A nodeless/serverless redistribution of Mozilla's PDF.js for serverless enviroments, like Deno Deploy and Cloudflare Workers with zero dependencies.

pdfjs-serverless_deno.ts

//ORIGINAL CODE REPO: https://github.com/johannschopplich/pdfjs-serverless
//# pnpm
//pnpm add pdfjs-serverless
//# npm
//npm install pdfjs-serverless

import { getDocument } from 'https://esm.sh/pdfjs-serverless'

const data = Deno.readFileSync('./dummy.pdf')
const doc = await getDocument(data).promise

console.log(await doc.getMetadata())

for (let i = 1; i <= doc.numPages; i++) {
  const page = await doc.getPage(i)
  const textContent = await page.getTextContent()
  const contents = textContent.items.map(item => item.str).join(' ')
  console.log(contents)
}

using_unpdf.ts

import { defineUnPDFConfig, extractPDFText } from 'node:unpdf'

// Use the serverless version of PDF.js
defineUnPDFConfig({
  pdfjs: () => import('pdfjs-serverless')
})

// Now, you can use the other methods provided by unpdf

// Fetch a PDF file from the web
const pdf = await fetch('https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf')
  .then(res => res.arrayBuffer())

// Pass the PDF buffer to the relevant method
const { totalPages, text } = await extractPDFText(
  new Uint8Array(pdf), { mergePages: true }
)