Remove tracked generated/data files and fix map link on status page

- Remove byty_*.json, mapa_bytu.html, .DS_Store and settings.local.json from git tracking
  (already in .gitignore, files kept locally)
- Fix "Otevřít mapu" link on scraper status page: / → /mapa_bytu.html

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

README.md

@@ -83,6 +83,10 @@ Merges all `byty_*.json` files into `byty_merged.json` and generates `mapa_bytu.
 
 **Deduplication logic:** Two listings are considered duplicates if they share the same normalized street name + price + area. PSN and CityHome have priority during dedup (loaded first), so their listings are kept over duplicates from other portals.
 
+### `regen_map.py`
+
+Regenerates the map from existing `byty_sreality.json` data without re-scraping. Fetches missing area values from the Sreality API, fixes URLs, and re-applies the area filter. Useful for tweaking map output after data has already been collected.
+
 ## Interactive map (`mapa_bytu.html`)
 
 The generated map is a standalone HTML file using Leaflet.js with CARTO basemap tiles. Features:
@@ -147,7 +151,7 @@ The project includes a Docker setup for unattended operation with a cron-based s
 │  PID 1: python3 -m http.server :8080    │
 │         serves /app/data/               │
 │                                         │
-│  crond:  runs run_all.sh every 4 hours  │
+│  crond:  runs run_all.sh at 06:00/18:00 │
 │          Europe/Prague timezone          │
 │                                         │
 │  /app/        -- scripts (.py, .sh)     │
@@ -156,7 +160,7 @@ The project includes a Docker setup for unattended operation with a cron-based s
 └─────────────────────────────────────────┘
 ```
 
-On startup, the HTTP server starts immediately. The initial scrape runs in the background. Subsequent cron runs update data in-place every 4 hours.
+On startup, the HTTP server starts immediately. The initial scrape runs in the background. Subsequent cron runs update data in-place twice daily at 06:00 and 18:00 CET/CEST.
 
 ### Quick start
 
@@ -197,13 +201,14 @@ Validation targets run scrapers with `--max-pages 1 --max-properties 10` for a f
 ├── scrape_psn.py           # PSN scraper
 ├── scrape_cityhome.py      # CityHome scraper
 ├── merge_and_map.py        # Merge all sources + generate final map
+├── regen_map.py            # Regenerate map from cached Sreality data
 ├── run_all.sh              # Orchestrator script (runs all scrapers + merge)
 ├── mapa_bytu.html          # Generated interactive map (output)
 ├── Makefile                # Docker management + validation shortcuts
 ├── build/
 │   ├── Dockerfile          # Container image definition (python:3.13-alpine)
 │   ├── entrypoint.sh       # Container entrypoint (HTTP server + cron + initial scrape)
-│   ├── crontab             # Cron schedule (every 4 hours)
+│   ├── crontab             # Cron schedule (06:00 and 18:00 CET)
 │   └── CONTAINER.md        # Container-specific documentation
 └── .gitignore              # Ignores byty_*.json, __pycache__, .vscode
 ```

build/Dockerfile

@@ -11,7 +11,7 @@ WORKDIR /app
 
 COPY scrape_and_map.py scrape_realingo.py scrape_bezrealitky.py \
      scrape_idnes.py scrape_psn.py scrape_cityhome.py \
-     merge_and_map.py generate_status.py scraper_stats.py \
+     merge_and_map.py regen_map.py generate_status.py scraper_stats.py \
      run_all.sh server.py ./
 
 COPY build/crontab /etc/crontabs/root

merge_and_map.py

@@ -9,7 +9,6 @@ from __future__ import annotations
 
 import json
 import re
-import unicodedata
 from pathlib import Path
 
 from scrape_and_map import generate_map, format_price
@@ -20,8 +19,14 @@ def normalize_street(locality: str) -> str:
     # "Studentská, Praha 6 - Dejvice" → "studentska"
     # "Rýnská, Praha" → "rynska"
     street = locality.split(",")[0].strip().lower()
-    # Remove diacritics using Unicode decomposition (handles all Czech characters)
+    # Remove diacritics (simple Czech)
-    street = unicodedata.normalize("NFKD", street).encode("ascii", "ignore").decode("ascii")
+    replacements = {
+        "á": "a", "č": "c", "ď": "d", "é": "e", "ě": "e",
+        "í": "i", "ň": "n", "ó": "o", "ř": "r", "š": "s",
+        "ť": "t", "ú": "u", "ů": "u", "ý": "y", "ž": "z",
+    }
+    for src, dst in replacements.items():
+        street = street.replace(src, dst)
     # Remove non-alphanumeric
     street = re.sub(r"[^a-z0-9]", "", street)
     return street
@@ -74,10 +79,6 @@ def main():
         if key in seen_keys:
             dupes += 1
             existing = seen_keys[key]
-            # Preserve earliest first_seen across sources
-            dup_fs = e.get("first_seen", "")
-            if dup_fs and (not existing.get("first_seen") or dup_fs < existing["first_seen"]):
-                existing["first_seen"] = dup_fs
             # Log it
             print(f"  Duplikát: {e['locality']} | {format_price(e['price'])} | {e.get('area', '?')} m² "
                   f"({e.get('source', '?')} vs {existing.get('source', '?')})")

