Add validation mode, structured logging, and CLI args to all scrapers
- Replace print() with Python logging module across all 6 scrapers for configurable log levels (DEBUG/INFO/WARNING/ERROR) - Add --max-pages, --max-properties, and --log-level CLI arguments to each scraper via argparse for limiting scrape scope - Add validation Make targets (validation, validation-local, validation-local-debug) for quick test runs with limited data - Update run_all.sh to parse and forward CLI args to all scrapers - Update mapa_bytu.html with latest scrape results Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Jan Novak
@@ -6,13 +6,17 @@ Výstup: byty_bezrealitky.json
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
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 +73,63 @@ 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 +140,11 @@ 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 +169,43 @@ 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)
|
||||
print("Stahuji inzeráty z Bezrealitky.cz")
|
||||
print(f"Cena: do {format_price(MAX_PRICE)}")
|
||||
print(f"Min. plocha: {MIN_AREA} m²")
|
||||
print(f"Patro: od {MIN_FLOOR}. NP")
|
||||
print(f"Region: Praha")
|
||||
logger.info("=" * 60)
|
||||
logger.info("Stahuji inzeráty z Bezrealitky.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")
|
||||
logger.info(f"Region: Praha")
|
||||
if cache:
|
||||
print(f"Cache: {len(cache)} bytů z minulého běhu")
|
||||
print("=" * 60)
|
||||
logger.info(f"Cache: {len(cache)} bytů z minulého běhu")
|
||||
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 +218,7 @@ 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 +228,57 @@ 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:")
|
||||
print(f" Vyloučeno (dispozice): {excluded_disp}")
|
||||
print(f" Vyloučeno (cena): {excluded_price}")
|
||||
print(f" Vyloučeno (plocha): {excluded_area}")
|
||||
print(f" Vyloučeno (bez GPS): {excluded_no_gps}")
|
||||
print(f" Zbývá: {len(pre_filtered)}")
|
||||
logger.info(f"\nPo předfiltraci:")
|
||||
logger.info(f" Vyloučeno (dispozice): {excluded_disp}")
|
||||
logger.info(f" Vyloučeno (cena): {excluded_price}")
|
||||
logger.info(f" Vyloučeno (plocha): {excluded_area}")
|
||||
logger.info(f" Vyloučeno (bez GPS): {excluded_no_gps}")
|
||||
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 +287,7 @@ 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 +296,30 @@ 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", {})
|
||||
@@ -317,26 +357,43 @@ def scrape():
|
||||
"image": "",
|
||||
}
|
||||
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}")
|
||||
print(f"Výsledky Bezrealitky:")
|
||||
print(f" Předfiltrováno: {len(pre_filtered)}")
|
||||
print(f" Z cache (přeskočeno): {cache_hits}")
|
||||
print(f" Vyloučeno (panel/síd): {excluded_panel}")
|
||||
print(f" Vyloučeno (patro): {excluded_floor}")
|
||||
print(f" Vyloučeno (bez detailu): {excluded_detail}")
|
||||
print(f" ✓ Vyhovující byty: {len(results)}")
|
||||
print(f"{'=' * 60}")
|
||||
logger.info(f"\n{'=' * 60}")
|
||||
logger.info(f"Výsledky Bezrealitky:")
|
||||
logger.info(f" Předfiltrováno: {len(pre_filtered)}")
|
||||
logger.info(f" Z cache (přeskočeno): {cache_hits}")
|
||||
logger.info(f" Vyloučeno (panel/síd): {excluded_panel}")
|
||||
logger.info(f" Vyloučeno (patro): {excluded_floor}")
|
||||
logger.info(f" Vyloučeno (bez detailu): {excluded_detail}")
|
||||
logger.info(f" ✓ Vyhovující byty: {len(results)}")
|
||||
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 +402,7 @@ if __name__ == "__main__":
|
||||
encoding="utf-8",
|
||||
)
|
||||
elapsed = time.time() - start
|
||||
print(f"\n✓ Data uložena: {json_path.resolve()}")
|
||||
print(f"⏱ Celkový čas: {elapsed:.0f} s")
|
||||
logger.info(f"\n✓ Data uložena: {json_path.resolve()}")
|
||||
logger.info(f"⏱ Celkový čas: {elapsed:.0f} s")
|
||||
else:
|
||||
print("\nŽádné byty z Bezrealitek neodpovídají kritériím :(")
|
||||
logger.info("\nŽádné byty z Bezrealitek neodpovídají kritériím :(")
|
||||
|
||||
Reference in New Issue
Block a user