Byty v Praze

commit 82d1f94104c64d795333ba66eed3dc87fa909650 Author: littlemeat Date: Fri Feb 13 16:10:14 2026 +0000 v1 diff --git a/mapa_bytu.html b/mapa_bytu.html new file mode 100644 index 0000000..fc6888c --- /dev/null +++ b/mapa_bytu.html @@ -0,0 +1,1084 @@ + + + + + +Byty v Praze — mapa (710 bytů) + + + + + +

Celkem: 710 bytů

Cena: 380 000 Kč — 13 500 000 Kč

Průměr: 10 404 910 Kč

Dispozice:

3+kk (361)

3+1 (94)

4+kk (56)

4+1 (9)

5+kk (4)

+ + +

+ + + + \ No newline at end of file diff --git a/merge_and_map.py b/merge_and_map.py new file mode 100644 index 0000000..551a65d --- /dev/null +++ b/merge_and_map.py @@ -0,0 +1,113 @@ +#!/usr/bin/env python3 +""" +Sloučí data ze Sreality, Realinga, Bezrealitek, iDNES, PSN a CityHome, +deduplikuje a vygeneruje mapu. +Deduplikace: stejná ulice (z locality) + stejná cena + stejná plocha = duplikát. +PSN a CityHome mají při deduplikaci prioritu (načtou se první). +""" +from __future__ import annotations + +import json +import re +from pathlib import Path + +from scrape_and_map import generate_map, format_price + + +def normalize_street(locality: str) -> str: + """Extract and normalize street name from locality string.""" + # "Studentská, Praha 6 - Dejvice" → "studentska" + # "Rýnská, Praha" → "rynska" + street = locality.split(",")[0].strip().lower() + # Remove diacritics (simple Czech) + replacements = { + "á": "a", "č": "c", "ď": "d", "é": "e", "ě": "e", + "í": "i", "ň": "n", "ó": "o", "ř": "r", "š": "s", + "ť": "t", "ú": "u", "ů": "u", "ý": "y", "ž": "z", + } + for src, dst in replacements.items(): + street = street.replace(src, dst) + # Remove non-alphanumeric + street = re.sub(r"[^a-z0-9]", "", street) + return street + + +def dedup_key(estate: dict) -> str: + """Create deduplication key from street + price + area.""" + street = normalize_street(estate.get("locality", "")) + price = estate.get("price", 0) + area = estate.get("area") or 0 + return f"{street}_{price}_{area}" + + +def main(): + # Definice zdrojů — PSN a CityHome jako první (mají prioritu při deduplikaci) + sources = [ + ("PSN", "byty_psn.json"), + ("CityHome", "byty_cityhome.json"), + ("Sreality", "byty_sreality.json"), + ("Realingo", "byty_realingo.json"), + ("Bezrealitky", "byty_bezrealitky.json"), + ("iDNES", "byty_idnes.json"), + ] + + all_estates = [] + + for label, filename in sources: + path = Path(filename) + if path.exists(): + data = json.loads(path.read_text(encoding="utf-8")) + # Ensure source is set (Sreality legacy) + if label == "Sreality": + for e in data: + if "source" not in e: + e["source"] = "sreality" + all_estates.extend(data) + print(f"{label:12s} {len(data)} bytů") + else: + print(f"{label:12s} data nenalezena ({filename})") + + print(f"Celkem: {len(all_estates)} bytů před deduplikací") + + # Deduplicate — prefer Sreality (has better detail URLs) + seen_keys = {} + deduplicated = [] + dupes = 0 + + for e in all_estates: + key = dedup_key(e) + if key in seen_keys: + dupes += 1 + existing = seen_keys[key] + # Log it + print(f" Duplikát: {e['locality']} | {format_price(e['price'])} | {e.get('area', '?')} m² " + f"({e.get('source', '?')} vs {existing.get('source', '?')})") + else: + seen_keys[key] = e + deduplicated.append(e) + + print(f"\nOdstraněno duplikátů: {dupes}") + print(f"Výsledek: {len(deduplicated)} unikátních bytů") + + # Count by source + by_source = {} + for e in deduplicated: + src = e.get("source", "unknown") + by_source[src] = by_source.get(src, 0) + 1 + for src, count in sorted(by_source.items()): + print(f" {src}: {count}") + + # Save merged data + merged_path = Path("byty_merged.json") + merged_path.write_text( + json.dumps(deduplicated, ensure_ascii=False, indent=2), + encoding="utf-8", + ) + print(f"\n✓ Sloučená data: {merged_path.resolve()}") + + # Generate map + generate_map(deduplicated) + + +if __name__ == "__main__": + main() diff --git a/regen_map.py b/regen_map.py new file mode 100644 index 0000000..0d8f6f3 --- /dev/null +++ b/regen_map.py @@ -0,0 +1,114 @@ +#!