regen_map.py

@@ -0,0 +1,114 @@
+#!/usr/bin/env python3
+"""
+Přegeneruje mapu z již stažených dat (byty_sreality.json).
+Doplní chybějící plochy ze Sreality API, opraví URL, aplikuje filtry.
+"""
+from __future__ import annotations
+
+import json
+import time
+import urllib.request
+from pathlib import Path
+
+from scrape_and_map import (
+    generate_map, format_price, MIN_AREA, HEADERS, DETAIL_API
+)
+
+
+def api_get(url: str) -> dict:
+    req = urllib.request.Request(url, headers=HEADERS)
+    with urllib.request.urlopen(req, timeout=30) as resp:
+        return json.loads(resp.read().decode("utf-8"))
+
+
+def fix_sreality_url(estate: dict) -> str:
+    """Fix the Sreality URL to include disposition segment (only if missing)."""
+    disp = estate.get("disposition", "")
+    slug_map = {
+        "1+kk": "1+kk", "1+1": "1+1", "2+kk": "2+kk", "2+1": "2+1",
+        "3+kk": "3+kk", "3+1": "3+1", "4+kk": "4+kk", "4+1": "4+1",
+        "5+kk": "5+kk", "5+1": "5+1", "6+": "6-a-vice", "Atypický": "atypicky",
+    }
+    slug = slug_map.get(disp, "byt")
+    old_url = estate.get("url", "")
+    parts = old_url.split("/")
+    try:
+        byt_idx = parts.index("byt")
+        # Only insert if disposition slug is not already there
+        if byt_idx + 1 < len(parts) and parts[byt_idx + 1] == slug:
+            return old_url  # already correct
+        parts.insert(byt_idx + 1, slug)
+        return "/".join(parts)
+    except ValueError:
+        return old_url
+
+
+def fetch_area(hash_id: int) -> int | None:
+    """Fetch area from detail API."""
+    try:
+        url = DETAIL_API.format(hash_id)
+        detail = api_get(url)
+        for item in detail.get("items", []):
+            name = item.get("name", "")
+            if "žitná ploch" in name or "zitna ploch" in name.lower():
+                return int(item["value"])
+    except Exception:
+        pass
+    return None
+
+
+def main():
+    json_path = Path("byty_sreality.json")
+    if not json_path.exists():
+        print("Soubor byty_sreality.json nenalezen. Nejprve spusť scrape_and_map.py")
+        return
+
+    estates = json.loads(json_path.read_text(encoding="utf-8"))
+    print(f"Načteno {len(estates)} bytů z byty_sreality.json")
+
+    # Step 1: Fetch missing areas
+    missing_area = [e for e in estates if e.get("area") is None]
+    print(f"Doplňuji plochu u {len(missing_area)} bytů...")
+
+    for i, e in enumerate(missing_area):
+        time.sleep(0.3)
+        area = fetch_area(e["hash_id"])
+        if area is not None:
+            e["area"] = area
+        if (i + 1) % 50 == 0:
+            print(f"  {i + 1}/{len(missing_area)} ...")
+
+    # Count results
+    with_area = sum(1 for e in estates if e.get("area") is not None)
+    print(f"Plocha doplněna: {with_area}/{len(estates)}")
+
+    # Step 2: Fix URLs
+    for e in estates:
+        e["url"] = fix_sreality_url(e)
+
+    # Step 3: Filter by min area
+    filtered = []
+    excluded = 0
+    for e in estates:
+        area = e.get("area")
+        if area is not None and area < MIN_AREA:
+            excluded += 1
+            continue
+        filtered.append(e)
+
+    print(f"Vyloučeno (< {MIN_AREA} m²): {excluded}")
+    print(f"Zbývá: {len(filtered)} bytů")
+
+    # Save updated data
+    filtered_path = Path("byty_sreality.json")
+    filtered_path.write_text(
+        json.dumps(filtered, ensure_ascii=False, indent=2),
+        encoding="utf-8",
+    )
+
+    # Generate map
+    generate_map(filtered)
+
+
+if __name__ == "__main__":
+    main()

run_all.sh

@@ -84,6 +84,9 @@ exec > >(tee -a "$LOG_FILE") 2>&1
 step "Sreality"
 python3 scrape_and_map.py $SCRAPER_ARGS || { echo -e "${RED}✗ Sreality selhalo${NC}"; FAILED=$((FAILED + 1)); }
 
+step "Realingo"
+python3 scrape_realingo.py $SCRAPER_ARGS || { echo -e "${RED}✗ Realingo selhalo${NC}"; FAILED=$((FAILED + 1)); }
+
 step "Bezrealitky"
 python3 scrape_bezrealitky.py $SCRAPER_ARGS || { echo -e "${RED}✗ Bezrealitky selhalo${NC}"; FAILED=$((FAILED + 1)); }
 
@@ -98,9 +101,6 @@ PID_CH=$!
 wait $PID_PSN || { echo -e "${RED}✗ PSN selhalo${NC}"; FAILED=$((FAILED + 1)); }
 wait $PID_CH  || { echo -e "${RED}✗ CityHome selhalo${NC}"; FAILED=$((FAILED + 1)); }
 
-step "Realingo"
-python3 scrape_realingo.py $SCRAPER_ARGS || { echo -e "${RED}✗ Realingo selhalo${NC}"; FAILED=$((FAILED + 1)); }
-
 # ── Sloučení + mapa ──────────────────────────────────────────
 
 step "Sloučení dat a generování mapy"

scrape_and_map.py

@@ -13,9 +13,9 @@ import math
 import time
 import urllib.request
 import urllib.parse
-from datetime import datetime, timedelta
+from datetime import datetime
 from pathlib import Path
-from scraper_stats import write_stats, validate_listing
+from scraper_stats import write_stats
 
 STATS_FILE = "stats_sreality.json"
 
@@ -45,9 +45,9 @@ HEADERS = {
 
 
 def api_get(url: str) -> dict:
-    """Fetch JSON from Sreality API with retry."""
+    """Fetch JSON from Sreality API."""
-    for attempt in range(3):
+    logger.debug(f"HTTP GET request: {url}")
-        logger.debug(f"HTTP GET request (attempt {attempt + 1}/3): {url}")
+    logger.debug(f"Headers: {HEADERS}")
     req = urllib.request.Request(url, headers=HEADERS)
     try:
         with urllib.request.urlopen(req, timeout=30) as resp:
@@ -55,15 +55,8 @@ def api_get(url: str) -> dict:
             logger.debug(f"HTTP response: status={resp.status}, size={len(response_data)} bytes")
             logger.debug(f"Response preview: {response_data[:200]}")
             return json.loads(response_data)
-        except urllib.error.HTTPError:
-            raise
     except (urllib.error.URLError, ConnectionError, OSError) as e:
-            if attempt < 2:
+        logger.error(f"HTTP request failed for {url}: {e}", exc_info=True)
-                wait = (attempt + 1) * 2
-                logger.warning(f"Connection error (retry {attempt + 1}/3 after {wait}s): {e}")
-                time.sleep(wait)
-            else:
-                logger.error(f"HTTP request failed after 3 attempts: {e}", exc_info=True)
         raise
 
