unpdf 1.0.5 → 1.1.0

package/README.md

@@ -10,7 +10,7 @@ This library is also intended as a modern alternative to the unmaintained but st
 
 - 🏗️ Made for Node.js, browser and serverless environments
 - 🪭 Includes serverless build of PDF.js ([`unpdf/pdfjs`](./package.json#L34))
-- 💬 Extract [text](#extract-text-from-pdf) and [images](#extractimages) from PDF files
+- 💬 Extract [text](#extract-text-from-pdf), [links](#extractlinks), and [images](#extractimages) from PDF files
 - 🧠 Perfect for AI applications and PDF summarization
 - 🧱 Opt-in to legacy PDF.js build
 - 💨 Zero dependencies
@@ -169,6 +169,39 @@ function extractText(
 }>
 ```
 
+### `extractLinks`
+
+Extracts all links from a PDF document, including hyperlinks and external URLs.
+
+**Type Declaration**
+
+```ts
+function extractLinks(
+  data: DocumentInitParameters['data'] | PDFDocumentProxy,
+): Promise<{
+  totalPages: number
+  links: string[]
+}>
+```
+
+**Example**
+
+```ts
+import { readFile } from 'node:fs/promises'
+import { extractLinks, getDocumentProxy } from 'unpdf'
+
+// Load a PDF file
+const buffer = await readFile('./document.pdf')
+const pdf = await getDocumentProxy(new Uint8Array(buffer))
+
+// Extract all links from the PDF
+const { totalPages, links } = await extractLinks(pdf)
+
+console.log(`Total pages: ${totalPages}`)
+console.log(`Found ${links.length} links:`)
+for (const link of links) console.log(link)
+```
+
 ### `extractImages`
 
 Extracts images from a specific page of a PDF document, including necessary metadata such as width, height, and calculated color channels.

package/dist/index.cjs

@@ -145,7 +145,7 @@ async function extractImages$1(data, pageNumber) {
       continue;
     }
     const imageKey = operatorList.argsArray[i][0];
-    const image = imageKey.startsWith("g_") ? await page.commonObjs.get(imageKey) : await page.objs.get(imageKey);
+    const image = imageKey.startsWith("g_") ? await new Promise((resolve) => page.commonObjs.get(imageKey, (resolvedImage) => resolve(resolvedImage))) : await new Promise((resolve) => page.objs.get(imageKey, (resolvedImage) => resolve(resolvedImage)));
     if (!image || !image.data || !image.width || !image.height) {
       continue;
     }
@@ -203,6 +203,28 @@ async function createIsomorphicCanvasFactory(canvasImport) {
   throw new Error("Unsupported environment for canvas creation.");
 }
 
+async function extractLinks$1(data) {
+  const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
+  const pageLinks = await Promise.all(
+    Array.from({ length: pdf.numPages }, (_, i) => getPageLinks(pdf, i + 1))
+  );
+  return {
+    totalPages: pdf.numPages,
+    links: pageLinks.flat()
+  };
+}
+async function getPageLinks(document, pageNumber) {
+  const page = await document.getPage(pageNumber);
+  const annotations = await page.getAnnotations();
+  const links = [];
+  for (const annotation of annotations) {
+    if (annotation.subtype === "Link" && annotation.url) {
+      links.push(annotation.url);
+    }
+  }
+  return links;
+}
+
 async function getMeta$1(data) {
   const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
   const meta = await pdf.getMetadata();
@@ -252,10 +274,15 @@ const renderPageAsImage = async (...args) => {
   await resolvePDFJSImport();
   return await renderPageAsImage$1(...args);
 };
+const extractLinks = async (...args) => {
+  await resolvePDFJSImport();
+  return await extractLinks$1(...args);
+};
 
 exports.configureUnPDF = configureUnPDF;
 exports.definePDFJSModule = definePDFJSModule;
 exports.extractImages = extractImages;
+exports.extractLinks = extractLinks;
 exports.extractText = extractText;
 exports.getDocumentProxy = getDocumentProxy;
 exports.getMeta = getMeta;

package/dist/index.d.cts

@@ -34,6 +34,11 @@ declare function renderPageAsImage$1(data: DocumentInitParameters['data'] | PDFD
     height?: number;
 }): Promise<ArrayBuffer>;
 
+declare function extractLinks$1(data: DocumentInitParameters['data'] | PDFDocumentProxy): Promise<{
+    totalPages: number;
+    links: string[];
+}>;
+
 declare function getMeta$1(data: DocumentInitParameters['data'] | PDFDocumentProxy): Promise<{
     info: Record<string, any>;
     metadata: Record<string, any>;
@@ -86,5 +91,6 @@ declare const getMeta: typeof getMeta$1;
 declare const extractText: typeof extractText$1;
 declare const extractImages: typeof extractImages$1;
 declare const renderPageAsImage: typeof renderPageAsImage$1;
+declare const extractLinks: typeof extractLinks$1;
 