/usr/bin/env python3 +""" +Přegeneruje mapu z již stažených dat (byty_sreality.json). +Doplní chybějící plochy ze Sreality API, opraví URL, aplikuje filtry. +""" +from __future__ import annotations + +import json +import time +import urllib.request +from pathlib import Path + +from scrape_and_map import ( + generate_map, format_price, MIN_AREA, HEADERS, DETAIL_API +) + + +def api_get(url: str) -> dict: + req = urllib.request.Request(url, headers=HEADERS) + with urllib.request.urlopen(req, timeout=30) as resp: + return json.loads(resp.read().decode("utf-8")) + + +def fix_sreality_url(estate: dict) -> str: + """Fix the Sreality URL to include disposition segment (only if missing).""" + disp = estate.get("disposition", "") + slug_map = { + "1+kk": "1+kk", "1+1": "1+1", "2+kk": "2+kk", "2+1": "2+1", + "3+kk": "3+kk", "3+1": "3+1", "4+kk": "4+kk", "4+1": "4+1", + "5+kk": "5+kk", "5+1": "5+1", "6+": "6-a-vice", "Atypický": "atypicky", + } + slug = slug_map.get(disp, "byt") + old_url = estate.get("url", "") + parts = old_url.split("/") + try: + byt_idx = parts.index("byt") + # Only insert if disposition slug is not already there + if byt_idx + 1 < len(parts) and parts[byt_idx + 1] == slug: + return old_url # already correct + parts.insert(byt_idx + 1, slug) + return "/".join(parts) + except ValueError: + return old_url + + +def fetch_area(hash_id: int) -> int | None: + """Fetch area from detail API.""" + try: + url = DETAIL_API.format(hash_id) + detail = api_get(url) + for item in detail.get("items", []): + name = item.get("name", "") + if "žitná ploch" in name or "zitna ploch" in name.lower(): + return int(item["value"]) + except Exception: + pass + return None + + +def main(): + json_path = Path("byty_sreality.json") + if not json_path.exists(): + print("Soubor byty_sreality.json nenalezen. Nejprve spusť scrape_and_map.py") + return + + estates = json.loads(json_path.read_text(encoding="utf-8")) + print(f"Načteno {len(estates)} bytů z byty_sreality.json") + + # Step 1: Fetch missing areas + missing_area = [e for e in estates if e.get("area") is None] + print(f"Doplňuji plochu u {len(missing_area)} bytů...") + + for i, e in enumerate(missing_area): + time.sleep(0.3) + area = fetch_area(e["hash_id"]) + if area is not None: + e["area"] = area + if (i + 1) % 50 == 0: + print(f" {i + 1}/{len(missing_area)} ...") + + # Count results + with_area = sum(1 for e in estates if e.get("area") is not None) + print(f"Plocha doplněna: {with_area}/{len(estates)}") + + # Step 2: Fix URLs + for e in estates: + e["url"] = fix_sreality_url(e) + + # Step 3: Filter by min area + filtered = [] + excluded = 0 + for e in estates: + area = e.get("area") + if area is not None and area < MIN_AREA: + excluded += 1 + continue + filtered.append(e) + + print(f"Vyloučeno (< {MIN_AREA} m²): {excluded}") + print(f"Zbývá: {len(filtered)} bytů") + + # Save updated data + filtered_path = Path("byty_sreality.json") + filtered_path.write_text( + json.dumps(filtered, ensure_ascii=False, indent=2), + encoding="utf-8", + ) + + # Generate map + generate_map(filtered) + + +if __name__ == "__main__": + main() diff --git a/run_all.sh b/run_all.sh new file mode 100644 index 0000000..d82c5db --- /dev/null +++ b/run_all.sh @@ -0,0 +1,63 @@ +#!/usr/bin/env bash +# ============================================================ +# Spustí všechny scrapery, sloučí data a otevře mapu. +# Použití: ./run_all.sh +# ============================================================ +set -euo pipefail +cd "$(dirname "$0")" + +GREEN='\033[0;32m' +RED='\033[0;31m' +BOLD='\033[1m' +NC='\033[0m' + +TOTAL=6 +CURRENT=0 +FAILED=0 + +step() { + CURRENT=$((CURRENT + 1)) + echo "" + echo -e "${BOLD}[$CURRENT/$TOTAL] $1${NC}" + echo "------------------------------------------------------------" +} + +# ── Scrapery (paralelně kde to jde) ───────────────────────── + +step "Sreality" +python3 scrape_and_map.py || { echo -e "${RED}✗ Sreality selhalo${NC}"; FAILED=$((FAILED + 1)); } + +step "Realingo" +python3 scrape_realingo.py || { echo -e "${RED}✗ Realingo selhalo${NC}"; FAILED=$((FAILED + 1)); } + +step "Bezrealitky" +python3 scrape_bezrealitky.py || { 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)); } + +step "PSN + CityHome" +python3 scrape_psn.py & +PID_PSN=$! +python3 scrape_cityhome.py & +PID_CH=$! +wait $PID_PSN || { echo -e "${RED}✗ PSN selhalo${NC}"; FAILED=$((FAILED + 1)); } +wait $PID_CH || { echo -e "${RED}✗ CityHome selhalo${NC}"; FAILED=$((FAILED + 1)); } + +# ── Sloučení + mapa ────────────────────────────────────────── + +step "Sloučení dat a generování mapy" +python3 merge_and_map.py || { echo -e "${RED}✗ Merge selhal${NC}"; FAILED=$((FAILED + 1)); } + +# ── Otevření mapy ──────────────────────────────────────────── + +echo "" +echo "============================================================" +if [ $FAILED -eq 0 ]; then + echo -e "${GREEN}${BOLD}Hotovo! Všech 6 zdrojů úspěšně staženo.${NC}" +else + echo -e "${RED}${BOLD}Hotovo s $FAILED chybami.${NC}" +fi +echo "============================================================" + +open mapa_bytu.html diff --git a/scrape_and_map.py b/scrape_and_map.py new file mode 100644 index 0000000..5456ab8 --- /dev/null +++ b/scrape_and_map.py @@ -0,0 +1,848 @@ +#!/usr/bin/env python3 +""" +Sreality scraper + interactive map generator. +Hledá byty na prodej v Praze podle zadaných kritérií a generuje HTML mapu. +""" + +from __future__ import annotations + +import json +import math +import time +import urllib.request +import urllib.parse +from datetime import datetime +from pathlib import Path + +# ── Konfigurace filtrů ────────────────────────────────────────────────────── + +MAX_PRICE = 13_500_000 # Kč +MIN_AREA = 69 # m² — vyloučit byty menší než toto +DISPOSITIONS = [6, 7, 8, 9, 10, 11, 12] # 3+kk, 3+1, 4+kk, 4+1, 5+kk, 5+1, 6+ +MIN_FLOOR = 2 # stáhneme od 2. NP, na mapě označíme 2. NP zvlášť +REGION_ID = 10 # Praha +PER_PAGE = 60 + +# Sreality API base +API_BASE = "https://www.sreality.cz/api/cs/v2/estates" +DETAIL_API = "https://www.sreality.cz/api/cs/v2/estates/{}" + +# Klíčová slova pro vyloučení panelových domů / sídlišť +PANEL_KEYWORDS = {"panel", "panelový", "panelový dům", "panelák"} +SIDLISTE_KEYWORDS = {"sídliště", "sidliste"} + +HEADERS = { + "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36", + "Accept": "application/json", +} + + +def api_get(url: str) -> dict: + """Fetch JSON from Sreality API.""" + req = urllib.request.Request(url, headers=HEADERS) + with urllib.request.urlopen(req, timeout=30) as resp: + return json.loads(resp.read().decode("utf-8")) + + +def build_list_url(disposition: int, page: int = 1) -> str: + """Build Sreality API URL for a given disposition.""" + params = { + "category_main_cb": 1, # byty + "category_type_cb": 1, # prodej + "category_sub_cb": disposition, + "locality_region_id": REGION_ID, + "czk_price_summary_order2": f"0|{MAX_PRICE}", + "floor_number": f"{MIN_FLOOR}|99", + "per_page": PER_PAGE, + "page": page, + } + return f"{API_BASE}?{urllib.parse.urlencode(params)}" + + +def fetch_estates_for_disposition(disposition: int) -> 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 ...") + 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") + + for page in range(2, total_pages + 1): + time.sleep(0.5) + print(f" Fetching page {page}/{total_pages} ...") + url = build_list_url(disposition, page=page) + data = api_get(url) + estates.extend(data.get("_embedded", {}).get("estates", [])) + + return estates + + +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) + except Exception as e: + print(f" Warning: Could not fetch detail for {hash_id}: {e}") + return None + + +def parse_floor_from_detail(detail: dict) -> int | None: + """Extract floor number from detail items.""" + for item in detail.get("items", []): + if item.get("name") == "Podlaží" or item.get("name") == "Podlazi": + val = item.get("value", "") + # Format: "3. podlaží z celkem 5 ..." or similar + parts = val.split(".") + if parts: + try: + return int(parts[0].strip()) + except ValueError: + pass + return None + + +def is_panel_or_sidliste(detail: dict) -> tuple[bool, str]: + """ + Check if the estate is panel construction or on a sídliště. + Returns (should_exclude, reason). + """ + reasons = [] + for item in detail.get("items", []): + name = (item.get("name") or "").lower() + value = str(item.get("value") or "").lower() + + # Check "Stavba" field for panel + if name in ("stavba", "konstrukce"): + if "panel" in value: + reasons.append(f"stavba: {value}") + + # Check "Umístění objektu" for sídliště + if name in ("umístění objektu", "umisteni objektu"): + if "sídliště" in value or "sidliste" in value: + reasons.append(f"umístění: {value}") + + # Also check description text + description = str(detail.get("text", {}).get("value", "")).lower() + locality_text = str(detail.get("locality", {}).get("value", "")).lower() if isinstance(detail.get("locality"), dict) else "" + + return (len(reasons) > 0, "; ".join(reasons)) + + +def disposition_label(sub_cb: int) -> str: + """Human-readable disposition label.""" + labels = { + 2: "1+kk", 3: "1+1", 4: "2+kk", 5: "2+1", + 6: "3+kk", 7: "3+1", 8: "4+kk", 9: "4+1", + 10: "5+kk", 11: "5+1", 12: "6+", 16: "Atypický", + } + return labels.get(sub_cb, "?") + + +def disposition_url_slug(sub_cb: int) -> str: + """URL slug for disposition in Sreality URLs.""" + slugs = { + 2: "1+kk", 3: "1+1", 4: "2+kk", 5: "2+1", + 6: "3+kk", 7: "3+1", 8: "4+kk", 9: "4+1", + 10: "5+kk", 11: "5+1", 12: "6-a-vice", 16: "atypicky", + } + return slugs.get(sub_cb, "byt") + + +def sreality_url(hash_id: int, seo: dict) -> str: + """Build human-readable Sreality URL from estate data.""" + cat_type = {1: "prodej", 2: "pronajem"}.get(seo.get("category_type_cb", 1), "prodej") + cat_main = {1: "byt", 2: "dum", 3: "pozemek", 4: "komercni"}.get(seo.get("category_main_cb", 1), "byt") + cat_sub = disposition_url_slug(seo.get("category_sub_cb", 0)) + locality = seo.get("locality", "praha") + return f"https://www.sreality.cz/detail/{cat_type}/{cat_main}/{cat_sub}/{locality}/{hash_id}" + + +def format_price(price: int) -> str: + """Format price in CZK with spaces.""" + s = str(price) + parts = [] + while s: + parts.append(s[-3:]) + s = s[:-3] + return " ".join(reversed(parts)) + " Kč" + + +# ── Hlavní scraping ───────────────────────────────────────────────────────── + +def load_cache(json_path: str = "byty_sreality.json") -> dict[int, dict]: + """Load previously scraped data as cache keyed by hash_id.""" + path = Path(json_path) + if not path.exists(): + return {} + try: + data = json.loads(path.read_text(encoding="utf-8")) + return {e["hash_id"]: e for e in data if "hash_id" in e} + except (json.JSONDecodeError, KeyError): + return {} + + +def scrape(): + """Main scraping function. Returns list of filtered estates.""" + all_estates_raw = [] + cache = load_cache() + + print("=" * 60) + print("Stahuji inzeráty ze Sreality.cz") + print(f"Cena: do {format_price(MAX_PRICE)}") + print(f"Dispozice: {', '.join(disposition_label(d) for d in DISPOSITIONS)}") + print(f"Patro: od {MIN_FLOOR}. NP") + print(f"Region: Praha") + if cache: + print(f"Cache: {len(cache)} bytů z minulého běhu") + print("=" * 60) + + for disp in DISPOSITIONS: + print(f"\n▸ Dispozice: {disposition_label(disp)}") + estates = fetch_estates_for_disposition(disp) + for e in estates: + e["_disposition_cb"] = disp + all_estates_raw.extend(estates) + time.sleep(0.5) + + # Deduplicate by hash_id + seen = set() + unique_estates = [] + for e in all_estates_raw: + hid = e.get("hash_id") + if hid and hid not in seen: + seen.add(hid) + unique_estates.append(e) + + print(f"\n{'=' * 60}") + print(f"Staženo celkem: {len(unique_estates)} unikátních inzerátů") + print(f"Stahuji detaily pro filtrování panelu/sídlišť...") + print(f"{'=' * 60}") + + # Fetch details and filter + results = [] + excluded_panel = 0 + excluded_no_gps = 0 + excluded_no_detail = 0 + excluded_small = 0 + cache_hits = 0 + + for i, estate in enumerate(unique_estates): + 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 + 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 + results.append(cached) + continue + + # Fetch detail + time.sleep(0.3) + detail = get_estate_detail(hash_id) + if not detail: + excluded_no_detail += 1 + continue + + # Check panel / sídliště + is_excluded, reason = is_panel_or_sidliste(detail) + if is_excluded: + excluded_panel += 1 + print(f" ✗ Vyloučen #{hash_id}: {reason}") + continue + + # Parse floor + floor = parse_floor_from_detail(detail) + + # Get area — field name can be truncated ("Užitná ploch" or "Užitná plocha") + area = None + for item in detail.get("items", []): + name = item.get("name", "") + if "žitná ploch" in name or "zitna ploch" in name.lower(): + try: + area = int(item["value"]) + except (ValueError, KeyError): + pass + break + + # 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)") + continue + + # Get building type + building_type = None + for item in detail.get("items", []): + if item.get("name") in ("Stavba", "Konstrukce"): + building_type = item.get("value") + break + + # Get ownership + ownership = None + for item in detail.get("items", []): + if item.get("name") in ("Vlastnictví", "Vlastnictvi"): + ownership = item.get("value") + break + + disp_cb = estate.get("_disposition_cb") or estate.get("seo", {}).get("category_sub_cb") + seo = estate.get("seo", {}) + + result = { + "hash_id": hash_id, + "name": estate.get("name", ""), + "price": estate.get("price", 0), + "price_formatted": format_price(estate.get("price", 0)), + "locality": estate.get("locality", ""), + "lat": gps["lat"], + "lon": gps["lon"], + "disposition": disposition_label(disp_cb), + "floor": floor, + "area": area, + "building_type": building_type, + "ownership": ownership, + "url": sreality_url(hash_id, seo), + "image": (estate.get("_links", {}).get("images", [{}])[0].get("href", "") if estate.get("_links", {}).get("images") else ""), + } + results.append(result) + + if (i + 1) % 20 == 0: + print(f" Zpracováno {i + 1}/{len(unique_estates)} ...") + + print(f"\n{'=' * 60}") + print(f"Výsledky:") + print(f" Celkem staženo: {len(unique_estates)}") + print(f" Z cache (přeskočeno): {cache_hits}") + print(f" Vyloučeno (panel/síd): {excluded_panel}") + print(f" Vyloučeno (<{MIN_AREA} m²): {excluded_small}") + print(f" Vyloučeno (bez GPS): {excluded_no_gps}") + print(f" Vyloučeno (bez detailu): {excluded_no_detail}") + print(f" ✓ Vyhovující byty: {len(results)}") + print(f"{'=' * 60}") + + return results + + +# ── Generování HTML mapy ──────────────────────────────────────────────────── + +def generate_map(estates: list[dict], output_path: str = "mapa_bytu.html"): + """Generate an interactive Leaflet.js HTML map.""" + + # Color by disposition + color_map = { + "3+kk": "#2196F3", # blue + "3+1": "#4CAF50", # green + "4+kk": "#FF9800", # orange + "4+1": "#F44336", # red + "5+kk": "#9C27B0", # purple + "5+1": "#795548", # brown + "6+": "#607D8B", # grey-blue + } + + markers_js = "" + for e in estates: + color = color_map.get(e["disposition"], "#999999") + 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" + ownership_text = e["ownership"] or "neuvedeno" + + # Floor warning for 2nd floor + floor_note = "" + if e["floor"] == 2: + floor_note = '
⚠ 2. NP — zvážit klidnost lokality' + + source = e.get("source", "sreality") + source_labels = {"sreality": "Sreality", "realingo": "Realingo", "bezrealitky": "Bezrealitky", "idnes": "iDNES", "psn": "PSN", "cityhome": "CityHome"} + source_colors = {"sreality": "#1976D2", "realingo": "#00897B", "bezrealitky": "#E91E63", "idnes": "#FF6F00", "psn": "#D32F2F", "cityhome": "#D32F2F"} + source_label = source_labels.get(source, source) + source_color = source_colors.get(source, "#999") + + hash_id = e.get("hash_id", "") + + popup = ( + f'

