Puppeteer 이미지 인식 기술을 활용하여 Baidu 인덱스 크롤러를 구현하는 방법

npm install --save puppeteer

npm config set PUPPETEER_DOWNLOAD_HOST=https://npm.taobao.org/mirrors
npm install --save puppeteer

// npm
npm install --save puppeteer --ignore-scripts

// node
puppeteer.launch({ executablePath: '/path/to/Chrome' });

// 启动浏览器，
// headless参数如果设置为true，Puppeteer将在后台操作你Chromium，换言之你将看不到浏览器的操作过程
// 设为false则相反，会在你电脑上打开浏览器，显示浏览器每一操作。
const browser = await puppeteer.launch({headless:false});
const page = await browser.newPage();

// 打开百度指数
await page.goto(BAIDU_INDEX_URL);

// 模拟登陆
await page.click('...');
await page.waitForSelecto('...');
// 输入百度账号密码然后登录
await page.type('...','username');
await page.type('...','password');
await page.click('...');
await page.waitForNavigation();
console.log(':white_check_mark: 登录成功');

// 获取chart第一天的坐标
const position = await page.evaluate(() => {
 const $image = document.querySelector('...');
 const $area = document.querySelector('...');
 const areaRect = $area.getBoundingClientRect();
 const imageRect = $image.getBoundingClientRect();

 // 滚动到图表可视化区域
 window.scrollBy(0, areaRect.top);

 return { x: imageRect.x, y: 200 }；
});

// 移动鼠标，触发tooltip
await page.mouse.move(position.x, position.y);
await page.waitForSelector('...');

// 获取tooltip信息
const tooltipInfo = await page.evaluate(() => {
 const $tooltip = document.querySelector('...');
 const $title = $tooltip.querySelector('...');
 const $value = $tooltip.querySelector('...');
 const valueRect = $value.getBoundingClientRect();
 const padding = 5;

 return {
 title: $title.textContent.split(' ')[0],
 x: valueRect.x - padding,
 y: valueRect.y,
 width: valueRect.width + padding * 2,
 height: valueRect.height
 }
});

await page.screenshot({ path: imgPath });

// 对图片进行裁剪，只保留数字部分
const img = await jimp.read(imgPath);
await img.crop(tooltipInfo.x, tooltipInfo.y, tooltipInfo.width, tooltipInfo.height);
// 将图片放大一些，识别准确率会有提升
await img.scale(5);
await img.write(imgPath);

Tesseract.process(imgPath, (err, val) => {
if (err || val == null) {
 console.error(':x: 识别失败：' + imgPath);
 return;
}
console.log(val);

const recognition = require('./src/recognition');
const Spider = require('./src/spider');

module.exports = {
 async run (word, options, puppeteerOptions = { headless: true }) {
 const spider = new Spider({ 
 imgDir, 
 ...options 
 }, puppeteerOptions);

 // 抓取数据
 await spider.run(word);

 // 读取抓取到的截图，做图像识别
 const wordDir = path.resolve(imgDir, word);
 const imgNames = fs.readdirSync(wordDir);
 const result = [];

 imgNames = imgNames.filter(item => path.extname(item) === '.png');

 for (let i = 0; i < imgNames.length; i++) {
 const imgPath = path.resolve(wordDir, imgNames[i]);
 const val = await recognition.run(imgPath);
 result.push(val);
 }

 return result;
 }
}