feat(amazon-shopping): parse filters and extract search candidates

2026-04-15 18:31:44 -05:00
parent 8ad532545d
commit ef326896f4
15 changed files with 822 additions and 10 deletions
@@ -0,0 +1,65 @@
+import assert from "node:assert/strict";
+import { readFile } from "node:fs/promises";
+import { join } from "node:path";
+import { describe, it } from "node:test";
+
+import { extractSearchPage } from "../src/search-page.js";
+
+const fixturePath = join(import.meta.dirname, "fixtures", "search-results.html");
+
+describe("extractSearchPage", () => {
+  it("extracts normalized product candidates from sanitized search HTML", async () => {
+    const html = await readFile(fixturePath, "utf8");
+    const extracted = extractSearchPage(html, "https://www.amazon.com/s?k=led+bulbs");
+
+    assert.equal(extracted.status, "ok");
+    assert.equal(extracted.products.length, 2);
+    assert.equal(extracted.products[0]?.asin, "B0TESTLED1");
+    assert.equal(extracted.products[0]?.url, "https://www.amazon.com/dp/B0TESTLED1");
+    assert.equal(extracted.products[0]?.price?.amount, 18.99);
+    assert.equal(extracted.products[0]?.unitPrice?.amount, 0.38);
+    assert.equal(extracted.products[0]?.rating, 4.6);
+    assert.equal(extracted.products[0]?.reviewCount, 1234);
+    assert.equal(extracted.products[0]?.delivery?.free, true);
+    assert.equal(extracted.products[0]?.isSponsored, false);
+    assert.equal(extracted.products[1]?.isSponsored, true);
+    assert.equal(extracted.nextPageUrl, "https://www.amazon.com/s?k=led+bulbs&page=2");
+  });
+
+  it("detects Amazon challenge pages", () => {
+    const extracted = extractSearchPage("<html><title>Robot Check</title><body>Enter the characters you see below</body></html>", "https://www.amazon.com/s?k=x");
+
+    assert.equal(extracted.status, "challenge");
+    assert.match(extracted.warnings[0] ?? "", /challenge/i);
+    assert.equal(extracted.products.length, 0);
+  });
+
+  it("returns ok with no products for empty or cardless pages", () => {
+    const extracted = extractSearchPage("<html><body>No results</body></html>", "https://www.amazon.com/s?k=x");
+
+    assert.equal(extracted.status, "ok");
+    assert.deepEqual(extracted.products, []);
+    assert.equal(extracted.nextPageUrl, undefined);
+  });
+
+  it("skips malformed ASINs and cards without titles", () => {
+    const extracted = extractSearchPage(`
+      <div data-asin="bad"><h2><a href="/dp/bad">Bad ASIN</a></h2></div>
+      <div data-asin="B0VALID1234"></div>
+    `, "https://www.amazon.com/s?k=x");
+
+    assert.equal(extracted.status, "ok");
+    assert.equal(extracted.products.length, 0);
+  });
+
+  it("keeps candidates with missing price and records missing price later", () => {
+    const extracted = extractSearchPage(`
+      <div data-asin="B0NOPRICE1">
+        <h2><a href="/dp/B0NOPRICE1">No Price Product</a></h2>
+      </div>
+    `, "https://www.amazon.com/s?k=x");
+
+    assert.equal(extracted.products.length, 1);
+    assert.equal(extracted.products[0]?.price, undefined);
+  });
+});