵌入脚本的方式
    JavaScript数据结构
    JavaScript语言调试技巧
    CSS+DIV布局
    在HTML文档中应用CSS
    CSS常用属性
    定义CSS
  • 原文地址:https://www.cnblogs.com/liuliu3/p/9988588.html
Copyright © 2020-2023  润新知