import { extractImages } from "../extractImages";
describe("extractImages", () => {
const baseUrl = "https://example.com/page.html";
it("should extract images from img tags", async () => {
const html = `
`;
const images = await extractImages(html, baseUrl);
expect(images).toContain("https://example.com/image1.jpg");
expect(images).toContain("https://example.com/images/image2.png");
expect(images).toContain("https://external.com/image3.gif");
expect(images).toHaveLength(3);
});
it("should extract lazy-loaded images from data-src", async () => {
const html = `
![Lazy loaded image]()
`;
const images = await extractImages(html, baseUrl);
expect(images).toContain("https://example.com/lazy-image.webp");
expect(images).toContain("https://example.com/regular.jpg");
expect(images).toContain("https://example.com/ignored.jpg");
});
it("should extract images from srcset", async () => {
const html = `
![Responsive image]()
`;
const images = await extractImages(html, baseUrl);
expect(images).toContain("https://example.com/small.jpg");
expect(images).toContain("https://example.com/medium.jpg");
expect(images).toContain("https://example.com/large.jpg");
expect(images).toHaveLength(3);
});
it("should extract images from picture elements", async () => {
const html = `
`;
const images = await extractImages(html, baseUrl);
expect(images).toContain("https://example.com/image.avif");
expect(images).toContain("https://example.com/image.webp");
expect(images).toContain("https://example.com/image.jpg");
});
it("should extract images from meta tags", async () => {
const html = `
`;
const images = await extractImages(html, baseUrl);
expect(images).toContain("https://example.com/og-image.jpg");
expect(images).toContain("https://example.com/og-image-secure.jpg");
expect(images).toContain("https://example.com/twitter-image.png");
expect(images).toContain("https://example.com/schema-image.jpg");
});
it("should extract images from link tags", async () => {
const html = `
`;
const images = await extractImages(html, baseUrl);
expect(images).toContain("https://example.com/favicon.ico");
expect(images).toContain("https://example.com/apple-touch-icon.png");
expect(images).toContain("https://example.com/link-image.jpg");
});
it("should extract background images from inline styles", async () => {
const html = `
Content
Content
Content
`;
const images = await extractImages(html, baseUrl);
expect(images).toContain("https://example.com/background1.jpg");
expect(images).toContain("https://example.com/images/background2.png");
expect(images).toContain("https://example.com/background3.gif");
});
it("should extract video poster images", async () => {
const html = `
`;
const images = await extractImages(html, baseUrl);
expect(images).toContain("https://example.com/video-poster.jpg");
expect(images).toContain("https://example.com/videos/poster.png");
});
it("should handle protocol-relative URLs", async () => {
const html = `
`;
const images = await extractImages(html, baseUrl);
expect(images).toContain("https://cdn.example.com/image.jpg");
});
it("should handle data URIs", async () => {
const html = `
`;
const images = await extractImages(html, baseUrl);
expect(images).toContain("data:image/png;base64,iVBORw0KGgoAAAANS...");
});
it("should respect base tag", async () => {
const html = `
`;
const images = await extractImages(html, baseUrl);
expect(images).toContain("https://different.com/base/image.jpg");
});
it("should remove duplicates", async () => {
const html = `
`;
const images = await extractImages(html, baseUrl);
const duplicateCount = images.filter(img =>
img.includes("duplicate.jpg"),
).length;
expect(duplicateCount).toBe(1);
});
it("should handle invalid URLs gracefully", async () => {
const html = `
)
![Empty]()
![No src]()
`;
const images = await extractImages(html, baseUrl);
expect(images).toContain("https://example.com/valid.jpg");
expect(images).not.toContain("javascript:alert('xss')");
expect(images).toHaveLength(1);
});
});
`;
const images = await extractImages(html, baseUrl);
expect(images).toContain("https://example.com/small.jpg");
expect(images).toContain("https://example.com/medium.jpg");
expect(images).toContain("https://example.com/large.jpg");
expect(images).toHaveLength(3);
});
it("should extract images from picture elements", async () => {
const html = `
`;
const images = await extractImages(html, baseUrl);
expect(images).toContain("https://example.com/lazy-image.webp");
expect(images).toContain("https://example.com/regular.jpg");
expect(images).toContain("https://example.com/ignored.jpg");
});
it("should extract images from srcset", async () => {
const html = `
`;
const images = await extractImages(html, baseUrl);
expect(images).toContain("https://cdn.example.com/image.jpg");
});
it("should handle data URIs", async () => {
const html = `