📌  相关文章
📜  pdfjs 获取所有存在的文本 - Javascript 代码示例

📅  最后修改于: 2022-03-11 15:03:11.644000             🧑  作者: Mango

代码示例1
import PDFJS from "pdfjs-dist";
import PDFJSWorker from "pdfjs-dist/build/pdf.worker.js"; // add this to fit 2.3.0

PDFJS.disableTextLayer = true;
PDFJS.disableWorker = true; // not availaible anymore since 2.3.0 (see imports)

const getPageText = async (pdf: Pdf, pageNo: number) => {
  const page = await pdf.getPage(pageNo);
  const tokenizedText = await page.getTextContent();
  const pageText = tokenizedText.items.map(token => token.str).join("");
  return pageText;
};

/* see example of a PDFSource below */
export const getPDFText = async (source: PDFSource): Promise => {
  Object.assign(window, {pdfjsWorker: PDFJSWorker}); // added to fit 2.3.0
  const pdf: Pdf = await PDFJS.getDocument(source).promise;
  const maxPages = pdf.numPages;
  const pageTextPromises = [];
  for (let pageNo = 1; pageNo <= maxPages; pageNo += 1) {
    pageTextPromises.push(getPageText(pdf, pageNo));
  }
  const pageTexts = await Promise.all(pageTextPromises);
  return pageTexts.join(" ");
};