Make listing discovery unit-aware

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

@@ -7,24 +7,11 @@ import {
   gotoListing,
   sleep,
 } from "./real-estate-photo-common.js";
-
-function parseAddress(rawAddress) {
-  const address = String(rawAddress || "").trim();
-  if (!address) {
-    fail("Missing address.");
-  }
-  return address;
-}
-
-function buildSearchUrl(address) {
-  const slug = address
-    .replace(/,/g, "")
-    .replace(/#/g, "")
-    .trim()
-    .split(/\s+/)
-    .join("-");
-  return `https://www.zillow.com/homes/${encodeURIComponent(slug)}_rb/`;
-}
+import {
+  buildZillowAddressSlug,
+  parseAddressIdentity,
+  scoreAddressCandidate,
+} from "./real-estate-address.js";
 
 function normalizeListingUrl(url) {
   try {
@@ -53,20 +40,31 @@ async function collectListingUrl(page) {
       if (!href) continue;
       const absolute = toAbsolute(href);
       if (!absolute) continue;
-      candidates.push(absolute);
+      const text = (anchor.textContent || "").replace(/\s+/g, " ").trim();
+      const aria = anchor.getAttribute("aria-label") || "";
+      const title = anchor.getAttribute("title") || "";
+      const parentText = (anchor.parentElement?.textContent || "").replace(/\s+/g, " ").trim();
+      candidates.push({
+        url: absolute,
+        text,
+        aria,
+        title,
+        parentText,
+      });
     }
 
     const unique = [];
     for (const candidate of candidates) {
-      if (!unique.includes(candidate)) unique.push(candidate);
+      if (!unique.some((item) => item.url === candidate.url)) unique.push(candidate);
     }
-    return unique[0] || null;
+    return unique;
   });
 }
 
 async function main() {
-  const address = parseAddress(process.argv[2]);
-  const searchUrl = buildSearchUrl(address);
+  const address = String(process.argv[2] || "").trim();
+  const identity = parseAddressIdentity(address);
+  const searchUrl = `https://www.zillow.com/homes/${encodeURIComponent(buildZillowAddressSlug(address))}_rb/`;
   const { context, page } = await createPageSession({ headless: process.env.HEADLESS !== "false" });
 
   try {
@@ -77,15 +75,33 @@ async function main() {
 
     let listingUrl = null;
     if (page.url().includes("/homedetails/")) {
-      listingUrl = normalizeListingUrl(page.url());
-      attempts.push("Zillow search URL resolved directly to a property page.");
+      const directScore = scoreAddressCandidate(
+        identity,
+        `${page.url()} ${(await page.title()) || ""}`
+      );
+      if (directScore.matched) {
+        listingUrl = normalizeListingUrl(page.url());
+        attempts.push("Zillow search URL resolved directly to a matching property page.");
+      } else {
+        attempts.push("Zillow redirected to a property page, but it did not match the requested address closely enough.");
+      }
     } else {
       const discovered = await collectListingUrl(page);
-      if (discovered) {
-        listingUrl = normalizeListingUrl(discovered);
-        attempts.push("Zillow search results exposed a homedetails link.");
+      const scored = discovered
+        .map((candidate) => ({
+          ...candidate,
+          match: scoreAddressCandidate(
+            identity,
+            `${candidate.url} ${candidate.text} ${candidate.aria} ${candidate.title} ${candidate.parentText}`
+          )
+        }))
+        .sort((a, b) => b.match.score - a.match.score);
+
+      if (scored[0]?.match.matched) {
+        listingUrl = normalizeListingUrl(scored[0].url);
+        attempts.push(`Zillow search results exposed a matching homedetails link with score ${scored[0].match.score}.`);
       } else {
-        attempts.push("Zillow discovery did not expose a homedetails link for this address.");
+        attempts.push("Zillow discovery did not expose a confident homedetails match for this address.");
       }
     }