Add Zillow and HAR photo extractors

skills/web-automation/scripts/har-photos.js

@@ -0,0 +1,83 @@
+#!/usr/bin/env node
+
+import {
+  clickPhotoEntryPoint,
+  collectRenderedImageCandidates,
+  createPageSession,
+  dismissCommonOverlays,
+  fail,
+  gotoListing,
+  normalizeImageCandidates,
+  parseTarget,
+  scrollUntilSettled,
+  sleep,
+  waitForPhotoExperience,
+} from "./real-estate-photo-common.js";
+
+const HAR_LABELS = [
+  /^Show all photos$/i,
+  /^View all photos$/i,
+  /^All photos$/i,
+  /^Photos$/i,
+];
+
+async function getAnnouncedPhotoCount(page) {
+  return page.evaluate(() => {
+    const text = document.body?.innerText || "";
+    const match = text.match(/(\d+)\s+photos/i);
+    return match ? Number(match[1]) : null;
+  });
+}
+
+async function main() {
+  const requestedUrl = parseTarget(process.argv[2]);
+  const { context, page } = await createPageSession({ headless: process.env.HEADLESS !== "false" });
+
+  try {
+    await gotoListing(page, requestedUrl);
+    await dismissCommonOverlays(page);
+
+    const expectedPhotoCount = await getAnnouncedPhotoCount(page);
+    const beforeUrl = page.url();
+    const clickedLabel = await clickPhotoEntryPoint(page, HAR_LABELS);
+    await waitForPhotoExperience(page, beforeUrl);
+    await scrollUntilSettled(page);
+    await sleep(1200);
+
+    const candidates = await collectRenderedImageCandidates(page);
+    const photos = normalizeImageCandidates(candidates, {
+      hostIncludes: ["pics.harstatic.com", "photos.harstatic.com"],
+      minWidth: 240,
+      minHeight: 180,
+    });
+
+    if (!photos.length) {
+      fail("HAR photo extraction failed.", "No large image URLs were found after opening the HAR all-photos view.");
+    }
+
+    const result = {
+      source: "har",
+      requestedUrl,
+      finalUrl: page.url(),
+      title: await page.title(),
+      clickedLabel,
+      expectedPhotoCount,
+      complete: expectedPhotoCount ? photos.length >= expectedPhotoCount : true,
+      photoCount: photos.length,
+      imageUrls: photos.map((photo) => photo.url),
+      notes: ["Opened HAR all-photos flow and extracted large rendered image URLs from the photo page."],
+    };
+
+    process.stdout.write(`${JSON.stringify(result, null, 2)}\n`);
+    await context.close();
+  } catch (error) {
+    try {
+      await context.close();
+    } catch {
+      // Ignore close errors after the primary failure.
+    }
+    fail("HAR photo extraction failed.", error instanceof Error ? error.message : String(error));
+  }
+}
+
+main();