 
@@ -360,11 +353,7 @@ def scrape(max_pages: int | None = None, max_properties: int | None = None):
             "url": sreality_url(hash_id, seo),
             "image": (estate.get("_links", {}).get("images", [{}])[0].get("href", "") if estate.get("_links", {}).get("images") else ""),
             "scraped_at": datetime.now().strftime("%Y-%m-%d"),
-            "first_seen": cached.get("first_seen", datetime.now().strftime("%Y-%m-%d")) if cached else datetime.now().strftime("%Y-%m-%d"),
-            "last_changed": datetime.now().strftime("%Y-%m-%d"),
         }
-        if not validate_listing(result, "sreality"):
-            continue
         results.append(result)
         details_fetched += 1
 
@@ -440,30 +429,18 @@ def generate_map(estates: list[dict], output_path: str = "mapa_bytu.html"):
     ]
     for bcolor, blabel in bands:
         price_legend_items += (
-            f'<div class="price-band" data-color="{bcolor}" onclick="toggleColorFilter(\'{bcolor}\')" '
+            f'<div style="display:flex;align-items:center;gap:6px;margin:2px 0;">'
-            f'style="display:flex;align-items:center;gap:6px;margin:2px 0;padding:2px 4px;'
-            f'border-radius:4px;border:2px solid transparent;">'
             f'<span style="width:14px;height:14px;border-radius:50%;background:{bcolor};'
             f'display:inline-block;border:2px solid white;box-shadow:0 1px 3px rgba(0,0,0,0.3);flex-shrink:0;"></span>'
             f'<span>{blabel}</span></div>'
         )
-    price_legend_items += (
-        '<div id="price-filter-reset" style="display:none;margin:3px 0 0 4px;">'
-        '<a href="#" onclick="resetColorFilter();return false;" '
-        'style="font-size:11px;color:#1976D2;text-decoration:none;">✕ Zobrazit všechny ceny</a>'
-        '</div>'
-    )
     # New marker indicator — bigger dot, no extra border
     price_legend_items += (
         '<div style="display:flex;align-items:center;gap:6px;margin:6px 0 0 0;'
         'padding-top:6px;border-top:1px solid #eee;">'
-        '<span style="display:inline-flex;align-items:center;gap:3px;flex-shrink:0;">'
+        '<span style="width:18px;height:18px;border-radius:50%;background:#66BB6A;'
-        '<span style="width:14px;height:14px;border-radius:50%;background:#66BB6A;'
+        'display:inline-block;box-shadow:0 1px 4px rgba(0,0,0,0.35);flex-shrink:0;"></span>'
-        'display:inline-block;box-shadow:0 1px 3px rgba(0,0,0,0.3);"></span>'
+        '<span>Nové (z dnešního scrapu) — větší</span></div>'
-        '<span style="font-size:8px;font-weight:700;background:#FFD600;color:#333;'
-        'padding:1px 3px;border-radius:2px;">NEW</span>'
-        '</span>'
-        '<span>Nové (≤ 1 den)</span></div>'
     )
 
     markers_js = ""
@@ -485,32 +462,18 @@ def generate_map(estates: list[dict], output_path: str = "mapa_bytu.html"):
         source_label = source_labels.get(source, source)
         source_color = source_colors.get(source, "#999")
 
-        hash_id = f"{source}_{e.get('hash_id', '')}"
+        hash_id = e.get("hash_id", "")
 
-        first_seen = e.get("first_seen", "")
+        scraped_at = e.get("scraped_at", "")
-        last_changed = e.get("last_changed", "")
+        is_new = scraped_at == datetime.now().strftime("%Y-%m-%d")
-        today = datetime.now().strftime("%Y-%m-%d")
-        yesterday = (datetime.now() - timedelta(days=1)).strftime("%Y-%m-%d")
-        is_new = first_seen in (today, yesterday)
 
         new_badge = (
             '<span style="margin-left:6px;font-size:11px;background:#FFD600;color:#333;'
             'padding:1px 6px;border-radius:3px;font-weight:bold;">NOVÉ</span>'
             if is_new else ""
         )
-
-        date_parts = []
-        if first_seen:
-            date_parts.append(f'Přidáno: {first_seen}')
-        if last_changed and last_changed != first_seen:
-            date_parts.append(f'Změněno: {last_changed}')
-        date_row = (
-            f'<span style="font-size:11px;color:#888;">{"&nbsp;·&nbsp;".join(date_parts)}</span><br>'
-            if date_parts else ""
-        )
-
         popup = (
-            f'<div style="min-width:280px;font-family:system-ui,sans-serif;" data-hashid="{hash_id}" data-first-seen="{first_seen}" data-last-changed="{last_changed}">'
+            f'<div style="min-width:280px;font-family:system-ui,sans-serif;" data-hashid="{hash_id}">'
             f'<b style="font-size:14px;">{format_price(e["price"])}</b>'
             f'<span style="margin-left:8px;font-size:11px;background:{source_color};color:white;'
             f'padding:1px 6px;border-radius:3px;">{source_label}</span>{new_badge}<br>'
@@ -518,9 +481,7 @@ def generate_map(estates: list[dict], output_path: str = "mapa_bytu.html"):
             f'{floor_note}<br><br>'
             f'<b>{e["locality"]}</b><br>'
             f'Stavba: {building_text}<br>'
-            f'Vlastnictví: {ownership_text}<br>'
+            f'Vlastnictví: {ownership_text}<br><br>'
-            f'{date_row}'
-            f'<br>'
             f'<a href="{e["url"]}" target="_blank" '
             f'style="color:{source_color};text-decoration:none;font-weight:bold;">'
             f'→ Otevřít na {source_label}</a>'
@@ -552,7 +513,7 @@ def generate_map(estates: list[dict], output_path: str = "mapa_bytu.html"):
         else:
             marker_fn = "addMarker"
         markers_js += (
-            f"  {marker_fn}({e['lat']}, {e['lon']}, '{color}', '{popup}', '{hash_id}', '{first_seen}', '{last_changed}');\n"
+            f"  {marker_fn}({e['lat']}, {e['lon']}, '{color}', '{popup}', '{hash_id}');\n"
         )
 
     # Build legend — price per m² bands + disposition counts
@@ -618,12 +579,12 @@ def generate_map(estates: list[dict], output_path: str = "mapa_bytu.html"):
   .heart-icon-fav svg path {{ stroke: gold !important; stroke-width: 2.5 !important; filter: drop-shadow(0 0 4px rgba(255,193,7,0.7)); }}
   .heart-icon-rej {{ opacity: 0.4 !important; filter: grayscale(1); }}
   .reject-overlay {{ background: none !important; border: none !important; pointer-events: none !important; }}
-  .new-badge-icon {{ background: none !important; border: none !important; pointer-events: none !important; }}
+  @keyframes pulse-new {{
-  .new-badge {{
+    0%   {{ stroke-opacity: 1;   stroke-width: 3px; r: 11; }}
-    font-size: 9px; font-weight: 700; color: #333; background: #FFD600;
+    50%  {{ stroke-opacity: 0.4; stroke-width: 6px; r: 12; }}
-    padding: 1px 4px; border-radius: 3px; white-space: nowrap;
+    100% {{ stroke-opacity: 1;   stroke-width: 3px; r: 11; }}
-    box-shadow: 0 1px 3px rgba(0,0,0,0.3); letter-spacing: 0.5px;
   }}
+  .marker-new {{ animation: pulse-new 2s ease-in-out infinite; }}
   .info-panel {{
     position: absolute; top: 10px; right: 10px; z-index: 1000;
     background: white; padding: 16px; border-radius: 10px;
@@ -656,10 +617,6 @@ def generate_map(estates: list[dict], output_path: str = "mapa_bytu.html"):
   .info-panel .stats {{ color: #666; margin-bottom: 10px; padding-bottom: 10px; border-bottom: 1px solid #eee; }}
   .filter-section {{ margin-top: 10px; padding-top: 10px; border-top: 1px solid #eee; }}
   .filter-section label {{ display: flex; align-items: center; gap: 6px; margin: 3px 0; cursor: pointer; }}
-  .price-band {{ cursor: pointer; transition: background 0.12s; }}
-  .price-band:hover {{ background: #f0f0f0; }}
-  .price-band.active {{ border-color: #333 !important; background: #e8f0fe; }}
-  .price-band.dimmed {{ opacity: 0.35; }}
   .filter-section input[type="checkbox"] {{ accent-color: #1976D2; }}
   #floor-filter {{ margin-top: 8px; }}
   #floor-filter select {{ width: 100%; padding: 4px; border-radius: 4px; border: 1px solid #ccc; }}
@@ -698,23 +655,11 @@ def generate_map(estates: list[dict], output_path: str = "mapa_bytu.html"):
     </div>
     <div style="margin-top:6px;">
       <label>Max cena:
-        <input type="number" id="max-price" value="13500000" max="14000000" step="500000"
+        <select id="max-price" onchange="applyFilters()">
-          style="width:130px;padding:2px 4px;border:1px solid #ccc;border-radius:3px;"
+          <option value="13500000">13 500 000 Kč</option>
-          onchange="applyFilters()" onkeyup="applyFilters()"> Kč
+          <option value="12000000">12 000 000 Kč</option>
-      </label>
+          <option value="10000000">10 000 000 Kč</option>
-    </div>
+          <option value="8000000">8 000 000 Kč</option>
-    <div style="margin-top:6px;">
-      <label>Přidáno / změněno:
-        <select id="days-filter" onchange="applyFilters()" style="width:100%;padding:4px;border-radius:4px;border:1px solid #ccc;">
-          <option value="0">Vše</option>
-          <option value="1">za 1 den</option>
-          <option value="2">za 2 dny</option>
-          <option value="3">za 3 dny</option>
-          <option value="4">za 4 dny</option>
-          <option value="5">za 5 dní</option>
-          <option value="7">za 7 dní</option>
-          <option value="14">za 14 dní</option>
-          <option value="30">za 30 dní</option>
         </select>
       </label>
     </div>
@@ -748,39 +693,9 @@ L.tileLayer('https://{{s}}.basemaps.cartocdn.com/light_only_labels/{{z}}/{{x}}/{
   pane: 'shadowPane',
 }}).addTo(map);
 
-var selectedColors = [];
-
-function toggleColorFilter(color) {{
-  var idx = selectedColors.indexOf(color);
-  if (idx >= 0) selectedColors.splice(idx, 1);
-  else selectedColors.push(color);
-  document.querySelectorAll('.price-band').forEach(function(el) {{
-    var c = el.getAttribute('data-color');
-    if (selectedColors.length === 0) {{
-      el.classList.remove('active', 'dimmed');
-    }} else if (selectedColors.indexOf(c) >= 0) {{
-      el.classList.add('active'); el.classList.remove('dimmed');
-    }} else {{
-      el.classList.add('dimmed'); el.classList.remove('active');
-    }}
-  }});
-  document.getElementById('price-filter-reset').style.display =
-    selectedColors.length > 0 ? 'block' : 'none';
-  applyFilters();
-}}
-
-function resetColorFilter() {{
-  selectedColors = [];
-  document.querySelectorAll('.price-band').forEach(function(el) {{
-    el.classList.remove('active', 'dimmed');
-  }});
-  document.getElementById('price-filter-reset').style.display = 'none';
-  applyFilters();
-}}
-
 var allMarkers = [];
 
