Files
sisvietnamvn_01/extract.js
2026-05-24 13:49:25 +07:00

35 lines
1.1 KiB
JavaScript

const fs = require('fs');
const path = require('path');
const filePath = path.join(__dirname, 'bài viết', 'Trang chủ - Bệnh Viện Đa Khoa Quốc Tế S.I.S Cần Thơ.html');
const content = fs.readFileSync(filePath, 'utf8');
// Extract images
const imgRegex = /<img[^>]+src="([^">]+)"/g;
let match;
const images = new Set();
while ((match = imgRegex.exec(content)) !== null) {
images.add(match[1]);
}
// Extract headings and paragraphs
const textRegex = /<(h1|h2|h3|p)[^>]*>(.*?)<\/\1>/gs;
const texts = [];
while ((match = textRegex.exec(content)) !== null) {
const tag = match[1];
const innerHtml = match[2].trim();
// Strip inner tags
const plainText = innerHtml.replace(/<[^>]+>/g, '').trim();
if (plainText.length > 10) {
texts.push(`[${tag.toUpperCase()}] ${plainText}`);
}
}
const result = {
images: Array.from(images).filter(src => src.indexOf('data:image') === -1 && src.indexOf('.svg') === -1),
texts: texts
};
fs.writeFileSync('extracted_content.json', JSON.stringify(result, null, 2));
console.log('Done extraction. Found', result.images.length, 'images and', result.texts.length, 'text blocks.');