115 lines
3.3 KiB
Python
115 lines
3.3 KiB
Python
#!/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()
|