-function addMarker(lat, lon, color, popup, hashId, firstSeen, lastChanged) {{
+function addMarker(lat, lon, color, popup, hashId) {{
   var marker = L.circleMarker([lat, lon], {{
     radius: 8,
     fillColor: color,
@@ -789,35 +704,26 @@ function addMarker(lat, lon, color, popup, hashId, firstSeen, lastChanged) {{
     opacity: 1,
     fillOpacity: 0.85,
   }}).bindPopup(popup);
-  marker._data = {{ lat: lat, lon: lon, color: color, hashId: hashId, firstSeen: firstSeen || '', lastChanged: lastChanged || '' }};
+  marker._data = {{ lat: lat, lon: lon, color: color, hashId: hashId }};
   allMarkers.push(marker);
   marker.addTo(map);
 }}
 
-function addNewMarker(lat, lon, color, popup, hashId, firstSeen, lastChanged) {{
+function addNewMarker(lat, lon, color, popup, hashId) {{
   var marker = L.circleMarker([lat, lon], {{
-    radius: 8,
+    radius: 12,
     fillColor: color,
-    color: '#fff',
+    color: color,
-    weight: 2,
+    weight: 4,
-    opacity: 1,
+    opacity: 0.35,
-    fillOpacity: 0.85,
+    fillOpacity: 0.95,
   }}).bindPopup(popup);
-  marker._data = {{ lat: lat, lon: lon, color: color, hashId: hashId, isNew: true, firstSeen: firstSeen || '', lastChanged: lastChanged || '' }};
+  marker._data = {{ lat: lat, lon: lon, color: color, hashId: hashId, isNew: true }};
   allMarkers.push(marker);
   marker.addTo(map);
-  var badge = L.marker([lat, lon], {{
+  marker.on('add', function() {{
-    icon: L.divIcon({{
+    if (marker._path) marker._path.classList.add('marker-new');
-      className: 'new-badge-icon',
-      html: '<span class="new-badge">NEW</span>',
-      iconSize: [32, 14],
-      iconAnchor: [-6, 7],
-    }}),
-    interactive: false,
-    pane: 'markerPane',
   }});
-  badge.addTo(map);
-  marker._newBadge = badge;
 }}
 
 function heartIcon(color) {{
@@ -850,11 +756,11 @@ function starIcon() {{
   }});
 }}
 
-function addHeartMarker(lat, lon, color, popup, hashId, firstSeen, lastChanged) {{
+function addHeartMarker(lat, lon, color, popup, hashId) {{
   var marker = L.marker([lat, lon], {{
     icon: heartIcon(color),
   }}).bindPopup(popup);
-  marker._data = {{ lat: lat, lon: lon, color: color, hashId: hashId, isHeart: true, firstSeen: firstSeen || '', lastChanged: lastChanged || '' }};
+  marker._data = {{ lat: lat, lon: lon, color: color, hashId: hashId, isHeart: true }};
   allMarkers.push(marker);
   marker.addTo(map);
 }}
@@ -873,11 +779,6 @@ function loadRatings() {{
 
 function saveRatings(ratings) {{
   localStorage.setItem(RATINGS_KEY, JSON.stringify(ratings));
-  fetch('/api/ratings', {{
-    method: 'POST',
-    headers: {{'Content-Type': 'application/json'}},
-    body: JSON.stringify(ratings)
-  }}).catch(function() {{}});
 }}
 
 function addRejectStrike(marker) {{
@@ -925,7 +826,6 @@ function applyMarkerStyle(marker, status) {{
   }} else {{
     if (status === 'fav') {{
       removeRejectStrike(marker);
-      if (marker._newBadge && map.hasLayer(marker._newBadge)) map.removeLayer(marker._newBadge);
       if (!marker._data._origCircle) marker._data._origCircle = true;
       var popup = marker.getPopup();
       var popupContent = popup ? popup.getContent() : '';
@@ -949,7 +849,6 @@ function applyMarkerStyle(marker, status) {{
       }}
       // Add strikethrough line over the marker
       addRejectStrike(marker);
-      if (marker._newBadge && map.hasLayer(marker._newBadge)) map.removeLayer(marker._newBadge);
     }} else {{
       if (marker._data._origCircle && !(marker instanceof L.CircleMarker)) {{
         revertToCircle(marker, {{ radius: 8, fillColor: marker._data.color, color: '#fff', weight: 2, fillOpacity: 0.85 }});
@@ -962,7 +861,6 @@ function applyMarkerStyle(marker, status) {{
       }}
       if (marker._path) marker._path.classList.remove('marker-rejected');
       removeRejectStrike(marker);
-      if (marker._newBadge && !map.hasLayer(marker._newBadge)) marker._newBadge.addTo(map);
     }}
   }}
 }}
@@ -1118,21 +1016,11 @@ map.on('popupopen', function(e) {{
 // ── Filters ────────────────────────────────────────────────────
 function applyFilters() {{
   var minFloor = parseInt(document.getElementById('min-floor').value);
-  var maxPriceEl = document.getElementById('max-price');
+  var maxPrice = parseInt(document.getElementById('max-price').value);
-  var maxPrice = parseInt(maxPriceEl.value) || 14000000;
-  if (maxPrice > 14000000) {{ maxPrice = 14000000; maxPriceEl.value = 14000000; }}
   var hideRejected = document.getElementById('hide-rejected').checked;
-  var daysFilter = parseInt(document.getElementById('days-filter').value) || 0;
   var ratings = loadRatings();
   var visible = 0;
 
-  var cutoff = null;
-  if (daysFilter > 0) {{
-    cutoff = new Date();
-    cutoff.setDate(cutoff.getDate() - daysFilter);
-    cutoff.setHours(0, 0, 0, 0);
-  }}
-
   allMarkers.forEach(function(m) {{
     var popup = m.getPopup().getContent();
     var floorMatch = popup.match(/(\\d+)\\. NP/);
@@ -1145,14 +1033,6 @@ function applyFilters() {{
     if (floor !== null && floor < minFloor) show = false;
     if (price > maxPrice) show = false;
 
-    if (cutoff) {{
-      var fs = m._data.firstSeen ? new Date(m._data.firstSeen) : null;
-      var lc = m._data.lastChanged ? new Date(m._data.lastChanged) : null;
-      if (!((fs && fs >= cutoff) || (lc && lc >= cutoff))) show = false;
-    }}
-
-    if (selectedColors.length > 0 && selectedColors.indexOf(m._data.color) < 0) show = false;
-
     var r = ratings[m._data.hashId];
     if (hideRejected && r && r.status === 'reject') show = false;
 
