Features

PDF.js Compatibility

Tip

The serverless PDF.js bundle provided byunpdf is built from PDF.js v5.4.394.

Installation

# pnpmpnpm add -D unpdf# npmnpm install -D unpdf# yarnyarn add -D unpdf

Usage

Extract Text From PDF

import{extractText,getDocumentProxy}from'unpdf'// Either fetch a PDF file from the web or load it from the file systemconstbuffer=awaitfetch('https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf').then(res=>res.arrayBuffer())constbuffer=awaitreadFile('./dummy.pdf')// Then, load the PDF file into a PDF.js documentconstpdf=awaitgetDocumentProxy(newUint8Array(buffer))// Finally, extract the text from the PDF fileconst{ totalPages, text}=awaitextractText(pdf,{mergePages:true})console.log(`Total pages:${totalPages}`)console.log(text)

Official or Legacy PDF.js Build

Warning

PDF.js v5.x usesPromise.withResolvers, which may not be supported in all environments, such as Node < 22. Consider to use the bundled serverless build, which includes a polyfill, or use an older version of PDF.js.

import{definePDFJSModule,extractText,getDocumentProxy}from'unpdf'// Define the PDF.js build before using any other unpdf methodawaitdefinePDFJSModule(()=>import('pdfjs-dist'))// Now, you can use all unpdf methods with the official PDF.js buildconstpdf=awaitgetDocumentProxy(/* … */)const{ text}=awaitextractText(pdf)

PDF.js API

import{getResolvedPDFJS}from'unpdf'const{ version}=awaitgetResolvedPDFJS()

Note

If no other PDF.js build was defined, the serverless build will always be used.

import{readFile}from'node:fs/promises'import{getResolvedPDFJS}from'unpdf'const{ getDocument}=awaitgetResolvedPDFJS()constdata=awaitreadFile('./dummy.pdf')constdocument=awaitgetDocument(newUint8Array(data)).promiseconsole.log(awaitdocument.getMetadata())

API

definePDFJSModule

functiondefinePDFJSModule(pdfjs:()=>Promise<PDFJS>):Promise<void>

getResolvedPDFJS

functiongetResolvedPDFJS():Promise<PDFJS>

getMeta

functiongetMeta(data:DocumentInitParameters['data']|PDFDocumentProxy,options?:{parseDates?:boolean},):Promise<{info:Record<string,any>metadata:Record<string,any>}>

extractText

functionextractText(data:DocumentInitParameters['data']|PDFDocumentProxy,options?:{mergePages?:false}):Promise<{totalPages:numbertext:string[]}>functionextractText(data:DocumentInitParameters['data']|PDFDocumentProxy,options:{mergePages:true}):Promise<{totalPages:numbertext:string}>

extractLinks

functionextractLinks(data:DocumentInitParameters['data']|PDFDocumentProxy,):Promise<{totalPages:numberlinks:string[]}>

import{readFile}from'node:fs/promises'import{extractLinks,getDocumentProxy}from'unpdf'// Load a PDF fileconstbuffer=awaitreadFile('./document.pdf')constpdf=awaitgetDocumentProxy(newUint8Array(buffer))// Extract all links from the PDFconst{ totalPages, links}=awaitextractLinks(pdf)console.log(`Total pages:${totalPages}`)console.log(`Found${links.length} links:`)for(constlinkoflinks)console.log(link)

extractImages

Note

This method will only work in Node.js and browser environments.

interfaceExtractedImageObject{data:Uint8ClampedArraywidth:numberheight:numberchannels:1|3|4key:string}functionextractImages(data:DocumentInitParameters['data']|PDFDocumentProxy,pageNumber:number,):Promise<ExtractedImageObject[]>

Note

The following example uses thesharp library to process and save the extracted images. You will need to install it with your preferred package manager.

import{readFile,writeFile}from'node:fs/promises'importsharpfrom'sharp'import{extractImages,getDocumentProxy}from'unpdf'asyncfunctionextractPdfImages(){constbuffer=awaitreadFile('./document.pdf')constpdf=awaitgetDocumentProxy(newUint8Array(buffer))// Extract images from page 1constimagesData=awaitextractImages(pdf,1)console.log(`Found${imagesData.length} images on page 1`)// Process each image with sharp (optional)lettotalImagesProcessed=0for(constimgDataofimagesData){constimageIndex=++totalImagesProcessedawaitsharp(imgData.data,{raw:{width:imgData.width,height:imgData.height,channels:imgData.channels}}).png().toFile(`image-${imageIndex}.png`)console.log(`Saved image${imageIndex} (${imgData.width}x${imgData.height},${imgData.channels} channels)`)}}extractPdfImages().catch(console.error)

renderPageAsImage

Note

This method will only work in Node.js and browser environments.

functionrenderPageAsImage(data:DocumentInitParameters['data']|PDFDocumentProxy,pageNumber:number,options?:{canvasImport?:()=>Promise<typeofimport('@napi-rs/canvas')>/**@default 1.0 */scale?:numberwidth?:numberheight?:numbertoDataURL?:false},):Promise<ArrayBuffer>functionrenderPageAsImage(data:DocumentInitParameters['data']|PDFDocumentProxy,pageNumber:number,options:{canvasImport?:()=>Promise<typeofimport('@napi-rs/canvas')>/**@default 1.0 */scale?:numberwidth?:numberheight?:numbertoDataURL:true},):Promise<string>

import{definePDFJSModule,renderPageAsImage}from'unpdf'// Use the official PDF.js buildawaitdefinePDFJSModule(()=>import('pdfjs-dist'))constpdf=awaitreadFile('./dummy.pdf')constbuffer=newUint8Array(pdf)constpageNumber=1constresult=awaitrenderPageAsImage(buffer,pageNumber,{canvasImport:()=>import('@napi-rs/canvas'),scale:2,})awaitwriteFile('dummy-page-1.png',newUint8Array(result))

import{definePDFJSModule,renderPageAsImage}from'unpdf'awaitdefinePDFJSModule(()=>import('pdfjs-dist'))constpdf=awaitreadFile('./dummy.pdf')constbuffer=newUint8Array(pdf)constpageNumber=1constresult=awaitrenderPageAsImage(buffer,pageNumber,{canvasImport:()=>import('@napi-rs/canvas'),scale:2,toDataURL:true,})consthtml=`<!DOCTYPE html><html lang="en">  <head>    <meta charset="UTF-8">    <meta name="viewport" content="width=device-width, initial-scale=1.0">    <title>Dummy Page</title>  </head>  <body>    <img alt="Example Page" src="${result}">  </body></html>`awaitwriteFile('dummy-page-1.html',html)

License