' + f'{format_price(e["price"])}' + f'{source_label}
' + f'{e["disposition"]} | {area_text} | {floor_text}' + f'{floor_note}

' + f'{e["locality"]}
' + f'Stavba: {building_text}
' + f'Vlastnictví: {ownership_text}

' + f'' + f'→ Otevřít na {source_label}' + f'

' + f'

' + f'' + f'' + f'' + f'

' + f'' + f'

' + ) + # Escape for JS + popup = popup.replace("'", "\\'").replace("\n", "") + + is_fav = source in ("psn", "cityhome") + marker_fn = "addHeartMarker" if is_fav else "addMarker" + markers_js += ( + f" {marker_fn}({e['lat']}, {e['lon']}, '{color}', '{popup}', '{hash_id}');\n" + ) + + # Build legend + legend_items = "" + 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(): + count = disp_counts.get(disp, 0) + if count > 0: + legend_items += ( + f'

' + f'' + f'{disp} ({count})

' + ) + + # Heart marker legend for PSN/CityHome + fav_count = sum(1 for e in estates if e.get("source") in ("psn", "cityhome")) + if fav_count > 0: + legend_items += ( + f'

' + f'' + f'PSN / CityHome ({fav_count})

' + ) + + # Price stats + prices = [e["price"] for e in estates if e["price"] > 0] + min_price = format_price(min(prices)) if prices else "N/A" + max_price = format_price(max(prices)) if prices else "N/A" + avg_price = format_price(int(sum(prices) / len(prices))) if prices else "N/A" + + html = f""" + + + + +Byty v Praze — mapa ({len(estates)} bytů) + + + + + +

Byty v Praze

Celkem: {len(estates)} bytů

Cena: {min_price} — {max_price}

Průměr: {avg_price}

Dispozice:

+ {legend_items} + + +

+ + + +""" + + path = Path(output_path) + path.write_text(html, encoding="utf-8") + print(f"\n✓ Mapa uložena: {path.resolve()}") + return str(path.resolve()) + + +# ── Main ───────────────────────────────────────────────────────────────────── + +if __name__ == "__main__": + start = time.time() + estates = scrape() + + if estates: + # Save raw data as JSON backup + json_path = Path("byty_sreality.json") + json_path.write_text( + json.dumps(estates, ensure_ascii=False, indent=2), + encoding="utf-8", + ) + print(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") + print(f"\nOtevři v prohlížeči:\n file://{map_path}") + else: + print("\nŽádné byty neodpovídají kritériím :(")