@@ -1161,12 +1041,10 @@ function applyFilters() {{
       visible++;
       // Show strike line if rejected and visible
       if (m._rejectStrike && !map.hasLayer(m._rejectStrike)) m._rejectStrike.addTo(map);
-      if (m._newBadge && !map.hasLayer(m._newBadge)) m._newBadge.addTo(map);
     }} else {{
       if (map.hasLayer(m)) map.removeLayer(m);
       // Hide strike line when marker hidden
       if (m._rejectStrike && map.hasLayer(m._rejectStrike)) map.removeLayer(m._rejectStrike);
-      if (m._newBadge && map.hasLayer(m._newBadge)) map.removeLayer(m._newBadge);
     }}
   }});
 
@@ -1181,25 +1059,8 @@ function applyFilters() {{
   document.getElementById('visible-count').textContent = visible;
 }}
 
-// Initialize ratings: load from server, merge with localStorage, then restore
+// Initialize ratings on load
-function initRatings() {{
-  var local = loadRatings();
-  fetch('/api/ratings')
-    .then(function(r) {{ return r.ok ? r.json() : null; }})
-    .then(function(server) {{
-      if (server && typeof server === 'object') {{
-        var merged = Object.assign({{}}, local, server);
-        localStorage.setItem(RATINGS_KEY, JSON.stringify(merged));
-      }}
 restoreRatings();
-      updateRatingCounts();
-    }})
-    .catch(function() {{
-      restoreRatings();
-      updateRatingCounts();
-    }});
-}}
-initRatings();
 
 // ── Panel toggle ──────────────────────────────────────────────
 function togglePanel() {{

scrape_bezrealitky.py

@@ -15,7 +15,7 @@ import re
 import time
 import urllib.request
 from pathlib import Path
-from scraper_stats import write_stats, validate_listing
+from scraper_stats import write_stats
 
 STATS_FILE = "stats_bezrealitky.json"
 
@@ -71,35 +71,19 @@ HEADERS = {
 BASE_URL = "https://www.bezrealitky.cz"
 
 
-def fetch_url(url: str, retries: int = 3) -> str:
-    """Fetch URL and return HTML string with retry on transient errors."""
-    for attempt in range(retries):
-        try:
-            logger.debug(f"HTTP GET request (attempt {attempt + 1}/{retries}): {url}")
-            req = urllib.request.Request(url, headers=HEADERS)
-            resp = urllib.request.urlopen(req, timeout=30)
-            html = resp.read().decode("utf-8")
-            logger.debug(f"HTTP response: status={resp.status}, size={len(html)} bytes")
-            return html
-        except urllib.error.HTTPError:
-            raise
-        except (ConnectionResetError, ConnectionError, urllib.error.URLError, OSError) as e:
-            if attempt < retries - 1:
-                wait = (attempt + 1) * 2
-                logger.warning(f"Connection error (retry {attempt + 1}/{retries} after {wait}s): {e}")
-                time.sleep(wait)
-            else:
-                logger.error(f"HTTP request failed after {retries} attempts: {e}", exc_info=True)
-                raise
-
-
 def fetch_page(page: int) -> tuple[list[dict], int]:
     """
     Fetch a listing page from Bezrealitky.
     Returns (list of advert dicts from Apollo cache, total count).
     """
     url = f"{BASE_URL}/vypis/nabidka-prodej/byt/praha?page={page}"
-    html = fetch_url(url)
+    logger.debug(f"HTTP GET request: {url}")
+    logger.debug(f"Headers: {HEADERS}")
+    req = urllib.request.Request(url, headers=HEADERS)
+    try:
+        resp = urllib.request.urlopen(req, timeout=30)
+        html = resp.read().decode("utf-8")
+        logger.debug(f"HTTP response: status={resp.status}, size={len(html)} bytes")
 
         match = re.search(
             r'<script id="__NEXT_DATA__" type="application/json">(.*?)</script>',
@@ -129,13 +113,20 @@ def fetch_page(page: int) -> tuple[list[dict], int]:
 
         logger.debug(f"Page {page}: found {len(adverts)} adverts, total={total}")
         return adverts, total
+    except (urllib.error.URLError, ConnectionError, OSError) as e:
+        logger.error(f"HTTP request failed for {url}: {e}", exc_info=True)
+        raise
 
 
 def fetch_detail(uri: str) -> dict | None:
     """Fetch detail page for a listing."""
     try:
         url = f"{BASE_URL}/nemovitosti-byty-domy/{uri}"
-        html = fetch_url(url)
+        logger.debug(f"HTTP GET request: {url}")
+        req = urllib.request.Request(url, headers=HEADERS)
+        resp = urllib.request.urlopen(req, timeout=30)
+        html = resp.read().decode("utf-8")
+        logger.debug(f"HTTP response: status={resp.status}, size={len(html)} bytes")
 
         match = re.search(
             r'<script id="__NEXT_DATA__" type="application/json">(.*?)</script>',
@@ -371,11 +362,7 @@ def scrape(max_pages: int | None = None, max_properties: int | None = None):
             "source": "bezrealitky",
             "image": "",
             "scraped_at": datetime.now().strftime("%Y-%m-%d"),
-            "first_seen": cached.get("first_seen", datetime.now().strftime("%Y-%m-%d")) if cached else datetime.now().strftime("%Y-%m-%d"),
-            "last_changed": datetime.now().strftime("%Y-%m-%d"),
         }
-        if not validate_listing(result, "bezrealitky"):
-            continue
         results.append(result)
         properties_fetched += 1
 

scrape_cityhome.py

@@ -14,7 +14,7 @@ import time
 import urllib.request
 from datetime import datetime
 from pathlib import Path
-from scraper_stats import write_stats, validate_listing
+from scraper_stats import write_stats
 
 STATS_FILE = "stats_cityhome.json"
 
