feat: AR-House initial commit

2026-07-03 12:24:58 -04:00
commit 047c05287a
216 changed files with 127552 additions and 0 deletions
@@ -0,0 +1,91 @@
+"""Find the JSON API endpoint that bcpa.net's JS calls to populate property data."""
+from pathlib import Path
+import json
+
+
+def probe():
+    from playwright.sync_api import sync_playwright
+
+    out_dir = Path(__file__).parent.parent / "_probe_out" / "bcpa"
+    folio = "484226062150"
+
+    json_responses = []
+    all_xhr = []
+
+    with sync_playwright() as p:
+        browser = p.chromium.launch(headless=True)
+        ctx = browser.new_context(
+            user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 Chrome/131.0.0.0 Safari/537.36",
+        )
+        page = ctx.new_page()
+
+        def on_response(resp):
+            try:
+                u = resp.url
+                if any(x in u for x in (".css", ".png", ".jpg", ".woff", ".ico", ".gif", "google", "fonts.")):
+                    return
+                ct = resp.headers.get("content-type", "")
+                all_xhr.append({"url": u[:200], "status": resp.status, "ct": ct})
+                if "json" in ct.lower():
+                    try:
+                        body = resp.text()
+                        json_responses.append({
+                            "url": u,
+                            "status": resp.status,
+                            "body_preview": body[:500],
+                            "body_full": body,
+                        })
+                    except Exception:
+                        pass
+            except Exception:
+                pass
+
+        page.on("response", on_response)
+
+        # Try the SPA URL (which we know loads data)
+        spa_url = f"https://web.bcpa.net/bcpaclient/#/Record-Search?folio={folio}"
+        print(f"[1] Loading SPA: {spa_url}")
+        page.goto(spa_url, wait_until="domcontentloaded", timeout=30000)
+        page.wait_for_timeout(15000)
+
+        print(f"\n[2] All XHR/network responses captured ({len(all_xhr)}):")
+        for r in all_xhr:
+            if any(x in r["ct"] for x in ("json", "xml", "html")):
+                print(f"    {r['status']} [{r['ct'][:30]}] {r['url'][:130]}")
+
+        print(f"\n[3] JSON responses found: {len(json_responses)}")
+        for jr in json_responses:
+            print(f"\n  URL: {jr['url']}")
+            print(f"  Status: {jr['status']}")
+            print(f"  Preview: {jr['body_preview']}")
+
+        # Save full JSON responses
+        if json_responses:
+            (out_dir / "json_responses.json").write_text(
+                json.dumps(json_responses, indent=2), encoding="utf-8"
+            )
+
+        # Also try directly hitting common ASP.NET WebMethod endpoints
+        print(f"\n[4] Probing common WebMethod endpoint patterns directly:")
+        candidates = [
+            f"https://web.bcpa.net/bcpaclient/search.aspx/getOwnerInfo",
+            f"https://web.bcpa.net/bcpaclient/search.aspx/getPropertyData",
+            f"https://web.bcpa.net/bcpaclient/search.aspx/getRecordByFolio",
+            f"https://web.bcpa.net/bcpaclient/search.aspx/GetRecordByFolio",
+        ]
+        for url_test in candidates:
+            try:
+                resp = page.request.post(url_test, data=json.dumps({"folioNumber": folio}),
+                                          headers={"Content-Type": "application/json"})
+                ct = resp.headers.get("content-type", "")
+                body = (resp.text())[:200]
+                print(f"  POST {url_test}: {resp.status} [{ct[:30]}] body={body!r}")
+            except Exception as e:
+                print(f"  POST {url_test}: ERROR {e}")
+
+        browser.close()
+        print(f"\n[OK] saved to {out_dir}/")
+
+
+if __name__ == "__main__":
+    probe()