美团众包抢单助手，美团抢单辅助器app，外卖抢单辅助脚本插件

/**
 * AutoJS综合演示脚本
 * 功能包含：界面操作、数据处理、定时任务等
 */

// ========== 基础配置 ==========
auto.waitFor();
device.keepScreenOn(3600 * 1000); // 保持屏幕亮1小时
setScreenMetrics(1080, 2340); // 设置屏幕分辨率

// ========== 全局变量 ==========
const CONFIG = {
    retryTimes: 3,
    waitTimeout: 1500,
    debugMode: true
};

// ========== 主功能模块 ==========
function main() {
    log("脚本启动");
    initRuntime();
    
    // 执行任务序列
    executeTaskSequence([
        openApp,
        loginOperation,
        checkNotifications,
        processMainPage,
        cleanUp
    ]);
    
    log("脚本执行完成");
}

// ========== 功能函数 ==========
function initRuntime() {
    // 初始化运行时环境
    if (!requestScreenCapture()) {
        toast("请授予截图权限");
        exit();
    }
    events.on("exit", () => {
        device.cancelKeepingAwake();
    });
}

function executeTaskSequence(tasks) {
    // 顺序执行任务数组
    tasks.forEach((task, index) => {
        log("开始执行任务" + (index + 1));
        let retry = 0;
        while (retry < CONFIG.retryTimes) {
            try {
                if (task()) break;
            } catch (e) {
                log("任务异常:" + e);
            }
            retry++;
            sleep(1000);
        }
    });
}

function openApp() {
    // 打开目标应用
    const appName = "目标应用";
    if (!launchApp(appName)) {
        log("打开应用失败");
        return false;
    }
    sleep(CONFIG.waitTimeout);
    return true;
}

function loginOperation() {
    // 登录操作处理
    const loginBtn = findElement("text", "登录");
    if (loginBtn) {
        click(loginBtn.bounds().centerX(), loginBtn.bounds().centerY());
        sleep(2000);
        
        // 输入账号密码
        const account = findElement("id", "account_input");
        const password = findElement("id", "password_input");
        
        if (account && password) {
            account.setText("test_user");
            password.setText("123456");
            sleep(500);
            
            // 点击确认按钮
            const confirm = findElement("text", "确认登录");
            if (confirm) {
                click(confirm.bounds().centerX(), confirm.bounds().centerY());
                sleep(3000);
                return true;
            }
        }
    }
    return false;
}

// ========== 工具函数 ==========
function findElement(strategy, value) {
    // 增强的元素查找函数
    let element = null;
    switch (strategy) {
        case "text":
            element = text(value).findOne(CONFIG.waitTimeout);
            break;
        case "id":
            element = id(value).findOne(CONFIG.waitTimeout);
            break;
        case "desc":
            element = desc(value).findOne(CONFIG.waitTimeout);
            break;
    }
    return element;
}

function click(x, y) {
    // 增强的点击函数
    if (typeof x === "number" && typeof y === "number") {
        press(x, y, 50);
    } else if (x && x.bounds) {
        press(x.bounds().centerX(), x.bounds().centerY(), 50);
    }
    sleep(300 + Math.random() * 200); // 随机延迟
}

// ========== 日志系统 ==========
function log(message) {
    if (CONFIG.debugMode) {
        console.log(new Date().toLocaleString() + " - " + message);
    }
}

// ========== 脚本入口 ==========
module.exports = main;

// 立即执行
main();

import cv2
import numpy as np
import pytesseract
from PIL import Image
from skimage import filters

class CustomOCR:
    def __init__(self, config_path=None):
        self.min_confidence = 0.7
        self.preprocess_methods = {
            'adaptive_thresh': self._adaptive_threshold,
            'otsu': self._otsu_threshold,
            'edge_preserve': self._edge_preserving_filter
        }
        
    def _adaptive_threshold(self, image):
        gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
        return cv2.adaptiveThreshold(
            gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
            cv2.THRESH_BINARY, 11, 2)

    def _otsu_threshold(self, image):
        gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
        blur = cv2.GaussianBlur(gray, (5,5), 0)
        _, thresh = cv2.threshold(
            blur, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
        return thresh

    def _edge_preserving_filter(self, image):
        return cv2.edgePreservingFilter(image, flags=1, sigma_s=60, sigma_r=0.4)

    def preprocess_image(self, image, method='otsu'):
        processor = self.preprocess_methods.get(method)
        if not processor:
            raise ValueError(f"Unsupported method: {method}")
        return processor(image)

    def detect_text_regions(self, image):
        gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
        sobelx = cv2.Sobel(gray, cv2.CV_8U, 1, 0, ksize=3)
        _, binary = cv2.threshold(sobelx, 0, 255, cv2.THRESH_OTSU)
        kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (30, 5))
        closed = cv2.morphologyEx(binary, cv2.MORPH_CLOSE, kernel)
        contours, _ = cv2.findContours(
            closed.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
        return sorted(contours, key=cv2.contourArea, reverse=True)

    def recognize_text(self, image, lang='eng+chi_sim'):
        custom_config = r'--oem 3 --psm 6 -c tessedit_char_whitelist=0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ'
        text_data = pytesseract.image_to_data(
            image, lang=lang, output_type=pytesseract.Output.DICT,
            config=custom_config)
        
        results = []
        for i in range(len(text_data['text'])):
            if int(text_data['conf'][i]) > self.min_confidence * 100:
                results.append({
                    'text': text_data['text'][i],
                    'confidence': float(text_data['conf'][i]) / 100,
                    'bbox': (
                        text_data['left'][i],
                        text_data['top'][i],
                        text_data['width'][i],
                        text_data['height'][i])
                })
        return results

    def process_image(self, image_path):
        image = cv2.imread(image_path)
        processed = self.preprocess_image(image)
        contours = self.detect_text_regions(processed)
        
        final_text = []
        for cnt in contours:
            x,y,w,h = cv2.boundingRect(cnt)
            roi = image[y:y+h, x:x+w]
            text_results = self.recognize_text(roi)
            final_text.extend(text_results)
        
        return {
            'original_image': image,
            'processed_image': processed,
            'text_results': final_text
        }

from ocr_system import CustomOCR
import matplotlib.pyplot as plt

def visualize_results(result):
    plt.figure(figsize=(12,8))
    
    plt.subplot(1,2,1)
    plt.imshow(cv2.cvtColor(result['original_image'], cv2.COLOR_BGR2RGB))
    plt.title('Original Image')
    
    plt.subplot(1,2,2)
    plt.imshow(result['processed_image'], cmap='gray')
    plt.title('Processed Image')
    
    for item in result['text_results']:
        x,y,w,h = item['bbox']
        plt.gca().add_patch(plt.Rectangle(
            (x,y), w, h, fill=False, edgecolor='red', linewidth=2))
        plt.text(x, y-5, f"{item['text']}({item['confidence']:.2f})", 
                color='red', fontsize=8)
    
    plt.tight_layout()
    plt.show()

if __name__ == '__main__':
    ocr = CustomOCR()
    result = ocr.process_image('test_document.jpg')
    print("识别结果:", [item['text'] for item in result['text_results']])
    visualize_results(result)