Merge pull request #173 from Alpha4615/add-author-tag-support

Author: ospfranco

__tests__/index.spec.ts

@@ -31,6 +31,14 @@ describe(`#getLinkPreview()`, () => {
     expect(linkInfo.charset?.toLowerCase()).toEqual(`utf-8`);
   });
 
+  it("should extract author from news article", async () => {
+    const linkInfo: any = await getLinkPreview(
+      `https://www.usatoday.com/story/special/contributor-content/2025/10/15/why-chaos-engineering-is-more-important-than-ever-in-the-ai-era/86712877007/`
+    );
+
+    expect(linkInfo.author).toEqual(`Matt Emma`);
+  })
+
   it(`should extract link info from a URL with a newline`, async () => {
     const linkInfo: any = await getLinkPreview(
       `

index.ts

@@ -6,6 +6,7 @@ interface ILinkPreviewResponse {
   url: string;
   title: string;
   siteName: string | undefined;
+  author: string | undefined;
   description: string | undefined;
   mediaType: string;
   contentType: string | undefined;
@@ -74,6 +75,13 @@ function getSiteName(doc: cheerio.Root) {
   return siteName;
 }
 
+function getAuthor(doc: cheerio.Root) {
+  const author =
+    metaTagContent(doc, `author`, `name`) ||
+    metaTagContent(doc, `article:author`, `property`);
+  return author;  
+}
+
 function getDescription(doc: cheerio.Root) {
   const description =
     metaTagContent(doc, `description`, `name`) ||
@@ -301,6 +309,7 @@ function parseTextResponse(
     title: getTitle(doc),
     siteName: getSiteName(doc),
     description: getDescription(doc),
+    author: getAuthor(doc),
     mediaType: getMediaType(doc) || `website`,
     contentType,
     images: getImages(doc, url, options.imagesPropertyType),