kyj-yanglao-web-new/extract_pdf.js

const pdfjsLib = require('pdfjs-dist/legacy/build/pdf.js');
const fs = require('fs');

const pdfPath = 'd:/Users/chenjun/kyj-yanglao-web-new/src/views/elderly/apply/check-in/颐年集团养老服务合同-2026年6月终版docx.pdf';
const outPath = 'd:/Users/chenjun/kyj-yanglao-web-new/contract_pages.json';

async function main() {
  const data = new Uint8Array(fs.readFileSync(pdfPath));
  const loadingTask = pdfjsLib.getDocument({ data });
  const pdf = await loadingTask.promise;
  console.log('Pages:', pdf.numPages);
  const pages = [];
  for (let i = 1; i <= pdf.numPages; i++) {
    const page = await pdf.getPage(i);
    const content = await page.getTextContent();
    const lines = [];
    let lastY = null;
    let currentLine = '';
    for (const item of content.items) {
      if (lastY !== null && Math.abs(item.transform[5] - lastY) > 3) {
        lines.push(currentLine);
        currentLine = '';
      }
      currentLine += item.str;
      lastY = item.transform[5];
    }
    if (currentLine) lines.push(currentLine);
    const text = lines.join('\n');
    pages.push({ page: i, text });
    console.log('--- PAGE', i, '---');
    console.log(text);
    console.log();
  }
  fs.writeFileSync(outPath, JSON.stringify(pages, null, 2), 'utf8');
  console.log('Saved to', outPath);
}
main().catch(err => { console.error(err); process.exit(1); });