使用Javascript从pdf中提取文本的特定部分？

npm install pdfjs-dist

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

async function extractTextFromPDF(url, searchText) {
  // 加载 PDF 文档
  const loadingTask = pdfjsLib.getDocument(url);
  const pdf = await loadingTask.promise;

  let extractedText = '';

  // 遍历每一页
  for (let pageNum = 1; pageNum <= pdf.numPages; pageNum++) {
    const page = await pdf.getPage(pageNum);
    const textContent = await page.getTextContent();

    // 提取文本
    const pageText = textContent.items.map(item => item.str).join(' ');
    extractedText += pageText + '\n';
  }

  // 查找特定部分
  const startIndex = extractedText.indexOf(searchText);
  if (startIndex !== -1) {
    const endIndex = extractedText.indexOf('\n', startIndex);
    const foundText = extractedText.substring(startIndex, endIndex);
    console.log('Found text:', foundText);
  } else {
    console.log('Text not found');
  }
}

// 示例用法
const pdfUrl = 'path/to/your/pdf-file.pdf';
const searchText = 'specific text to find';
extractTextFromPDF(pdfUrl, searchText);