Airbnb Market Intel — Occupancy & Revenue
Pricing
Pay per usage
Scrape Airbnb listings for any city: name, URL, price per night, coordinates, rating, reviews, 12-month calendar, occupancy rate, estimated monthly revenue. For investors and property managers.
{ "$schema": "https://apify.com/schemas/v1/actor.ide.json", "actorSpecification": 1, "name": "my-first-scraper", "title": "Scrape single page in Python", "description": "Scrape data from single page with provided URL.", "version": "0.0", "buildTag": "latest", "meta": { "templateId": "python-start", "generatedBy": "<FILL-IN-MODEL>" }, "inputSchema": "./input_schema.json", "outputSchema": "./output_schema.json", "storages": { "dataset": "./dataset_schema.json" }, "dockerfile": "../Dockerfile"}{ "$schema": "https://apify.com/schemas/v1/dataset.ide.json", "actorSpecification": 1, "fields": {}, "views": { "overview": { "title": "Overview", "transformation": { "fields": ["level", "text"] }, "display": { "component": "table", "properties": { "level": { "label": "Level", "format": "text" }, "text": { "label": "Text", "format": "text" } } } } }}{ "title": "Airbnb Market Intel input", "type": "object", "schemaVersion": 1, "properties": { "location": { "title": "Location", "type": "string", "description": "Город (например, \"Lisbon, Portugal\") или полный URL поиска Airbnb.", "editor": "textfield", "prefill": "Lisbon, Portugal" }, "maxListings": { "title": "Max listings", "type": "integer", "description": "Максимальное число объявлений для обработки.", "default": 50, "minimum": 1, "maximum": 1000, "editor": "number" } }, "required": ["location"]}{ "$schema": "https://apify.com/schemas/v1/output.ide.json", "actorOutputSchemaVersion": 1, "title": "Output schema", "properties": { "results": { "type": "string", "title": "Results", "template": "{{links.apiDefaultDatasetUrl}}/items" } }}1
1import asyncio2
3from .main import main4
5if __name__ == '__main__':6 asyncio.run(main())1"""Логика Airbnb: URL поиска, парсинг выдачи и детальной страницы."""2
3from __future__ import annotations4
5import base646import json7import re8from datetime import date, datetime, timezone9from typing import Any10from urllib.parse import parse_qsl, quote, urlencode, urlsplit, urlunsplit11
12from apify import Actor13
14from .utils import (15 FetchError,16 calc_occupancy,17 extract_json_from_script,18 fetch_html,19 fetch_json,20 find_key,21 first_value,22 httpx,23 iter_dicts,24 parse_calendar,25 parse_price,26)27
28BASE_URL = "https://www.airbnb.com"29# Публичный ключ веб-клиента Airbnb (используется, если не найден в HTML)30FALLBACK_API_KEY = "d306zoyjsyarp7ifhu67rjxn52tv0t20"31# Persisted query для календаря PDP32CALENDAR_HASH = "8f08e03c7bd16fcad3c92a3592c19a8b559a0d0855a84028d1163d4733ed9ade"33CALENDAR_MONTHS = 1234HOST_RE = re.compile(r"^(?:Hosted by|Stay with)\s+(.+)$", re.IGNORECASE)35API_KEY_RE = re.compile(r'"api_config"\s*:\s*\{\s*"key"\s*:\s*"([^"]+)"')36NIGHTS_RE = re.compile(r"(\d+)\s+nights?\s+x\s+(.+)$", re.IGNORECASE)37
38
39def build_search_url(location: str, cursor: str | None = None) -> str:40 """Строит URL поиска по городу или дополняет готовый URL поиска."""41 location = location.strip()42 if location.startswith(("http://", "https://")):43 parts = urlsplit(location)44 query = dict(parse_qsl(parts.query, keep_blank_values=True))45 else:46 parts = urlsplit(f"{BASE_URL}/s/{quote(location)}/homes")47 query = {"refinement_paths[]": "/homes"}48
49 # Английская локаль и USD — для стабильного парсинга цен и текстов50 query.update({"locale": "en", "currency": "USD"})51 if cursor:52 query["cursor"] = cursor53 else:54 query.pop("cursor", None)55 return urlunsplit((parts.scheme, parts.netloc, parts.path, urlencode(query), ""))56
57
58def decode_listing_id(raw: Any) -> str | None:59 """Приводит id к числу: "123" или base64("DemandStayListing:123")."""60 if raw is None:61 return None62 value = str(raw).strip()63 if value.isdigit():64 return value65 try:66 decoded = base64.b64decode(value + "=" * (-len(value) % 4)).decode("utf-8")67 except (ValueError, UnicodeDecodeError):68 return None69 tail = decoded.rsplit(":", 1)[-1]70 return tail if tail.isdigit() else None71
72
73def _text(value: Any) -> str | None:74 """Достаёт строку из простого или локализованного значения."""75 if isinstance(value, str):76 return value or None77 if isinstance(value, dict):78 for key in ("localizedStringWithTranslationPreference", "localizedString", "text"):79 if isinstance(value.get(key), str):80 return value[key]81 return None82
83
84def _extract_currency(text: str | None) -> str | None:85 """Грубо вытаскивает код валюты из текста цены."""86 if not text:87 return None88 for code in ("USD", "EUR", "GBP", "CHF", "RUB", "JPY", "CAD", "AUD"):89 if code in text:90 return code91 for symbol, code in (("$", "USD"), ("€", "EUR"), ("£", "GBP"), ("₽", "RUB"), ("Fr.", "CHF")):92 if symbol in text:93 return code94 return None95
96
97def _parse_rating(item: dict[str, Any], listing: dict[str, Any]) -> tuple[float | None, int | None]:98 """Рейтинг и число отзывов из "4.92 (123)" или a11y-подписи."""99 text = str(100 item.get("avgRatingLocalized")101 or listing.get("avgRatingLocalized")102 or item.get("avgRatingA11yLabel")103 or ""104 )105 match = re.search(r"(\d+(?:[.,]\d+)?)\s*\((\d[\d,]*)\)", text)106 if match:107 return float(match.group(1).replace(",", ".")), int(match.group(2).replace(",", ""))108 match = re.search(r"(\d+(?:\.\d+)?)\s*out of 5.*?(\d[\d,]*)\s+review", text, re.IGNORECASE)109 if match:110 return float(match.group(1)), int(match.group(2).replace(",", ""))111
112 rating = listing.get("avgRating")113 reviews = listing.get("reviewsCount")114 return (115 float(rating) if isinstance(rating, (int, float)) else None,116 int(reviews) if isinstance(reviews, int) else None,117 )118
119
120def _parse_price_line(item: dict[str, Any]) -> tuple[float | None, str | None]:121 """Цена за ночь и исходный текст цены из карточки поиска.122
123 Новая структура Airbnb: per-night цена лежит в explanationData.priceDetails,124 строка вида "5 nights x Fr. 148.05". primaryLine содержит общую сумму за все ночи.125 """126 display = item.get("structuredDisplayPrice") or {}127 primary = display.get("primaryLine") or {}128 explanation = display.get("explanationData") or {}129
130 # Ищем per-night в explanationData131 for group in explanation.get("priceDetails") or []:132 if not isinstance(group, dict):133 continue134 for entry in group.get("items") or []:135 if not isinstance(entry, dict):136 continue137 desc = entry.get("description") or ""138 m = NIGHTS_RE.search(desc)139 if m:140 per_night_text = m.group(2).strip()141 per_night = parse_price(per_night_text)142 if per_night:143 return per_night, desc144
145 # Fallback: primaryLine (это может быть total, но хотя бы что-то)146 price_value = primary.get("discountedPrice") or primary.get("price")147 qualifier = primary.get("qualifier") or ""148 if price_value:149 text = f"{price_value} {qualifier}".strip()150 else:151 text = primary.get("accessibilityLabel")152 return parse_price(text), text153
154
155def _parse_search_result(item: dict[str, Any]) -> dict[str, Any] | None:156 """Преобразует одну карточку выдачи в запись объявления."""157 listing = item.get("listing") or {}158 demand = item.get("demandStayListing") or {}159 listing_id = decode_listing_id(160 listing.get("id") or demand.get("id") or item.get("propertyId") or item.get("listingId")161 )162 if not listing_id:163 return None164
165 coordinate = (166 listing.get("coordinate")167 or (demand.get("location") or {}).get("coordinate")168 or {}169 )170 rating, reviews_count = _parse_rating(item, listing)171 price, price_text = _parse_price_line(item)172 title = _text(item.get("title")) or _text(listing.get("title"))173
174 name = (175 _text(listing.get("name"))176 or _text((demand.get("description") or {}).get("name"))177 or _text(item.get("nameLocalized"))178 or _text(item.get("subtitle"))179 or title180 )181
182 return {183 "id": listing_id,184 "name": name,185 "url": f"{BASE_URL}/rooms/{listing_id}",186 "price": price,187 "price_text": price_text,188 "currency": _extract_currency(price_text),189 "coordinates": {190 "lat": coordinate.get("latitude"),191 "lng": coordinate.get("longitude"),192 },193 "rating": rating,194 "reviews_count": reviews_count,195 "host_name": None,196 "room_type": listing.get("roomTypeCategory")197 or listing.get("roomType")198 or title,199 }200
