Trust embedded Zillow photo sets without visible count

docs/web-automation.md

@@ -182,6 +182,7 @@ node zillow-photos.js "https://www.zillow.com/homedetails/4141-Whiteley-Dr-Corpu
 What it does:
 - opens the listing page with CloakBrowser
 - first checks whether the rendered listing shell already exposes a complete photo set in Zillow's embedded `__NEXT_DATA__` payload
+- if the visible `See all XX photos` count is missing, still trusts the embedded set when the page metadata confirms the count or when the embedded set is already clearly substantial
 - only tries the `See all photos` / `See all X photos` entry point when the initial structured data is incomplete
 - returns direct `photos.zillowstatic.com` image URLs as JSON
 - fails fast with a timeout if the browser-backed extraction stalls

skills/web-automation/SKILL.md

@@ -158,6 +158,7 @@ The discovery scripts are purpose-built for the common address-to-listing workfl
 The photo scripts are purpose-built for the common `See all photos` / `Show all photos` workflow:
 - open the listing page
 - on Zillow, first inspect the rendered listing shell for a complete structured `__NEXT_DATA__` photo set
+- if the visible page count is missing, trust the structured Zillow photo set when page metadata confirms the count or when the embedded set is already clearly substantial
 - only force the all-photos click path when the initial Zillow page data is incomplete
 - wait for the resulting photo page or scroller view when the click path is actually needed
 - extract direct image URLs from the rendered page

skills/web-automation/scripts/zillow-photo-data.js

@@ -58,11 +58,29 @@ export function extractZillowStructuredPhotoCandidatesFromNextDataScript(scriptT
   return out;
 }
 
-export function shouldUseStructuredZillowPhotos(candidates, expectedPhotoCount) {
+const DEFAULT_MINIMUM_TRUSTED_STRUCTURED_PHOTO_COUNT = 12;
-  const count = Array.isArray(candidates) ? candidates.length : 0;
-  if (!Number.isFinite(expectedPhotoCount) || expectedPhotoCount <= 0) {
-    return false;
-  }
 
+export function shouldUseStructuredZillowPhotos(candidates, options = {}) {
+  const count = Array.isArray(candidates) ? candidates.length : 0;
+  const normalizedOptions =
+    typeof options === "number"
+      ? { expectedPhotoCount: options }
+      : options && typeof options === "object"
+        ? options
+        : {};
+  const expectedPhotoCount = Number(normalizedOptions.expectedPhotoCount || 0);
+  const fallbackPhotoCount = Number(normalizedOptions.fallbackPhotoCount || 0);
+  const minimumTrustCount = Number(
+    normalizedOptions.minimumTrustCount || DEFAULT_MINIMUM_TRUSTED_STRUCTURED_PHOTO_COUNT
+  );
+
+  if (Number.isFinite(expectedPhotoCount) && expectedPhotoCount > 0) {
     return count >= expectedPhotoCount;
   }
+
+  if (Number.isFinite(fallbackPhotoCount) && fallbackPhotoCount > 0) {
+    return count >= fallbackPhotoCount;
+  }
+
+  return count >= minimumTrustCount;
+}

skills/web-automation/scripts/zillow-photo-data.test.mjs

@@ -84,5 +84,38 @@ test("shouldUseStructuredZillowPhotos returns false when structured photos are i
     url: `https://photos.zillowstatic.com/fp/photo-${index + 1}-p_d.jpg`,
   }));
 
-  assert.equal(shouldUseStructuredZillowPhotos(candidates, 29), false);
+  assert.equal(shouldUseStructuredZillowPhotos(candidates, { expectedPhotoCount: 29 }), false);
+});
+
+test("shouldUseStructuredZillowPhotos returns true when meta-description count matches even without visible page count", () => {
+  const candidates = Array.from({ length: 29 }, (_, index) => ({
+    url: `https://photos.zillowstatic.com/fp/photo-${index + 1}-p_d.jpg`,
+  }));
+
+  assert.equal(
+    shouldUseStructuredZillowPhotos(candidates, { expectedPhotoCount: null, fallbackPhotoCount: 29 }),
+    true
+  );
+});
+
+test("shouldUseStructuredZillowPhotos returns true for a substantial structured set when no count signal is available", () => {
+  const candidates = Array.from({ length: 18 }, (_, index) => ({
+    url: `https://photos.zillowstatic.com/fp/photo-${index + 1}-p_d.jpg`,
+  }));
+
+  assert.equal(
+    shouldUseStructuredZillowPhotos(candidates, { expectedPhotoCount: null, fallbackPhotoCount: null }),
+    true
+  );
+});
+
+test("shouldUseStructuredZillowPhotos returns false for a tiny structured set when no count signal is available", () => {
+  const candidates = Array.from({ length: 5 }, (_, index) => ({
+    url: `https://photos.zillowstatic.com/fp/photo-${index + 1}-p_d.jpg`,
+  }));
+
+  assert.equal(
+    shouldUseStructuredZillowPhotos(candidates, { expectedPhotoCount: null, fallbackPhotoCount: null }),
+    false
+  );
 });

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

@@ -35,6 +35,17 @@ async function getAnnouncedPhotoCount(page) {
   });
 }
 
+async function getMetaDescriptionPhotoCount(page) {
+  return page.evaluate(() => {
+    const content =
+      document.querySelector('meta[name="description"]')?.getAttribute("content") ||
+      document.querySelector('meta[property="og:description"]')?.getAttribute("content") ||
+      "";
+    const match = content.match(/\b(\d+)\s+photos\b/i);
+    return match ? Number(match[1]) : null;
+  });
+}
+
 function collapseZillowPhotos(candidates) {
   const byBaseId = new Map();
 
@@ -137,14 +148,29 @@ export async function extractZillowPhotos(rawUrl, options = {}) {
           await dismissCommonOverlays(page);
 
           const expectedPhotoCount = await getAnnouncedPhotoCount(page);
+          const fallbackPhotoCount = await getMetaDescriptionPhotoCount(page);
           const initialStructuredPhotos = normalizeZillowPhotos(
             await collectZillowStructuredPhotoCandidates(page)
           );
 
-          if (shouldUseStructuredZillowPhotos(initialStructuredPhotos, expectedPhotoCount)) {
+          if (
+            shouldUseStructuredZillowPhotos(initialStructuredPhotos, {
+              expectedPhotoCount,
+              fallbackPhotoCount,
+            })
+          ) {
             const notes = [
               "The rendered Zillow listing shell already exposed a complete structured photo set, so extraction completed without relying on the all-photos click path.",
             ];
+            if (!expectedPhotoCount && fallbackPhotoCount) {
+              notes.push(
+                `Trusted the embedded Zillow photo set using the page metadata count of ${fallbackPhotoCount} photos.`
+              );
+            } else if (!expectedPhotoCount && !fallbackPhotoCount) {
+              notes.push(
+                "Trusted a substantial embedded Zillow photo set even though the page did not expose an explicit photo count."
+              );
+            }
             if (attempt > 1) {
               notes.push(
                 "Recovered after retrying Zillow photo extraction once because the first browser session closed unexpectedly."
@@ -156,7 +182,7 @@ export async function extractZillowPhotos(rawUrl, options = {}) {
               finalUrl: page.url(),
               title: await page.title(),
               clickedLabel: null,
-              expectedPhotoCount,
+              expectedPhotoCount: expectedPhotoCount || fallbackPhotoCount || null,
               complete: true,
               photoCount: initialStructuredPhotos.length,
               imageUrls: initialStructuredPhotos.map((photo) => photo.url),