Remove regen_map.py references from Dockerfile and README

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

README.md

@@ -83,10 +83,6 @@ 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:
@@ -151,7 +147,7 @@ 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 at 06:00/18:00 │
+│  crond:  runs run_all.sh every 4 hours  │
 │          Europe/Prague timezone          │
 │                                         │
 │  /app/        -- scripts (.py, .sh)     │
@@ -160,7 +156,7 @@ 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 twice daily at 06:00 and 18:00 CET/CEST.
+On startup, the HTTP server starts immediately. The initial scrape runs in the background. Subsequent cron runs update data in-place every 4 hours.
 
 ### Quick start
 
@@ -201,14 +197,13 @@ 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 (06:00 and 18:00 CET)
+│   ├── crontab             # Cron schedule (every 4 hours)
 │   └── 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 regen_map.py generate_status.py scraper_stats.py \
+     merge_and_map.py generate_status.py scraper_stats.py \
      run_all.sh server.py ./
 
 COPY build/crontab /etc/crontabs/root

merge_and_map.py

@@ -9,6 +9,7 @@ from __future__ import annotations
 
 import json
 import re
+import unicodedata
 from pathlib import Path
 
 from scrape_and_map import generate_map, format_price
@@ -19,14 +20,8 @@ def normalize_street(locality: str) -> str:
     # "Studentská, Praha 6 - Dejvice" → "studentska"
     # "Rýnská, Praha" → "rynska"
     street = locality.split(",")[0].strip().lower()
-    # Remove diacritics (simple Czech)
+    # Remove diacritics using Unicode decomposition (handles all Czech characters)
-    replacements = {
+    street = unicodedata.normalize("NFKD", street).encode("ascii", "ignore").decode("ascii")
-        "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

regen_map.py

@@ -1,114 +0,0 @@
-#!/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()

scrape_and_map.py

@@ -13,9 +13,9 @@ import math
 import time
 import urllib.request
 import urllib.parse
-from datetime import datetime
+from datetime import datetime, timedelta
 from pathlib import Path
-from scraper_stats import write_stats
+from scraper_stats import write_stats, validate_listing
 
 STATS_FILE = "stats_sreality.json"
 
@@ -45,19 +45,26 @@ HEADERS = {
 
 
 def api_get(url: str) -> dict:
-    """Fetch JSON from Sreality API."""
+    """Fetch JSON from Sreality API with retry."""
-    logger.debug(f"HTTP GET request: {url}")
+    for attempt in range(3):
-    logger.debug(f"Headers: {HEADERS}")
+        logger.debug(f"HTTP GET request (attempt {attempt + 1}/3): {url}")
-    req = urllib.request.Request(url, headers=HEADERS)
+        req = urllib.request.Request(url, headers=HEADERS)
-    try:
+        try:
-        with urllib.request.urlopen(req, timeout=30) as resp:
+            with urllib.request.urlopen(req, timeout=30) as resp:
-            response_data = resp.read().decode("utf-8")
+                response_data = resp.read().decode("utf-8")
-            logger.debug(f"HTTP response: status={resp.status}, size={len(response_data)} bytes")
+                logger.debug(f"HTTP response: status={resp.status}, size={len(response_data)} bytes")
-            logger.debug(f"Response preview: {response_data[:200]}")
+                logger.debug(f"Response preview: {response_data[:200]}")
-            return json.loads(response_data)
+                return json.loads(response_data)
-    except (urllib.error.URLError, ConnectionError, OSError) as e:
+        except urllib.error.HTTPError:
-        logger.error(f"HTTP request failed for {url}: {e}", exc_info=True)
+            raise
-        raise
+        except (urllib.error.URLError, ConnectionError, OSError) as e:
+            if attempt < 2:
+                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
 
 
 def build_list_url(disposition: int, page: int = 1) -> str:
@@ -356,6 +363,8 @@ def scrape(max_pages: int | None = None, max_properties: int | None = None):
             "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
 
@@ -448,9 +457,13 @@ def generate_map(estates: list[dict], output_path: str = "mapa_bytu.html"):
     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="width:18px;height:18px;border-radius:50%;background:#66BB6A;'
+        '<span style="display:inline-flex;align-items:center;gap:3px;flex-shrink:0;">'
-        'display:inline-block;box-shadow:0 1px 4px rgba(0,0,0,0.35);flex-shrink:0;"></span>'
+        '<span style="width:14px;height:14px;border-radius:50%;background:#66BB6A;'
-        '<span>Nové (z dnešního scrapu) — větší</span></div>'
+        'display:inline-block;box-shadow:0 1px 3px rgba(0,0,0,0.3);"></span>'
+        '<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 = ""
@@ -472,11 +485,13 @@ 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 = e.get("hash_id", "")
+        hash_id = f"{source}_{e.get('hash_id', '')}"
 
         first_seen = e.get("first_seen", "")
         last_changed = e.get("last_changed", "")
-        is_new = first_seen == 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;'
@@ -603,12 +618,12 @@ 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; }}
-  @keyframes pulse-new {{
+  .new-badge-icon {{ background: none !important; border: none !important; pointer-events: none !important; }}
-    0%   {{ stroke-opacity: 1;   stroke-width: 3px; r: 11; }}
+  .new-badge {{
-    50%  {{ stroke-opacity: 0.4; stroke-width: 6px; r: 12; }}
+    font-size: 9px; font-weight: 700; color: #333; background: #FFD600;
-    100% {{ stroke-opacity: 1;   stroke-width: 3px; r: 11; }}
+    padding: 1px 4px; border-radius: 3px; white-space: nowrap;
+    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;
@@ -683,12 +698,9 @@ def generate_map(estates: list[dict], output_path: str = "mapa_bytu.html"):
     </div>
     <div style="margin-top:6px;">
       <label>Max cena:
-        <select id="max-price" onchange="applyFilters()">
+        <input type="number" id="max-price" value="13500000" max="14000000" step="500000"
-          <option value="13500000">13 500 000 Kč</option>
+          style="width:130px;padding:2px 4px;border:1px solid #ccc;border-radius:3px;"
-          <option value="12000000">12 000 000 Kč</option>
+          onchange="applyFilters()" onkeyup="applyFilters()"> Kč
-          <option value="10000000">10 000 000 Kč</option>
-          <option value="8000000">8 000 000 Kč</option>
-        </select>
       </label>
     </div>
     <div style="margin-top:6px;">
@@ -784,19 +796,28 @@ function addMarker(lat, lon, color, popup, hashId, firstSeen, lastChanged) {{
 
 function addNewMarker(lat, lon, color, popup, hashId, firstSeen, lastChanged) {{
   var marker = L.circleMarker([lat, lon], {{
-    radius: 12,
+    radius: 8,
     fillColor: color,
-    color: color,
+    color: '#fff',
-    weight: 4,
+    weight: 2,
-    opacity: 0.35,
+    opacity: 1,
-    fillOpacity: 0.95,
+    fillOpacity: 0.85,
   }}).bindPopup(popup);
   marker._data = {{ lat: lat, lon: lon, color: color, hashId: hashId, isNew: true, firstSeen: firstSeen || '', lastChanged: lastChanged || '' }};
   allMarkers.push(marker);
   marker.addTo(map);
-  marker.on('add', function() {{
+  var badge = L.marker([lat, lon], {{
-    if (marker._path) marker._path.classList.add('marker-new');
+    icon: L.divIcon({{
+      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) {{
@@ -852,6 +873,11 @@ 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) {{
@@ -899,6 +925,7 @@ 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() : '';
@@ -922,6 +949,7 @@ 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 }});
@@ -934,6 +962,7 @@ 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);
     }}
   }}
 }}
@@ -1089,7 +1118,9 @@ map.on('popupopen', function(e) {{
 // ── Filters ────────────────────────────────────────────────────
 function applyFilters() {{
   var minFloor = parseInt(document.getElementById('min-floor').value);
-  var maxPrice = parseInt(document.getElementById('max-price').value);
+  var maxPriceEl = document.getElementById('max-price');
+  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();
@@ -1130,10 +1161,12 @@ 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);
     }}
   }});
 
@@ -1148,8 +1181,25 @@ function applyFilters() {{
   document.getElementById('visible-count').textContent = visible;
 }}
 
-// Initialize ratings on load
+// Initialize ratings: load from server, merge with localStorage, then restore
-restoreRatings();
+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
+from scraper_stats import write_stats, validate_listing
 
 STATS_FILE = "stats_bezrealitky.json"
 
@@ -71,62 +71,71 @@ 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}"
-    logger.debug(f"HTTP GET request: {url}")
+    html = fetch_url(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(
+    match = re.search(
-            r'<script id="__NEXT_DATA__" type="application/json">(.*?)</script>',
+        r'<script id="__NEXT_DATA__" type="application/json">(.*?)</script>',
-            html, re.DOTALL
+        html, re.DOTALL
-        )
+    )
-        if not match:
+    if not match:
-            logger.debug("No __NEXT_DATA__ script found in HTML")
+        logger.debug("No __NEXT_DATA__ script found in HTML")
-            return [], 0
+        return [], 0
 
-        data = json.loads(match.group(1))
+    data = json.loads(match.group(1))
-        cache = data["props"]["pageProps"]["apolloCache"]
+    cache = data["props"]["pageProps"]["apolloCache"]
 
-        # Extract adverts from cache
+    # Extract adverts from cache
-        adverts = []
+    adverts = []
-        for key, val in cache.items():
+    for key, val in cache.items():
-            if key.startswith("Advert:") and isinstance(val, dict) and val.get("__typename") == "Advert":
+        if key.startswith("Advert:") and isinstance(val, dict) and val.get("__typename") == "Advert":
-                adverts.append(val)
+            adverts.append(val)
 
-        # Get total count from ROOT_QUERY
+    # Get total count from ROOT_QUERY
-        total = 0
+    total = 0
-        root = cache.get("ROOT_QUERY", {})
+    root = cache.get("ROOT_QUERY", {})
-        for key, val in root.items():
+    for key, val in root.items():
-            if "listAdverts" in key and isinstance(val, dict):
+        if "listAdverts" in key and isinstance(val, dict):
-                tc = val.get("totalCount")
+            tc = val.get("totalCount")
-                if tc and tc > total:
+            if tc and tc > total:
-                    total = tc
+                total = tc
 
-        logger.debug(f"Page {page}: found {len(adverts)} adverts, total={total}")
+    logger.debug(f"Page {page}: found {len(adverts)} adverts, total={total}")
-        return adverts, 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}"
-        logger.debug(f"HTTP GET request: {url}")
+        html = fetch_url(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>',
@@ -365,6 +374,8 @@ def scrape(max_pages: int | None = None, max_properties: int | None = None):
             "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
+from scraper_stats import write_stats, validate_listing
 
 STATS_FILE = "stats_cityhome.json"
 
@@ -375,6 +375,8 @@ def scrape(max_pages: int | None = None, max_properties: int | None = None):
             "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

@@ -15,9 +15,8 @@ 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
+from scraper_stats import write_stats, validate_listing
 
 STATS_FILE = "stats_idnes.json"
 
@@ -468,6 +467,8 @@ def scrape(max_pages: int | None = None, max_properties: int | None = None):
             "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
+from scraper_stats import write_stats, validate_listing
 
 STATS_FILE = "stats_psn.json"
 
@@ -38,19 +38,25 @@ BASE_URL = "https://psn.cz"
 UNITS_API = f"{BASE_URL}/api/units-list"
 
 
-def fetch_json(url: str) -> dict:
+def fetch_json(url: str, retries: int = 3) -> dict:
-    """Fetch JSON via curl (urllib SSL may fail on Cloudflare)."""
+    """Fetch JSON via curl (urllib SSL may fail on Cloudflare) with retry."""
-    logger.debug(f"HTTP GET: {url}")
+    for attempt in range(retries):
-    result = subprocess.run(
+        logger.debug(f"HTTP GET (attempt {attempt + 1}/{retries}): {url}")
-        ["curl", "-s", "-L", "--max-time", "30",
+        result = subprocess.run(
-         "-H", f"User-Agent: {UA}",
+            ["curl", "-s", "-L", "--max-time", "30",
-         "-H", "Accept: application/json",
+             "-H", f"User-Agent: {UA}",
-         url],
+             "-H", "Accept: application/json",
-        capture_output=True, text=True, timeout=60
+             url],
-    )
+            capture_output=True, text=True, timeout=60
-    if result.returncode != 0:
+        )
-        raise RuntimeError(f"curl failed ({result.returncode}): {result.stderr[:200]}")
+        if result.returncode == 0:
-    return json.loads(result.stdout)
+            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):
@@ -255,6 +261,8 @@ def scrape(max_properties: int | None = None):
             "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
+from scraper_stats import write_stats, validate_listing
 
 STATS_FILE = "stats_realingo.json"
 
@@ -56,6 +56,28 @@ 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:
@@ -63,41 +85,26 @@ def fetch_listing_page(page: int = 1) -> tuple[list[dict], int]:
     else:
         url = f"{BASE_URL}/prodej_byty/praha/{page}_strana/"
 
-    logger.debug(f"HTTP GET request: {url}")
+    html = fetch_url(url)
-    logger.debug(f"Headers: {HEADERS}")
+    match = re.search(
-    req = urllib.request.Request(url, headers=HEADERS)
+        r'<script id="__NEXT_DATA__" type="application/json">(.*?)</script>',
-    try:
+        html, re.DOTALL
-        resp = urllib.request.urlopen(req, timeout=30)
+    )
-        html = resp.read().decode("utf-8")
+    if not match:
-        logger.debug(f"HTTP response: status={resp.status}, size={len(html)} bytes")
+        logger.debug("No __NEXT_DATA__ script found in HTML")
+        return [], 0
 
-        match = re.search(
+    data = json.loads(match.group(1))
-            r'<script id="__NEXT_DATA__" type="application/json">(.*?)</script>',
+    offer_list = data["props"]["pageProps"]["store"]["offer"]["list"]
-            html, re.DOTALL
+    logger.debug(f"Page {page}: found {len(offer_list['data'])} items, total={offer_list['total']}")
-        )
+    return offer_list["data"], offer_list["total"]
-        if not match:
-            logger.debug("No __NEXT_DATA__ script found in HTML")
-            return [], 0
-
-        data = json.loads(match.group(1))
-        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}"
-        logger.debug(f"HTTP GET request: {url}")
+        html = fetch_url(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
@@ -324,6 +331,8 @@ def scrape(max_pages: int | None = None, max_properties: int | None = None):
             "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

@@ -1,13 +1,53 @@
-"""Shared utility for writing per-scraper run statistics to JSON."""
+"""Shared utilities for scraper run statistics and listing validation."""
 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."""