@@ -255,16 +255,6 @@ def scrape(max_pages: int | None = None, max_properties: int | None = None):
         else:
             logger.info(f"✗ {slug}: GPS nenalezeno")
 
-    # Load previous output for first_seen/last_changed tracking
-    _prev_cache: dict[str, dict] = {}
-    _prev_path = Path("byty_cityhome.json")
-    if _prev_path.exists():
-        try:
-            for _item in json.loads(_prev_path.read_text(encoding="utf-8")):
-                _prev_cache[str(_item["hash_id"])] = _item
-        except Exception:
-            pass
-
     # Step 3: Filter listings
     logger.info(f"\nFáze 3: Filtrování...")
     results = []
@@ -372,11 +362,7 @@ def scrape(max_pages: int | None = None, max_properties: int | None = None):
             "source": "cityhome",
             "image": "",
             "scraped_at": datetime.now().strftime("%Y-%m-%d"),
-            "first_seen": _prev_cache.get(f"cityhome_{slug}_{listing['unit_name']}", {}).get("first_seen", datetime.now().strftime("%Y-%m-%d")),
-            "last_changed": datetime.now().strftime("%Y-%m-%d") if _prev_cache.get(f"cityhome_{slug}_{listing['unit_name']}", {}).get("price") != price else _prev_cache[f"cityhome_{slug}_{listing['unit_name']}"].get("last_changed", datetime.now().strftime("%Y-%m-%d")),
         }
-        if not validate_listing(result, "cityhome"):
-            continue
         results.append(result)
         properties_fetched += 1
 

scrape_idnes.py

@@ -15,8 +15,9 @@ import re
 import time
 import urllib.request
 import urllib.parse
+from html.parser import HTMLParser
 from pathlib import Path
-from scraper_stats import write_stats, validate_listing
+from scraper_stats import write_stats
 
 STATS_FILE = "stats_idnes.json"
 
@@ -464,11 +465,7 @@ def scrape(max_pages: int | None = None, max_properties: int | None = None):
             "source": "idnes",
             "image": "",
             "scraped_at": datetime.now().strftime("%Y-%m-%d"),
-            "first_seen": cached.get("first_seen", datetime.now().strftime("%Y-%m-%d")) if cached else datetime.now().strftime("%Y-%m-%d"),
-            "last_changed": datetime.now().strftime("%Y-%m-%d"),
         }
-        if not validate_listing(result, "idnes"):
-            continue
         results.append(result)
         properties_fetched += 1
 

scrape_psn.py

@@ -15,7 +15,7 @@ import time
 from datetime import datetime
 from pathlib import Path
 from urllib.parse import urlencode
-from scraper_stats import write_stats, validate_listing
+from scraper_stats import write_stats
 
 STATS_FILE = "stats_psn.json"
 
@@ -38,10 +38,9 @@ BASE_URL = "https://psn.cz"
 UNITS_API = f"{BASE_URL}/api/units-list"
 
 
-def fetch_json(url: str, retries: int = 3) -> dict:
+def fetch_json(url: str) -> dict:
-    """Fetch JSON via curl (urllib SSL may fail on Cloudflare) with retry."""
+    """Fetch JSON via curl (urllib SSL may fail on Cloudflare)."""
-    for attempt in range(retries):
+    logger.debug(f"HTTP GET: {url}")
-        logger.debug(f"HTTP GET (attempt {attempt + 1}/{retries}): {url}")
     result = subprocess.run(
         ["curl", "-s", "-L", "--max-time", "30",
          "-H", f"User-Agent: {UA}",
@@ -49,14 +48,9 @@ def fetch_json(url: str, retries: int = 3) -> dict:
          url],
         capture_output=True, text=True, timeout=60
     )
-        if result.returncode == 0:
+    if result.returncode != 0:
+        raise RuntimeError(f"curl failed ({result.returncode}): {result.stderr[:200]}")
     return json.loads(result.stdout)
-        if attempt < retries - 1:
-            wait = (attempt + 1) * 2
-            logger.warning(f"curl failed (retry {attempt + 1}/{retries} after {wait}s): {result.stderr[:200]}")
-            time.sleep(wait)
-        else:
-            raise RuntimeError(f"curl failed after {retries} attempts ({result.returncode}): {result.stderr[:200]}")
 
 
 def fix_gps(lat, lng):
@@ -118,16 +112,6 @@ def scrape(max_properties: int | None = None):
     all_units = data.get("units", {}).get("data", [])
     logger.info(f"Staženo jednotek celkem: {len(all_units)}")
 
-    # Load previous output for first_seen/last_changed tracking
-    _prev_cache: dict[str, dict] = {}
-    _prev_path = Path("byty_psn.json")
-    if _prev_path.exists():
-        try:
-            for _item in json.loads(_prev_path.read_text(encoding="utf-8")):
-                _prev_cache[str(_item["hash_id"])] = _item
-        except Exception:
-            pass
-
     # Filtrování
     results = []
     excluded = {
@@ -258,11 +242,7 @@ def scrape(max_properties: int | None = None):
             "source": "psn",
             "image": "",
             "scraped_at": datetime.now().strftime("%Y-%m-%d"),
-            "first_seen": _prev_cache.get(str(unit_id), {}).get("first_seen", datetime.now().strftime("%Y-%m-%d")),
-            "last_changed": datetime.now().strftime("%Y-%m-%d") if _prev_cache.get(str(unit_id), {}).get("price") != int(price) else _prev_cache[str(unit_id)].get("last_changed", datetime.now().strftime("%Y-%m-%d")),
         }
-        if not validate_listing(result, "psn"):
-            continue
         results.append(result)
         properties_fetched += 1
 

scrape_realingo.py

@@ -15,7 +15,7 @@ import re
 import time
 import urllib.request
 from pathlib import Path
-from scraper_stats import write_stats, validate_listing
+from scraper_stats import write_stats
 
 STATS_FILE = "stats_realingo.json"
 
@@ -56,28 +56,6 @@ HEADERS = {
 BASE_URL = "https://www.realingo.cz"
 
