mirror of
https://github.com/openclaw/openclaw.git
synced 2026-05-06 08:30:42 +00:00
86099ec62a
* refactor(web-fetch): move readability extraction to plugin * fix(web-fetch): cache extractor resolution by config * fix(test): remove redundant stat assertions
51 lines
1.5 KiB
TypeScript
51 lines
1.5 KiB
TypeScript
import { describe, expect, it } from "vitest";
|
|
import { createReadabilityWebContentExtractor } from "./web-content-extractor.js";
|
|
|
|
const SAMPLE_HTML = `<!doctype html>
|
|
<html lang="en">
|
|
<head>
|
|
<meta charset="utf-8" />
|
|
<title>Example Article</title>
|
|
</head>
|
|
<body>
|
|
<nav>
|
|
<ul>
|
|
<li><a href="/home">Home</a></li>
|
|
<li><a href="/about">About</a></li>
|
|
</ul>
|
|
</nav>
|
|
<main>
|
|
<article>
|
|
<h1>Example Article</h1>
|
|
<p>Main content starts here with enough words to satisfy readability.</p>
|
|
<p>Second paragraph for a bit more signal.</p>
|
|
</article>
|
|
</main>
|
|
<footer>Footer text</footer>
|
|
</body>
|
|
</html>`;
|
|
|
|
describe("web readability extractor", () => {
|
|
it("extracts readable text", async () => {
|
|
const extractor = createReadabilityWebContentExtractor();
|
|
const result = await extractor.extract({
|
|
html: SAMPLE_HTML,
|
|
url: "https://example.com/article",
|
|
extractMode: "text",
|
|
});
|
|
expect(result?.text).toContain("Main content starts here");
|
|
expect(result?.title).toBe("Example Article");
|
|
});
|
|
|
|
it("extracts readable markdown", async () => {
|
|
const extractor = createReadabilityWebContentExtractor();
|
|
const result = await extractor.extract({
|
|
html: SAMPLE_HTML,
|
|
url: "https://example.com/article",
|
|
extractMode: "markdown",
|
|
});
|
|
expect(result?.text).toContain("Main content starts here");
|
|
expect(result?.title).toBe("Example Article");
|
|
});
|
|
});
|