Created
August 23, 2025 03:13
-
-
Save jeremy-code/fc5349f9b9c8fc5a7c48387d2602a224 to your computer and use it in GitHub Desktop.
Extract all images from a PDF page using PDF.js
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import { OPS, type PDFPageProxy, type ImageKind } from "pdfjs-dist/legacy/build/pdf.mjs"; | |
| // https://github.com/mozilla/pdf.js/blob/master/src/core/image.js#L698 | |
| type ImageObject = { | |
| width: number; | |
| height: number; | |
| interpolate: undefined; | |
| kind: (typeof ImageKind)[keyof typeof ImageKind]; | |
| data: Uint8Array | Uint8ClampedArray; | |
| dataLen: number; | |
| ref: string; | |
| }; | |
| /** | |
| * Extracts {@link ImageObject} instances from a PDF page from PDF.js | |
| */ | |
| const extractImagesFromPage = async (page: PDFPageProxy) => { | |
| const operatorList = await page.getOperatorList(); | |
| const images = operatorList.fnArray.reduce<Record<string, ImageObject>>( | |
| (acc, fn, index) => { | |
| if (fn === OPS.paintImageXObject) { | |
| const imageName = operatorList.argsArray[index][0]; | |
| const image: ImageObject = page.objs.has(imageName) | |
| ? page.objs.get(imageName) | |
| : page.commonObjs.has(imageName) | |
| ? page.commonObjs.get(imageName) | |
| : null; | |
| acc[imageName] = image; | |
| } | |
| return acc; | |
| }, | |
| {} | |
| ); | |
| return images; | |
| }; | |
| export { extractImagesFromPage }; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment