Unify server, persist ratings via API, refresh scraper data

- Replace split setup (ratings_server.py on :8081 + http.server on :8080)
  with a single combined Flask server (server.py) on :8080 that serves
  static files and the /api/ratings GET/POST endpoints
- Ratings are now persisted server-side: mapa_bytu.html loads ratings
  from GET /api/ratings on startup (API as source of truth) and POSTs
  on every change — enables cross-browser and cross-device state sharing
  while keeping localStorage as a synchronous read cache
- Dockerfile: install flask, copy server.py instead of ratings_server.py,
  expose only port 8080
- entrypoint.sh: start single server process instead of two
- Makefile: add serve / serve-debug targets for local development
- scrape_psn.py: fix log label, add --max-pages stub arg for CLI parity
- Refresh all scraped property data

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

.claude/settings.local.json

@@ -0,0 +1,31 @@
+{
+  "permissions": {
+    "allow": [
+      "WebFetch(domain:github.com)",
+      "WebFetch(domain:www.sreality.cz)",
+      "WebFetch(domain:webscraping.pro)",
+      "WebFetch(domain:raw.githubusercontent.com)",
+      "Bash(python3:*)",
+      "Bash(open:*)",
+      "WebFetch(domain:www.realingo.cz)",
+      "WebFetch(domain:api.realingo.cz)",
+      "Bash(curl:*)",
+      "Bash(grep:*)",
+      "WebFetch(domain:www.realitni-pes.cz)",
+      "WebFetch(domain:www.bezrealitky.cz)",
+      "WebFetch(domain:apify.com)",
+      "WebFetch(domain:www.bezrealitky.com)",
+      "WebFetch(domain:reality.idnes.cz)",
+      "Bash(# Final checks: robots.txt and response time for rate limiting clues curl -s -L -H \"\"User-Agent: Mozilla/5.0 \\(Windows NT 10.0; Win64; x64\\) AppleWebKit/537.36 \\(KHTML, like Gecko\\) Chrome/120.0.0.0 Safari/537.36\"\" \"\"https://reality.idnes.cz/robots.txt\"\")",
+      "WebFetch(domain:www.cityhome.cz)",
+      "WebFetch(domain:www.psn.cz)",
+      "WebFetch(domain:www.city-home.cz)",
+      "WebFetch(domain:psn.cz)",
+      "WebFetch(domain:api.psn.cz)",
+      "Bash(done)",
+      "Bash(# Final summary: count total units across all projects\n# Get the total count from the unitsCountData we already extracted\necho \"\"From unitsCountData on /prodej page:\"\"\necho \"\"  type_id 0 \\(Prodej bytů a ateliérů\\): 146\"\"\necho \"\"  type_id 1 \\(Prodej komerčních nemovitostí\\): 14\"\"\necho \"\"  type_id 2 \\(Pronájem bytů\\): 3\"\"\necho \"\"  type_id 3 \\(Pronájem komerčních nemovitostí\\): 48\"\"\necho \"\"\"\"\necho \"\"Total for-sale projects: 19\"\"\necho \"\"\"\"\necho \"\"Disposition counts from the data:\"\"\npython3 << 'PYEOF'\n# Extract disposition counts from prodej page\nimport re\n\nwith open\\('/tmp/psn_prodej_p1.html', 'r', encoding='utf-8'\\) as f:\n    html = f.read\\(\\)\n\n# Find disposition data\nidx = html.find\\('\\\\\\\\\"disposition\\\\\\\\\":['\\)\nif idx >= 0:\n    chunk = html[idx:idx+2000].replace\\('\\\\\\\\\"', '\"'\\)\n    # Extract name and count pairs\n    import re\n    pairs = re.findall\\(r'\"name\":\"\\([^\"]+\\)\",\"count\":\\(\\\\d+\\)', chunk\\)\n    for name, count in pairs:\n        print\\(f\"  {name}: {count}\"\\)\nPYEOF)",
+      "Bash(ls:*)",
+      "Bash(chmod:*)"
+    ]
+  }
+}

.gitea/workflows/build.yaml

@@ -0,0 +1,35 @@
+name: Build and Push
+
+on:
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Image tag'
+        required: true
+        default: 'latest'
+  push:
+    tags:
+      - '*'
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Login to Gitea registry
+        run: echo "${{ secrets.REGISTRY_TOKEN }}" | docker login -u ${{ github.actor }} --password-stdin gitea.home.hrajfrisbee.cz
+
+      - name: Build and push
+        run: |
+          TAG=${{ github.ref_name }}
+          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
+            TAG=${{ inputs.tag }}
+          fi
+          IMAGE=gitea.home.hrajfrisbee.cz/${{ github.repository }}:$TAG
+          docker build -f build/Dockerfile -t $IMAGE .
+          docker push $IMAGE

.gitignore

@@ -0,0 +1,3 @@
+.vscode/
+__pycache__/
+byty_*.json

Makefile

@@ -0,0 +1,79 @@
+IMAGE_NAME        := maru-hleda-byt
+CONTAINER_NAME    := maru-hleda-byt
+VOLUME_NAME       := maru-hleda-byt-data
+VALIDATION_CONTAINER := maru-hleda-byt-validation
+VALIDATION_VOLUME  := maru-hleda-byt-validation-data
+PORT              := 8080
+
+.PHONY: build run stop logs scrape restart clean help validation validation-local validation-stop validation-local-debug serve serve-debug
+
+help:
+	@echo "Available targets:"
+	@echo "  build               - Build the Docker image"
+	@echo "  run                 - Build and run the Docker container in the background"
+	@echo "  stop                - Stop and remove the running container"
+	@echo "  logs                - Show live container logs"
+	@echo "  scrape              - Run the scraping script inside the container"
+	@echo "  validation          - Run scraping with limits (1 page, 10 properties) in Docker container"
+	@echo "  validation-stop     - Stop the validation Docker container"
+	@echo "  validation-local    - Run scraping with limits (1 page, 10 properties) locally with Python"
+	@echo "  validation-local-debug - Run validation locally with DEBUG logging"
+	@echo "  restart             - Restart the container (stop and run again)"
+	@echo "  clean               - Stop container and remove the Docker image"
+	@echo "  serve               - Run server.py locally (DATA_DIR=., port $(PORT))"
+	@echo "  serve-debug         - Run server.py locally with DEBUG logging"
+	@echo "  help                - Show this help message"
+
+build:
+	docker build -f build/Dockerfile -t $(IMAGE_NAME) .
+
+run: build
+	docker run -d --name $(CONTAINER_NAME) \
+		-p $(PORT):8080 \
+		-v $(VOLUME_NAME):/app/data \
+		--restart unless-stopped \
+		$(IMAGE_NAME)
+	@echo "Map will be at http://localhost:$(PORT)/mapa_bytu.html"
+
+stop:
+	docker stop $(CONTAINER_NAME) && docker rm $(CONTAINER_NAME)
+
+logs:
+	docker logs -f $(CONTAINER_NAME)
+
+scrape:
+	docker exec $(CONTAINER_NAME) bash /app/run_all.sh
+
+validation: build
+	@docker stop $(VALIDATION_CONTAINER) 2>/dev/null || true
+	@docker rm $(VALIDATION_CONTAINER) 2>/dev/null || true
+	docker run -d --name $(VALIDATION_CONTAINER) \
+		-p 8081:8080 \
+		-v $(VALIDATION_VOLUME):/app/data \
+		--restart unless-stopped \
+		$(IMAGE_NAME)
+	@sleep 2
+	docker exec $(VALIDATION_CONTAINER) bash /app/run_all.sh --max-pages 1 --max-properties 10
+	@echo "Validation map will be at http://localhost:8081/mapa_bytu.html"
+
+validation-stop:
+	@docker stop $(VALIDATION_CONTAINER) 2>/dev/null || true
+	@docker rm $(VALIDATION_CONTAINER) 2>/dev/null || true
+	@echo "Validation container stopped and removed"
+
+validation-local:
+	./run_all.sh --max-pages 1 --max-properties 10
+
+validation-local-debug:
+	./run_all.sh --max-pages 1 --max-properties 10 --log-level DEBUG
+
+serve:
+	DATA_DIR=. PORT=$(PORT) python server.py
+
+serve-debug:
+	DATA_DIR=. PORT=$(PORT) python server.py --verbose
+
+restart: stop run
+
+clean: stop
+	docker rmi $(IMAGE_NAME)

README.md

@@ -0,0 +1,244 @@
+# Maru hleda byt
+
+Apartment search aggregator for Prague. Scrapes listings from 6 Czech real estate portals, filters them by configurable criteria, deduplicates across sources, and generates a single interactive map with all matching apartments.
+
+Built for a specific use case: finding a 3+kk or larger apartment in Prague, excluding panel construction ("panelak") and housing estates ("sidliste"), with personal rating support.
+
+## How it works
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│                        run_all.sh                           │
+│  Orchestrates all scrapers, then merges results into map    │
+├─────────┬──────────┬──────────┬────────┬────────┬───────────┤
+│Sreality │Realingo  │Bezreal.  │iDNES   │PSN     │CityHome   │
+│ (API)   │ (HTML)   │ (HTML)   │ (HTML) │ (HTML) │ (HTML)    │
+├─────────┴──────────┴──────────┴────────┴────────┴───────────┤
+│              merge_and_map.py                               │
+│  Loads all byty_*.json, deduplicates, generates HTML map    │
+├─────────────────────────────────────────────────────────────┤
+│              mapa_bytu.html                                 │
+│  Interactive Leaflet.js map with filters & ratings          │
+└─────────────────────────────────────────────────────────────┘
+```
+
+### Pipeline
+
+1. **Scraping** -- Each scraper independently fetches listings from its portal, applies filters, and saves results to a JSON file (`byty_<source>.json`).
+2. **Merging** -- `merge_and_map.py` loads all 6 JSON files, deduplicates listings (by street name + price + area), and generates the final `mapa_bytu.html`.
+3. **Serving** -- The HTML map can be opened locally as a file, or served via Docker with a built-in HTTP server.
+
+### Execution order in `run_all.sh`
+
+Scrapers run sequentially (to avoid overwhelming any single portal), except PSN and CityHome which run in parallel (different sites). If a scraper fails, it is logged but does not abort the pipeline -- remaining scrapers continue.
+
+```
+1. scrape_and_map.py   (Sreality)
+2. scrape_realingo.py  (Realingo)
+3. scrape_bezrealitky.py (Bezrealitky)
+4. scrape_idnes.py     (iDNES Reality)
+5. scrape_psn.py + scrape_cityhome.py  (parallel)
+6. merge_and_map.py    (merge + map generation)
+```
+
+## Scrapers
+
+All scrapers share the same CLI interface and a consistent two-phase approach:
+
+1. **Phase 1** -- Fetch listing pages (paginated) to get a list of all available apartments.
+2. **Phase 2** -- Fetch detail pages for each listing to get floor, construction type, and other data needed for filtering.
+
+Each scraper uses a **JSON file cache**: if a listing's `hash_id` and `price` haven't changed since the last run, the cached data is reused and the detail page is not re-fetched. This significantly reduces runtime on subsequent runs.
+
+### Source details
+
+| Scraper | Portal | Data source | Output file | Notes |
+|---------|--------|-------------|-------------|-------|
+| `scrape_and_map.py` | [Sreality.cz](https://sreality.cz) | REST API (JSON) | `byty_sreality.json` | Main scraper. Also contains `generate_map()` used by all other scripts. |
+| `scrape_realingo.py` | [Realingo.cz](https://realingo.cz) | `__NEXT_DATA__` JSON in HTML | `byty_realingo.json` | Next.js app, data extracted from server-side props. |
+| `scrape_bezrealitky.py` | [Bezrealitky.cz](https://bezrealitky.cz) | `__NEXT_DATA__` Apollo cache in HTML | `byty_bezrealitky.json` | Next.js app with Apollo GraphQL cache in page source. |
+| `scrape_idnes.py` | [Reality iDNES](https://reality.idnes.cz) | HTML parsing (regex) | `byty_idnes.json` | Traditional HTML site. GPS extracted from `dataLayer.push()`. Retry logic with 5 attempts and exponential backoff. |
+| `scrape_psn.py` | [PSN.cz](https://psn.cz) | RSC (React Server Components) escaped JSON in HTML | `byty_psn.json` | Uses `curl` instead of `urllib` due to Cloudflare SSL issues. Hardcoded list of Prague projects with GPS coordinates. |
+| `scrape_cityhome.py` | [city-home.cz](https://city-home.cz) | HTML table parsing (data attributes on `<tr>`) | `byty_cityhome.json` | CityHome/SATPO developer projects. GPS fetched from project locality pages. |
+
+### Scraper filter criteria
+
+All scrapers apply the same core filters (with minor per-source variations):
+
+| Filter | Value | Notes |
+|--------|-------|-------|
+| **Max price** | 13 500 000 CZK | PSN and CityHome use 14 000 000 CZK |
+| **Min area** | 69 m^2 | |
+| **Min floor** | 2. NP (2nd floor) | 2nd floor apartments are included but flagged on the map |
+| **Dispositions** | 3+kk, 3+1, 4+kk, 4+1, 5+kk, 5+1, 6+ | |
+| **Region** | Praha | |
+| **Construction** | Excludes panel ("panelak") | |
+| **Location** | Excludes housing estates ("sidliste") | |
+
+## Utility scripts
+
+### `merge_and_map.py`
+
+Merges all `byty_*.json` files into `byty_merged.json` and generates `mapa_bytu.html`.
+
+**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:
+
+- **Color-coded markers** by disposition (3+kk = blue, 3+1 = green, 4+kk = orange, etc.)
+- **Heart-shaped markers** for PSN and CityHome listings (developer favorites)
+- **Source badge** in each popup (Sreality, Realingo, Bezrealitky, iDNES, PSN, CityHome)
+- **Client-side filters:** minimum floor, maximum price, hide rejected
+- **Rating system** (persisted in `localStorage`):
+  - Star -- mark as favorite (enlarged marker with pulsing glow)
+  - Reject -- dim the marker, optionally hide it
+  - Notes -- free-text notes per listing
+- **2nd floor warning** -- listings on 2. NP show an orange warning in the popup
+- **Statistics panel** -- total count, price range, average price, disposition breakdown
+
+## CLI arguments
+
+All scrapers accept the same arguments. When run via `run_all.sh`, these arguments are forwarded to every scraper.
+
+```
+--max-pages N         Maximum number of listing pages to scrape per source.
+                      Limits the breadth of the initial listing fetch.
+                      (For PSN: max pages per project)
+
+--max-properties N    Maximum number of properties to fetch details for per source.
+                      Limits the depth of the detail-fetching phase.
+
+--log-level LEVEL     Logging verbosity. One of: DEBUG, INFO, WARNING, ERROR.
+                      Default: INFO.
+                      DEBUG shows HTTP request/response details, filter decisions
+                      for every single listing, and cache hit/miss info.
+
+-h, --help            Show help message (run_all.sh only).
+```
+
+### Examples
+
+```bash
+# Full scrape (all pages, all properties)
+./run_all.sh
+
+# Quick validation run (1 page per source, max 10 properties each)
+./run_all.sh --max-pages 1 --max-properties 10
+
+# Full scrape with debug logging
+./run_all.sh --log-level DEBUG
+
+# Run a single scraper
+python3 scrape_bezrealitky.py --max-pages 2 --max-properties 5 --log-level DEBUG
+```
+
+## Running with Docker
+
+The project includes a Docker setup for unattended operation with a cron-based schedule.
+
+### Container architecture
+
+```
+┌─────────────────────────────────────────┐
+│  Container (python:3.13-alpine)         │
+│                                         │
+│  PID 1: python3 -m http.server :8080    │
+│         serves /app/data/               │
+│                                         │
+│  crond:  runs run_all.sh at 06:00/18:00 │
+│          Europe/Prague timezone          │
+│                                         │
+│  /app/        -- scripts (.py, .sh)     │
+│  /app/data/   -- volume (JSON + HTML)   │
+│         ^ symlinked from /app/byty_*    │
+└─────────────────────────────────────────┘
+```
+
+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
+
+```bash
+make run         # Build image + start container on port 8080
+# Map available at http://localhost:8080/mapa_bytu.html
+```
+
+### Makefile targets
+
+| Target | Description |
+|--------|-------------|
+| `make help` | Show all available targets |
+| `make build` | Build the Docker image |
+| `make run` | Build and run the container (port 8080) |
+| `make stop` | Stop and remove the container |
+| `make logs` | Tail container logs |
+| `make scrape` | Trigger a manual scrape inside the running container |
+| `make restart` | Stop and re-run the container |
+| `make clean` | Stop container and remove the Docker image |
+| `make validation` | Run a limited scrape in a separate Docker container (port 8081) |
+| `make validation-stop` | Stop the validation container |
+| `make validation-local` | Run a limited scrape locally (1 page, 10 properties) |
+| `make validation-local-debug` | Same as above with `--log-level DEBUG` |
+
+### Validation mode
+
+Validation targets run scrapers with `--max-pages 1 --max-properties 10` for a fast smoke test (~30 seconds instead of several minutes). The Docker validation target runs on port 8081 in a separate container so it doesn't interfere with production data.
+
+## Project structure
+
+```
+.
+├── scrape_and_map.py       # Sreality scraper + map generator (generate_map())
+├── scrape_realingo.py      # Realingo scraper
+├── scrape_bezrealitky.py   # Bezrealitky scraper
+├── scrape_idnes.py         # iDNES Reality scraper
+├── 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)
+│   └── CONTAINER.md        # Container-specific documentation
+└── .gitignore              # Ignores byty_*.json, __pycache__, .vscode
+```
+
+## Dependencies
+
+**None.** All scrapers use only the Python standard library (`urllib`, `json`, `re`, `argparse`, `logging`, `html.parser`). The only external tool required is `curl` (used by `scrape_psn.py` for Cloudflare TLS compatibility).
+
+The Docker image is based on `python:3.13-alpine` (~70 MB) with `curl`, `bash`, and `tzdata` added.
+
+## Caching behavior
+
+Each scraper maintains a JSON file cache (`byty_<source>.json`). On each run:
+
+1. The previous JSON file is loaded and indexed by `hash_id`.
+2. For each listing found in the current run, if the `hash_id` exists in cache **and** the price is unchanged, the cached record is reused without fetching the detail page.
+3. New or changed listings trigger a detail page fetch.
+4. The JSON file is overwritten with the fresh results at the end.
+
+This means the first run is slow (fetches every detail page with rate-limiting delays), but subsequent runs are much faster as they only fetch details for new or changed listings.
+
+## Rate limiting
+
+Each scraper includes polite delays between requests:
+
+| Scraper | Delay between requests |
+|---------|----------------------|
+| Sreality | 0.3s (details), 0.5s (pages) |
+| Realingo | 0.3s (details), 0.5s (pages) |
+| Bezrealitky | 0.4s (details), 0.5s (pages) |
+| iDNES | 0.4s (details), 1.0s (pages) + retry backoff (3/6/9/12s) |
+| PSN | 0.5s (per project page) |
+| CityHome | 0.5s (per project GPS fetch) |

build/.dockerignore

@@ -0,0 +1,5 @@
+.git
+mapa_bytu.html
+byty_*.json
+*.pyc
+__pycache__

build/CONTAINER.md

@@ -0,0 +1,100 @@
+# Container Setup
+
+OCI container image for the apartment finder. Runs two processes:
+
+1. **Web server** (`python3 -m http.server`) serving `mapa_bytu.html` on port 8080
+2. **Cron job** running `run_all.sh` (all 6 scrapers + merge) every 12 hours
+
+## Architecture
+
+```
+┌─────────────────────────────────────────┐
+│  Container (python:3.13-alpine)         │
+│                                         │
+│  PID 1: python3 -m http.server :8080    │
+│         serves /app/data/               │
+│                                         │
+│  crond:  runs run_all.sh at 06:00/18:00 │
+│          Europe/Prague timezone          │
+│                                         │
+│  /app/        ← scripts (.py, .sh)      │
+│  /app/data/   ← volume (JSON + HTML)    │
+│         ↑ symlinked from /app/byty_*    │
+└─────────────────────────────────────────┘
+```
+
+On startup, the web server starts immediately. The initial scrape runs in the background and populates data as it completes. Subsequent cron runs update the data in-place.
+
+## Build and Run
+
+```bash
+# Build the image
+docker build -t maru-hleda-byt .
+
+# Run with persistent data volume
+docker run -d --name maru-hleda-byt \
+  -p 8080:8080 \
+  -v maru-hleda-byt-data:/app/data \
+  --restart unless-stopped \
+  maru-hleda-byt
+```
+
+Access the map at **http://localhost:8080/mapa_bytu.html**
+
+## Volume Persistence
+
+A named volume `maru-hleda-byt-data` stores:
+
+- `byty_*.json` — cached scraper data (6 source files + 1 merged)
+- `mapa_bytu.html` — the generated interactive map
+
+The JSON cache is important: each scraper skips re-fetching properties that haven't changed. Without the volume, every container restart triggers a full re-scrape of all 6 portals (several minutes with rate limiting).
+
+## Cron Schedule
+
+Scrapers run at **06:00** and **18:00 Europe/Prague time** (CET/CEST).
+
+Cron output is forwarded to the container's stdout/stderr, visible via `docker logs`.
+
+## Operations
+
+```bash
+# View logs (including cron and scraper output)
+docker logs -f maru-hleda-byt
+
+# Check cron schedule
+docker exec maru-hleda-byt crontab -l
+
+# Trigger a manual scrape
+docker exec maru-hleda-byt bash /app/run_all.sh
+
+# Stop / start (data persists in volume)
+docker stop maru-hleda-byt
+docker start maru-hleda-byt
+
+# Rebuild after code changes
+docker stop maru-hleda-byt && docker rm maru-hleda-byt
+docker build -t maru-hleda-byt .
+docker run -d --name maru-hleda-byt \
+  -p 8080:8080 \
+  -v maru-hleda-byt-data:/app/data \
+  --restart unless-stopped \
+  maru-hleda-byt
+```
+
+## Troubleshooting
+
+**Map shows 404**: The initial background scrape hasn't finished yet. Check `docker logs` for progress. First run takes a few minutes due to rate-limited API calls.
+
+**SSL errors from PSN scraper**: The `scrape_psn.py` uses `curl` (not Python urllib) specifically for Cloudflare SSL compatibility. Alpine's curl includes modern TLS via OpenSSL, so this should work. If not, check that `ca-certificates` is installed (`apk add ca-certificates`).
+
+**Health check failing**: The health check has a 5-minute start period to allow the initial scrape to complete. If it still fails, verify the HTTP server is running: `docker exec maru-hleda-byt wget -q -O /dev/null http://localhost:8080/`.
+
+**Timezone verification**: `docker exec maru-hleda-byt date` should show Czech time.
+
+## Image Details
+
+- **Base**: `python:3.13-alpine` (~55 MB)
+- **Added packages**: `curl`, `bash`, `tzdata` (~10 MB)
+- **No pip packages** — all scrapers use Python standard library only
+- **Approximate image size**: ~70 MB

build/Dockerfile

@@ -0,0 +1,28 @@
+FROM python:3.13-alpine
+
+RUN apk add --no-cache curl bash tzdata \
+    && cp /usr/share/zoneinfo/Europe/Prague /etc/localtime \
+    && echo "Europe/Prague" > /etc/timezone
+
+ENV PYTHONUNBUFFERED=1
+
+RUN pip install --no-cache-dir flask
+
+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 run_all.sh server.py ./
+
+COPY build/crontab /etc/crontabs/root
+COPY build/entrypoint.sh /entrypoint.sh
+RUN chmod +x /entrypoint.sh run_all.sh
+
+RUN mkdir -p /app/data
+
+EXPOSE 8080
+
+HEALTHCHECK --interval=60s --timeout=5s --start-period=300s \
+    CMD wget -q -O /dev/null http://localhost:8080/ || exit 1
+
+ENTRYPOINT ["/entrypoint.sh"]

build/Makefile

@@ -0,0 +1,31 @@
+IMAGE_NAME     := maru-hleda-byt
+CONTAINER_NAME := maru-hleda-byt
+VOLUME_NAME    := maru-hleda-byt-data
+PORT           := 8080
+
+.PHONY: build run stop logs scrape restart clean
+
+build:
+	docker build -f build/Dockerfile -t $(IMAGE_NAME) .
+
+run: build
+	docker run -d --name $(CONTAINER_NAME) \
+		-p $(PORT):8080 \
+		-v $(VOLUME_NAME):/app/data \
+		--restart unless-stopped \
+		$(IMAGE_NAME)
+	@echo "Map will be at http://localhost:$(PORT)/mapa_bytu.html"
+
+stop:
+	docker stop $(CONTAINER_NAME) && docker rm $(CONTAINER_NAME)
+
+logs:
+	docker logs -f $(CONTAINER_NAME)
+
+scrape:
+	docker exec $(CONTAINER_NAME) bash /app/run_all.sh
+
+restart: stop run
+
+clean: stop
+	docker rmi $(IMAGE_NAME)

build/crontab

@@ -0,0 +1 @@
+0 6,18 * * * cd /app && bash /app/run_all.sh >> /proc/1/fd/1 2>> /proc/1/fd/2

build/entrypoint.sh

@@ -0,0 +1,22 @@
+#!/bin/bash
+set -euo pipefail
+
+DATA_DIR="/app/data"
+
+# Create symlinks so scripts (which write to /app/) persist data to the volume
+for f in byty_sreality.json byty_realingo.json byty_bezrealitky.json \
+         byty_idnes.json byty_psn.json byty_cityhome.json byty_merged.json \
+         mapa_bytu.html ratings.json; do
+    # Remove real file if it exists (e.g. baked into image)
+    [ -f "/app/$f" ] && [ ! -L "/app/$f" ] && rm -f "/app/$f"
+    ln -sf "$DATA_DIR/$f" "/app/$f"
+done
+
+echo "[entrypoint] Starting crond..."
+crond -b -l 2
+
+echo "[entrypoint] Starting initial scrape in background..."
+bash /app/run_all.sh &
+
+echo "[entrypoint] Starting combined server on port 8080..."
+exec DATA_DIR="$DATA_DIR" python3 /app/server.py

byty_bezrealitky.json

@@ -0,0 +1,40 @@
+[
+  {
+    "hash_id": 981278,
+    "name": "Prodej bytu 3+kk 70 m²",
+    "price": 11890000,
+    "price_formatted": "11 890 000 Kč",
+    "locality": "Argentinská, Praha - Holešovice",
+    "lat": 50.1026043,
+    "lon": 14.4435365,
+    "disposition": "3+kk",
+    "floor": 3,
+    "area": 70,
+    "building_type": "Cihlová",
+    "ownership": "Osobní",
+    "url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/981278-nabidka-prodej-bytu-argentinska-praha",
+    "source": "bezrealitky",
+    "image": "",
+    "first_seen": "2026-02-15",
+    "last_updated": "2026-02-15"
+  },
+  {
+    "hash_id": 991217,
+    "name": "Prodej bytu 3+kk 71 m²",
+    "price": 11490000,
+    "price_formatted": "11 490 000 Kč",
+    "locality": "Kolbenova, Praha - Vysočany",
+    "lat": 50.1113213,
+    "lon": 14.5106858,
+    "disposition": "3+kk",
+    "floor": 3,
+    "area": 71,
+    "building_type": "Cihlová",
+    "ownership": "Osobní",
+    "url": "https://www.bezrealitky.cz/nemovitosti-byty-domy/991217-nabidka-prodej-bytu-kolbenova-praha",
+    "source": "bezrealitky",
+    "image": "",
+    "last_updated": "2026-02-15",
+    "first_seen": "2026-02-15"
+  }
+]

byty_cityhome.json

@@ -0,0 +1,38 @@
+[
+  {
+    "hash_id": "cityhome_na-vaclavce-34_Byt A2.3",
+    "name": "Prodej bytu 3+1, 99 m² — Na Václavce 34",
+    "price": 13490000,
+    "price_formatted": "13 490 000 Kč",
+    "locality": "Na Václavce 34, Praha 5",
+    "lat": 50.0652858,
+    "lon": 14.3931318,
+    "disposition": "3+1",
+    "floor": 2,
+    "area": 99.1,
+    "building_type": "Cihlová",
+    "ownership": "neuvedeno",
+    "url": "https://www.city-home.cz/projekty/na-vaclavce-34/nabidka-nemovitosti/byt-a23",
+    "source": "cityhome",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": "cityhome_na-vaclavce-34_Byt A3.2",
+    "name": "Prodej bytu 3+1, 95 m² — Na Václavce 34",
+    "price": 13490000,
+    "price_formatted": "13 490 000 Kč",
+    "locality": "Na Václavce 34, Praha 5",
+    "lat": 50.0652858,
+    "lon": 14.3931318,
+    "disposition": "3+1",
+    "floor": 3,
+    "area": 95.6,
+    "building_type": "Cihlová",
+    "ownership": "neuvedeno",
+    "url": "https://www.city-home.cz/projekty/na-vaclavce-34/nabidka-nemovitosti/byt-a32",
+    "source": "cityhome",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  }
+]

byty_idnes.json

@@ -0,0 +1,290 @@
+[
+  {
+    "hash_id": "699ed0af74468ff4c2079aa1",
+    "name": "Prodej bytu 3+1 86 m²",
+    "price": 4600000,
+    "price_formatted": "4 600 000 Kč",
+    "locality": "Hynka Puce, Praha 5 - Stodůlky",
+    "lat": 50.049168412058556,
+    "lon": 14.302095927878957,
+    "disposition": "3+1",
+    "floor": 8,
+    "area": 86,
+    "building_type": "Cihlová",
+    "ownership": "družstevní",
+    "url": "https://reality.idnes.cz/detail/prodej/byt/praha-13-hynka-puce/699ed0af74468ff4c2079aa1/",
+    "source": "idnes",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": "699ecf47513757ba150e0c74",
+    "name": "Prodej bytu 3+kk 83 m²",
+    "price": 11390000,
+    "price_formatted": "11 390 000 Kč",
+    "locality": "Kytlická, Praha 9 - Prosek",
+    "lat": 50.1251431182,
+    "lon": 14.5077027612,
+    "disposition": "3+kk",
+    "floor": 8,
+    "area": 83,
+    "building_type": "2011",
+    "ownership": "osobní",
+    "url": "https://reality.idnes.cz/detail/prodej/byt/praha-9-kytlicka/699ecf47513757ba150e0c74/",
+    "source": "idnes",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": "699c09d25d571b3c7b026d3e",
+    "name": "Prodej bytu 3+kk 93 m²",
+    "price": 11890000,
+    "price_formatted": "11 890 000 Kč",
+    "locality": "Kříženeckého náměstí, Praha 5 - Hlubočepy",
+    "lat": 50.03137852,
+    "lon": 14.39175816,
+    "disposition": "3+kk",
+    "floor": 3,
+    "area": 93,
+    "building_type": "Cihlová",
+    "ownership": "osobní",
+    "url": "https://reality.idnes.cz/detail/prodej/byt/praha-5-krizeneckeho-namesti/699c09d25d571b3c7b026d3e/",
+    "source": "idnes",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": "693690e98418631b48025208",
+    "name": "Prodej bytu 3+1 87 m²",
+    "price": 11323000,
+    "price_formatted": "11 323 000 Kč",
+    "locality": "Libušská, Praha 4 - Libuš",
+    "lat": 50.009743674736,
+    "lon": 14.460835345662,
+    "disposition": "3+1",
+    "floor": 2,
+    "area": 87,
+    "building_type": "Cihlová",
+    "ownership": "družstevní",
+    "url": "https://reality.idnes.cz/detail/prodej/byt/praha-12-libusska/693690e98418631b48025208/",
+    "source": "idnes",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": "699487a84abe8029bd065570",
+    "name": "Prodej bytu 3+1 96 m²",
+    "price": 13490000,
+    "price_formatted": "13 490 000 Kč",
+    "locality": "Na Václavce, Praha 5 - Smíchov",
+    "lat": 50.0652882346,
+    "lon": 14.3931192571,
+    "disposition": "3+1",
+    "floor": 4,
+    "area": 96,
+    "building_type": "Cihlová",
+    "ownership": "osobní",
+    "url": "https://reality.idnes.cz/detail/prodej/byt/praha-5-na-vaclavce/699487a84abe8029bd065570/",
+    "source": "idnes",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": "697c7e54d08e16f19902d777",
+    "name": "Prodej bytu 3+kk 76 m²",
+    "price": 11590040,
+    "price_formatted": "11 590 040 Kč",
+    "locality": "Žilinská, Praha 4 - Záběhlice",
+    "lat": 50.04710645755815,
+    "lon": 14.473057214055794,
+    "disposition": "3+kk",
+    "floor": 5,
+    "area": 76,
+    "building_type": "Cihlová",
+    "ownership": "osobní",
+    "url": "https://reality.idnes.cz/detail/prodej/byt/praha-4-zilinska/697c7e54d08e16f19902d777/",
+    "source": "idnes",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": "68f5f1e873fec2e50c0cc20e",
+    "name": "Prodej bytu 3+kk 85 m²",
+    "price": 13499900,
+    "price_formatted": "13 499 900 Kč",
+    "locality": "Hořejší nábřeží, Praha 5 - Smíchov",
+    "lat": 50.0724036111,
+    "lon": 14.4103030556,
+    "disposition": "3+kk",
+    "floor": 3,
+    "area": 85,
+    "building_type": "Cihlová",
+    "ownership": "osobní",
+    "url": "https://reality.idnes.cz/detail/prodej/byt/praha-5-horejsi-nabrezi/68f5f1e873fec2e50c0cc20e/",
+    "source": "idnes",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": "6941cf632ff10124be08ce19",
+    "name": "Prodej bytu 4+kk 94 m²",
+    "price": 13249900,
+    "price_formatted": "13 249 900 Kč",
+    "locality": "V dolině, Praha 10 - Michle",
+    "lat": 50.0579944444,
+    "lon": 14.4682905556,
+    "disposition": "4+kk",
+    "floor": 14,
+    "area": 94,
+    "building_type": "Cihlová",
+    "ownership": "osobní",
+    "url": "https://reality.idnes.cz/detail/prodej/byt/praha-10-v-doline/6941cf632ff10124be08ce19/",
+    "source": "idnes",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": "690c2cba1c264f9f43027912",
+    "name": "Prodej bytu 3+kk 74 m²",
+    "price": 10631123,
+    "price_formatted": "10 631 123 Kč",
+    "locality": "Voskovcova, Praha 5 - Hlubočepy",
+    "lat": 50.0290438889,
+    "lon": 14.3641566667,
+    "disposition": "3+kk",
+    "floor": 6,
+    "area": 74,
+    "building_type": "Cihlová",
+    "ownership": "osobní",
+    "url": "https://reality.idnes.cz/detail/prodej/byt/praha-5-voskovcova/690c2cba1c264f9f43027912/",
+    "source": "idnes",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": "68404b3d8178bbed020f1742",
+    "name": "Prodej bytu 3+kk 71 m²",
+    "price": 10990000,
+    "price_formatted": "10 990 000 Kč",
+    "locality": "Praha 10 - Uhříněves",
+    "lat": 50.026899,
+    "lon": 14.613713,
+    "disposition": "3+kk",
+    "floor": 5,
+    "area": 71,
+    "building_type": "Skeletová",
+    "ownership": "osobní",
+    "url": "https://reality.idnes.cz/detail/prodej/byt/praha-22/68404b3d8178bbed020f1742/",
+    "source": "idnes",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": "6932bf9dc9442dc194054416",
+    "name": "Prodej bytu 3+kk 71 m²",
+    "price": 8100000,
+    "price_formatted": "8 100 000 Kč",
+    "locality": "Štětínská, Praha 8 - Bohnice, okres Praha",
+    "lat": 50.1297302,
+    "lon": 14.4286652,
+    "disposition": "3+kk",
+    "floor": 5,
+    "area": 71,
+    "building_type": "1974",
+    "ownership": "osobní",
+    "url": "https://reality.idnes.cz/detail/prodej/byt/praha-8-stetinska/6932bf9dc9442dc194054416/",
+    "source": "idnes",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": "699eacc0a56ec9b4a80069b6",
+    "name": "Prodej bytu 3+kk 81 m²",
+    "price": 13000000,
+    "price_formatted": "13 000 000 Kč",
+    "locality": "Hlučkova, Praha 9 - Letňany",
+    "lat": 50.141739,
+    "lon": 14.522086,
+    "disposition": "3+kk",
+    "floor": 17,
+    "area": 81,
+    "building_type": "Smíšená",
+    "ownership": "osobní",
+    "url": "https://reality.idnes.cz/detail/prodej/byt/praha-18-hluckova/699eacc0a56ec9b4a80069b6/",
+    "source": "idnes",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": "682b20ae5fcffc3dc8072856",
+    "name": "Prodej bytu 3+kk 78 m²",
+    "price": 12463000,
+    "price_formatted": "12 463 000 Kč",
+    "locality": "Kubelíkova, Praha 3 - Žižkov",
+    "lat": 50.0823325029164,
+    "lon": 14.451052236466976,
+    "disposition": "3+kk",
+    "floor": 5,
+    "area": 78,
+    "building_type": "Cihlová",
+    "ownership": "osobní",
+    "url": "https://reality.idnes.cz/detail/prodej/byt/praha-3-kubelikova/682b20ae5fcffc3dc8072856/",
+    "source": "idnes",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": "68f0b7b4263df471cb050df9",
+    "name": "Prodej bytu 4+kk 75 m²",
+    "price": 10363000,
+    "price_formatted": "10 363 000 Kč",
+    "locality": "Karla Guta, Praha 10 - Uhříněves",
+    "lat": 50.030382258,
+    "lon": 14.5931238354,
+    "disposition": "4+kk",
+    "floor": 4,
+    "area": 75,
+    "building_type": "Cihlová",
+    "ownership": "osobní",
+    "url": "https://reality.idnes.cz/detail/prodej/byt/praha-22-karla-guta/68f0b7b4263df471cb050df9/",
+    "source": "idnes",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": "695cdf5113e97880200d9e62",
+    "name": "Prodej bytu 3+kk 82 m²",
+    "price": 11133000,
+    "price_formatted": "11 133 000 Kč",
+    "locality": "K Vinoři, Praha 9 - Kbely",
+    "lat": 50.132835725,
+    "lon": 14.5613326001,
+    "disposition": "3+kk",
+    "floor": 3,
+    "area": 82,
+    "building_type": "2026",
+    "ownership": "osobní",
+    "url": "https://reality.idnes.cz/detail/prodej/byt/praha-19-k-vinori/695cdf5113e97880200d9e62/",
+    "source": "idnes",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": "69930de7098209b20e066a6c",
+    "name": "Prodej bytu 3+kk 91 m²",
+    "price": 11000000,
+    "price_formatted": "11 000 000 Kč",
+    "locality": "Formanská, Praha 4 - Újezd u Průhonic, okres Praha",
+    "lat": 50.0114383,
+    "lon": 14.5469,
+    "disposition": "3+kk",
+    "floor": 3,
+    "area": 91,
+    "building_type": "2017",
+    "ownership": "osobní",
+    "url": "https://reality.idnes.cz/detail/prodej/byt/praha-11-formanska/69930de7098209b20e066a6c/",
+    "source": "idnes",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  }
+]

byty_psn.json

@@ -0,0 +1,20 @@
+[
+  {
+    "hash_id": "8941",
+    "name": "Prodej bytu 3+kk, 102 m² — JITRO",
+    "price": 13994000,
+    "price_formatted": "13 994 000 Kč",
+    "locality": "Litevská 1174/8, Praha 10",
+    "lat": 50.0729,
+    "lon": 14.4767,
+    "disposition": "3+kk",
+    "floor": 2,
+    "area": 102.7,
+    "building_type": "neuvedeno",
+    "ownership": "osobní",
+    "url": "https://psn.cz/prodej/ubytovaci-jednotka-3-kk-litevska-praha-10-vrsovice-lit4219",
+    "source": "psn",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  }
+]

byty_realingo.json

@@ -0,0 +1,164 @@
+[
+  {
+    "hash_id": 24515963,
+    "name": "Prodej bytu 3+kk 83 m²",
+    "price": 11390000,
+    "price_formatted": "11 390 000 Kč",
+    "locality": "Kytlická, Praha",
+    "lat": 50.1251431182,
+    "lon": 14.5077027612,
+    "disposition": "3+kk",
+    "floor": 4,
+    "area": 83,
+    "building_type": "WIREFRAME",
+    "ownership": "Osobní",
+    "url": "https://www.realingo.cz/prodej/byt-3+kk-kytlicka-praha/24515963",
+    "source": "realingo",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 24515884,
+    "name": "Prodej bytu 3+kk 81 m²",
+    "price": 13000000,
+    "price_formatted": "13 000 000 Kč",
+    "locality": "Hlučkova 869, Praha",
+    "lat": 50.142303781599,
+    "lon": 14.522362316941,
+    "disposition": "3+kk",
+    "floor": 5,
+    "area": 81,
+    "building_type": "OTHER",
+    "ownership": "Osobní",
+    "url": "https://www.realingo.cz/prodej/byt-3+kk-hluckova-869-praha/24515884",
+    "source": "realingo",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 24515669,
+    "name": "Prodej bytu Atypický None m²",
+    "price": 8487297,
+    "price_formatted": "8 487 297 Kč",
+    "locality": "Praha, 190 00",
+    "lat": 50.106598,
+    "lon": 14.506245,
+    "disposition": "Atypický",
+    "floor": null,
+    "area": null,
+    "building_type": "neuvedeno",
+    "ownership": "neuvedeno",
+    "url": "https://www.realingo.cz/prodej/byt-ostatni-byty-praha-190-00/24515669",
+    "source": "realingo",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 24515653,
+    "name": "Prodej bytu Atypický None m²",
+    "price": 8890000,
+    "price_formatted": "8 890 000 Kč",
+    "locality": "Praha, 130 00",
+    "lat": 50.087602,
+    "lon": 14.470882,
+    "disposition": "Atypický",
+    "floor": null,
+    "area": null,
+    "building_type": "neuvedeno",
+    "ownership": "neuvedeno",
+    "url": "https://www.realingo.cz/prodej/byt-ostatni-byty-praha-130-00/24515653",
+    "source": "realingo",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 24515514,
+    "name": "Prodej bytu Atypický None m²",
+    "price": 7490000,
+    "price_formatted": "7 490 000 Kč",
+    "locality": "Praha, 141 00",
+    "lat": 50.045786,
+    "lon": 14.470711,
+    "disposition": "Atypický",
+    "floor": null,
+    "area": null,
+    "building_type": "neuvedeno",
+    "ownership": "neuvedeno",
+    "url": "https://www.realingo.cz/prodej/byt-ostatni-byty-praha-141-00/24515514",
+    "source": "realingo",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 24514922,
+    "name": "Prodej bytu Atypický None m²",
+    "price": 12132000,
+    "price_formatted": "12 132 000 Kč",
+    "locality": "Praha, 120 00",
+    "lat": 50.076449,
+    "lon": 14.435263,
+    "disposition": "Atypický",
+    "floor": null,
+    "area": null,
+    "building_type": "neuvedeno",
+    "ownership": "neuvedeno",
+    "url": "https://www.realingo.cz/prodej/byt-2+kk-slezska-praha/24514922",
+    "source": "realingo",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 24514813,
+    "name": "Prodej bytu Atypický None m²",
+    "price": 8490000,
+    "price_formatted": "8 490 000 Kč",
+    "locality": "Praha, 100 00",
+    "lat": 50.074273,
+    "lon": 14.493284,
+    "disposition": "Atypický",
+    "floor": null,
+    "area": null,
+    "building_type": "neuvedeno",
+    "ownership": "neuvedeno",
+    "url": "https://www.realingo.cz/prodej/byt-ostatni-byty-praha-100-00/24514813",
+    "source": "realingo",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 24514769,
+    "name": "Prodej bytu Atypický None m²",
+    "price": 6980000,
+    "price_formatted": "6 980 000 Kč",
+    "locality": "Praha, 154 00",
+    "lat": 50.010056,
+    "lon": 14.353809,
+    "disposition": "Atypický",
+    "floor": null,
+    "area": null,
+    "building_type": "neuvedeno",
+    "ownership": "neuvedeno",
+    "url": "https://www.realingo.cz/prodej/byt-ostatni-byty-praha-154-00/24514769",
+    "source": "realingo",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 24514708,
+    "name": "Prodej bytu Atypický None m²",
+    "price": 5362000,
+    "price_formatted": "5 362 000 Kč",
+    "locality": "Praha, 155 00",
+    "lat": 50.030571,
+    "lon": 14.308491,
+    "disposition": "Atypický",
+    "floor": null,
+    "area": null,
+    "building_type": "neuvedeno",
+    "ownership": "neuvedeno",
+    "url": "https://www.realingo.cz/prodej/byt-ostatni-byty-praha-155-00/24514708",
+    "source": "realingo",
+    "image": "",
+    "scraped_at": "2026-02-25"
+  }
+]

byty_sreality.json

@@ -0,0 +1,548 @@
+[
+  {
+    "hash_id": 938877772,
+    "name": "Prodej bytu 3+kk 99 m²",
+    "price": 12990000,
+    "price_formatted": "12 990 000 Kč",
+    "locality": "Čeljabinská, Praha 10 - Vršovice",
+    "lat": 50.069641,
+    "lon": 14.470198,
+    "disposition": "3+kk",
+    "floor": 3,
+    "area": 99,
+    "building_type": "Smíšená",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-vrsovice-celjabinska/938877772",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p7_D/kBfrbpoeNBLdvLCneFodIxL/21cc.jpeg?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 2036855628,
+    "name": "Prodej bytu 3+kk 83 m²",
+    "price": 10490000,
+    "price_formatted": "10 490 000 Kč",
+    "locality": "Na Výrovně, Praha 5 - Stodůlky",
+    "lat": 50.039608,
+    "lon": 14.316702,
+    "disposition": "3+kk",
+    "floor": 2,
+    "area": 83,
+    "building_type": "Cihlová",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-stodulky-na-vyrovne/2036855628",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p7_C/nPXMbbUsvqW7e6cQFkEl5P/7399.jpeg?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 2148991820,
+    "name": "Prodej bytu 3+kk 72 m²",
+    "price": 10990000,
+    "price_formatted": "10 990 000 Kč",
+    "locality": "Pod Marjánkou, Praha 6 - Břevnov",
+    "lat": 50.084381,
+    "lon": 14.372257,
+    "disposition": "3+kk",
+    "floor": 4,
+    "area": 72,
+    "building_type": "Cihlová",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-brevnov-pod-marjankou/2148991820",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p7_C/kOzkBkwYBTCNNSBPI1FiGB0F/c3a0.jpeg?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 3226313292,
+    "name": "Prodej bytu 3+kk 83 m²",
+    "price": 13500000,
+    "price_formatted": "13 500 000 Kč",
+    "locality": "Na Neklance, Praha 5 - Smíchov",
+    "lat": 50.060715,
+    "lon": 14.401836,
+    "disposition": "3+kk",
+    "floor": 4,
+    "area": 83,
+    "building_type": "Cihlová",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-smichov-na-neklance/3226313292",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p8_A/kBfrbpoeND2I1YDy2Fq7ErU/6389.jpeg?fl=res,400,300,3|shr,,20|jpg,90",
+    "last_updated": "2026-02-15",
+    "first_seen": "2026-02-15"
+  },
+  {
+    "hash_id": 475530060,
+    "name": "Prodej bytu 3+kk 83 m²",
+    "price": 12250000,
+    "price_formatted": "12 250 000 Kč",
+    "locality": "Radouňova, Praha 5 - Stodůlky",
+    "lat": 50.039043,
+    "lon": 14.314881,
+    "disposition": "3+kk",
+    "floor": 3,
+    "area": 83,
+    "building_type": "Cihlová",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-stodulky-radounova/475530060",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p7_A/nDJ4VEZEqxQDMR0LFbAhGV/d4cf.png?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 2303799884,
+    "name": "Prodej bytu 3+kk 88 m² (Jednopodlažní)",
+    "price": 12860000,
+    "price_formatted": "12 860 000 Kč",
+    "locality": "Spojovací, Praha 9 - Vysočany",
+    "lat": 50.100174,
+    "lon": 14.492079,
+    "disposition": "3+kk",
+    "floor": 3,
+    "area": 88,
+    "building_type": "Skeletová",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-vysocany-spojovaci/2303799884",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_oV_A/kQOIvbF2D1DN63hulCAKv40/3667.png?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 3493290828,
+    "name": "Prodej bytu 3+kk 83 m²",
+    "price": 11390000,
+    "price_formatted": "11 390 000 Kč",
+    "locality": "Kytlická, Praha 9 - Prosek",
+    "lat": 50.125145,
+    "lon": 14.507703,
+    "disposition": "3+kk",
+    "floor": 4,
+    "area": 83,
+    "building_type": "Skeletová",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-prosek-kytlicka/3493290828",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p8_C/nPVpfd5QLLDqk1BGdrF3rQMW/0fe5.jpeg?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 151528268,
+    "name": "Prodej bytu 3+kk 86 m²",
+    "price": 11390000,
+    "price_formatted": "11 390 000 Kč",
+    "locality": "Spojovací, Praha",
+    "lat": 50.101852,
+    "lon": 14.486118,
+    "disposition": "3+kk",
+    "floor": 2,
+    "area": 86,
+    "building_type": "Smíšená",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha--spojovaci/151528268",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_of_C/kPxr1WDRoIBXSQV6LE550j7/1607.png?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 1837527884,
+    "name": "Prodej bytu 3+kk 73 m² (Jednopodlažní)",
+    "price": 12790000,
+    "price_formatted": "12 790 000 Kč",
+    "locality": "Vrázova, Praha - Smíchov",
+    "lat": 50.071224,
+    "lon": 14.407872,
+    "disposition": "3+kk",
+    "floor": 3,
+    "area": 73,
+    "building_type": "Cihlová",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-smichov-vrazova/1837527884",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p8_C/kY1K2LlXQDnuVLD65F2mjiY/96d4.png?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 3330433868,
+    "name": "Prodej bytu 3+kk 93 m²",
+    "price": 11890000,
+    "price_formatted": "11 890 000 Kč",
+    "locality": "Kříženeckého náměstí, Praha 5 - Hlubočepy",
+    "lat": 50.03138,
+    "lon": 14.391757,
+    "disposition": "3+kk",
+    "floor": 2,
+    "area": 93,
+    "building_type": "Cihlová",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-hlubocepy-krizeneckeho-namesti/3330433868",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p8_C/nPVpfd5QLLChvUCFgIF2b8p9/bffb.jpeg?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 2053579340,
+    "name": "Prodej bytu 3+kk 76 m²",
+    "price": 11858981,
+    "price_formatted": "11 858 981 Kč",
+    "locality": "Za Novákovou zahradou, Praha - Satalice",
+    "lat": 50.122192,
+    "lon": 14.57646,
+    "disposition": "3+kk",
+    "floor": 3,
+    "area": 76,
+    "building_type": "Smíšená",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-satalice-za-novakovou-zahradou/2053579340",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_oe_B/nO1Ur3YPjB17k9qAElHGe3/e889.jpeg?fl=res,400,300,3|shr,,20|jpg,90",
+    "last_updated": "2026-02-15",
+    "first_seen": "2026-02-15"
+  },
+  {
+    "hash_id": 3651539788,
+    "name": "Prodej bytu 3+kk 69 m² (Jednopodlažní)",
+    "price": 13500000,
+    "price_formatted": "13 500 000 Kč",
+    "locality": "Zvěřinova, Praha 3 - Strašnice",
+    "lat": 50.084606,
+    "lon": 14.482681,
+    "disposition": "3+kk",
+    "floor": 12,
+    "area": 69,
+    "building_type": "Smíšená",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-strasnice-zverinova/3651539788",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_og_D/nDJ4VEZEqxmIDK5SFVQ67V/47d3.png?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 4005061452,
+    "name": "Prodej bytu 3+kk 101 m² (Jednopodlažní)",
+    "price": 12875000,
+    "price_formatted": "12 875 000 Kč",
+    "locality": "U Hostavického potoka, Praha 9 - Hostavice",
+    "lat": 50.086601,
+    "lon": 14.5636,
+    "disposition": "3+kk",
+    "floor": 5,
+    "area": 101,
+    "building_type": "Cihlová",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-hostavice-u-hostavickeho-potoka/4005061452",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p8_B/kY1K2LlXQBdLY8B5hFyVzb6/c266.png?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 589460300,
+    "name": "Prodej bytu 3+kk 75 m²",
+    "price": 13126000,
+    "price_formatted": "13 126 000 Kč",
+    "locality": "Ke Slivenci, Praha - Lochkov",
+    "lat": 50.004192,
+    "lon": 14.355805,
+    "disposition": "3+kk",
+    "floor": 2,
+    "area": 75,
+    "building_type": "Skeletová",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-lochkov-ke-slivenci/589460300",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p8_A/kBfrbpoeNCgOJyFn9Fq0T4y/bed6.png?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 2926625612,
+    "name": "Prodej bytu 3+kk 85 m²",
+    "price": 13499900,
+    "price_formatted": "13 499 900 Kč",
+    "locality": "Hořejší nábřeží, Praha 5 - Smíchov",
+    "lat": 50.072403,
+    "lon": 14.410302,
+    "disposition": "3+kk",
+    "floor": 3,
+    "area": 85,
+    "building_type": "Cihlová",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-smichov-horejsi-nabrezi/2926625612",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p8_C/nPVpfd5QLLBPLz5GC0F3Hshx/c1f4.jpeg?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 3672994636,
+    "name": "Prodej bytu 3+kk 81 m²",
+    "price": 12390000,
+    "price_formatted": "12 390 000 Kč",
+    "locality": "Stochovská, Praha 6 - Ruzyně",
+    "lat": 50.082985,
+    "lon": 14.311815,
+    "disposition": "3+kk",
+    "floor": 3,
+    "area": 81,
+    "building_type": "Smíšená",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-ruzyne-stochovska/3672994636",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p8_C/nPVpfd5QLLD53UiFNrF2fBro/c20c.jpeg?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 4070581580,
+    "name": "Prodej bytu 3+kk 77 m²",
+    "price": 12207113,
+    "price_formatted": "12 207 113 Kč",
+    "locality": "Marie Podvalové, Praha - Čakovice",
+    "lat": 50.157696,
+    "lon": 14.519159,
+    "disposition": "3+kk",
+    "floor": 2,
+    "area": 77,
+    "building_type": "Skeletová",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-cakovice-marie-podvalove/4070581580",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p8_A/kBfrbpoeNBFLmuFzPFuWw0w/0867.jpeg?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 2772919116,
+    "name": "Prodej bytu 3+kk 81 m²",
+    "price": 13000000,
+    "price_formatted": "13 000 000 Kč",
+    "locality": "Hlučkova, Praha 9 - Letňany",
+    "lat": 50.141739,
+    "lon": 14.522086,
+    "disposition": "3+kk",
+    "floor": 5,
+    "area": 81,
+    "building_type": "Smíšená",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-letnany-hluckova/2772919116",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p8_C/nPVpfd5QLLDqzReGOMF3mju3/0593.jpeg?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 2242032460,
+    "name": "Prodej bytu 3+kk 98 m²",
+    "price": 12762764,
+    "price_formatted": "12 762 764 Kč",
+    "locality": "Lodžská, Praha 8 - Bohnice",
+    "lat": 50.13076,
+    "lon": 14.423249,
+    "disposition": "3+kk",
+    "floor": 5,
+    "area": 98,
+    "building_type": "Smíšená",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-bohnice-lodzska/2242032460",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p8_B/kY1K2LlXQBsPCGB2DFyc98H/0138.jpeg?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 3617202764,
+    "name": "Prodej bytu 3+kk 79 m²",
+    "price": 12959520,
+    "price_formatted": "12 959 520 Kč",
+    "locality": "Komárkova, Praha 4 - Chodov",
+    "lat": 50.036095,
+    "lon": 14.48035,
+    "disposition": "3+kk",
+    "floor": 3,
+    "area": 79,
+    "building_type": "Smíšená",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-chodov-komarkova/3617202764",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p8_B/kY1K2LlXQCEs3VCXcFzFm2Z/52f3.jpeg?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 2860663372,
+    "name": "Prodej bytu 3+kk 78 m² (Jednopodlažní)",
+    "price": 12463000,
+    "price_formatted": "12 463 000 Kč",
+    "locality": "Kubelíkova, Praha",
+    "lat": 50.082317,
+    "lon": 14.450463,
+    "disposition": "3+kk",
+    "floor": 4,
+    "area": 78,
+    "building_type": "Cihlová",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha--kubelikova/2860663372",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_oZ_C/nsLxLojIBfZuBIjJDOugLv/2953.png?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 158065228,
+    "name": "Prodej bytu 3+kk 73 m²",
+    "price": 10947779,
+    "price_formatted": "10 947 779 Kč",
+    "locality": "Marie Podvalové, Praha - Čakovice",
+    "lat": 50.157696,
+    "lon": 14.519159,
+    "disposition": "3+kk",
+    "floor": 4,
+    "area": 73,
+    "building_type": "Skeletová",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-cakovice-marie-podvalove/158065228",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p8_A/nPXMbbUsvqawIkHTbFrh4zH/4f1d.jpeg?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 4227625804,
+    "name": "Prodej bytu 3+kk 81 m²",
+    "price": 10990000,
+    "price_formatted": "10 990 000 Kč",
+    "locality": "Ukrajinská, Praha 10 - Vršovice",
+    "lat": 50.065208,
+    "lon": 14.450711,
+    "disposition": "3+kk",
+    "floor": 5,
+    "area": 81,
+    "building_type": "Cihlová",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-vrsovice-ukrajinska/4227625804",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p8_A/nPXMbbUsvqDzGaHEfWFp5WXH/fd47.jpeg?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 1313456972,
+    "name": "Prodej bytu 3+kk 87 m²",
+    "price": 3641309,
+    "price_formatted": "3 641 309 Kč",
+    "locality": "Praha 9",
+    "lat": 50.106956,
+    "lon": 14.510207,
+    "disposition": "3+kk",
+    "floor": 5,
+    "area": 87,
+    "building_type": "Smíšená",
+    "ownership": "Družstevní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-praha-9-/1313456972",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p8_B/kY1K2LlXQBsPCGXMFvI8II/9010.jpeg?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 1671439692,
+    "name": "Prodej bytu 3+kk 77 m²",
+    "price": 12556524,
+    "price_formatted": "12 556 524 Kč",
+    "locality": "Marie Podvalové, Praha - Čakovice",
+    "lat": 50.157696,
+    "lon": 14.519159,
+    "disposition": "3+kk",
+    "floor": 3,
+    "area": 77,
+    "building_type": "Skeletová",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-cakovice-marie-podvalove/1671439692",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p8_A/nPXMbbUsvqW7e6HmhFuWvTy/67cb.jpeg?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 576226124,
+    "name": "Prodej bytu 3+kk 71 m²",
+    "price": 12026912,
+    "price_formatted": "12 026 912 Kč",
+    "locality": "Hábova, Praha 5 - Stodůlky",
+    "lat": 50.04636,
+    "lon": 14.310556,
+    "disposition": "3+kk",
+    "floor": 3,
+    "area": 71,
+    "building_type": "Smíšená",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-stodulky-habova/576226124",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_of_A/nO5OZtPbfGXuqXa5EzIqYl/4c78.jpeg?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 473465676,
+    "name": "Prodej bytu 3+kk 73 m²",
+    "price": 12349349,
+    "price_formatted": "12 349 349 Kč",
+    "locality": "Hábova, Praha 5 - Stodůlky",
+    "lat": 50.04636,
+    "lon": 14.310556,
+    "disposition": "3+kk",
+    "floor": 3,
+    "area": 73,
+    "building_type": "Smíšená",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-stodulky-habova/473465676",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_of_A/nO5OZtPbfGCc8bBbKEzIlyN/5708.jpeg?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 2185458508,
+    "name": "Prodej bytu 3+kk 76 m²",
+    "price": 11978000,
+    "price_formatted": "11 978 000 Kč",
+    "locality": "Matoušova, Praha - Smíchov",
+    "lat": 50.074284,
+    "lon": 14.405826,
+    "disposition": "3+kk",
+    "floor": 2,
+    "area": 76,
+    "building_type": "Cihlová",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-smichov-matousova/2185458508",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p8_C/kY1K2LlXQJGqrEMbF29iKr/c977.png?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 3988325196,
+    "name": "Prodej bytu 3+kk 83 m² (Jednopodlažní)",
+    "price": 13190000,
+    "price_formatted": "13 190 000 Kč",
+    "locality": "Práčská, Praha",
+    "lat": 50.053101,
+    "lon": 14.507191,
+    "disposition": "3+kk",
+    "floor": 2,
+    "area": 83,
+    "building_type": "Kamenná",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha--pracska/3988325196",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p7_A/kOzkBkwYBTDPt7SL0bFanjav/5b75.png?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 3019572044,
+    "name": "Prodej bytu 3+kk 76 m²",
+    "price": 10790000,
+    "price_formatted": "10 790 000 Kč",
+    "locality": "Plzákova, Praha - Kbely",
+    "lat": 50.13237,
+    "lon": 14.53639,
+    "disposition": "3+kk",
+    "floor": 3,
+    "area": 76,
+    "building_type": "Cihlová",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-kbely-plzakova/3019572044",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p7_A/nDJ4VEZEqCaOxZQ8PFZch2R/b90f.png?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 3704697676,
+    "name": "Prodej bytu 3+kk 72 m²",
+    "price": 8000000,
+    "price_formatted": "8 000 000 Kč",
+    "locality": "Litevská, Praha 10 - Vršovice",
+    "lat": 50.072536,
+    "lon": 14.476557,
+    "disposition": "3+kk",
+    "floor": 5,
+    "area": 72,
+    "building_type": "Cihlová",
+    "ownership": "Družstevní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-vrsovice-litevska/3704697676",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_of_A/nOztZkD4ZlC2Y2EU6E0MiZv/15fc.png?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  },
+  {
+    "hash_id": 1137623884,
+    "name": "Prodej bytu 3+kk 71 m²",
+    "price": 12318349,
+    "price_formatted": "12 318 349 Kč",
+    "locality": "Praha 9",
+    "lat": 50.106956,
+    "lon": 14.510207,
+    "disposition": "3+kk",
+    "floor": 4,
+    "area": 71,
+    "building_type": "Skeletová",
+    "ownership": "Osobní",
+    "url": "https://www.sreality.cz/detail/prodej/byt/3+kk/praha-praha-9-/1137623884",
+    "image": "https://d18-a.sdn.cz/d_18/c_img_p8_B/nPVpfd5QLLksKHbwFvjCd6/56ac.jpeg?fl=res,400,300,3|shr,,20|jpg,90",
+    "scraped_at": "2026-02-25"
+  }
+]

generate_status.py

@@ -0,0 +1,202 @@
+#!/usr/bin/env python3
+"""Generate status.json from scraper JSON outputs and run log."""
+from __future__ import annotations
+
+import json
+import os
+import re
+import sys
+from datetime import datetime
+from pathlib import Path
+from typing import Optional
+
+HERE = Path(__file__).parent
+
+SOURCE_FILES = {
+    "Sreality":    "byty_sreality.json",
+    "Realingo":    "byty_realingo.json",
+    "Bezrealitky": "byty_bezrealitky.json",
+    "iDNES":       "byty_idnes.json",
+    "PSN":         "byty_psn.json",
+    "CityHome":    "byty_cityhome.json",
+}
+
+MERGED_FILE = "byty_merged.json"
+
+
+def count_source(path: Path) -> dict:
+    """Read a scraper JSON and return accepted count + file mtime."""
+    if not path.exists():
+        return {"accepted": 0, "error": "soubor nenalezen"}
+    try:
+        data = json.loads(path.read_text(encoding="utf-8"))
+        mtime = datetime.fromtimestamp(path.stat().st_mtime).isoformat(timespec="seconds")
+        return {"accepted": len(data), "updated_at": mtime}
+    except Exception as e:
+        return {"accepted": 0, "error": str(e)}
+
+
+def parse_log(log_path: str) -> dict[str, dict]:
+    """Parse scraper run log and extract per-source statistics.
+
+    Scrapers log summary lines like:
+      ✓ Vyhovující byty:    12
+      Vyloučeno (prodáno):   5
+      Staženo stránek:       3
+      Staženo inzerátů:      48
+      Celkem bytů v cache:   120
+    and section headers like:
+      [2/6] Realingo
+    """
+    if not log_path or not os.path.exists(log_path):
+        return {}
+
+    with open(log_path, encoding="utf-8") as f:
+        content = f.read()
+
+    # Split into per-source sections by the [N/6] Step header
+    # Each section header looks like "[2/6] Realingo\n----..."
+    section_pattern = re.compile(r'\[(\d+)/\d+\]\s+(.+)\n-+', re.MULTILINE)
+    sections_found = list(section_pattern.finditer(content))
+
+    if not sections_found:
+        return {}
+
+    stats = {}
+    for i, match in enumerate(sections_found):
+        step_name = match.group(2).strip()
+        start = match.end()
+        end = sections_found[i + 1].start() if i + 1 < len(sections_found) else len(content)
+        section_text = content[start:end]
+
+        # Identify which sources this section covers
+        # "PSN + CityHome" covers both
+        source_names = []
+        for name in SOURCE_FILES:
+            if name.lower() in step_name.lower():
+                source_names.append(name)
+        if not source_names:
+            continue
+
+        # Parse numeric summary lines
+        def extract(pattern: str) -> Optional[int]:
+            m = re.search(pattern, section_text)
+            return int(m.group(1)) if m else None
+
+        # Lines present in all/most scrapers
+        accepted = extract(r'Vyhovující byty[:\s]+(\d+)')
+        fetched = extract(r'Staženo inzerátů[:\s]+(\d+)')
+        pages = extract(r'Staženo stránek[:\s]+(\d+)')
+        cached = extract(r'Celkem bytů v cache[:\s]+(\d+)')
+        cache_hits = extract(r'Cache hit[:\s]+(\d+)')
+
+        # Rejection reasons — collect all into a dict
+        excluded = {}
+        for m in re.finditer(r'Vyloučeno\s+\(([^)]+)\)[:\s]+(\d+)', section_text):
+            excluded[m.group(1)] = int(m.group(2))
+        # Also PSN-style "Vyloučeno (prodáno): N"
+        total_excluded = sum(excluded.values()) if excluded else extract(r'Vyloučen\w*[:\s]+(\d+)')
+
+        entry = {}
+        if accepted is not None:
+            entry["accepted"] = accepted
+        if fetched is not None:
+            entry["fetched"] = fetched
+        if pages is not None:
+            entry["pages"] = pages
+        if cached is not None:
+            entry["cached"] = cached
+        if cache_hits is not None:
+            entry["cache_hits"] = cache_hits
+        if excluded:
+            entry["excluded"] = excluded
+        elif total_excluded is not None:
+            entry["excluded_total"] = total_excluded
+
+        for name in source_names:
+            stats[name] = entry
+
+    return stats
+
+
+def main():
+    start_time = None
+    duration_sec = None
+
+    if len(sys.argv) >= 3:
+        start_time = sys.argv[1]
+        try:
+            duration_sec = int(sys.argv[2])
+        except ValueError:
+            pass
+
+    if not start_time:
+        start_time = datetime.now().isoformat(timespec="seconds")
+
+    log_path = sys.argv[3] if len(sys.argv) >= 4 else None
+    log_stats = parse_log(log_path)
+
+    sources = []
+    for name, filename in SOURCE_FILES.items():
+        path = HERE / filename
+        info = count_source(path)
+        info["name"] = name
+
+        # Merge log stats
+        ls = log_stats.get(name, {})
+        for k in ("fetched", "pages", "cached", "cache_hits", "excluded", "excluded_total"):
+            if k in ls:
+                info[k] = ls[k]
+        # Override accepted from log if available (log is authoritative for latest run)
+        if "accepted" in ls:
+            info["accepted"] = ls["accepted"]
+
+        sources.append(info)
+
+    # Total accepted before dedup
+    total_accepted = sum(s.get("accepted", 0) for s in sources)
+
+    # Merged / deduplicated count
+    merged_path = HERE / MERGED_FILE
+    deduplicated = 0
+    if merged_path.exists():
+        try:
+            merged = json.loads(merged_path.read_text(encoding="utf-8"))
+            deduplicated = len(merged)
+        except Exception:
+            pass
+
+    duplicates_removed = total_accepted - deduplicated if deduplicated else 0
+
+    status = {
+        "status": "done",
+        "timestamp": start_time,
+        "duration_sec": duration_sec,
+        "total_accepted": total_accepted,
+        "deduplicated": deduplicated,
+        "duplicates_removed": duplicates_removed,
+        "sources": sources,
+    }
+
+    out = HERE / "status.json"
+    out.write_text(json.dumps(status, ensure_ascii=False, indent=2), encoding="utf-8")
+    print(f"Status uložen: {out}")
+    print(f"  Celkem bytů (před dedup): {total_accepted}")
+    print(f"  Po deduplikaci:           {deduplicated}")
+    if duplicates_removed:
+        print(f"  Odstraněno duplikátů:     {duplicates_removed}")
+    for s in sources:
+        acc = s.get("accepted", 0)
+        err = s.get("error", "")
+        exc = s.get("excluded", {})
+        exc_total = sum(exc.values()) if exc else s.get("excluded_total", 0)
+        parts = [f"{s['name']:12s}: {acc} bytů"]
+        if exc_total:
+            parts.append(f"({exc_total} vyloučeno)")
+        if err:
+            parts.append(f"[CHYBA: {err}]")
+        print("  " + "  ".join(parts))
+
+
+if __name__ == "__main__":
+    main()

project/todo.md

@@ -0,0 +1,19 @@
+## Features to add
+
+- testing: run very limited scrape: 1 page, 10 properties so that we can do some validations on it
+- makefile: add target to run locally (with the webserver)
+- feature: store date of the last scrape somewhere, so that we know how fresh data are
+- feature: ?? mark property with scrape when it first appeared - we might be able to look at recent diffs only
+
+
+## code organization
+- prepare reasonable code structure from the bunch of "random" files
+
+
+## documentation
+- precisely document original intent of the app (Maru has to provide this)
+
+##
+- prepare production run
+    - probably in home kubernetes
+    - maru-hleda-byt.lab.home.hrajfrisbee.cz

run_all.sh

@@ -2,6 +2,8 @@
 # ============================================================
 # Spustí všechny scrapery, sloučí data a otevře mapu.
 # Použití:  ./run_all.sh
+# Nebo s limity:  ./run_all.sh --max-pages 1 --max-properties 10
+# Nebo s logováním:  ./run_all.sh --log-level DEBUG
 # ============================================================
 set -euo pipefail
 cd "$(dirname "$0")"
@@ -14,6 +16,50 @@ NC='\033[0m'
 TOTAL=6
 CURRENT=0
 FAILED=0
+START_TIME=$(date -u +"%Y-%m-%dT%H:%M:%S")
+START_EPOCH=$(date +%s)
+LOG_FILE="$(pwd)/scrape_run.log"
+
+# Mark status as running
+echo '{"status":"running"}' > status.json
+
+show_help() {
+    echo "Usage: ./run_all.sh [OPTIONS]"
+    echo ""
+    echo "Spustí všechny scrapery, sloučí data a otevře mapu."
+    echo ""
+    echo "Options:"
+    echo "  --max-pages N         Maximální počet stránek ke stažení z každého zdroje"
+    echo "  --max-properties N    Maximální počet nemovitostí ke stažení z každého zdroje"
+    echo "  --log-level LEVEL     Úroveň logování (DEBUG, INFO, WARNING, ERROR)"
+    echo "  -h, --help            Zobrazí tuto nápovědu"
+    echo ""
+    echo "Examples:"
+    echo "  ./run_all.sh                                  # plný běh"
+    echo "  ./run_all.sh --max-pages 1 --max-properties 10  # rychlý test"
+    echo "  ./run_all.sh --log-level DEBUG                # s debug logováním"
+}
+
+# Parse arguments
+SCRAPER_ARGS=""
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        -h|--help)
+            show_help
+            exit 0
+            ;;
+        --max-pages|--max-properties|--log-level)
+            SCRAPER_ARGS="$SCRAPER_ARGS $1 $2"
+            shift 2
+            ;;
+        *)
+            echo "Unknown argument: $1"
+            echo ""
+            show_help
+            exit 1
+            ;;
+    esac
+done
 
 step() {
     CURRENT=$((CURRENT + 1))
@@ -23,23 +69,25 @@ step() {
 }
 
 # ── Scrapery (paralelně kde to jde) ─────────────────────────
+# Tee all output to log file for status generation
+exec > >(tee -a "$LOG_FILE") 2>&1
 
 step "Sreality"
-python3 scrape_and_map.py || { echo -e "${RED}✗ Sreality selhalo${NC}"; FAILED=$((FAILED + 1)); }
+python3 scrape_and_map.py $SCRAPER_ARGS || { echo -e "${RED}✗ Sreality selhalo${NC}"; FAILED=$((FAILED + 1)); }
 
 step "Realingo"
-python3 scrape_realingo.py || { echo -e "${RED}✗ Realingo selhalo${NC}"; FAILED=$((FAILED + 1)); }
+python3 scrape_realingo.py $SCRAPER_ARGS || { echo -e "${RED}✗ Realingo selhalo${NC}"; FAILED=$((FAILED + 1)); }
 
 step "Bezrealitky"
-python3 scrape_bezrealitky.py || { echo -e "${RED}✗ Bezrealitky selhalo${NC}"; FAILED=$((FAILED + 1)); }
+python3 scrape_bezrealitky.py $SCRAPER_ARGS || { echo -e "${RED}✗ Bezrealitky selhalo${NC}"; FAILED=$((FAILED + 1)); }
 
 step "iDNES Reality"
-python3 scrape_idnes.py || { echo -e "${RED}✗ iDNES selhalo${NC}"; FAILED=$((FAILED + 1)); }
+python3 scrape_idnes.py $SCRAPER_ARGS || { echo -e "${RED}✗ iDNES selhalo${NC}"; FAILED=$((FAILED + 1)); }
 
 step "PSN + CityHome"
-python3 scrape_psn.py &
+python3 scrape_psn.py $SCRAPER_ARGS &
 PID_PSN=$!
-python3 scrape_cityhome.py &
+python3 scrape_cityhome.py $SCRAPER_ARGS &
 PID_CH=$!
 wait $PID_PSN || { echo -e "${RED}✗ PSN selhalo${NC}"; FAILED=$((FAILED + 1)); }
 wait $PID_CH  || { echo -e "${RED}✗ CityHome selhalo${NC}"; FAILED=$((FAILED + 1)); }
@@ -51,6 +99,12 @@ python3 merge_and_map.py || { echo -e "${RED}✗ Merge selhal${NC}"; FAILED=$((F
 
 # ── Otevření mapy ────────────────────────────────────────────
 
+# ── Generování statusu ─────────────────────────────────────
+
+END_EPOCH=$(date +%s)
+DURATION=$((END_EPOCH - START_EPOCH))
+python3 generate_status.py "$START_TIME" "$DURATION" "$LOG_FILE"
+
 echo ""
 echo "============================================================"
 if [ $FAILED -eq 0 ]; then
@@ -60,4 +114,4 @@ else
 fi
 echo "============================================================"
 
-open mapa_bytu.html
+command -v open &>/dev/null && open mapa_bytu.html || true

scrape_and_map.py

@@ -6,7 +6,9 @@ Hledá byty na prodej v Praze podle zadaných kritérií a generuje HTML mapu.
 
 from __future__ import annotations
 
+import argparse
 import json
+import logging
 import math
 import time
 import urllib.request
@@ -14,6 +16,8 @@ import urllib.parse
 from datetime import datetime
 from pathlib import Path
 
+logger = logging.getLogger(__name__)
+
 # ── Konfigurace filtrů ──────────────────────────────────────────────────────
 
 MAX_PRICE = 13_500_000  # Kč
@@ -39,9 +43,18 @@ HEADERS = {
 
 def api_get(url: str) -> dict:
     """Fetch JSON from Sreality API."""
+    logger.debug(f"HTTP GET request: {url}")
+    logger.debug(f"Headers: {HEADERS}")
     req = urllib.request.Request(url, headers=HEADERS)
-    with urllib.request.urlopen(req, timeout=30) as resp:
+    try:
-        return json.loads(resp.read().decode("utf-8"))
+        with urllib.request.urlopen(req, timeout=30) as resp:
+            response_data = resp.read().decode("utf-8")
+            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.URLError, ConnectionError, OSError) as e:
+        logger.error(f"HTTP request failed for {url}: {e}", exc_info=True)
+        raise
 
 
 def build_list_url(disposition: int, page: int = 1) -> str:
@@ -59,20 +72,26 @@ def build_list_url(disposition: int, page: int = 1) -> str:
     return f"{API_BASE}?{urllib.parse.urlencode(params)}"
 
 
-def fetch_estates_for_disposition(disposition: int) -> list[dict]:
+def fetch_estates_for_disposition(disposition: int, max_pages: int | None = None) -> list[dict]:
     """Fetch all estates for a given disposition, handling pagination."""
     url = build_list_url(disposition, page=1)
-    print(f"  Fetching disposition {disposition}, page 1 ...")
+    logger.info(f"Fetching disposition {disposition}, page 1 ...")
     data = api_get(url)
     total = data.get("result_size", 0)
     estates = data.get("_embedded", {}).get("estates", [])
     total_pages = math.ceil(total / PER_PAGE) if total > 0 else 0
 
-    print(f"  → {total} results, {total_pages} pages")
+    logger.info(f"→ {total} results, {total_pages} pages")
+
+    # Limit pages if max_pages is specified
+    if max_pages is not None:
+        original_pages = total_pages
+        total_pages = min(total_pages, max_pages)
+        logger.debug(f"Max pages limit reached: limiting {original_pages} pages to {total_pages}")
 
     for page in range(2, total_pages + 1):
         time.sleep(0.5)
-        print(f"  Fetching page {page}/{total_pages} ...")
+        logger.info(f"Fetching page {page}/{total_pages} ...")
         url = build_list_url(disposition, page=page)
         data = api_get(url)
         estates.extend(data.get("_embedded", {}).get("estates", []))
@@ -84,9 +103,12 @@ def get_estate_detail(hash_id: int) -> dict | None:
     """Fetch detail for a single estate to get floor info and building type."""
     try:
         url = DETAIL_API.format(hash_id)
-        return api_get(url)
+        logger.debug(f"Fetching detail for hash_id={hash_id}")
+        detail = api_get(url)
+        logger.debug(f"Detail fetched for hash_id={hash_id}, keys: {list(detail.keys())[:5]}")
+        return detail
     except Exception as e:
-        print(f"    Warning: Could not fetch detail for {hash_id}: {e}")
+        logger.warning(f"Could not fetch detail for hash_id={hash_id}: {e}", exc_info=True)
         return None
 
 
@@ -185,24 +207,28 @@ def load_cache(json_path: str = "byty_sreality.json") -> dict[int, dict]:
         return {}
 
 
-def scrape():
+def scrape(max_pages: int | None = None, max_properties: int | None = None):
     """Main scraping function. Returns list of filtered estates."""
     all_estates_raw = []
     cache = load_cache()
 
-    print("=" * 60)
+    logger.info("=" * 60)
-    print("Stahuji inzeráty ze Sreality.cz")
+    logger.info("Stahuji inzeráty ze Sreality.cz")
-    print(f"Cena: do {format_price(MAX_PRICE)}")
+    logger.info(f"Cena: do {format_price(MAX_PRICE)}")
-    print(f"Dispozice: {', '.join(disposition_label(d) for d in DISPOSITIONS)}")
+    logger.info(f"Dispozice: {', '.join(disposition_label(d) for d in DISPOSITIONS)}")
-    print(f"Patro: od {MIN_FLOOR}. NP")
+    logger.info(f"Patro: od {MIN_FLOOR}. NP")
-    print(f"Region: Praha")
+    logger.info(f"Region: Praha")
     if cache:
-        print(f"Cache: {len(cache)} bytů z minulého běhu")
+        logger.info(f"Cache: {len(cache)} bytů z minulého běhu")
-    print("=" * 60)
+    if max_pages:
+        logger.info(f"Limit stran: {max_pages}")
+    if max_properties:
+        logger.info(f"Limit majetků: {max_properties}")
+    logger.info("=" * 60)
 
     for disp in DISPOSITIONS:
-        print(f"\n▸ Dispozice: {disposition_label(disp)}")
+        logger.info(f"\n▸ Dispozice: {disposition_label(disp)}")
-        estates = fetch_estates_for_disposition(disp)
+        estates = fetch_estates_for_disposition(disp, max_pages=max_pages)
         for e in estates:
             e["_disposition_cb"] = disp
         all_estates_raw.extend(estates)
@@ -217,10 +243,10 @@ def scrape():
             seen.add(hid)
             unique_estates.append(e)
 
-    print(f"\n{'=' * 60}")
+    logger.info(f"\n{'=' * 60}")
-    print(f"Staženo celkem: {len(unique_estates)} unikátních inzerátů")
+    logger.info(f"Staženo celkem: {len(unique_estates)} unikátních inzerátů")
-    print(f"Stahuji detaily pro filtrování panelu/sídlišť...")
+    logger.info(f"Stahuji detaily pro filtrování panelu/sídlišť...")
-    print(f"{'=' * 60}")
+    logger.info(f"{'=' * 60}")
 
     # Fetch details and filter
     results = []
@@ -229,19 +255,26 @@ def scrape():
     excluded_no_detail = 0
     excluded_small = 0
     cache_hits = 0
+    details_fetched = 0
 
     for i, estate in enumerate(unique_estates):
+        # Stop if max_properties reached
+        if max_properties is not None and details_fetched >= max_properties:
+            logger.debug(f"Max properties limit reached: {max_properties}")
+            break
         hash_id = estate.get("hash_id")
         gps = estate.get("gps", {})
 
         if not gps or not gps.get("lat") or not gps.get("lon"):
             excluded_no_gps += 1
+            logger.debug(f"Filter: hash_id={hash_id} - excluded (no GPS)")
             continue
 
         # Check cache — if hash_id exists and price unchanged, reuse
         cached = cache.get(hash_id)
         if cached and cached.get("price") == estate.get("price", 0):
             cache_hits += 1
+            logger.debug(f"Cache hit for hash_id={hash_id}")
             results.append(cached)
             continue
 
@@ -250,13 +283,15 @@ def scrape():
         detail = get_estate_detail(hash_id)
         if not detail:
             excluded_no_detail += 1
+            logger.debug(f"Filter: hash_id={hash_id} - excluded (no detail)")
             continue
 
         # Check panel / sídliště
         is_excluded, reason = is_panel_or_sidliste(detail)
         if is_excluded:
             excluded_panel += 1
-            print(f"  ✗ Vyloučen #{hash_id}: {reason}")
+            logger.debug(f"Filter: hash_id={hash_id} - excluded (panel/sídliště): {reason}")
+            logger.info(f"✗ Vyloučen #{hash_id}: {reason}")
             continue
 
         # Parse floor
@@ -276,7 +311,8 @@ def scrape():
         # Filter by minimum area
         if area is not None and area < MIN_AREA:
             excluded_small += 1
-            print(f"  ✗ Vyloučen #{hash_id}: malá plocha ({area} m²)")
+            logger.debug(f"Filter: hash_id={hash_id} - excluded (area {area} m² < {MIN_AREA} m²)")
+            logger.info(f"✗ Vyloučen #{hash_id}: malá plocha ({area} m²)")
             continue
 
         # Get building type
@@ -311,22 +347,24 @@ def scrape():
             "ownership": ownership,
             "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"),
         }
         results.append(result)
+        details_fetched += 1
 
         if (i + 1) % 20 == 0:
-            print(f"  Zpracováno {i + 1}/{len(unique_estates)} ...")
+            logger.info(f"Zpracováno {i + 1}/{len(unique_estates)} ...")
 
-    print(f"\n{'=' * 60}")
+    logger.info(f"\n{'=' * 60}")
-    print(f"Výsledky:")
+    logger.info(f"Výsledky:")
-    print(f"  Celkem staženo:       {len(unique_estates)}")
+    logger.info(f"  Celkem staženo:       {len(unique_estates)}")
-    print(f"  Z cache (přeskočeno): {cache_hits}")
+    logger.info(f"  Z cache (přeskočeno): {cache_hits}")
-    print(f"  Vyloučeno (panel/síd): {excluded_panel}")
+    logger.info(f"  Vyloučeno (panel/síd): {excluded_panel}")
-    print(f"  Vyloučeno (<{MIN_AREA} m²):  {excluded_small}")
+    logger.info(f"  Vyloučeno (<{MIN_AREA} m²):  {excluded_small}")
-    print(f"  Vyloučeno (bez GPS):   {excluded_no_gps}")
+    logger.info(f"  Vyloučeno (bez GPS):   {excluded_no_gps}")
-    print(f"  Vyloučeno (bez detailu): {excluded_no_detail}")
+    logger.info(f"  Vyloučeno (bez detailu): {excluded_no_detail}")
-    print(f"  ✓ Vyhovující byty:    {len(results)}")
+    logger.info(f"  ✓ Vyhovující byty:    {len(results)}")
-    print(f"{'=' * 60}")
+    logger.info(f"{'=' * 60}")
 
     return results
 
@@ -336,20 +374,58 @@ def scrape():
 def generate_map(estates: list[dict], output_path: str = "mapa_bytu.html"):
     """Generate an interactive Leaflet.js HTML map."""
 
-    # Color by disposition
+    # Color by price per m² — cool blue→warm red scale, no yellow
-    color_map = {
+    # Thresholds based on Prague market distribution (p25=120k, p50=144k, p75=162k)
-        "3+kk": "#2196F3",   # blue
+    price_color_scale = [
-        "3+1": "#4CAF50",    # green
+        (110_000, "#1565C0"),   # < 110k/m²  → deep blue (levné)
-        "4+kk": "#FF9800",   # orange
+        (130_000, "#42A5F5"),   # 110–130k   → light blue
-        "4+1": "#F44336",    # red
+        (150_000, "#66BB6A"),   # 130–150k   → green (střed)
-        "5+kk": "#9C27B0",   # purple
+        (165_000, "#EF6C00"),   # 150–165k   → dark orange
-        "5+1": "#795548",    # brown
+        (float("inf"), "#C62828"),  # > 165k → dark red (drahé)
-        "6+": "#607D8B",     # grey-blue
+    ]
-    }
+
+    def price_color(estate: dict) -> str:
+        price = estate.get("price") or 0
+        area = estate.get("area") or 0
+        if not area:
+            return "#9E9E9E"
+        ppm2 = price / area
+        for threshold, color in price_color_scale:
+            if ppm2 < threshold:
+                return color
+        return "#E53935"
+
+    # Legend bands for info panel (built once)
+    price_legend_items = (
+        '<div style="margin-bottom:4px;font-size:12px;color:#555;font-weight:600;">Cena / m²:</div>'
+    )
+    bands = [
+        ("#1565C0", "< 110 000 Kč/m²"),
+        ("#42A5F5", "110 – 130 000 Kč/m²"),
+        ("#66BB6A", "130 – 150 000 Kč/m²"),
+        ("#EF6C00", "150 – 165 000 Kč/m²"),
+        ("#C62828", "> 165 000 Kč/m²"),
+        ("#9E9E9E", "cena/plocha neuvedena"),
+    ]
+    for bcolor, blabel in bands:
+        price_legend_items += (
+            f'<div style="display:flex;align-items:center;gap:6px;margin:2px 0;">'
+            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>'
+        )
+    # 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="width:18px;height:18px;border-radius:50%;background:#66BB6A;'
+        'display:inline-block;box-shadow:0 1px 4px rgba(0,0,0,0.35);flex-shrink:0;"></span>'
+        '<span>Nové (z dnešního scrapu) — větší</span></div>'
+    )
 
     markers_js = ""
     for e in estates:
-        color = color_map.get(e["disposition"], "#999999")
+        color = price_color(e)
         floor_text = f'{e["floor"]}. NP' if e["floor"] else "neuvedeno"
         area_text = f'{e["area"]} m²' if e["area"] else "neuvedeno"
         building_text = e["building_type"] or "neuvedeno"
@@ -368,11 +444,19 @@ def generate_map(estates: list[dict], output_path: str = "mapa_bytu.html"):
 
         hash_id = e.get("hash_id", "")
 
+        scraped_at = e.get("scraped_at", "")
+        is_new = scraped_at == datetime.now().strftime("%Y-%m-%d")
+
+        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 ""
+        )
         popup = (
             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><br>'
+            f'padding:1px 6px;border-radius:3px;">{source_label}</span>{new_badge}<br>'
             f'<span style="color:#666;">{e["disposition"]} | {area_text} | {floor_text}</span>'
             f'{floor_note}<br><br>'
             f'<b>{e["locality"]}</b><br>'
@@ -401,27 +485,33 @@ def generate_map(estates: list[dict], output_path: str = "mapa_bytu.html"):
         popup = popup.replace("'", "\\'").replace("\n", "")
 
         is_fav = source in ("psn", "cityhome")
-        marker_fn = "addHeartMarker" if is_fav else "addMarker"
+
+        if is_fav:
+            marker_fn = "addHeartMarker"
+        elif is_new:
+            marker_fn = "addNewMarker"
+        else:
+            marker_fn = "addMarker"
         markers_js += (
             f"  {marker_fn}({e['lat']}, {e['lon']}, '{color}', '{popup}', '{hash_id}');\n"
         )
 
-    # Build legend
+    # Build legend — price per m² bands + disposition counts
-    legend_items = ""
+    legend_items = price_legend_items
+
+    # Disposition counts below the color legend
     disp_counts = {}
     for e in estates:
         d = e["disposition"]
         disp_counts[d] = disp_counts.get(d, 0) + 1
-    for disp, color in color_map.items():
+    disp_order = ["3+kk", "3+1", "4+kk", "4+1", "5+kk", "5+1", "6+"]
-        count = disp_counts.get(disp, 0)
+    disp_summary = ", ".join(
-        if count > 0:
+        f"{d} ({disp_counts[d]})" for d in disp_order if d in disp_counts
-            legend_items += (
+    )
-                f'<div style="display:flex;align-items:center;gap:6px;margin:3px 0;">'
+    legend_items += (
-                f'<span style="width:14px;height:14px;border-radius:50%;'
+        f'<div style="margin-top:8px;padding-top:6px;border-top:1px solid #eee;'
-                f'background:{color};display:inline-block;border:2px solid white;'
+        f'font-size:12px;color:#666;">{disp_summary}</div>'
-                f'box-shadow:0 1px 3px rgba(0,0,0,0.3);"></span>'
+    )
-                f'<span>{disp} ({count})</span></div>'
-            )
 
     # Heart marker legend for PSN/CityHome
     fav_count = sum(1 for e in estates if e.get("source") in ("psn", "cityhome"))
@@ -456,6 +546,7 @@ def generate_map(estates: list[dict], output_path: str = "mapa_bytu.html"):
   body {{ font-family: system-ui, -apple-system, sans-serif; }}
   #map {{ width: 100%; height: 100vh; }}
   .heart-icon {{ background: none !important; border: none !important; }}
+  .star-icon {{ background: none !important; border: none !important; }}
   .rate-btn:hover {{ background: #f0f0f0 !important; }}
   .rate-btn.active-fav {{ background: #FFF9C4 !important; border-color: #FFC107 !important; }}
   .rate-btn.active-rej {{ background: #FFEBEE !important; border-color: #F44336 !important; }}
@@ -466,13 +557,42 @@ def generate_map(estates: list[dict], output_path: str = "mapa_bytu.html"):
   }}
   .marker-favorite {{ animation: pulse-glow 2s ease-in-out infinite; border-radius: 50%; }}
   .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: 0.2 !important; }}
+  .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 {{
+    0%   {{ stroke-opacity: 1;   stroke-width: 3px; r: 11; }}
+    50%  {{ stroke-opacity: 0.4; stroke-width: 6px; r: 12; }}
+    100% {{ stroke-opacity: 1;   stroke-width: 3px; r: 11; }}
+  }}
+  .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;
     box-shadow: 0 2px 12px rgba(0,0,0,0.15); max-width: 260px;
     font-size: 13px; line-height: 1.5;
+    transition: transform 0.3s ease, opacity 0.3s ease;
   }}
+  .info-panel.collapsed {{
+    transform: translateX(calc(100% + 20px));
+    opacity: 0; pointer-events: none;
+  }}
+  .panel-open-btn {{
+    position: absolute; top: 10px; right: 10px; z-index: 1001;
+    width: 40px; height: 40px; border-radius: 8px;
+    background: white; border: none; cursor: pointer;
+    box-shadow: 0 2px 12px rgba(0,0,0,0.15);
+    font-size: 20px; display: flex; align-items: center; justify-content: center;
+    transition: opacity 0.3s ease;
+  }}
+  .panel-open-btn.hidden {{ opacity: 0; pointer-events: none; }}
+  .panel-close-btn {{
+    position: absolute; top: 8px; right: 8px;
+    width: 28px; height: 28px; border-radius: 6px;
+    background: none; border: 1px solid #ddd; cursor: pointer;
+    font-size: 16px; display: flex; align-items: center; justify-content: center;
+    color: #888;
+  }}
+  .panel-close-btn:hover {{ background: #f0f0f0; color: #333; }}
   .info-panel h2 {{ font-size: 16px; margin-bottom: 8px; }}
   .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; }}
@@ -480,18 +600,26 @@ def generate_map(estates: list[dict], output_path: str = "mapa_bytu.html"):
   .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; }}
+  .status-link {{ display: block; margin-top: 10px; padding-top: 10px; border-top: 1px solid #eee; text-align: center; }}
+  .status-link a {{ color: #1976D2; text-decoration: none; font-size: 12px; }}
+  @media (max-width: 600px) {{
+    .info-panel {{ max-width: calc(100vw - 60px); right: 10px; }}
+    .info-panel.collapsed {{ transform: translateX(calc(100% + 20px)); }}
+    .panel-close-btn {{ top: 6px; right: 6px; }}
+  }}
 </style>
 </head>
 <body>
 <div id="map"></div>
-<div class="info-panel">
+<button class="panel-open-btn hidden" id="panel-open-btn" onclick="togglePanel()">☰</button>
+<div class="info-panel" id="info-panel">
+  <button class="panel-close-btn" id="panel-close-btn" onclick="togglePanel()">✕</button>
   <h2>Byty v Praze</h2>
   <div class="stats">
     <div>Celkem: <b id="visible-count">{len(estates)}</b> bytů</div>
     <div>Cena: {min_price} — {max_price}</div>
     <div>Průměr: {avg_price}</div>
   </div>
-  <div><b>Dispozice:</b></div>
   {legend_items}
   <div class="filter-section">
     <b>Filtry:</b>
@@ -525,6 +653,7 @@ def generate_map(estates: list[dict], output_path: str = "mapa_bytu.html"):
       Skrýt zamítnuté
     </label>
   </div>
+  <div class="status-link"><a href="status.html">Scraper status</a></div>
 </div>
 
 <script>
@@ -560,6 +689,23 @@ function addMarker(lat, lon, color, popup, hashId) {{
   marker.addTo(map);
 }}
 
+function addNewMarker(lat, lon, color, popup, hashId) {{
+  var marker = L.circleMarker([lat, lon], {{
+    radius: 12,
+    fillColor: color,
+    color: color,
+    weight: 4,
+    opacity: 0.35,
+    fillOpacity: 0.95,
+  }}).bindPopup(popup);
+  marker._data = {{ lat: lat, lon: lon, color: color, hashId: hashId, isNew: true }};
+  allMarkers.push(marker);
+  marker.addTo(map);
+  marker.on('add', function() {{
+    if (marker._path) marker._path.classList.add('marker-new');
+  }});
+}}
+
 function heartIcon(color) {{
   var svg = '<svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24">'
     + '<path d="M12 21.35l-1.45-1.32C5.4 15.36 2 12.28 2 8.5 '
@@ -575,6 +721,21 @@ function heartIcon(color) {{
   }});
 }}
 
+function starIcon() {{
+  var svg = '<svg xmlns="http://www.w3.org/2000/svg" width="28" height="28" viewBox="0 0 24 24">'
+    + '<path d="M12 2l3.09 6.26L22 9.27l-5 4.87L18.18 22 12 18.27 '
+    + '5.82 22 7 14.14 2 9.27l6.91-1.01L12 2z" '
+    + 'fill="#FFC107" stroke="#F57F17" stroke-width="1" '
+    + 'filter="drop-shadow(0 1px 3px rgba(0,0,0,0.3))"/></svg>';
+  return L.divIcon({{
+    html: svg,
+    className: 'star-icon',
+    iconSize: [28, 28],
+    iconAnchor: [14, 14],
+    popupAnchor: [0, -14],
+  }});
+}}
+
 function addHeartMarker(lat, lon, color, popup, hashId) {{
   var marker = L.marker([lat, lon], {{
     icon: heartIcon(color),
@@ -600,6 +761,36 @@ function saveRatings(ratings) {{
   localStorage.setItem(RATINGS_KEY, JSON.stringify(ratings));
 }}
 
+function addRejectStrike(marker) {{
+  removeRejectStrike(marker);
+  var color = marker._data.color || '#999';
+  // SVG "no entry" icon — circle with diagonal line, colored to match marker
+  var svg = '<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" width="20" height="20">'
+    + '<circle cx="12" cy="12" r="10" fill="none" stroke="' + color + '" stroke-width="2.5" opacity="0.85"/>'
+    + '<line x1="5.5" y1="5.5" x2="18.5" y2="18.5" stroke="' + color + '" stroke-width="2.5" stroke-linecap="round" opacity="0.85"/>'
+    + '</svg>';
+  var icon = L.divIcon({{
+    className: 'reject-overlay',
+    html: svg,
+    iconSize: [20, 20],
+    iconAnchor: [10, 10],
+  }});
+  var m = L.marker([marker._data.lat, marker._data.lon], {{
+    icon: icon,
+    interactive: false,
+    pane: 'markerPane',
+  }});
+  m.addTo(map);
+  marker._rejectStrike = m;
+}}
+
+function removeRejectStrike(marker) {{
+  if (marker._rejectStrike) {{
+    map.removeLayer(marker._rejectStrike);
+    marker._rejectStrike = null;
+  }}
+}}
+
 function applyMarkerStyle(marker, status) {{
   if (marker._data.isHeart) {{
     var el = marker._icon;
@@ -614,26 +805,59 @@ function applyMarkerStyle(marker, status) {{
     }}
   }} else {{
     if (status === 'fav') {{
-      marker.setStyle({{
+      removeRejectStrike(marker);
-        radius: 12, fillOpacity: 1, weight: 3,
+      if (!marker._data._origCircle) marker._data._origCircle = true;
-        fillColor: marker._data.color, color: '#fff',
+      var popup = marker.getPopup();
-      }});
+      var popupContent = popup ? popup.getContent() : '';
-      if (marker._path) marker._path.classList.add('marker-favorite');
+      var wasOnMap = map.hasLayer(marker);
+      if (wasOnMap) map.removeLayer(marker);
+      var starMarker = L.marker([marker._data.lat, marker._data.lon], {{
+        icon: starIcon(),
+      }}).bindPopup(popupContent);
+      starMarker._data = marker._data;
+      var idx = allMarkers.indexOf(marker);
+      if (idx !== -1) allMarkers[idx] = starMarker;
+      if (wasOnMap) starMarker.addTo(map);
     }} else if (status === 'reject') {{
-      marker.setStyle({{
+      if (marker._data._origCircle && !(marker instanceof L.CircleMarker)) {{
-        radius: 6, fillOpacity: 0.15, fillColor: '#999', color: '#bbb', weight: 1,
+        revertToCircle(marker, {{ radius: 6, fillOpacity: 0.35, fillColor: marker._data.color, color: '#fff', weight: 1 }});
-      }});
+      }} else {{
-      if (marker._path) marker._path.classList.remove('marker-favorite');
+        marker.setStyle({{
+          radius: 6, fillOpacity: 0.35, fillColor: marker._data.color, color: '#fff', weight: 1,
+        }});
+        if (marker._path) marker._path.classList.remove('marker-favorite');
+      }}
+      // Add strikethrough line over the marker
+      addRejectStrike(marker);
     }} else {{
-      marker.setStyle({{
+      if (marker._data._origCircle && !(marker instanceof L.CircleMarker)) {{
-        radius: 8, fillColor: marker._data.color, color: '#fff',
+        revertToCircle(marker, {{ radius: 8, fillColor: marker._data.color, color: '#fff', weight: 2, fillOpacity: 0.85 }});
-        weight: 2, fillOpacity: 0.85,
+      }} else {{
-      }});
+        marker.setStyle({{
-      if (marker._path) marker._path.classList.remove('marker-favorite');
+          radius: 8, fillColor: marker._data.color, color: '#fff',
+          weight: 2, fillOpacity: 0.85,
+        }});
+        if (marker._path) marker._path.classList.remove('marker-favorite');
+      }}
+      if (marker._path) marker._path.classList.remove('marker-rejected');
+      removeRejectStrike(marker);
     }}
   }}
 }}
 
+function revertToCircle(marker, style) {{
+  var popup = marker.getPopup();
+  var popupContent = popup ? popup.getContent() : '';
+  var wasOnMap = map.hasLayer(marker);
+  if (wasOnMap) map.removeLayer(marker);
+  var cm = L.circleMarker([marker._data.lat, marker._data.lon], style).bindPopup(popupContent);
+  cm._data = marker._data;
+  delete cm._data._starRef;
+  var idx = allMarkers.indexOf(marker);
+  if (idx !== -1) allMarkers[idx] = cm;
+  if (wasOnMap) cm.addTo(map);
+}}
+
 function rateMarker(marker, action) {{
   var hashId = marker._data.hashId;
   var ratings = loadRatings();
@@ -795,8 +1019,12 @@ function applyFilters() {{
     if (show) {{
       if (!map.hasLayer(m)) m.addTo(map);
       visible++;
+      // Show strike line if rejected and visible
+      if (m._rejectStrike && !map.hasLayer(m._rejectStrike)) m._rejectStrike.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);
     }}
   }});
 
@@ -814,21 +1042,55 @@ function applyFilters() {{
 // Initialize ratings on load
 restoreRatings();
 
+// ── Panel toggle ──────────────────────────────────────────────
+function togglePanel() {{
+  var panel = document.getElementById('info-panel');
+  var openBtn = document.getElementById('panel-open-btn');
+  var isOpen = !panel.classList.contains('collapsed');
+  if (isOpen) {{
+    panel.classList.add('collapsed');
+    openBtn.classList.remove('hidden');
+  }} else {{
+    panel.classList.remove('collapsed');
+    openBtn.classList.add('hidden');
+  }}
+}}
+
+// On mobile, start with panel collapsed
+if (window.innerWidth <= 600) {{
+  document.getElementById('info-panel').classList.add('collapsed');
+  document.getElementById('panel-open-btn').classList.remove('hidden');
+}}
+
 </script>
 </body>
 </html>"""
 
     path = Path(output_path)
     path.write_text(html, encoding="utf-8")
-    print(f"\n✓ Mapa uložena: {path.resolve()}")
+    logger.info(f"\n✓ Mapa uložena: {path.resolve()}")
     return str(path.resolve())
 
 
 # ── Main ─────────────────────────────────────────────────────────────────────
 
 if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Scrape apartments from Sreality.cz")
+    parser.add_argument("--max-pages", type=int, help="Maximum number of pages to scrape")
+    parser.add_argument("--max-properties", type=int, help="Maximum number of properties to fetch details for")
+    parser.add_argument("--log-level", type=str, default="INFO", choices=["DEBUG", "INFO", "WARNING", "ERROR"],
+                        help="Logging level (default: INFO)")
+    args = parser.parse_args()
+
+    # Configure logging
+    logging.basicConfig(
+        level=getattr(logging, args.log_level),
+        format="[%(levelname)s] %(asctime)s - %(name)s - %(message)s",
+        handlers=[logging.StreamHandler()]
+    )
+
     start = time.time()
-    estates = scrape()
+    estates = scrape(max_pages=args.max_pages, max_properties=args.max_properties)
 
     if estates:
         # Save raw data as JSON backup
@@ -837,12 +1099,12 @@ if __name__ == "__main__":
             json.dumps(estates, ensure_ascii=False, indent=2),
             encoding="utf-8",
         )
-        print(f"✓ Data uložena: {json_path.resolve()}")
+        logger.info(f"✓ Data uložena: {json_path.resolve()}")
 
         # Generate map
         map_path = generate_map(estates)
         elapsed = time.time() - start
-        print(f"\n⏱  Celkový čas: {elapsed:.0f} s")
+        logger.info(f"\n⏱  Celkový čas: {elapsed:.0f} s")
-        print(f"\nOtevři v prohlížeči:\n  file://{map_path}")
+        logger.info(f"\nOtevři v prohlížeči:\n  file://{map_path}")
     else:
-        print("\nŽádné byty neodpovídají kritériím :(")
+        logger.info("\nŽádné byty neodpovídají kritériím :(")

scrape_bezrealitky.py

@@ -6,13 +6,18 @@ Výstup: byty_bezrealitky.json
 """
 from __future__ import annotations
 
+import argparse
+from datetime import datetime
 import json
+import logging
 import math
 import re
 import time
 import urllib.request
 from pathlib import Path
 
+logger = logging.getLogger(__name__)
+
 # ── Konfigurace ─────────────────────────────────────────────────────────────
 
 MAX_PRICE = 13_500_000
@@ -69,51 +74,63 @@ def fetch_page(page: int) -> tuple[list[dict], int]:
     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}")
+    logger.debug(f"Headers: {HEADERS}")
     req = urllib.request.Request(url, headers=HEADERS)
-    resp = urllib.request.urlopen(req, timeout=30)
-    html = resp.read().decode("utf-8")
-
-    match = re.search(
-        r'<script id="__NEXT_DATA__" type="application/json">(.*?)</script>',
-        html, re.DOTALL
-    )
-    if not match:
-        return [], 0
-
-    data = json.loads(match.group(1))
-    cache = data["props"]["pageProps"]["apolloCache"]
-
-    # Extract adverts from cache
-    adverts = []
-    for key, val in cache.items():
-        if key.startswith("Advert:") and isinstance(val, dict) and val.get("__typename") == "Advert":
-            adverts.append(val)
-
-    # Get total count from ROOT_QUERY
-    total = 0
-    root = cache.get("ROOT_QUERY", {})
-    for key, val in root.items():
-        if "listAdverts" in key and isinstance(val, dict):
-            tc = val.get("totalCount")
-            if tc and tc > total:
-                total = tc
-
-    return adverts, total
-
-
-def fetch_detail(uri: str) -> dict | None:
-    """Fetch detail page for a listing."""
     try:
-        url = f"{BASE_URL}/nemovitosti-byty-domy/{uri}"
-        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
         )
         if not match:
+            logger.debug("No __NEXT_DATA__ script found in HTML")
+            return [], 0
+
+        data = json.loads(match.group(1))
+        cache = data["props"]["pageProps"]["apolloCache"]
+
+        # Extract adverts from cache
+        adverts = []
+        for key, val in cache.items():
+            if key.startswith("Advert:") and isinstance(val, dict) and val.get("__typename") == "Advert":
+                adverts.append(val)
+
+        # Get total count from ROOT_QUERY
+        total = 0
+        root = cache.get("ROOT_QUERY", {})
+        for key, val in root.items():
+            if "listAdverts" in key and isinstance(val, dict):
+                tc = val.get("totalCount")
+                if tc and tc > total:
+                    total = tc
+
+        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}"
+        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
+        )
+        if not match:
+            logger.debug("No __NEXT_DATA__ script found in detail page")
             return None
 
         data = json.loads(match.group(1))
@@ -124,10 +141,11 @@ def fetch_detail(uri: str) -> dict | None:
             if key.startswith("Advert:") and isinstance(val, dict):
                 # Detail pages have much more fields
                 if "construction" in val or "etage" in val or "ownership" in val:
+                    logger.debug(f"Detail found for {uri}: construction={val.get('construction')}, etage={val.get('etage')}")
                     return val
 
     except Exception as e:
-        print(f"    Warning: detail failed for {uri}: {e}")
+        logger.warning(f"Detail failed for {uri}: {e}", exc_info=True)
     return None
 
 
@@ -152,35 +170,43 @@ def load_cache(json_path: str = "byty_bezrealitky.json") -> dict[int, dict]:
         return {}
 
 
-def scrape():
+def scrape(max_pages: int | None = None, max_properties: int | None = None):
     cache = load_cache()
 
-    print("=" * 60)
+    logger.info("=" * 60)
-    print("Stahuji inzeráty z Bezrealitky.cz")
+    logger.info("Stahuji inzeráty z Bezrealitky.cz")
-    print(f"Cena: do {format_price(MAX_PRICE)}")
+    logger.info(f"Cena: do {format_price(MAX_PRICE)}")
-    print(f"Min. plocha: {MIN_AREA} m²")
+    logger.info(f"Min. plocha: {MIN_AREA} m²")
-    print(f"Patro: od {MIN_FLOOR}. NP")
+    logger.info(f"Patro: od {MIN_FLOOR}. NP")
-    print(f"Region: Praha")
+    logger.info(f"Region: Praha")
     if cache:
-        print(f"Cache: {len(cache)} bytů z minulého běhu")
+        logger.info(f"Cache: {len(cache)} bytů z minulého běhu")
-    print("=" * 60)
+    if max_pages:
+        logger.info(f"Max. stran: {max_pages}")
+    if max_properties:
+        logger.info(f"Max. bytů: {max_properties}")
+    logger.info("=" * 60)
 
     # Step 1: Fetch all listing pages
-    print("\nFáze 1: Stahování seznamu inzerátů...")
+    logger.info("\nFáze 1: Stahování seznamu inzerátů...")
     all_adverts = {}  # id -> advert dict (dedup)
     page = 1
     total = None
 
     while True:
-        print(f"  Strana {page} ...")
+        if max_pages and page > max_pages:
+            logger.debug(f"Max pages limit reached: {max_pages}")
+            break
+        logger.info(f"Strana {page} ...")
         adverts, total_count = fetch_page(page)
 
         if total is None and total_count > 0:
             total = total_count
             total_pages = math.ceil(total / PER_PAGE)
-            print(f"  → Celkem {total} inzerátů, ~{total_pages} stran")
+            logger.info(f"→ Celkem {total} inzerátů, ~{total_pages} stran")
 
         if not adverts:
+            logger.debug(f"No adverts found on page {page}, stopping")
             break
 
         for adv in adverts:
@@ -193,7 +219,7 @@ def scrape():
             break
         time.sleep(0.5)
 
-    print(f"\n  Staženo: {len(all_adverts)} unikátních inzerátů")
+    logger.info(f"\nStaženo: {len(all_adverts)} unikátních inzerátů")
 
     # Step 2: Pre-filter by disposition, price, area from list data
     pre_filtered = []
@@ -203,47 +229,57 @@ def scrape():
     excluded_no_gps = 0
 
     for adv in all_adverts.values():
+        adv_id = adv.get("id")
         disp = adv.get("disposition", "")
         if disp not in WANTED_DISPOSITIONS:
             excluded_disp += 1
+            logger.debug(f"Filter: id={adv_id} - excluded (disposition {disp})")
             continue
 
         price = adv.get("price", 0) or 0
         if price > MAX_PRICE or price == 0:
             excluded_price += 1
+            logger.debug(f"Filter: id={adv_id} - excluded (price {price})")
             continue
 
         surface = adv.get("surface")
         if surface is not None and surface < MIN_AREA:
             excluded_area += 1
+            logger.debug(f"Filter: id={adv_id} - excluded (area {surface} m²)")
             continue
 
         gps = adv.get("gps", {})
         if not gps or not gps.get("lat") or not gps.get("lng"):
             excluded_no_gps += 1
+            logger.debug(f"Filter: id={adv_id} - excluded (no GPS)")
             continue
 
         pre_filtered.append(adv)
 
-    print(f"\nPo předfiltraci:")
+    logger.info(f"\nPo předfiltraci:")
-    print(f"  Vyloučeno (dispozice): {excluded_disp}")
+    logger.info(f"  Vyloučeno (dispozice): {excluded_disp}")
-    print(f"  Vyloučeno (cena):      {excluded_price}")
+    logger.info(f"  Vyloučeno (cena):      {excluded_price}")
-    print(f"  Vyloučeno (plocha):    {excluded_area}")
+    logger.info(f"  Vyloučeno (plocha):    {excluded_area}")
-    print(f"  Vyloučeno (bez GPS):   {excluded_no_gps}")
+    logger.info(f"  Vyloučeno (bez GPS):   {excluded_no_gps}")
-    print(f"  Zbývá:                 {len(pre_filtered)}")
+    logger.info(f"  Zbývá:                 {len(pre_filtered)}")
 
     # Step 3: Fetch details
-    print(f"\nFáze 2: Stahování detailů ({len(pre_filtered)} bytů)...")
+    logger.info(f"\nFáze 2: Stahování detailů ({len(pre_filtered)} bytů)...")
     results = []
     excluded_panel = 0
     excluded_floor = 0
     excluded_detail = 0
     cache_hits = 0
+    properties_fetched = 0
 
     for i, adv in enumerate(pre_filtered):
+        if max_properties and properties_fetched >= max_properties:
+            logger.debug(f"Max properties limit reached: {max_properties}")
+            break
         uri = adv.get("uri", "")
         if not uri:
             excluded_detail += 1
+            logger.debug(f"Filter: id={adv.get('id')} - excluded (no URI)")
             continue
 
         # Check cache — if hash_id exists and price unchanged, reuse
@@ -252,6 +288,7 @@ def scrape():
         cached = cache.get(adv_id)
         if cached and cached.get("price") == adv_price:
             cache_hits += 1
+            logger.debug(f"Cache hit for id={adv_id}")
             results.append(cached)
             continue
 
@@ -260,26 +297,30 @@ def scrape():
 
         if not detail:
             excluded_detail += 1
+            logger.debug(f"Filter: id={adv_id} - excluded (detail fetch failed)")
             continue
 
         # Check construction — exclude panel
         construction = detail.get("construction", "")
         if construction == "PANEL":
             excluded_panel += 1
-            print(f"  ✗ Vyloučen #{adv['id']}: panel")
+            logger.debug(f"Filter: id={adv['id']} - excluded (panel construction)")
+            logger.info(f"✗ Vyloučen #{adv['id']}: panel")
             continue
 
         # Check situation — exclude sídliště
         situation = detail.get("situation", "")
         if situation and "HOUSING_ESTATE" in str(situation).upper():
             excluded_panel += 1
-            print(f"  ✗ Vyloučen #{adv['id']}: sídliště")
+            logger.debug(f"Filter: id={adv['id']} - excluded (housing estate)")
+            logger.info(f"✗ Vyloučen #{adv['id']}: sídliště")
             continue
 
         # Check floor (etage)
         etage = detail.get("etage")
         if etage is not None and etage < MIN_FLOOR:
             excluded_floor += 1
+            logger.debug(f"Filter: id={adv_id} - excluded (floor {etage})")
             continue
 
         gps = adv.get("gps", {})
@@ -315,28 +356,46 @@ def scrape():
             "url": f"{BASE_URL}/nemovitosti-byty-domy/{uri}",
             "source": "bezrealitky",
             "image": "",
+            "scraped_at": datetime.now().strftime("%Y-%m-%d"),
         }
         results.append(result)
+        properties_fetched += 1
 
         if (i + 1) % 20 == 0:
-            print(f"  Zpracováno {i + 1}/{len(pre_filtered)} ...")
+            logger.info(f"Zpracováno {i + 1}/{len(pre_filtered)} ...")
 
-    print(f"\n{'=' * 60}")
+    logger.info(f"\n{'=' * 60}")
-    print(f"Výsledky Bezrealitky:")
+    logger.info(f"Výsledky Bezrealitky:")
-    print(f"  Předfiltrováno:        {len(pre_filtered)}")
+    logger.info(f"  Předfiltrováno:        {len(pre_filtered)}")
-    print(f"  Z cache (přeskočeno): {cache_hits}")
+    logger.info(f"  Z cache (přeskočeno): {cache_hits}")
-    print(f"  Vyloučeno (panel/síd): {excluded_panel}")
+    logger.info(f"  Vyloučeno (panel/síd): {excluded_panel}")
-    print(f"  Vyloučeno (patro):     {excluded_floor}")
+    logger.info(f"  Vyloučeno (patro):     {excluded_floor}")
-    print(f"  Vyloučeno (bez detailu): {excluded_detail}")
+    logger.info(f"  Vyloučeno (bez detailu): {excluded_detail}")
-    print(f"  ✓ Vyhovující byty:    {len(results)}")
+    logger.info(f"  ✓ Vyhovující byty:    {len(results)}")
-    print(f"{'=' * 60}")
+    logger.info(f"{'=' * 60}")
 
     return results
 
 
 if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Scrape apartments from Bezrealitky.cz")
+    parser.add_argument("--max-pages", type=int, default=None,
+                        help="Maximum number of listing pages to scrape")
+    parser.add_argument("--max-properties", type=int, default=None,
+                        help="Maximum number of properties to fetch details for")
+    parser.add_argument("--log-level", type=str, default="INFO", choices=["DEBUG", "INFO", "WARNING", "ERROR"],
+                        help="Logging level (default: INFO)")
+    args = parser.parse_args()
+
+    # Configure logging
+    logging.basicConfig(
+        level=getattr(logging, args.log_level),
+        format="[%(levelname)s] %(asctime)s - %(name)s - %(message)s",
+        handlers=[logging.StreamHandler()]
+    )
+
     start = time.time()
-    estates = scrape()
+    estates = scrape(max_pages=args.max_pages, max_properties=args.max_properties)
 
     if estates:
         json_path = Path("byty_bezrealitky.json")
@@ -345,7 +404,7 @@ if __name__ == "__main__":
             encoding="utf-8",
         )
         elapsed = time.time() - start
-        print(f"\n✓ Data uložena: {json_path.resolve()}")
+        logger.info(f"\n✓ Data uložena: {json_path.resolve()}")
-        print(f"⏱  Celkový čas: {elapsed:.0f} s")
+        logger.info(f"⏱  Celkový čas: {elapsed:.0f} s")
     else:
-        print("\nŽádné byty z Bezrealitek neodpovídají kritériím :(")
+        logger.info("\nŽádné byty z Bezrealitek neodpovídají kritériím :(")

scrape_cityhome.py

@@ -6,12 +6,17 @@ Výstup: byty_cityhome.json
 """
 from __future__ import annotations
 
+import argparse
 import json
+import logging
 import re
 import time
 import urllib.request
+from datetime import datetime
 from pathlib import Path
 
+logger = logging.getLogger(__name__)
+
 # ── Konfigurace ─────────────────────────────────────────────────────────────
 
 MAX_PRICE = 14_000_000
@@ -29,18 +34,26 @@ HEADERS = {
 BASE_URL = "https://www.city-home.cz"
 
 
-def fetch_url(url: str) -> str:
+def fetch_url(url: str, retries: int = 3) -> str:
-    """Fetch URL and return HTML string."""
+    """Fetch URL and return HTML string. Raises HTTPError on 4xx/5xx."""
-    for attempt in range(3):
+    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)
-            return resp.read().decode("utf-8")
+            html = resp.read().decode("utf-8")
+            logger.debug(f"HTTP response: status={resp.status}, size={len(html)} bytes")
+            return html
+        except urllib.error.HTTPError:
+            # Don't retry on HTTP errors (404, 403, etc.) — re-raise immediately
+            raise
         except (ConnectionResetError, ConnectionError, urllib.error.URLError) as e:
-            if attempt < 2:
+            if attempt < retries - 1:
-                time.sleep((attempt + 1) * 2)
+                wait = (attempt + 1) * 2
-                print(f"    Retry {attempt + 1}: {e}")
+                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
 
 
@@ -114,31 +127,21 @@ def parse_filter_page(html: str) -> list[dict]:
         if detail_url and not detail_url.startswith("http"):
             detail_url = BASE_URL + detail_url
 
-        # Extract floor from cells — look for pattern like "3.NP" or "2.PP"
+        # Parse table cells: [unit_name, unit_type_label, address, floor, disposition, area, transaction, price]
         cells = re.findall(r'<td[^>]*>(.*?)</td>', row_content, re.DOTALL)
-        floor = None
+        cell_texts = [re.sub(r'<[^>]+>', '', c).strip() for c in cells]
-        floor_text = ""
-        project_name = ""
 
-        for cell in cells:
+        # Cell[2] = address (e.g. "Žateckých 14"), cell[3] = floor (e.g. "3.NP")
-            cell_text = re.sub(r'<[^>]+>', '', cell).strip()
+        project_address = cell_texts[2] if len(cell_texts) > 2 else ""
-            # Floor pattern
+
-            np_match = re.search(r'(\d+)\.\s*NP', cell_text)
+        floor = None
-            pp_match = re.search(r'(\d+)\.\s*PP', cell_text)
+        if len(cell_texts) > 3:
+            np_match = re.search(r'(\d+)\.\s*NP', cell_texts[3])
+            pp_match = re.search(r'(\d+)\.\s*PP', cell_texts[3])
             if np_match:
                 floor = int(np_match.group(1))
-                floor_text = cell_text
             elif pp_match:
-                floor = -int(pp_match.group(1))  # Underground
+                floor = -int(pp_match.group(1))
-                floor_text = cell_text
-
-        # Extract project name — usually in a cell that's not a number/price/floor
-        for cell in cells:
-            cell_text = re.sub(r'<[^>]+>', '', cell).strip()
-            if cell_text and not re.match(r'^[\d\s.,]+$', cell_text) and "NP" not in cell_text and "PP" not in cell_text and "m²" not in cell_text and "Kč" not in cell_text and "EUR" not in cell_text and "CZK" not in cell_text:
-                if len(cell_text) > 3 and cell_text != unit_name:
-                    project_name = cell_text
-                    break
 
         listing = {
             "price": int(cena.group(1)),
@@ -148,45 +151,75 @@ def parse_filter_page(html: str) -> list[dict]:
             "project_id": project.group(1) if project else "",
             "transaction": transaction.group(1) if transaction else "",
             "disposition": dispozition.group(1) if dispozition else "",
-            "location": location.group(1) if location else "",
             "url": detail_url,
             "unit_name": unit_name,
             "floor": floor,
-            "project_name": project_name,
+            "project_address": project_address,
         }
         listings.append(listing)
 
     return listings
 
 
-def extract_project_gps(html: str) -> dict[str, tuple[float, float]]:
+def get_lokalita_urls(slug: str) -> list[str]:
-    """Extract GPS coordinates for projects from locality pages."""
+    """Return candidate lokalita URLs to try in order."""
-    # Pattern in JS: ['<h4>Project Name</h4>...', 'LAT', 'LON', '1', 'Name']
+    return [
-    gps_data = {}
+        f"{BASE_URL}/projekty/{slug}/lokalita",
-    for match in re.finditer(r"\['[^']*<h4>([^<]+)</h4>[^']*',\s*'([\d.]+)',\s*'([\d.]+)'", html):
+        f"{BASE_URL}/bytove-domy/{slug}/lokalita",
-        name = match.group(1).strip()
+        f"{BASE_URL}/bytove-domy/{slug}/lokalita1",
-        lat = float(match.group(2))
+    ]
-        lon = float(match.group(3))
-        gps_data[name] = (lat, lon)
-    return gps_data
 
 
-def scrape():
+def extract_project_gps(html: str) -> tuple[float, float] | None:
-    print("=" * 60)
+    """Extract project GPS from lokalita page JS variable.
-    print("Stahuji inzeráty z CityHome (city-home.cz)")
+
-    print(f"Cena: do {format_price(MAX_PRICE)}")
+    The page contains: var locations = [['<h4>Name</h4>...', 'LAT', 'LNG', 'CATEGORY', 'Label'], ...]
-    print(f"Min. plocha: {MIN_AREA} m²")
+    Category '1' = the project's own marker. Some projects have two cat-1 entries (data error);
-    print(f"Patro: od {MIN_FLOOR}. NP")
+    in that case we pick the one whose name contains a digit and is not a transit landmark.
-    print("=" * 60)
+    """
+    block = re.search(r'var locations\s*=\s*\[(.*?)\];', html, re.DOTALL)
+    if not block:
+        return None
+
+    entries = re.findall(
+        r"'<h4>(.*?)</h4>.*?',\s*'([\d.]+)',\s*'([\d.]+)',\s*'1'",
+        block.group(0),
+        re.DOTALL,
+    )
+    if not entries:
+        return None
+
+    if len(entries) == 1:
+        return float(entries[0][1]), float(entries[0][2])
+
+    # Multiple cat-1 entries: pick the real project marker
+    transit_re = re.compile(r'nádraží|park|metro|tramvaj|autobus|zastávka', re.IGNORECASE)
+    for name, lat, lng in entries:
+        if re.search(r'\d', name) and not transit_re.search(name):
+            return float(lat), float(lng)
+
+    # Fallback: first entry
+    return float(entries[0][1]), float(entries[0][2])
+
+
+def scrape(max_pages: int | None = None, max_properties: int | None = None):
+    logger.info("=" * 60)
+    logger.info("Stahuji inzeráty z CityHome (city-home.cz)")
+    logger.info(f"Cena: do {format_price(MAX_PRICE)}")
+    logger.info(f"Min. plocha: {MIN_AREA} m²")
+    logger.info(f"Patro: od {MIN_FLOOR}. NP")
+    if max_properties:
+        logger.info(f"Max. bytů: {max_properties}")
+    logger.info("=" * 60)
 
     # Step 1: Fetch the main filter page
-    print("\nFáze 1: Stahování seznamu bytů...")
+    logger.info("\nFáze 1: Stahování seznamu bytů...")
     html = fetch_url(f"{BASE_URL}/filtr-nemovitosti1")
     all_listings = parse_filter_page(html)
-    print(f"  Nalezeno: {len(all_listings)} jednotek")
+    logger.info(f"Nalezeno: {len(all_listings)} jednotek")
 
     # Step 2: Collect unique project slugs from detail URLs to fetch GPS
-    print("\nFáze 2: Stahování GPS souřadnic projektů...")
+    logger.info("\nFáze 2: Stahování GPS souřadnic projektů...")
     project_slugs = set()
     for listing in all_listings:
         url = listing.get("url", "")
@@ -198,23 +231,27 @@ def scrape():
     # Fetch GPS for each project from locality pages
     project_gps = {}
     for slug in sorted(project_slugs):
-        time.sleep(0.5)
+        time.sleep(0.3)
-        try:
+        gps = None
-            locality_url = f"{BASE_URL}/projekty/{slug}/lokalita"
+        for url in get_lokalita_urls(slug):
-            loc_html = fetch_url(locality_url)
+            try:
-            gps = extract_project_gps(loc_html)
+                logger.debug(f"Fetching project GPS: {url}")
-            if gps:
+                loc_html = fetch_url(url)
-                # Take first entry (the project itself)
+                gps = extract_project_gps(loc_html)
-                first_name, (lat, lon) = next(iter(gps.items()))
+                if gps:
-                project_gps[slug] = (lat, lon)
+                    break
-                print(f"  ✓ {slug}: {lat}, {lon}")
+            except Exception as e:
-            else:
+                logger.debug(f"GPS fetch failed for {url}: {e}")
-                print(f"  ✗ {slug}: GPS nenalezeno")
+                continue
-        except Exception as e:
+
-            print(f"  ✗ {slug}: chyba ({e})")
+        if gps:
+            project_gps[slug] = gps
+            logger.info(f"✓ {slug}: {gps[0]}, {gps[1]}")
+        else:
+            logger.info(f"✗ {slug}: GPS nenalezeno")
 
     # Step 3: Filter listings
-    print(f"\nFáze 3: Filtrování...")
+    logger.info(f"\nFáze 3: Filtrování...")
     results = []
     excluded_sold = 0
     excluded_type = 0
@@ -223,45 +260,57 @@ def scrape():
     excluded_area = 0
     excluded_floor = 0
     excluded_no_gps = 0
+    properties_fetched = 0
 
     for listing in all_listings:
+        if max_properties and properties_fetched >= max_properties:
+            logger.debug(f"Max properties limit reached: {max_properties}")
+            break
+        unit_name = listing.get("unit_name", "unknown")
         # Only available units
         if listing["free"] != "yes":
             excluded_sold += 1
+            logger.debug(f"Filter: {unit_name} - excluded (not free)")
             continue
 
         # Only apartments (unittype=2)
         if listing["unittype"] != 2:
             excluded_type += 1
+            logger.debug(f"Filter: {unit_name} - excluded (not apartment, unittype={listing['unittype']})")
             continue
 
         # Only sales
         if listing["transaction"] != "prodej":
             excluded_type += 1
+            logger.debug(f"Filter: {unit_name} - excluded (not sale, transaction={listing['transaction']})")
             continue
 
         # Disposition
         disp = listing["disposition"]
         if disp not in WANTED_DISPOSITIONS:
             excluded_disp += 1
+            logger.debug(f"Filter: {unit_name} - excluded (disposition {disp})")
             continue
 
         # Price
         price = listing["price"]
         if price <= 0 or price > MAX_PRICE:
             excluded_price += 1
+            logger.debug(f"Filter: {unit_name} - excluded (price {price})")
             continue
 
         # Area
         area = listing["area"]
         if area < MIN_AREA:
             excluded_area += 1
+            logger.debug(f"Filter: {unit_name} - excluded (area {area} m²)")
             continue
 
         # Floor
         floor = listing["floor"]
         if floor is not None and floor < MIN_FLOOR:
             excluded_floor += 1
+            logger.debug(f"Filter: {unit_name} - excluded (floor {floor})")
             continue
 
         # GPS from project
@@ -272,48 +321,81 @@ def scrape():
 
         if not gps:
             excluded_no_gps += 1
+            logger.debug(f"Filter: {unit_name} - excluded (no GPS for project {slug})")
             continue
 
         lat, lon = gps
 
+        # locality: use project address from cell (e.g. "Žateckých 14") + city from GPS lookup
+        project_address = listing.get("project_address", "")
+        # derive city from slug (GPS lookup key)
+        city_map = {
+            "karlinske-namesti-5": "Praha 8",
+            "melnicka-12": "Praha 7",
+            "na-vaclavce-34": "Praha 5",
+            "nad-kajetankou-12": "Praha 6",
+            "vosmikovych-3": "Praha 9",
+            "zateckych-14": "Praha 2",
+        }
+        city_str = city_map.get(slug, "Praha")
+        locality_str = f"{project_address}, {city_str}" if project_address else city_str
+
         result = {
             "hash_id": f"cityhome_{slug}_{listing['unit_name']}",
-            "name": f"Prodej bytu {disp} {area} m² — {listing['project_name']}",
+            "name": f"Prodej bytu {disp}, {int(area)} m² — {project_address}",
             "price": price,
             "price_formatted": format_price(price),
-            "locality": f"{listing['project_name']}, Praha",
+            "locality": locality_str,
             "lat": lat,
             "lon": lon,
             "disposition": disp,
             "floor": floor,
-            "area": area,
+            "area": float(area),
             "building_type": "Cihlová",  # CityHome renovuje cihlové domy
             "ownership": "neuvedeno",
             "url": url,
             "source": "cityhome",
             "image": "",
+            "scraped_at": datetime.now().strftime("%Y-%m-%d"),
         }
         results.append(result)
+        properties_fetched += 1
 
-    print(f"\n{'=' * 60}")
+    logger.info(f"\n{'=' * 60}")
-    print(f"Výsledky CityHome:")
+    logger.info(f"Výsledky CityHome:")
-    print(f"  Celkem jednotek:       {len(all_listings)}")
+    logger.info(f"  Celkem jednotek:       {len(all_listings)}")
-    print(f"  Vyloučeno (prodáno):   {excluded_sold}")
+    logger.info(f"  Vyloučeno (prodáno):   {excluded_sold}")
-    print(f"  Vyloučeno (typ):       {excluded_type}")
+    logger.info(f"  Vyloučeno (typ):       {excluded_type}")
-    print(f"  Vyloučeno (dispozice): {excluded_disp}")
+    logger.info(f"  Vyloučeno (dispozice): {excluded_disp}")
-    print(f"  Vyloučeno (cena):      {excluded_price}")
+    logger.info(f"  Vyloučeno (cena):      {excluded_price}")
-    print(f"  Vyloučeno (plocha):    {excluded_area}")
+    logger.info(f"  Vyloučeno (plocha):    {excluded_area}")
-    print(f"  Vyloučeno (patro):     {excluded_floor}")
+    logger.info(f"  Vyloučeno (patro):     {excluded_floor}")
-    print(f"  Vyloučeno (bez GPS):   {excluded_no_gps}")
+    logger.info(f"  Vyloučeno (bez GPS):   {excluded_no_gps}")
-    print(f"  ✓ Vyhovující byty:    {len(results)}")
+    logger.info(f"  ✓ Vyhovující byty:    {len(results)}")
-    print(f"{'=' * 60}")
+    logger.info(f"{'=' * 60}")
 
     return results
 
 
 if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Scrape apartments from CityHome")
+    parser.add_argument("--max-pages", type=int, default=None,
+                        help="Maximum number of listing pages to scrape (not applicable for CityHome)")
+    parser.add_argument("--max-properties", type=int, default=None,
+                        help="Maximum number of properties to include in results")
+    parser.add_argument("--log-level", type=str, default="INFO", choices=["DEBUG", "INFO", "WARNING", "ERROR"],
+                        help="Logging level (default: INFO)")
+    args = parser.parse_args()
+
+    # Configure logging
+    logging.basicConfig(
+        level=getattr(logging, args.log_level),
+        format="[%(levelname)s] %(asctime)s - %(name)s - %(message)s",
+        handlers=[logging.StreamHandler()]
+    )
+
     start = time.time()
-    estates = scrape()
+    estates = scrape(max_pages=args.max_pages, max_properties=args.max_properties)
 
     if estates:
         json_path = Path("byty_cityhome.json")
@@ -322,7 +404,7 @@ if __name__ == "__main__":
             encoding="utf-8",
         )
         elapsed = time.time() - start
-        print(f"\n✓ Data uložena: {json_path.resolve()}")
+        logger.info(f"\n✓ Data uložena: {json_path.resolve()}")
-        print(f"⏱  Celkový čas: {elapsed:.0f} s")
+        logger.info(f"⏱  Celkový čas: {elapsed:.0f} s")
     else:
-        print("\nŽádné byty z CityHome neodpovídají kritériím :(")
+        logger.info("\nŽádné byty z CityHome neodpovídají kritériím :(")

scrape_idnes.py

@@ -6,7 +6,10 @@ Výstup: byty_idnes.json
 """
 from __future__ import annotations
 
+import argparse
+from datetime import datetime
 import json
+import logging
 import math
 import re
 import time
@@ -15,6 +18,8 @@ import urllib.parse
 from html.parser import HTMLParser
 from pathlib import Path
 
+logger = logging.getLogger(__name__)
+
 # ── Konfigurace ─────────────────────────────────────────────────────────────
 
 MAX_PRICE = 13_500_000
@@ -51,17 +56,21 @@ def fetch_url(url: str) -> str:
     """Fetch URL and return HTML string with retry logic."""
     for attempt in range(MAX_RETRIES):
         try:
+            logger.debug(f"HTTP GET request (attempt {attempt + 1}/{MAX_RETRIES}): {url}")
+            logger.debug(f"Headers: {HEADERS}")
             req = urllib.request.Request(url, headers=HEADERS)
             resp = urllib.request.urlopen(req, timeout=30)
             data = resp.read()
+            logger.debug(f"HTTP response: status={resp.status}, size={len(data)} bytes")
             return data.decode("utf-8")
         except (ConnectionResetError, ConnectionError, urllib.error.URLError,
                 OSError) as e:
             if attempt < MAX_RETRIES - 1:
                 wait = (attempt + 1) * 3  # 3, 6, 9, 12s
-                print(f"    Retry {attempt + 1}/{MAX_RETRIES} (wait {wait}s): {e}")
+                logger.warning(f"Connection error (retry {attempt + 1}/{MAX_RETRIES} after {wait}s): {e}")
                 time.sleep(wait)
             else:
+                logger.error(f"HTTP request failed after {MAX_RETRIES} attempts: {e}", exc_info=True)
                 raise
 
 
@@ -269,38 +278,47 @@ def load_cache(json_path: str = "byty_idnes.json") -> dict[str, dict]:
         return {}
 
 
-def scrape():
+def scrape(max_pages: int | None = None, max_properties: int | None = None):
     cache = load_cache()
 
-    print("=" * 60)
+    logger.info("=" * 60)
-    print("Stahuji inzeráty z Reality iDNES")
+    logger.info("Stahuji inzeráty z Reality iDNES")
-    print(f"Cena: do {format_price(MAX_PRICE)}")
+    logger.info(f"Cena: do {format_price(MAX_PRICE)}")
-    print(f"Min. plocha: {MIN_AREA} m²")
+    logger.info(f"Min. plocha: {MIN_AREA} m²")
-    print(f"Patro: od {MIN_FLOOR}. NP")
+    logger.info(f"Patro: od {MIN_FLOOR}. NP")
-    print(f"Region: Praha")
+    logger.info(f"Region: Praha")
     if cache:
-        print(f"Cache: {len(cache)} bytů z minulého běhu")
+        logger.info(f"Cache: {len(cache)} bytů z minulého běhu")
-    print("=" * 60)
+    if max_pages:
+        logger.info(f"Max. stran: {max_pages}")
+    if max_properties:
+        logger.info(f"Max. bytů: {max_properties}")
+    logger.info("=" * 60)
 
     # Step 1: Fetch listing pages
-    print("\nFáze 1: Stahování seznamu inzerátů...")
+    logger.info("\nFáze 1: Stahování seznamu inzerátů...")
     all_listings = {}  # id -> listing dict
     page = 0
     total = None
 
     while True:
+        if max_pages and page >= max_pages:
+            logger.debug(f"Max pages limit reached: {max_pages}")
+            break
         url = build_list_url(page)
-        print(f"  Strana {page + 1} ...")
+        logger.info(f"Strana {page + 1} ...")
         html = fetch_url(url)
 
         if total is None:
             total = parse_total_count(html)
             total_pages = math.ceil(total / PER_PAGE) if total > 0 else 1
-            print(f"  → Celkem {total} inzerátů, ~{total_pages} stran")
+            logger.info(f"→ Celkem {total} inzerátů, ~{total_pages} stran")
 
         listings = parse_listings(html)
+        logger.debug(f"Page {page}: found {len(listings)} listings")
 
         if not listings:
+            logger.debug(f"No listings found on page {page}, stopping")
             break
 
         for item in listings:
@@ -313,7 +331,7 @@ def scrape():
             break
         time.sleep(1.0)
 
-    print(f"\n  Staženo: {len(all_listings)} unikátních inzerátů")
+    logger.info(f"\nStaženo: {len(all_listings)} unikátních inzerátů")
 
     # Step 2: Pre-filter by price and area from list data
     pre_filtered = []
@@ -322,40 +340,49 @@ def scrape():
     excluded_disp = 0
 
     for item in all_listings.values():
+        item_id = item["id"]
         if item["price"] <= 0 or item["price"] > MAX_PRICE:
             excluded_price += 1
+            logger.debug(f"Filter: id={item_id} - excluded (price {item['price']})")
             continue
 
         if item["area"] is not None and item["area"] < MIN_AREA:
             excluded_area += 1
+            logger.debug(f"Filter: id={item_id} - excluded (area {item['area']} m²)")
             continue
 
         if item["disposition"] == "?":
             excluded_disp += 1
+            logger.debug(f"Filter: id={item_id} - excluded (unknown disposition)")
             continue
 
         pre_filtered.append(item)
 
-    print(f"\nPo předfiltraci:")
+    logger.info(f"\nPo předfiltraci:")
-    print(f"  Vyloučeno (cena):      {excluded_price}")
+    logger.info(f"  Vyloučeno (cena):      {excluded_price}")
-    print(f"  Vyloučeno (plocha):    {excluded_area}")
+    logger.info(f"  Vyloučeno (plocha):    {excluded_area}")
-    print(f"  Vyloučeno (dispozice): {excluded_disp}")
+    logger.info(f"  Vyloučeno (dispozice): {excluded_disp}")
-    print(f"  Zbývá:                 {len(pre_filtered)}")
+    logger.info(f"  Zbývá:                 {len(pre_filtered)}")
 
     # Step 3: Fetch details for GPS, floor, construction
-    print(f"\nFáze 2: Stahování detailů ({len(pre_filtered)} bytů)...")
+    logger.info(f"\nFáze 2: Stahování detailů ({len(pre_filtered)} bytů)...")
     results = []
     excluded_panel = 0
     excluded_floor = 0
     excluded_no_gps = 0
     excluded_detail = 0
     cache_hits = 0
+    properties_fetched = 0
 
     for i, item in enumerate(pre_filtered):
+        if max_properties and properties_fetched >= max_properties:
+            logger.debug(f"Max properties limit reached: {max_properties}")
+            break
         # Check cache — if hash_id exists and price unchanged, reuse
         cached = cache.get(str(item["id"]))
         if cached and cached.get("price") == item["price"]:
             cache_hits += 1
+            logger.debug(f"Cache hit for id={item['id']}")
             results.append(cached)
             continue
 
@@ -365,34 +392,39 @@ def scrape():
         try:
             html = fetch_url(url)
         except Exception as e:
-            print(f"    Warning: detail failed for {item['id']}: {e}")
             excluded_detail += 1
+            logger.warning(f"Detail failed for id={item['id']}: {e}")
             continue
 
         detail = parse_detail(html)
+        logger.debug(f"Detail parsed for id={item['id']}: lat={detail.get('lat')}, lon={detail.get('lon')}, floor={detail.get('floor')}")
 
         # Must have GPS
         if not detail.get("lat") or not detail.get("lon"):
             excluded_no_gps += 1
+            logger.debug(f"Filter: id={item['id']} - excluded (no GPS)")
             continue
 
         # Check construction — exclude panel
         construction = detail.get("construction", "")
         if "panel" in construction:
             excluded_panel += 1
-            print(f"  ✗ Vyloučen {item['id'][:12]}...: panel ({construction})")
+            logger.debug(f"Filter: id={item['id']} - excluded (panel construction)")
+            logger.info(f"✗ Vyloučen {item['id'][:12]}...: panel ({construction})")
             continue
 
         # Check for sídliště in construction/description
         if "sídliště" in construction or "sidliste" in construction:
             excluded_panel += 1
-            print(f"  ✗ Vyloučen {item['id'][:12]}...: sídliště")
+            logger.debug(f"Filter: id={item['id']} - excluded (housing estate)")
+            logger.info(f"✗ Vyloučen {item['id'][:12]}...: sídliště")
             continue
 
         # Check floor
         floor = detail.get("floor")
         if floor is not None and floor < MIN_FLOOR:
             excluded_floor += 1
+            logger.debug(f"Filter: id={item['id']} - excluded (floor {floor})")
             continue
 
         # Map construction to Czech label
@@ -427,29 +459,47 @@ def scrape():
             "url": item["url"],
             "source": "idnes",
             "image": "",
+            "scraped_at": datetime.now().strftime("%Y-%m-%d"),
         }
         results.append(result)
+        properties_fetched += 1
 
         if (i + 1) % 20 == 0:
-            print(f"  Zpracováno {i + 1}/{len(pre_filtered)} ...")
+            logger.info(f"Zpracováno {i + 1}/{len(pre_filtered)} ...")
 
-    print(f"\n{'=' * 60}")
+    logger.info(f"\n{'=' * 60}")
-    print(f"Výsledky Reality iDNES:")
+    logger.info(f"Výsledky Reality iDNES:")
-    print(f"  Předfiltrováno:        {len(pre_filtered)}")
+    logger.info(f"  Předfiltrováno:        {len(pre_filtered)}")
-    print(f"  Z cache (přeskočeno): {cache_hits}")
+    logger.info(f"  Z cache (přeskočeno): {cache_hits}")
-    print(f"  Vyloučeno (panel/síd): {excluded_panel}")
+    logger.info(f"  Vyloučeno (panel/síd): {excluded_panel}")
-    print(f"  Vyloučeno (patro):     {excluded_floor}")
+    logger.info(f"  Vyloučeno (patro):     {excluded_floor}")
-    print(f"  Vyloučeno (bez GPS):   {excluded_no_gps}")
+    logger.info(f"  Vyloučeno (bez GPS):   {excluded_no_gps}")
-    print(f"  Vyloučeno (bez detailu): {excluded_detail}")
+    logger.info(f"  Vyloučeno (bez detailu): {excluded_detail}")
-    print(f"  ✓ Vyhovující byty:    {len(results)}")
+    logger.info(f"  ✓ Vyhovující byty:    {len(results)}")
-    print(f"{'=' * 60}")
+    logger.info(f"{'=' * 60}")
 
     return results
 
 
 if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Scrape apartments from Reality iDNES")
+    parser.add_argument("--max-pages", type=int, default=None,
+                        help="Maximum number of listing pages to scrape")
+    parser.add_argument("--max-properties", type=int, default=None,
+                        help="Maximum number of properties to fetch details for")
+    parser.add_argument("--log-level", type=str, default="INFO", choices=["DEBUG", "INFO", "WARNING", "ERROR"],
+                        help="Logging level (default: INFO)")
+    args = parser.parse_args()
+
+    # Configure logging
+    logging.basicConfig(
+        level=getattr(logging, args.log_level),
+        format="[%(levelname)s] %(asctime)s - %(name)s - %(message)s",
+        handlers=[logging.StreamHandler()]
+    )
+
     start = time.time()
-    estates = scrape()
+    estates = scrape(max_pages=args.max_pages, max_properties=args.max_properties)
 
     if estates:
         json_path = Path("byty_idnes.json")
@@ -458,7 +508,7 @@ if __name__ == "__main__":
             encoding="utf-8",
         )
         elapsed = time.time() - start
-        print(f"\n✓ Data uložena: {json_path.resolve()}")
+        logger.info(f"\n✓ Data uložena: {json_path.resolve()}")
-        print(f"⏱  Celkový čas: {elapsed:.0f} s")
+        logger.info(f"⏱  Celkový čas: {elapsed:.0f} s")
     else:
-        print("\nŽádné byty z Reality iDNES neodpovídají kritériím :(")
+        logger.info("\nŽádné byty z Reality iDNES neodpovídají kritériím :(")

scrape_psn.py

@@ -1,16 +1,22 @@
 #!/usr/bin/env python3
 """
 PSN.cz scraper.
-Stáhne byty na prodej v Praze z projektů PSN a vyfiltruje podle kritérií.
+Stáhne byty na prodej z API /api/units-list — jeden požadavek, žádné stránkování.
 Výstup: byty_psn.json
 """
 from __future__ import annotations
 
+import argparse
 import json
+import logging
 import re
 import subprocess
 import time
+from datetime import datetime
 from pathlib import Path
+from urllib.parse import urlencode
+
+logger = logging.getLogger(__name__)
 
 # ── Konfigurace ─────────────────────────────────────────────────────────────
 
@@ -18,78 +24,37 @@ MAX_PRICE = 14_000_000
 MIN_AREA = 69
 MIN_FLOOR = 2
 
-WANTED_DISPOSITIONS = {"3+kk", "3+1", "4+kk", "4+1", "5+kk", "5+1", "6+kk", "6+1"}
+WANTED_DISPOSITIONS = {"3+kk", "3+1", "4+kk", "4+1", "5+kk", "5+1", "6+kk", "6+1", "5+kk a větší"}
+
+# Pouze Praha — ostatní města (Brno, Pardubice, Špindlerův Mlýn) přeskočit
+WANTED_CITIES = {"Praha"}
 
 UA = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
 
 BASE_URL = "https://psn.cz"
-
+UNITS_API = f"{BASE_URL}/api/units-list"
-# Known Prague project slugs with GPS (from research)
-PRAGUE_PROJECTS = [
-    {"slug": "zit-branik", "name": "Žít Braník", "lat": 50.0353, "lon": 14.4125},
-    {"slug": "rostislavova-4", "name": "Rostislavova 4", "lat": 50.0620, "lon": 14.4463},
-    {"slug": "pod-drinopolem", "name": "Pod Drinopolem", "lat": 50.0851, "lon": 14.3720},
-    {"slug": "skyline-chodov", "name": "Skyline Chodov", "lat": 50.0418, "lon": 14.4990},
-    {"slug": "jitro", "name": "Jitro", "lat": 50.0729, "lon": 14.4768},
-    {"slug": "maroldka", "name": "Maroldka", "lat": 50.0614, "lon": 14.4517},
-    {"slug": "belehradska-29", "name": "Bělehradská 29", "lat": 50.0682, "lon": 14.4348},
-    {"slug": "jeseniova-93", "name": "Jeseniova 93", "lat": 50.0887, "lon": 14.4692},
-    {"slug": "vanguard", "name": "Vanguard", "lat": 50.0164, "lon": 14.4036},
-    {"slug": "vinohradska-160", "name": "Vinohradská 160", "lat": 50.0780, "lon": 14.4653},
-    {"slug": "hermanova24", "name": "Heřmanova 24", "lat": 50.1009, "lon": 14.4313},
-    {"slug": "vinohradska-8", "name": "Vinohradská 8", "lat": 50.0787, "lon": 14.4342},
-    {"slug": "bydleni-na-vysinach", "name": "Bydlení Na Výšinách", "lat": 50.1003, "lon": 14.4187},
-    {"slug": "bydleni-u-pekaren", "name": "Bydlení U Pekáren", "lat": 50.0555, "lon": 14.5414},
-    {"slug": "pechackova-6", "name": "Pechackova 6", "lat": 50.0734, "lon": 14.4063},
-    {"slug": "ahoj-vanguard", "name": "Ahoj Vanguard", "lat": 50.0164, "lon": 14.4033},
-]
 
 
-def fetch_url(url: str) -> str:
+def fetch_json(url: str) -> dict:
-    """Fetch URL via curl (urllib SSL too old for Cloudflare)."""
+    """Fetch JSON via curl (urllib SSL may fail on Cloudflare)."""
+    logger.debug(f"HTTP GET: {url}")
     result = subprocess.run(
         ["curl", "-s", "-L", "--max-time", "30",
          "-H", f"User-Agent: {UA}",
-         "-H", "Accept: text/html",
+         "-H", "Accept: application/json",
          url],
         capture_output=True, text=True, timeout=60
     )
     if result.returncode != 0:
         raise RuntimeError(f"curl failed ({result.returncode}): {result.stderr[:200]}")
-    return result.stdout
+    return json.loads(result.stdout)
 
 
-def extract_units_from_html(html: str) -> list[dict]:
+def fix_gps(lat, lng):
-    """Extract unit JSON objects from raw HTML with escaped quotes."""
+    """PSN má u některých projektů prohozené lat/lng — opravíme."""
-    # The HTML contains RSC data with escaped JSON: \\"key\\":\\"value\\"
+    if lat is not None and lng is not None and lat < 20 and lng > 20:
-    # Step 1: Unescape the double-backslash-quotes to regular quotes
+        return lng, lat
-    cleaned = html.replace('\\"', '"')
+    return lat, lng
-
-    # Step 2: Find each unit by looking for "title":"Byt and walking back to {
-    units = []
-    decoder = json.JSONDecoder()
-
-    for m in re.finditer(r'"title":"Byt', cleaned):
-        pos = m.start()
-        # Walk backwards to find the opening brace
-        depth = 0
-        found = False
-        for i in range(pos - 1, max(pos - 3000, 0), -1):
-            if cleaned[i] == '}':
-                depth += 1
-            elif cleaned[i] == '{':
-                if depth == 0:
-                    try:
-                        obj, end = decoder.raw_decode(cleaned, i)
-                        if isinstance(obj, dict) and 'price_czk' in obj:
-                            units.append(obj)
-                            found = True
-                    except (json.JSONDecodeError, ValueError):
-                        pass
-                    break
-                depth -= 1
-
-    return units
 
 
 def format_price(price: int) -> str:
@@ -101,197 +66,203 @@ def format_price(price: int) -> str:
     return " ".join(reversed(parts)) + " Kč"
 
 
-def scrape():
+def scrape(max_properties: int | None = None):
-    print("=" * 60)
+    logger.info("=" * 60)
-    print("Stahuji inzeráty z PSN.cz")
+    logger.info("Stahuji inzeráty z PSN.cz")
-    print(f"Cena: do {format_price(MAX_PRICE)}")
+    logger.info(f"Cena: do {format_price(MAX_PRICE)}")
-    print(f"Min. plocha: {MIN_AREA} m²")
+    logger.info(f"Min. plocha: {MIN_AREA} m²")
-    print(f"Patro: od {MIN_FLOOR}. NP")
+    logger.info(f"Patro: od {MIN_FLOOR}. NP")
-    print(f"Region: Praha ({len(PRAGUE_PROJECTS)} projektů)")
+    logger.info(f"Region: Praha")
-    print("=" * 60)
+    if max_properties:
+        logger.info(f"Max. bytů: {max_properties}")
+    logger.info("=" * 60)
 
-    # Fetch units from each Prague project
+    # Jediný API požadavek — vrátí všechny jednotky (cca 236)
-    all_units = []
+    params = urlencode({
+        "locale": "cs",
+        "filters": "{}",
+        "type": "list",
+        "order": "price-asc",
+        "offset": 0,
+        "limit": 500,
+    })
+    url = f"{UNITS_API}?{params}"
+    logger.info("Stahuji jednotky z API ...")
 
-    for proj in PRAGUE_PROJECTS:
+    try:
-        page = 1
+        data = fetch_json(url)
-        project_units = []
+    except Exception as e:
+        logger.error(f"Chyba při stahování: {e}", exc_info=True)
+        return []
 
-        while True:
+    all_units = data.get("units", {}).get("data", [])
-            url = f"{BASE_URL}/projekt/{proj['slug']}?page={page}"
+    logger.info(f"Staženo jednotek celkem: {len(all_units)}")
-            print(f"  {proj['name']} — strana {page} ...")
-            time.sleep(0.5)
 
-            try:
+    # Filtrování
-                html = fetch_url(url)
-            except Exception as e:
-                print(f"    Chyba: {e}")
-                break
-
-            units = extract_units_from_html(html)
-
-            if not units:
-                if page == 1:
-                    print(f"    → 0 jednotek")
-                break
-
-            # Add project info to each unit
-            for unit in units:
-                if not unit.get("latitude") or not unit.get("longitude"):
-                    unit["latitude"] = proj["lat"]
-                    unit["longitude"] = proj["lon"]
-                unit["_project_name"] = proj["name"]
-                unit["_project_slug"] = proj["slug"]
-
-            project_units.extend(units)
-
-            if page == 1:
-                print(f"    → {len(units)} jednotek na stránce")
-
-            # Check if there might be more pages
-            # If we got fewer than expected or same units, stop
-            if len(units) < 10:
-                break
-
-            page += 1
-            if page > 10:  # Safety limit
-                break
-
-        all_units.extend(project_units)
-
-    # Deduplicate by slug
-    seen_slugs = set()
-    unique_units = []
-    for u in all_units:
-        slug = u.get("slug", "")
-        if slug and slug not in seen_slugs:
-            seen_slugs.add(slug)
-            unique_units.append(u)
-        elif not slug:
-            unique_units.append(u)
-
-    print(f"\n  Staženo celkem: {len(unique_units)} unikátních jednotek")
-
-    # Filter
-    print(f"\nFiltrování...")
     results = []
-    excluded_sold = 0
+    excluded = {
-    excluded_type = 0
+        "prodáno": 0,
-    excluded_disp = 0
+        "typ": 0,
-    excluded_price = 0
+        "město": 0,
-    excluded_area = 0
+        "dispozice": 0,
-    excluded_floor = 0
+        "cena": 0,
-    excluded_panel = 0
+        "plocha": 0,
+        "patro": 0,
+    }
+    properties_fetched = 0
 
-    for unit in unique_units:
+    for unit in all_units:
-        # Only free units
+        if max_properties and properties_fetched >= max_properties:
+            break
+
+        unit_id = unit.get("id", "?")
+
+        # Pouze prodej bytů (type_id=0)
+        if unit.get("type_id") != 0:
+            excluded["typ"] += 1
+            logger.debug(f"id={unit_id}: přeskočen (type_id={unit.get('type_id')}, není prodej bytu)")
+            continue
+
+        # Pouze volné (ne rezervované, prodané, v přípravě)
+        sale_status = unit.get("sale_status", "")
         is_free = unit.get("is_free", False)
         is_sold = unit.get("is_sold", False)
         if is_sold or not is_free:
-            excluded_sold += 1
+            excluded["prodáno"] += 1
+            logger.debug(f"id={unit_id}: přeskočen (status={sale_status})")
             continue
 
-        # Only apartments
+        # Pouze Praha
-        category = str(unit.get("category", "")).lower()
+        city = (unit.get("location") or unit.get("address", {}).get("city") or "").strip()
-        if "byt" not in category and "ateliér" not in category:
+        # location field je typicky "Praha 4", "Praha 7" atd.
-            excluded_type += 1
+        city_base = city.split(" ")[0] if city else ""
+        if city_base not in WANTED_CITIES:
+            excluded["město"] += 1
+            logger.debug(f"id={unit_id}: přeskočen (město={city})")
             continue
 
-        # Disposition
+        # Dispozice
         disp = unit.get("disposition", "")
         if disp not in WANTED_DISPOSITIONS:
-            excluded_disp += 1
+            excluded["dispozice"] += 1
+            logger.debug(f"id={unit_id}: přeskočen (dispozice={disp})")
             continue
 
-        # Price
+        # Cena
-        price = unit.get("price_czk") or unit.get("action_price_czk") or 0
+        price = unit.get("action_price_czk") or unit.get("price_czk") or 0
-        if price <= 0 or price > MAX_PRICE:
+        if not price or price <= 0 or price > MAX_PRICE:
-            excluded_price += 1
+            excluded["cena"] += 1
+            logger.debug(f"id={unit_id}: přeskočen (cena={price})")
             continue
 
-        # Area
+        # Plocha
         area = unit.get("total_area") or unit.get("floor_area") or 0
         if area < MIN_AREA:
-            excluded_area += 1
+            excluded["plocha"] += 1
+            logger.debug(f"id={unit_id}: přeskočen (plocha={area} m²)")
             continue
 
-        # Floor
+        # Patro
         floor_str = str(unit.get("floor", ""))
         floor = None
         if floor_str:
             try:
                 floor = int(floor_str)
             except ValueError:
-                floor_match = re.search(r'(-?\d+)', floor_str)
+                m = re.search(r'(-?\d+)', floor_str)
-                if floor_match:
+                if m:
-                    floor = int(floor_match.group(1))
+                    floor = int(m.group(1))
 
         if floor is not None and floor < MIN_FLOOR:
-            excluded_floor += 1
+            excluded["patro"] += 1
+            logger.debug(f"id={unit_id}: přeskočen (patro={floor})")
             continue
 
-        # Construction — check for panel
+        # GPS — opravit prohozené souřadnice
-        build_type = str(unit.get("build_type", "")).lower()
+        lat_raw = unit.get("latitude")
-        if "panel" in build_type:
+        lng_raw = unit.get("longitude")
-            excluded_panel += 1
+        lat, lng = fix_gps(lat_raw, lng_raw)
-            print(f"  ✗ Vyloučen: panel ({build_type})")
+        if not lat or not lng:
+            logger.warning(f"id={unit_id}: chybí GPS souřadnice, přeskakuji")
             continue
 
-        # Build construction label
+        # Sestavit adresu pro locality
-        building_type = "neuvedeno"
+        addr = unit.get("address") or {}
-        if build_type and build_type != "nevybráno":
+        street = addr.get("street", "")
-            if "cihlo" in build_type or "cihla" in build_type:
+        street_no = addr.get("street_no", "")
-                building_type = "Cihlová"
+        if street and street_no:
-            elif "skelet" in build_type:
+            locality_str = f"{street} {street_no}, {city}"
-                building_type = "Skeletová"
+        elif street:
-            else:
+            locality_str = f"{street}, {city}"
-                building_type = build_type.capitalize()
+        else:
+            project_name = unit.get("project", "")
+            locality_str = f"{project_name}, {city}" if project_name else city
 
-        lat = unit.get("latitude", 0)
+        # URL na detail jednotky
-        lon = unit.get("longitude", 0)
+        unit_slug = unit.get("slug", "")
-
+        project_slug = ""
-        slug = unit.get("slug", "")
+        # project_slug lze odvodit z projektu nebo z reference_no
-        project_slug = unit.get("_project_slug", "")
+        # API nevrací project_slug přímo — použijeme reference_no nebo jen ID
-        detail_url = f"{BASE_URL}/projekt/{project_slug}/{slug}" if slug else f"{BASE_URL}/projekt/{project_slug}"
+        reference_no = unit.get("reference_no", "")
+        if unit_slug:
+            detail_url = f"{BASE_URL}/prodej/{unit_slug}"
+        elif reference_no:
+            detail_url = f"{BASE_URL}/prodej/{reference_no}"
+        else:
+            detail_url = BASE_URL
 
         result = {
-            "hash_id": unit.get("id", slug),
+            "hash_id": str(unit_id),
-            "name": f"Prodej bytu {disp} {area} m² — {unit.get('_project_name', '')}",
+            "name": f"Prodej bytu {disp}, {int(area)} m² — {unit.get('project', locality_str)}",
             "price": int(price),
             "price_formatted": format_price(int(price)),
-            "locality": f"{unit.get('street', unit.get('_project_name', ''))}, Praha",
+            "locality": locality_str,
             "lat": lat,
-            "lon": lon,
+            "lon": lng,
             "disposition": disp,
             "floor": floor,
-            "area": area,
+            "area": float(area),
-            "building_type": building_type,
+            "building_type": "neuvedeno",
-            "ownership": unit.get("ownership", "neuvedeno") or "neuvedeno",
+            "ownership": "osobní",
             "url": detail_url,
             "source": "psn",
             "image": "",
+            "scraped_at": datetime.now().strftime("%Y-%m-%d"),
         }
         results.append(result)
+        properties_fetched += 1
 
-    print(f"\n{'=' * 60}")
+    logger.info(f"\n{'=' * 60}")
-    print(f"Výsledky PSN:")
+    logger.info(f"Výsledky PSN:")
-    print(f"  Celkem jednotek:       {len(unique_units)}")
+    logger.info(f"  Staženo inzerátů:      {len(all_units)}")
-    print(f"  Vyloučeno (prodáno):   {excluded_sold}")
+    for reason, count in excluded.items():
-    print(f"  Vyloučeno (typ):       {excluded_type}")
+        if count:
-    print(f"  Vyloučeno (dispozice): {excluded_disp}")
+            logger.info(f"  Vyloučeno ({reason}): {count}")
-    print(f"  Vyloučeno (cena):      {excluded_price}")
+    logger.info(f"  ✓ Vyhovující byty:    {len(results)}")
-    print(f"  Vyloučeno (plocha):    {excluded_area}")
+    logger.info(f"{'=' * 60}")
-    print(f"  Vyloučeno (patro):     {excluded_floor}")
-    print(f"  Vyloučeno (panel):     {excluded_panel}")
-    print(f"  ✓ Vyhovující byty:    {len(results)}")
-    print(f"{'=' * 60}")
 
     return results
 
 
 if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Scrape apartments from PSN.cz")
+    parser.add_argument("--max-pages", type=int, default=None,
+                        help="Ignored — PSN uses a single API call, no pagination")
+    parser.add_argument("--max-properties", type=int, default=None,
+                        help="Maximum number of properties to include in results")
+    parser.add_argument("--log-level", type=str, default="INFO",
+                        choices=["DEBUG", "INFO", "WARNING", "ERROR"],
+                        help="Logging level (default: INFO)")
+    args = parser.parse_args()
+
+    logging.basicConfig(
+        level=getattr(logging, args.log_level),
+        format="[%(levelname)s] %(asctime)s - %(name)s - %(message)s",
+        handlers=[logging.StreamHandler()]
+    )
+
     start = time.time()
-    estates = scrape()
+    estates = scrape(max_properties=args.max_properties)
 
     if estates:
         json_path = Path("byty_psn.json")
@@ -300,7 +271,7 @@ if __name__ == "__main__":
             encoding="utf-8",
         )
         elapsed = time.time() - start
-        print(f"\n✓ Data uložena: {json_path.resolve()}")
+        logger.info(f"\n✓ Data uložena: {json_path.resolve()}")
-        print(f"⏱  Celkový čas: {elapsed:.0f} s")
+        logger.info(f"⏱  Celkový čas: {elapsed:.1f} s")
     else:
-        print("\nŽádné byty z PSN neodpovídají kritériím :(")
+        logger.info("\nŽádné byty z PSN neodpovídají kritériím :(")

scrape_realingo.py

@@ -6,13 +6,18 @@ Výstup: byty_realingo.json
 """
 from __future__ import annotations
 
+import argparse
+from datetime import datetime
 import json
+import logging
 import math
 import re
 import time
 import urllib.request
 from pathlib import Path
 
+logger = logging.getLogger(__name__)
+
 # ── Konfigurace (sdílená se Sreality scraperem) ─────────────────────────────
 
 MAX_PRICE = 13_500_000
@@ -55,44 +60,57 @@ 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}")
+    logger.debug(f"Headers: {HEADERS}")
     req = urllib.request.Request(url, headers=HEADERS)
-    resp = urllib.request.urlopen(req, timeout=30)
-    html = resp.read().decode("utf-8")
-
-    match = re.search(
-        r'<script id="__NEXT_DATA__" type="application/json">(.*?)</script>',
-        html, re.DOTALL
-    )
-    if not match:
-        return [], 0
-
-    data = json.loads(match.group(1))
-    offer_list = data["props"]["pageProps"]["store"]["offer"]["list"]
-    return offer_list["data"], offer_list["total"]
-
-
-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}"
-        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
         )
         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}")
+        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
+        )
+        if not match:
+            logger.debug("No __NEXT_DATA__ script found in detail page")
             return None
 
         data = json.loads(match.group(1))
         details = data["props"]["pageProps"]["store"]["offer"]["details"]
         # Get first (only) detail entry
         for detail_data in details.values():
+            logger.debug(f"Detail fetched for {listing_url}")
             return detail_data
     except Exception as e:
-        print(f"    Warning: detail fetch failed for {listing_url}: {e}")
+        logger.warning(f"Detail fetch failed for {listing_url}: {e}", exc_info=True)
     return None
 
 
@@ -117,34 +135,42 @@ def load_cache(json_path: str = "byty_realingo.json") -> dict[int, dict]:
         return {}
 
 
-def scrape():
+def scrape(max_pages: int | None = None, max_properties: int | None = None):
     cache = load_cache()
 
-    print("=" * 60)
+    logger.info("=" * 60)
-    print("Stahuji inzeráty z Realingo.cz")
+    logger.info("Stahuji inzeráty z Realingo.cz")
-    print(f"Cena: do {format_price(MAX_PRICE)}")
+    logger.info(f"Cena: do {format_price(MAX_PRICE)}")
-    print(f"Min. plocha: {MIN_AREA} m²")
+    logger.info(f"Min. plocha: {MIN_AREA} m²")
-    print(f"Patro: od {MIN_FLOOR}. NP")
+    logger.info(f"Patro: od {MIN_FLOOR}. NP")
-    print(f"Region: Praha")
+    logger.info(f"Region: Praha")
     if cache:
-        print(f"Cache: {len(cache)} bytů z minulého běhu")
+        logger.info(f"Cache: {len(cache)} bytů z minulého běhu")
-    print("=" * 60)
+    if max_pages:
+        logger.info(f"Max. stran: {max_pages}")
+    if max_properties:
+        logger.info(f"Max. bytů: {max_properties}")
+    logger.info("=" * 60)
 
     # Step 1: Fetch all listing pages
-    print("\nFáze 1: Stahování seznamu inzerátů...")
+    logger.info("\nFáze 1: Stahování seznamu inzerátů...")
     all_listings = []
     page = 1
     total = None
 
     while True:
-        print(f"  Strana {page} ...")
+        if max_pages and page > max_pages:
+            logger.debug(f"Max pages limit reached: {max_pages}")
+            break
+        logger.info(f"Strana {page} ...")
         items, total_count = fetch_listing_page(page)
         if total is None:
             total = total_count
             total_pages = math.ceil(total / PER_PAGE)
-            print(f"  → Celkem {total} inzerátů, {total_pages} stran")
+            logger.info(f"→ Celkem {total} inzerátů, {total_pages} stran")
 
         if not items:
+            logger.debug(f"No items found on page {page}, stopping")
             break
 
         all_listings.extend(items)
@@ -153,7 +179,7 @@ def scrape():
             break
         time.sleep(0.5)
 
-    print(f"\n  Staženo: {len(all_listings)} inzerátů")
+    logger.info(f"\nStaženo: {len(all_listings)} inzerátů")
 
     # Step 2: Pre-filter by category, price, area from listing data
     pre_filtered = []
@@ -163,50 +189,60 @@ def scrape():
     excluded_no_gps = 0
 
     for item in all_listings:
+        item_id = item.get("id")
         cat = item.get("category", "")
         if cat not in WANTED_CATEGORIES:
             excluded_category += 1
+            logger.debug(f"Filter: id={item_id} - excluded (category {cat})")
             continue
 
         price = item.get("price", {}).get("total", 0) or 0
         if price > MAX_PRICE or price == 0:
             excluded_price += 1
+            logger.debug(f"Filter: id={item_id} - excluded (price {price})")
             continue
 
         area = item.get("area", {}).get("main")
         if area is not None and area < MIN_AREA:
             excluded_area += 1
+            logger.debug(f"Filter: id={item_id} - excluded (area {area} m²)")
             continue
 
         loc = item.get("location", {})
         if not loc.get("latitude") or not loc.get("longitude"):
             excluded_no_gps += 1
+            logger.debug(f"Filter: id={item_id} - excluded (no GPS)")
             continue
 
         pre_filtered.append(item)
 
-    print(f"\nPo předfiltraci:")
+    logger.info(f"\nPo předfiltraci:")
-    print(f"  Vyloučeno (dispozice): {excluded_category}")
+    logger.info(f"  Vyloučeno (dispozice): {excluded_category}")
-    print(f"  Vyloučeno (cena):      {excluded_price}")
+    logger.info(f"  Vyloučeno (cena):      {excluded_price}")
-    print(f"  Vyloučeno (plocha):    {excluded_area}")
+    logger.info(f"  Vyloučeno (plocha):    {excluded_area}")
-    print(f"  Vyloučeno (bez GPS):   {excluded_no_gps}")
+    logger.info(f"  Vyloučeno (bez GPS):   {excluded_no_gps}")
-    print(f"  Zbývá:                 {len(pre_filtered)}")
+    logger.info(f"  Zbývá:                 {len(pre_filtered)}")
 
     # Step 3: Fetch details for remaining listings (floor, building type)
-    print(f"\nFáze 2: Stahování detailů ({len(pre_filtered)} bytů)...")
+    logger.info(f"\nFáze 2: Stahování detailů ({len(pre_filtered)} bytů)...")
     results = []
     excluded_panel = 0
     excluded_floor = 0
     excluded_detail = 0
     cache_hits = 0
+    properties_fetched = 0
 
     for i, item in enumerate(pre_filtered):
+        if max_properties and properties_fetched >= max_properties:
+            logger.debug(f"Max properties limit reached: {max_properties}")
+            break
         # Check cache — if hash_id exists and price unchanged, reuse
         item_id = int(item["id"])
         item_price = item.get("price", {}).get("total", 0) or 0
         cached = cache.get(item_id)
         if cached and cached.get("price") == item_price:
             cache_hits += 1
+            logger.debug(f"Cache hit for id={item_id}")
             results.append(cached)
             continue
 
@@ -215,6 +251,7 @@ def scrape():
 
         if not detail_data:
             excluded_detail += 1
+            logger.debug(f"Filter: id={item_id} - excluded (detail fetch failed)")
             continue
 
         detail = detail_data.get("offer", {}).get("detail", {})
@@ -225,20 +262,23 @@ def scrape():
         building_type = detail.get("buildingType", "")
         if building_type == "PANEL":
             excluded_panel += 1
-            print(f"  ✗ Vyloučen #{item['id']}: panel")
+            logger.debug(f"Filter: id={item['id']} - excluded (panel construction)")
+            logger.info(f"✗ Vyloučen #{item['id']}: panel")
             continue
 
         # Check building position — exclude sídliště
         building_position = detail.get("buildingPosition", "")
         if building_position and "ESTATE" in str(building_position).upper():
             excluded_panel += 1
-            print(f"  ✗ Vyloučen #{item['id']}: sídliště")
+            logger.debug(f"Filter: id={item['id']} - excluded (building estate)")
+            logger.info(f"✗ Vyloučen #{item['id']}: sídliště")
             continue
 
         # Check floor
         floor = detail.get("floor")
         if floor is not None and floor < MIN_FLOOR:
             excluded_floor += 1
+            logger.debug(f"Filter: id={item_id} - excluded (floor {floor})")
             continue
 
         # Map building type
@@ -275,28 +315,46 @@ def scrape():
             "url": f"{BASE_URL}{item['url']}",
             "source": "realingo",
             "image": "",
+            "scraped_at": datetime.now().strftime("%Y-%m-%d"),
         }
         results.append(result)
+        properties_fetched += 1
 
         if (i + 1) % 20 == 0:
-            print(f"  Zpracováno {i + 1}/{len(pre_filtered)} ...")
+            logger.info(f"Zpracováno {i + 1}/{len(pre_filtered)} ...")
 
-    print(f"\n{'=' * 60}")
+    logger.info(f"\n{'=' * 60}")
-    print(f"Výsledky Realingo:")
+    logger.info(f"Výsledky Realingo:")
-    print(f"  Předfiltrováno:        {len(pre_filtered)}")
+    logger.info(f"  Předfiltrováno:        {len(pre_filtered)}")
-    print(f"  Z cache (přeskočeno): {cache_hits}")
+    logger.info(f"  Z cache (přeskočeno): {cache_hits}")
-    print(f"  Vyloučeno (panel/síd): {excluded_panel}")
+    logger.info(f"  Vyloučeno (panel/síd): {excluded_panel}")
-    print(f"  Vyloučeno (patro):     {excluded_floor}")
+    logger.info(f"  Vyloučeno (patro):     {excluded_floor}")
-    print(f"  Vyloučeno (bez detailu): {excluded_detail}")
+    logger.info(f"  Vyloučeno (bez detailu): {excluded_detail}")
-    print(f"  ✓ Vyhovující byty:    {len(results)}")
+    logger.info(f"  ✓ Vyhovující byty:    {len(results)}")
-    print(f"{'=' * 60}")
+    logger.info(f"{'=' * 60}")
 
     return results
 
 
 if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Scrape apartments from Realingo.cz")
+    parser.add_argument("--max-pages", type=int, default=None,
+                        help="Maximum number of listing pages to scrape")
+    parser.add_argument("--max-properties", type=int, default=None,
+                        help="Maximum number of properties to fetch details for")
+    parser.add_argument("--log-level", type=str, default="INFO", choices=["DEBUG", "INFO", "WARNING", "ERROR"],
+                        help="Logging level (default: INFO)")
+    args = parser.parse_args()
+
+    # Configure logging
+    logging.basicConfig(
+        level=getattr(logging, args.log_level),
+        format="[%(levelname)s] %(asctime)s - %(name)s - %(message)s",
+        handlers=[logging.StreamHandler()]
+    )
+
     start = time.time()
-    estates = scrape()
+    estates = scrape(max_pages=args.max_pages, max_properties=args.max_properties)
 
     if estates:
         json_path = Path("byty_realingo.json")
@@ -305,7 +363,7 @@ if __name__ == "__main__":
             encoding="utf-8",
         )
         elapsed = time.time() - start
-        print(f"\n✓ Data uložena: {json_path.resolve()}")
+        logger.info(f"\n✓ Data uložena: {json_path.resolve()}")
-        print(f"⏱  Celkový čas: {elapsed:.0f} s")
+        logger.info(f"⏱  Celkový čas: {elapsed:.0f} s")
     else:
-        print("\nŽádné byty z Realinga neodpovídají kritériím :(")
+        logger.info("\nŽádné byty z Realinga neodpovídají kritériím :(")

server.py

@@ -0,0 +1,119 @@
+#!/usr/bin/env python3
+"""
+Combined HTTP server: serves static files from DATA_DIR and
+provides the ratings API at /api/ratings.
+
+GET  /api/ratings        → returns ratings.json contents
+POST /api/ratings        → saves entire ratings object
+GET  /api/ratings/export → same as GET, with Content-Disposition: attachment
+GET  /<path>             → serves static file from DATA_DIR
+"""
+
+import argparse
+import json
+import logging
+import os
+import sys
+from pathlib import Path
+
+from flask import Flask, jsonify, request, send_from_directory
+
+parser = argparse.ArgumentParser(description="Flat-search map server")
+parser.add_argument("--log-level", "-l", default=None, choices=["DEBUG", "INFO", "WARNING", "ERROR"], help="Log level (default: INFO)")
+parser.add_argument("--verbose", "-v", action="store_true", help="Shorthand for --log-level DEBUG")
+args = parser.parse_args()
+
+log_level = logging.DEBUG if args.verbose else getattr(logging, args.log_level or "INFO")
+
+PORT = int(os.environ.get("PORT", 8080))
+DATA_DIR = Path(os.environ.get("DATA_DIR", ".")).resolve()
+RATINGS_FILE = DATA_DIR / "ratings.json"
+
+logging.basicConfig(
+    level=log_level,
+    format="%(asctime)s [server] %(levelname)s %(message)s",
+    datefmt="%Y-%m-%dT%H:%M:%S",
+)
+log = logging.getLogger(__name__)
+
+app = Flask(__name__, static_folder=None)
+app.json.ensure_ascii = False
+
+
+@app.after_request
+def add_cors(response):
+    response.headers["Access-Control-Allow-Origin"] = "*"
+    response.headers["Access-Control-Allow-Methods"] = "GET, POST, OPTIONS"
+    response.headers["Access-Control-Allow-Headers"] = "Content-Type"
+    return response
+
+
+def load_ratings() -> dict:
+    try:
+        if RATINGS_FILE.exists():
+            return json.loads(RATINGS_FILE.read_text(encoding="utf-8"))
+    except Exception as e:
+        log.error("Failed to load ratings: %s", e)
+    return {}
+
+
+def save_ratings(data: dict) -> None:
+    RATINGS_FILE.write_text(
+        json.dumps(data, ensure_ascii=False, indent=2),
+        encoding="utf-8",
+    )
+
+
+@app.route("/api/ratings", methods=["OPTIONS"])
+@app.route("/api/ratings/export", methods=["OPTIONS"])
+def ratings_options():
+    return ("", 204)
+
+
+@app.route("/api/ratings", methods=["GET"])
+def get_ratings():
+    ratings = load_ratings()
+    log.info("GET /api/ratings → %d ratings", len(ratings))
+    return jsonify(ratings)
+
+
+@app.route("/api/ratings/export", methods=["GET"])
+def export_ratings():
+    ratings = load_ratings()
+    log.info("GET /api/ratings/export → %d ratings", len(ratings))
+    response = jsonify(ratings)
+    response.headers["Content-Disposition"] = 'attachment; filename="ratings.json"'
+    return response
+
+
+@app.route("/api/ratings", methods=["POST"])
+def post_ratings():
+    length = request.content_length
+    if not length:
+        return jsonify({"error": "empty body"}), 400
+    try:
+        data = request.get_json(force=True, silent=False)
+    except Exception as e:
+        log.warning("Bad request body: %s", e)
+        return jsonify({"error": "invalid JSON"}), 400
+    if not isinstance(data, dict):
+        return jsonify({"error": "expected JSON object"}), 400
+    save_ratings(data)
+    log.info("POST /api/ratings → saved %d ratings", len(data))
+    return jsonify({"ok": True, "count": len(data)})
+
+
+@app.route("/")
+def index():
+    return send_from_directory(str(DATA_DIR), "mapa_bytu.html")
+
+
+@app.route("/<path:filename>")
+def static_files(filename):
+    return send_from_directory(str(DATA_DIR), filename)
+
+
+if __name__ == "__main__":
+    log.info("Server starting on port %d, data dir: %s", PORT, DATA_DIR)
+    log.info("Ratings file: %s", RATINGS_FILE)
+    app.run(host="0.0.0.0", port=PORT)

status.html

@@ -0,0 +1,204 @@
+<!DOCTYPE html>
+<html lang="cs">
+<head>
+<meta charset="UTF-8">
+<meta name="viewport" content="width=device-width, initial-scale=1.0">
+<title>Scraper status</title>
+<style>
+  * { margin: 0; padding: 0; box-sizing: border-box; }
+  body {
+    font-family: system-ui, -apple-system, sans-serif;
+    background: #f5f5f5; color: #333;
+    padding: 24px; max-width: 640px; margin: 0 auto;
+  }
+  h1 { font-size: 22px; margin-bottom: 4px; }
+  .subtitle { color: #888; font-size: 13px; margin-bottom: 24px; }
+  .card {
+    background: white; border-radius: 12px; padding: 20px;
+    box-shadow: 0 1px 4px rgba(0,0,0,0.08); margin-bottom: 16px;
+  }
+  .card h2 { font-size: 15px; margin-bottom: 12px; color: #555; }
+  .timestamp {
+    font-size: 28px; font-weight: 700; color: #1976D2;
+  }
+  .timestamp-ago { font-size: 13px; color: #999; margin-top: 2px; }
+
+  /* Source table */
+  .source-table { width: 100%; border-collapse: collapse; }
+  .source-table td { padding: 8px 0; border-bottom: 1px solid #f0f0f0; font-size: 14px; }
+  .source-table tr:last-child td { border-bottom: none; }
+  .source-table .name { font-weight: 600; }
+  .source-table .count { text-align: right; font-variant-numeric: tabular-nums; }
+  .source-table .rejected { text-align: right; color: #999; font-size: 12px; }
+  .badge {
+    display: inline-block; padding: 2px 8px; border-radius: 4px;
+    font-size: 11px; font-weight: 600; color: white;
+  }
+  .badge-ok { background: #4CAF50; }
+  .badge-err { background: #F44336; }
+  .badge-skip { background: #FF9800; }
+
+  /* Summary bar */
+  .summary-row {
+    display: flex; justify-content: space-between; align-items: center;
+    padding: 10px 0; border-bottom: 1px solid #f0f0f0;
+  }
+  .summary-row:last-child { border-bottom: none; }
+  .summary-label { font-size: 13px; color: #666; }
+  .summary-value { font-size: 18px; font-weight: 700; }
+
+  /* Source bar chart */
+  .bar-row { display: flex; align-items: center; gap: 8px; margin: 4px 0; }
+  .bar-label { width: 90px; font-size: 12px; text-align: right; color: #666; }
+  .bar-track { flex: 1; height: 20px; background: #f0f0f0; border-radius: 4px; overflow: hidden; position: relative; }
+  .bar-fill { height: 100%; border-radius: 4px; transition: width 0.5s ease; }
+  .bar-count { font-size: 12px; width: 36px; font-variant-numeric: tabular-nums; }
+
+  /* Loader */
+  .loader-wrap {
+    display: flex; flex-direction: column; align-items: center;
+    justify-content: center; padding: 60px 0;
+  }
+  .spinner {
+    width: 40px; height: 40px; border: 4px solid #e0e0e0;
+    border-top-color: #1976D2; border-radius: 50%;
+    animation: spin 0.8s linear infinite;
+  }
+  @keyframes spin { to { transform: rotate(360deg); } }
+  .loader-text { margin-top: 16px; color: #999; font-size: 14px; }
+
+  .error-msg { color: #F44336; padding: 40px 0; text-align: center; }
+  .link-row { text-align: center; margin-top: 8px; }
+  .link-row a { color: #1976D2; text-decoration: none; font-size: 14px; }
+</style>
+</head>
+<body>
+
+<h1>Scraper status</h1>
+<div class="subtitle">maru-hleda-byt</div>
+
+<div id="content">
+  <div class="loader-wrap">
+    <div class="spinner"></div>
+    <div class="loader-text">Nacitam status...</div>
+  </div>
+</div>
+
+<div class="link-row"><a href="mapa_bytu.html">Otevrit mapu</a></div>
+
+<script>
+var COLORS = {
+  sreality: '#1976D2',
+  realingo: '#7B1FA2',
+  bezrealitky: '#E65100',
+  idnes: '#C62828',
+  psn: '#2E7D32',
+  cityhome: '#00838F',
+};
+
+function timeAgo(dateStr) {
+  var d = new Date(dateStr);
+  var now = new Date();
+  var diff = Math.floor((now - d) / 1000);
+  if (diff < 60) return 'prave ted';
+  if (diff < 3600) return Math.floor(diff / 60) + ' min zpet';
+  if (diff < 86400) return Math.floor(diff / 3600) + ' hod zpet';
+  return Math.floor(diff / 86400) + ' dni zpet';
+}
+
+function formatDate(dateStr) {
+  var d = new Date(dateStr);
+  var day = d.getDate();
+  var months = ['ledna','unora','brezna','dubna','kvetna','cervna',
+    'cervence','srpna','zari','rijna','listopadu','prosince'];
+  var hh = String(d.getHours()).padStart(2, '0');
+  var mm = String(d.getMinutes()).padStart(2, '0');
+  return day + '. ' + months[d.getMonth()] + ' ' + d.getFullYear() + ', ' + hh + ':' + mm;
+}
+
+function render(data) {
+  // Check if scrape is currently running
+  if (data.status === 'running') {
+    document.getElementById('content').innerHTML =
+      '<div class="loader-wrap">' +
+      '<div class="spinner"></div>' +
+      '<div class="loader-text">Scraper prave bezi...</div>' +
+      '</div>';
+    setTimeout(loadStatus, 30000);
+    return;
+  }
+
+  var sources = data.sources || [];
+  var totalOk = 0, totalRej = 0;
+  var maxCount = 0;
+  sources.forEach(function(s) {
+    totalOk += s.accepted || 0;
+    totalRej += s.rejected || 0;
+    if (s.accepted > maxCount) maxCount = s.accepted;
+  });
+
+  var html = '';
+
+  // Timestamp card
+  html += '<div class="card">';
+  html += '<h2>Posledni scrape</h2>';
+  html += '<div class="timestamp">' + formatDate(data.timestamp) + '</div>';
+  html += '<div class="timestamp-ago">' + timeAgo(data.timestamp) + '</div>';
+  if (data.duration_sec) {
+    html += '<div class="timestamp-ago">Trvani: ' + Math.round(data.duration_sec) + 's</div>';
+  }
+  html += '</div>';
+
+  // Summary card
+  html += '<div class="card">';
+  html += '<h2>Souhrn</h2>';
+  html += '<div class="summary-row"><span class="summary-label">Vyhovujicich bytu</span><span class="summary-value" style="color:#4CAF50">' + totalOk + '</span></div>';
+  html += '<div class="summary-row"><span class="summary-label">Vyloucenych</span><span class="summary-value" style="color:#999">' + totalRej + '</span></div>';
+  if (data.deduplicated !== undefined) {
+    html += '<div class="summary-row"><span class="summary-label">Po deduplikaci (v mape)</span><span class="summary-value" style="color:#1976D2">' + data.deduplicated + '</span></div>';
+  }
+  html += '</div>';
+
+  // Sources card
+  html += '<div class="card">';
+  html += '<h2>Zdroje</h2>';
+  sources.forEach(function(s) {
+    var color = COLORS[s.name.toLowerCase()] || '#999';
+    var pct = maxCount > 0 ? Math.round((s.accepted / maxCount) * 100) : 0;
+    var badge = s.error
+      ? '<span class="badge badge-err">chyba</span>'
+      : (s.accepted === 0 ? '<span class="badge badge-skip">0</span>' : '<span class="badge badge-ok">OK</span>');
+
+    html += '<div style="margin-bottom:12px;">';
+    html += '<div style="display:flex;justify-content:space-between;align-items:center;margin-bottom:4px;">';
+    html += '<span style="font-weight:600;font-size:14px;">' + s.name + ' ' + badge + '</span>';
+    html += '<span style="font-size:12px;color:#999;">' + (s.rejected || 0) + ' vyloucenych</span>';
+    html += '</div>';
+    html += '<div class="bar-row">';
+    html += '<div class="bar-track"><div class="bar-fill" style="width:' + pct + '%;background:' + color + ';"></div></div>';
+    html += '<span class="bar-count">' + (s.accepted || 0) + '</span>';
+    html += '</div>';
+    html += '</div>';
+  });
+  html += '</div>';
+
+  document.getElementById('content').innerHTML = html;
+}
+
+function loadStatus() {
+  fetch('status.json?t=' + Date.now())
+    .then(function(r) {
+      if (!r.ok) throw new Error(r.status);
+      return r.json();
+    })
+    .then(render)
+    .catch(function(err) {
+      document.getElementById('content').innerHTML =
+        '<div class="error-msg">Status zatim neni k dispozici.<br><small>(' + err.message + ')</small></div>';
+    });
+}
+
+loadStatus();
+</script>
+</body>
+</html>