 
-def fetch_url(url: str, retries: int = 3) -> str:
-    """Fetch URL and return HTML string with retry on transient errors."""
-    for attempt in range(retries):
-        try:
-            logger.debug(f"HTTP GET request (attempt {attempt + 1}/{retries}): {url}")
-            req = urllib.request.Request(url, headers=HEADERS)
-            resp = urllib.request.urlopen(req, timeout=30)
-            html = resp.read().decode("utf-8")
-            logger.debug(f"HTTP response: status={resp.status}, size={len(html)} bytes")
-            return html
-        except urllib.error.HTTPError:
-            raise
-        except (ConnectionResetError, ConnectionError, urllib.error.URLError, OSError) as e:
-            if attempt < retries - 1:
-                wait = (attempt + 1) * 2
-                logger.warning(f"Connection error (retry {attempt + 1}/{retries} after {wait}s): {e}")
-                time.sleep(wait)
-            else:
-                logger.error(f"HTTP request failed after {retries} attempts: {e}", exc_info=True)
-                raise
-
-
 def fetch_listing_page(page: int = 1) -> tuple[list[dict], int]:
     """Fetch a page of Prague listings. Returns (items, total_count)."""
     if page == 1:
@@ -85,7 +63,14 @@ def fetch_listing_page(page: int = 1) -> tuple[list[dict], int]:
     else:
         url = f"{BASE_URL}/prodej_byty/praha/{page}_strana/"
 
-    html = fetch_url(url)
+    logger.debug(f"HTTP GET request: {url}")
+    logger.debug(f"Headers: {HEADERS}")
+    req = urllib.request.Request(url, headers=HEADERS)
+    try:
+        resp = urllib.request.urlopen(req, timeout=30)
+        html = resp.read().decode("utf-8")
+        logger.debug(f"HTTP response: status={resp.status}, size={len(html)} bytes")
+
         match = re.search(
             r'<script id="__NEXT_DATA__" type="application/json">(.*?)</script>',
             html, re.DOTALL
@@ -98,13 +83,21 @@ def fetch_listing_page(page: int = 1) -> tuple[list[dict], int]:
         offer_list = data["props"]["pageProps"]["store"]["offer"]["list"]
         logger.debug(f"Page {page}: found {len(offer_list['data'])} items, total={offer_list['total']}")
         return offer_list["data"], offer_list["total"]
+    except (urllib.error.URLError, ConnectionError, OSError) as e:
+        logger.error(f"HTTP request failed for {url}: {e}", exc_info=True)
+        raise
 
 
 def fetch_detail(listing_url: str) -> dict | None:
     """Fetch detail page for a listing to get floor, building type, etc."""
     try:
         url = f"{BASE_URL}{listing_url}"
-        html = fetch_url(url)
+        logger.debug(f"HTTP GET request: {url}")
+        req = urllib.request.Request(url, headers=HEADERS)
+        resp = urllib.request.urlopen(req, timeout=30)
+        html = resp.read().decode("utf-8")
+        logger.debug(f"HTTP response: status={resp.status}, size={len(html)} bytes")
+
         match = re.search(
             r'<script id="__NEXT_DATA__" type="application/json">(.*?)</script>',
             html, re.DOTALL
@@ -328,11 +321,7 @@ def scrape(max_pages: int | None = None, max_properties: int | None = None):
             "source": "realingo",
             "image": "",
             "scraped_at": datetime.now().strftime("%Y-%m-%d"),
-            "first_seen": cached.get("first_seen", datetime.now().strftime("%Y-%m-%d")) if cached else datetime.now().strftime("%Y-%m-%d"),
-            "last_changed": datetime.now().strftime("%Y-%m-%d"),
         }
-        if not validate_listing(result, "realingo"):
-            continue
         results.append(result)
         properties_fetched += 1
 

scraper_stats.py

@@ -1,53 +1,13 @@
-"""Shared utilities for scraper run statistics and listing validation."""
+"""Shared utility for writing per-scraper run statistics to JSON."""
 from __future__ import annotations
 
 import json
-import logging
 import os
 from pathlib import Path
 
 HERE = Path(__file__).parent
 DATA_DIR = Path(os.environ.get("DATA_DIR", HERE))
 
-_val_log = logging.getLogger(__name__)
-
-_REQUIRED_FIELDS = ("hash_id", "price", "locality", "lat", "lon", "url", "source")
-
-
-def validate_listing(listing: dict, context: str = "") -> bool:
-    """
-    Validate a listing dict before it is written to the output JSON.
-    Returns True if valid, False if the listing should be skipped.
-    Logs a warning for each invalid listing.
-    """
-    prefix = f"[{context}] " if context else ""
-
-    for field in _REQUIRED_FIELDS:
-        val = listing.get(field)
-        if val is None or val == "":
-            _val_log.warning(f"{prefix}Skipping listing — missing field '{field}': {listing.get('hash_id', '?')}")
-            return False
-
-    price = listing.get("price")
-    if not isinstance(price, (int, float)) or price <= 0:
-        _val_log.warning(f"{prefix}Skipping listing — invalid price={price!r}: {listing.get('hash_id', '?')}")
-        return False
-
-    lat, lon = listing.get("lat"), listing.get("lon")
-    if not isinstance(lat, (int, float)) or not isinstance(lon, (int, float)):
-        _val_log.warning(f"{prefix}Skipping listing — non-numeric GPS lat={lat!r} lon={lon!r}: {listing.get('hash_id', '?')}")
-        return False
-    if not (47.0 <= lat <= 52.0) or not (12.0 <= lon <= 19.0):
-        _val_log.warning(f"{prefix}Skipping listing — GPS outside Czech Republic lat={lat} lon={lon}: {listing.get('hash_id', '?')}")
-        return False
-
-    area = listing.get("area")
-    if area is not None and (not isinstance(area, (int, float)) or area <= 0):
-        _val_log.warning(f"{prefix}Skipping listing — invalid area={area!r}: {listing.get('hash_id', '?')}")
-        return False
-
-    return True
-
 
 def write_stats(filename: str, stats: dict) -> None:
     """Write scraper run stats dict to the data directory."""