Add purpose-aware property assessor intake

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

@@ -0,0 +1,139 @@
+#!/usr/bin/env node
+
+import {
+  createPageSession,
+  dismissCommonOverlays,
+  fail,
+  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) {
+  return `https://www.har.com/search/?q=${encodeURIComponent(address)}`;
+}
+
+function buildAddressTokens(address) {
+  return address
+    .toLowerCase()
+    .replace(/[^a-z0-9\s]/g, " ")
+    .split(/\s+/)
+    .filter(Boolean)
+    .filter((token) => !new Set(["tx", "dr", "st", "rd", "ave", "blvd", "ct", "ln", "cir"]).has(token));
+}
+
+function normalizeListingUrl(url) {
+  try {
+    const parsed = new URL(url);
+    parsed.search = "";
+    parsed.hash = "";
+    return parsed.toString();
+  } catch {
+    return null;
+  }
+}
+
+async function collectListingUrl(page) {
+  return page.evaluate(() => {
+    const toAbsolute = (href) => {
+      try {
+        return new URL(href, location.href).toString();
+      } catch {
+        return null;
+      }
+    };
+
+    const candidates = [];
+    for (const anchor of document.querySelectorAll('a[href*="/homedetail/"]')) {
+      const href = anchor.getAttribute("href");
+      if (!href) continue;
+      const absolute = toAbsolute(href);
+      if (!absolute) continue;
+      const text = (anchor.textContent || "").replace(/\s+/g, " ").trim();
+      const parentText = (anchor.parentElement?.textContent || "").replace(/\s+/g, " ").trim();
+      candidates.push({
+        url: absolute,
+        text,
+        parentText,
+      });
+    }
+
+    const unique = [];
+    for (const candidate of candidates) {
+      if (!unique.some((item) => item.url === candidate.url)) unique.push(candidate);
+    }
+    return unique;
+  });
+}
+
+async function main() {
+  const address = parseAddress(process.argv[2]);
+  const searchUrl = buildSearchUrl(address);
+  const { context, page } = await createPageSession({ headless: process.env.HEADLESS !== "false" });
+
+  try {
+    const attempts = [`Opened HAR search URL: ${searchUrl}`];
+    await gotoListing(page, searchUrl, 2500);
+    await dismissCommonOverlays(page);
+    await sleep(1500);
+
+    let listingUrl = null;
+    const addressTokens = buildAddressTokens(address);
+    if (page.url().includes("/homedetail/")) {
+      listingUrl = normalizeListingUrl(page.url());
+      attempts.push("HAR search URL resolved directly to a property page.");
+    } else {
+      const discovered = await collectListingUrl(page);
+      const scored = discovered
+        .map((candidate) => {
+          const haystack = `${candidate.url} ${candidate.text} ${candidate.parentText}`.toLowerCase();
+          const score = addressTokens.reduce(
+            (total, token) => total + (haystack.includes(token) ? 1 : 0),
+            0
+          );
+          return { ...candidate, score };
+        })
+        .sort((a, b) => b.score - a.score);
+
+      if (scored[0] && scored[0].score >= Math.min(3, addressTokens.length)) {
+        listingUrl = normalizeListingUrl(scored[0].url);
+        attempts.push(`HAR search results exposed a matching homedetail link with score ${scored[0].score}.`);
+      } else {
+        attempts.push("HAR discovery did not expose a confident homedetail match for this address.");
+      }
+    }
+
+    process.stdout.write(
+      `${JSON.stringify(
+        {
+          source: "har",
+          address,
+          searchUrl,
+          finalUrl: page.url(),
+          title: await page.title(),
+          listingUrl,
+          attempts,
+        },
+        null,
+        2
+      )}\n`
+    );
+    await context.close();
+  } catch (error) {
+    try {
+      await context.close();
+    } catch {
+      // Ignore close errors after the primary failure.
+    }
+    fail("HAR discovery failed.", error instanceof Error ? error.message : String(error));
+  }
+}
+
+main();