利用js提取PDF文件中的文本内容

<!-- 打开pdf时自动提取pdf文本内容 -->
<script src="https://cdnjs.cloudflare.com/ajax/libs/pdf.js/2.16.105/pdf.min.js"></script>
<script>
    pdfjsLib.GlobalWorkerOptions.workerSrc = 'https://cdnjs.cloudflare.com/ajax/libs/pdf.js/2.16.105/pdf.worker.min.js';

    const pdfInput = document.getElementById('userPdfInput');
    // fileinput事件
    pdfInput.addEventListener('change', async (event) => {
      const file = event.target.files[0];
      if (file) {
        const reader = new FileReader();
        reader.onload = async (e) => {
          const arrayBuffer = e.target.result;
          try {
            const pdf = await pdfjsLib.getDocument({ data: arrayBuffer }).promise;            
            let allText = '';
            for (let i = 1; i <= pdf.numPages; i++) {
                  const page = await pdf.getPage(i);
                  const textContent = await page.getTextContent();
                  const textItems = textContent.items.map(item => item.str);
                  const pageText = textItems.join('');
                  console.log(pageText)
                  allText += pageText;
              }
            console.log(allText ); 
          } catch (error) {
            console.error('提取文本时出错:', error);
          }
        };
        reader.readAsArrayBuffer(file);
      }
    });

  </script>