enrich data

extract_viewing_from_html.py

@@ -0,0 +1,45 @@
+#!/usr/bin/env python3
+"""Find viewing/pickup in actual HTML"""
+import asyncio
+from playwright.async_api import async_playwright
+import re
+
+async def main():
+    async with async_playwright() as p:
+        browser = await p.chromium.launch(headless=True)
+        page = await browser.new_page()
+
+        # Try a lot that should have viewing times
+        await page.goto("https://www.troostwijkauctions.com/l/woonunit-type-tp-4-b-6m-nr-102-A1-37889-102", wait_until='networkidle')
+
+        # Get text content
+        text_content = await page.evaluate("document.body.innerText")
+
+        print("Searching for viewing/pickup patterns...\n")
+
+        # Look for "Bezichtigingen" section
+        lines = text_content.split('\n')
+        for i, line in enumerate(lines):
+            if 'bezichtig' in line.lower() or 'viewing' in line.lower():
+                # Print surrounding context
+                context = lines[max(0, i-1):min(len(lines), i+5)]
+                print("FOUND Bezichtigingen:")
+                for c in context:
+                    print(f"  {c}")
+                print()
+                break
+
+        # Look for "Ophalen" section
+        for i, line in enumerate(lines):
+            if 'ophalen' in line.lower() or 'collection' in line.lower() or 'pickup' in line.lower():
+                context = lines[max(0, i-1):min(len(lines), i+5)]
+                print("FOUND Ophalen:")
+                for c in context:
+                    print(f"  {c}")
+                print()
+                break
+
+        await browser.close()
+
+if __name__ == "__main__":
+    asyncio.run(main())