diff --git a/apps/api/src/lib/entities.ts b/apps/api/src/lib/entities.ts
index 12d8c366..2f43b9a4 100644
--- a/apps/api/src/lib/entities.ts
+++ b/apps/api/src/lib/entities.ts
@@ -21,6 +21,7 @@ export type PageOptions = {
   replaceAllPathsWithAbsolutePaths?: boolean;
   parsePDF?: boolean;
   removeTags?: string | string[];
+  onlyIncludeTags?: string | string[];
 };
 
 export type ExtractorOptions = {
diff --git a/apps/api/src/scraper/WebScraper/utils/__tests__/removeUnwantedElements.test.ts b/apps/api/src/scraper/WebScraper/utils/__tests__/removeUnwantedElements.test.ts
index 0dc24c89..23b9cb69 100644
--- a/apps/api/src/scraper/WebScraper/utils/__tests__/removeUnwantedElements.test.ts
+++ b/apps/api/src/scraper/WebScraper/utils/__tests__/removeUnwantedElements.test.ts
@@ -100,4 +100,48 @@ describe('removeUnwantedElements', () => {
     expect(result).not.toContain('id="remove-this"');
     expect(result).toContain('class="keep"');
   });
+
+  it('should only include specified tags', () => {
+    const html = `<div><main>Main Content</main><aside>Remove</aside><footer>Footer Content</footer></div>`;
+    const options: PageOptions = { onlyIncludeTags: ['main', 'footer'] };
+    const result = removeUnwantedElements(html, options);
+    expect(result).toContain('<main>Main Content</main>');
+    expect(result).toContain('<footer>Footer Content</footer>');
+    expect(result).not.toContain('<aside>');
+  });
+
+  it('should handle multiple specified tags', () => {
+    const html = `<div><header>Header Content</header><main>Main Content</main><aside>Remove</aside><footer>Footer Content</footer></div>`;
+    const options: PageOptions = { onlyIncludeTags: ['header', 'main', 'footer'] };
+    const result = removeUnwantedElements(html, options);
+    expect(result).toContain('<header>Header Content</header>');
+    expect(result).toContain('<main>Main Content</main>');
+    expect(result).toContain('<footer>Footer Content</footer>');
+    expect(result).not.toContain('<aside>');
+  });
+
+  it('should handle nested specified tags', () => {
+    const html = `<div><main><section>Main Section</section></main><aside>Remove</aside><footer>Footer Content</footer></div>`;
+    const options: PageOptions = { onlyIncludeTags: ['main', 'footer'] };
+    const result = removeUnwantedElements(html, options);
+    expect(result).toContain('<main><section>Main Section</section></main>');
+    expect(result).toContain('<footer>Footer Content</footer>');
+    expect(result).not.toContain('<aside>');
+  });
+
+  it('should handle no specified tags', () => {
+    const html = `<div><main>Main Content</main><aside>Remove</aside><footer>Footer Content</footer></div>`;
+    const options: PageOptions = { onlyIncludeTags: [] };
+    const result = removeUnwantedElements(html, options);
+    expect(result).toBe('');
+  });
+
+  it('should handle specified tags as a string', () => {
+    const html = `<div><main>Main Content</main><aside>Remove</aside><footer>Footer Content</footer></div>`;
+    const options: PageOptions = { onlyIncludeTags: 'main' };
+    const result = removeUnwantedElements(html, options);
+    expect(result).toContain('<main>Main Content</main>');
+    expect(result).not.toContain('<aside>');
+    expect(result).not.toContain('<footer>');
+  });
 });
diff --git a/apps/api/src/scraper/WebScraper/utils/removeUnwantedElements.ts b/apps/api/src/scraper/WebScraper/utils/removeUnwantedElements.ts
index b69e0074..8b659889 100644
--- a/apps/api/src/scraper/WebScraper/utils/removeUnwantedElements.ts
+++ b/apps/api/src/scraper/WebScraper/utils/removeUnwantedElements.ts
@@ -4,6 +4,21 @@ import { excludeNonMainTags } from "./excludeTags";
 
 export const removeUnwantedElements = (html: string, pageOptions: PageOptions) => {
   const soup = cheerio.load(html);
+
+  if (pageOptions.onlyIncludeTags) {
+    if (typeof pageOptions.onlyIncludeTags === 'string') {
+      pageOptions.onlyIncludeTags = [pageOptions.onlyIncludeTags];
+    }
+    // Create a new root element to hold the tags to keep
+    const newRoot = cheerio.load('<div></div>')('div');
+    pageOptions.onlyIncludeTags.forEach(tag => {
+      soup(tag).each((index, element) => {
+        newRoot.append(soup(element).clone());
+      });
+    });
+    return newRoot.html();
+  }
+
   soup("script, style, iframe, noscript, meta, head").remove();
   
   if (pageOptions.removeTags) {