feat(amazon-shopping): scrape and filter amazon product results

2026-04-15 18:48:51 -05:00
parent ef326896f4
commit 1e0e265f1e
15 changed files with 844 additions and 6 deletions
@@ -0,0 +1,77 @@
+import assert from "node:assert/strict";
+import { readFile } from "node:fs/promises";
+import { join } from "node:path";
+import { describe, it } from "node:test";
+
+import { extractDetailPage } from "../src/detail-page.js";
+
+const fixturePath = join(import.meta.dirname, "fixtures", "product-detail.html");
+
+describe("extractDetailPage", () => {
+  it("extracts visible product detail fields from sanitized HTML", async () => {
+    const html = await readFile(fixturePath, "utf8");
+    const details = extractDetailPage(html, {
+      asin: "B0TESTLED1",
+      title: "Search title",
+      url: "https://www.amazon.com/dp/B0TESTLED1",
+      specs: [],
+      bullets: [],
+      matchedFilters: [],
+      missingFields: [],
+      extractionNotes: []
+    });
+
+    assert.equal(details.title, "Bright Daylight LED Bulbs 100W Equivalent, 50 Count");
+    assert.equal(details.price?.amount, 18.99);
+    assert.equal(details.delivery?.free, true);
+    assert.equal(details.availability, "In Stock");
+    assert.equal(details.seller, "Ships from Amazon.com");
+    assert.equal(details.bullets.length, 2);
+    assert.deepEqual(details.specs[0], { name: "Brand", value: "BrightCo" });
+    assert.equal(details.rating, 4.6);
+    assert.equal(details.reviewCount, 1234);
+    assert.equal(details.starBreakdown?.five, 72);
+  });
+
+  it("records missing detail-only fields", () => {
+    const details = extractDetailPage("<html><body><h1 id=\"productTitle\">Sparse Product</h1></body></html>", {
+      asin: "B0SPARSE01",
+      title: "Sparse",
+      url: "https://www.amazon.com/dp/B0SPARSE01",
+      specs: [],
+      bullets: [],
+      matchedFilters: [],
+      missingFields: [],
+      extractionNotes: []
+    });
+
+    assert.equal(details.price, undefined);
+    assert.ok(details.missingFields.includes("price"));
+    assert.ok(details.missingFields.includes("starBreakdown"));
+  });
+
+  it("drops script-like spec rows and trims availability metadata", () => {
+    const details = extractDetailPage(`
+      <h1 id="productTitle">Messy Product</h1>
+      <div id="availability">In Stock {"merchantId":"secretish"}</div>
+      <table>
+        <tr><td>Special Feature</td><td>(function(P) { tracking(); }) Real feature text</td></tr>
+        <tr><td>A19 Add to Cart logShoppableMetrics("x", true)</td><td>Buying Options</td></tr>
+        <tr><td>Wattage</td><td>15 watts</td></tr>
+        <tr><td>Customer Reviews</td><td>4.7 out of 5 stars tracking payload</td></tr>
+      </table>
+    `, {
+      asin: "B0MESSY001",
+      title: "Messy",
+      url: "https://www.amazon.com/dp/B0MESSY001",
+      specs: [],
+      bullets: [],
+      matchedFilters: [],
+      missingFields: [],
+      extractionNotes: []
+    });
+
+    assert.equal(details.availability, "In Stock");
+    assert.deepEqual(details.specs, [{ name: "Wattage", value: "15 watts" }]);
+  });
+});