如何使用 pdf-lib 从 PDFField 获取 PDF 页码

Question

我在我的 React TypeScript 应用程序中使用

pdf-lib

。如何获取

PDFDocument

中的所有文本字段以及该表单字段所在的页码。

const getAcroFieldRefs = (pdfDoc) => {
  if (!pdfDoc.catalog.getMaybe('AcroForm')) return [];
  const acroForm = pdfDoc.index.lookup(pdfDoc.catalog.get('AcroForm'));

  if (!acroForm.getMaybe('Fields')) return [];
  const acroFields = pdfDoc.index.lookup(acroForm.get('Fields'));

  return acroFields.array;
};

const pdfDoc = PDFDocumentFactory.load(fs.readFileSync('./form.pdf'));

const fieldRefs = getAcroFieldRefs(pdfDoc);

console.log('REFS:', fieldRefs.map(String));

const pages = pdfDoc.getPages();

const page1AnnotsRaw = pdfDoc.index.lookupMaybe(pages[0].getMaybe('Annots'));
const page1Annots = page1AnnotsRaw ? page1AnnotsRaw.array : [];

const page2AnnotsRaw = pdfDoc.index.lookupMaybe(pages[1].getMaybe('Annots'));
const page2Annots = page2AnnotsRaw ? page2AnnotsRaw.array : [];

console.log('PAGE_1_ANNOTS:', page1Annots.map(String));
console.log('PAGE_2_ANNOTS:', page2Annots.map(String));

fieldRefs.forEach((fieldRef) => {
  if (page1Annots.includes(fieldRef)) {
    console.log(`${fieldRef.toString()} belongs to page 1`);
  }
  if (page2Annots.includes(fieldRef)) {
    console.log(`${fieldRef.toString()} belongs to page 2`);
  }
});

Answer 1

function getPageIndexFromField(pdfDoc: PDFDocument, field: PDFField): number {
  let fieldPageIndex = -1;
  pdfDoc.getPages().forEach((aPage, index) => {
    const pageAnnotsRaw = aPage.node.lookupMaybe(
      PDFName.of("Annots"),
      PDFArray
    );
    const pageAnnots = pageAnnotsRaw ? pageAnnotsRaw.asArray() : [];
    if (pageAnnots.includes(field.ref)) {
      fieldPageIndex = index + 1;
    }
  });
  return fieldPageIndex;
}