-export { configureUnPDF, definePDFJSModule, extractImages, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImport };
+export { configureUnPDF, definePDFJSModule, extractImages, extractLinks, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImport };

package/dist/index.d.mts

@@ -34,6 +34,11 @@ declare function renderPageAsImage$1(data: DocumentInitParameters['data'] | PDFD
     height?: number;
 }): Promise<ArrayBuffer>;
 
+declare function extractLinks$1(data: DocumentInitParameters['data'] | PDFDocumentProxy): Promise<{
+    totalPages: number;
+    links: string[];
+}>;
+
 declare function getMeta$1(data: DocumentInitParameters['data'] | PDFDocumentProxy): Promise<{
     info: Record<string, any>;
     metadata: Record<string, any>;
@@ -86,5 +91,6 @@ declare const getMeta: typeof getMeta$1;
 declare const extractText: typeof extractText$1;
 declare const extractImages: typeof extractImages$1;
 declare const renderPageAsImage: typeof renderPageAsImage$1;
+declare const extractLinks: typeof extractLinks$1;
 
-export { configureUnPDF, definePDFJSModule, extractImages, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImport };
+export { configureUnPDF, definePDFJSModule, extractImages, extractLinks, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImport };

package/dist/index.d.ts

@@ -34,6 +34,11 @@ declare function renderPageAsImage$1(data: DocumentInitParameters['data'] | PDFD
     height?: number;
 }): Promise<ArrayBuffer>;
 
+declare function extractLinks$1(data: DocumentInitParameters['data'] | PDFDocumentProxy): Promise<{
+    totalPages: number;
+    links: string[];
+}>;
+
 declare function getMeta$1(data: DocumentInitParameters['data'] | PDFDocumentProxy): Promise<{
     info: Record<string, any>;
     metadata: Record<string, any>;
@@ -86,5 +91,6 @@ declare const getMeta: typeof getMeta$1;
 declare const extractText: typeof extractText$1;
 declare const extractImages: typeof extractImages$1;
 declare const renderPageAsImage: typeof renderPageAsImage$1;
+declare const extractLinks: typeof extractLinks$1;
 
-export { configureUnPDF, definePDFJSModule, extractImages, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImport };
+export { configureUnPDF, definePDFJSModule, extractImages, extractLinks, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImport };

package/dist/index.mjs

@@ -143,7 +143,7 @@ async function extractImages$1(data, pageNumber) {
       continue;
     }
     const imageKey = operatorList.argsArray[i][0];
-    const image = imageKey.startsWith("g_") ? await page.commonObjs.get(imageKey) : await page.objs.get(imageKey);
+    const image = imageKey.startsWith("g_") ? await new Promise((resolve) => page.commonObjs.get(imageKey, (resolvedImage) => resolve(resolvedImage))) : await new Promise((resolve) => page.objs.get(imageKey, (resolvedImage) => resolve(resolvedImage)));
     if (!image || !image.data || !image.width || !image.height) {
       continue;
     }
@@ -201,6 +201,28 @@ async function createIsomorphicCanvasFactory(canvasImport) {
   throw new Error("Unsupported environment for canvas creation.");
 }
 
+async function extractLinks$1(data) {
+  const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
+  const pageLinks = await Promise.all(
+    Array.from({ length: pdf.numPages }, (_, i) => getPageLinks(pdf, i + 1))
+  );
+  return {
+    totalPages: pdf.numPages,
+    links: pageLinks.flat()
+  };
+}
+async function getPageLinks(document, pageNumber) {
+  const page = await document.getPage(pageNumber);
+  const annotations = await page.getAnnotations();
+  const links = [];
+  for (const annotation of annotations) {
+    if (annotation.subtype === "Link" && annotation.url) {
+      links.push(annotation.url);
+    }
+  }
+  return links;
+}
+
 async function getMeta$1(data) {
   const pdf = isPDFDocumentProxy(data) ? data : await getDocumentProxy(data);
   const meta = await pdf.getMetadata();
@@ -250,5 +272,9 @@ const renderPageAsImage = async (...args) => {
   await resolvePDFJSImport();
   return await renderPageAsImage$1(...args);
 };
+const extractLinks = async (...args) => {
+  await resolvePDFJSImport();
+  return await extractLinks$1(...args);
+};
 
-export { configureUnPDF, definePDFJSModule, extractImages, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImport };
+export { configureUnPDF, definePDFJSModule, extractImages, extractLinks, extractText, getDocumentProxy, getMeta, getResolvedPDFJS, renderPageAsImage, resolvePDFJSImport };