201
202def parse_search(html: str) -> tuple[list[dict[str, Any]], str | None]:203 """Парсит страницу поиска: список объявлений и курсор следующей страницы."""204 data = extract_json_from_script(html)205 if data is None:206 Actor.log.warning("JSON состояния не найден на странице поиска")207 return [], None208
209 listings: dict[str, dict[str, Any]] = {}210 for results in find_key(data, "searchResults"):211 if not isinstance(results, list):212 continue213 for item in results:214 if not isinstance(item, dict):215 continue216 parsed = _parse_search_result(item)217 if parsed and parsed["id"] not in listings:218 listings[parsed["id"]] = parsed219
220 next_cursor: str | None = None221 for pagination in find_key(data, "paginationInfo"):222 if isinstance(pagination, dict) and pagination.get("nextPageCursor"):223 next_cursor = pagination["nextPageCursor"]224 break225
226 return list(listings.values()), next_cursor227
228
229def _extract_host_name(data: dict[str, Any]) -> str | None:230 """Имя хоста из секций детальной страницы."""231 host = first_value(data, "hostName")232 if isinstance(host, str):233 return host234 for item in iter_dicts(data):235 for key in ("title", "heading", "overviewTitle"):236 value = item.get(key)237 if isinstance(value, str):238 match = HOST_RE.match(value.strip())239 if match:240 return match.group(1).strip()241 for card in find_key(data, "cardData"):242 if isinstance(card, dict) and isinstance(card.get("name"), str):243 return card["name"]244 return None245
246
247def _extract_coordinates(data: dict[str, Any]) -> dict[str, float] | None:248 """Координаты из секции локации детальной страницы."""249 for item in iter_dicts(data):250 lat, lng = item.get("lat"), item.get("lng")251 if isinstance(lat, (int, float)) and isinstance(lng, (int, float)):252 return {"lat": float(lat), "lng": float(lng)}253 return None254
255
256async def fetch_calendar(257 client: httpx.AsyncClient,258 listing_id: str,259 api_key: str,260 referer: str,261 months: int = CALENDAR_MONTHS,262) -> dict[str, Any]:263 """Запрашивает календарь доступности через внутренний API Airbnb."""264 today = date.today()265 variables = {266 "request": {267 "count": months,268 "listingId": listing_id,269 "month": today.month,270 "year": today.year,271 }272 }273 extensions = {"persistedQuery": {"version": 1, "sha256Hash": CALENDAR_HASH}}274 params = {275 "operationName": "PdpAvailabilityCalendar",276 "locale": "en",277 "currency": "USD",278 "variables": json.dumps(variables, separators=(",", ":")),279 "extensions": json.dumps(extensions, separators=(",", ":")),280 }281 headers = {282 "X-Airbnb-API-Key": api_key,283 "Accept": "application/json",284 "Content-Type": "application/json",285 "Referer": referer,286 }287 payload = await fetch_json(288 client,289 f"{BASE_URL}/api/v3/PdpAvailabilityCalendar/{CALENDAR_HASH}",290 params=params,291 headers=headers,292 )293 if payload.get("errors"):294 raise ValueError(f"API календаря вернул ошибку: {payload['errors']}")295 return payload296
297
298async def parse_listing(client: httpx.AsyncClient, listing: dict[str, Any]) -> dict[str, Any]:299 """Дополняет объявление данными детальной страницы и метриками календаря."""300 html = await fetch_html(client, listing["url"], params={"locale": "en", "currency": "USD"})301 data = extract_json_from_script(html) or {}302 result = dict(listing)303
304 result["host_name"] = _extract_host_name(data) or listing.get("host_name")305 if not result.get("room_type"):306 result["room_type"] = first_value(data, "roomTypeCategory", "roomType")307 if not (result.get("coordinates") or {}).get("lat"):308 result["coordinates"] = _extract_coordinates(data) or result.get("coordinates")309
310 # Календарь иногда уже есть в состоянии страницы, иначе идём в API311 days = parse_calendar(data, CALENDAR_MONTHS)312 calendar_error: str | None = None313 if not days:314 key_match = API_KEY_RE.search(html)315 api_key = key_match.group(1) if key_match else FALLBACK_API_KEY316 try:317 payload = await fetch_calendar(client, listing["id"], api_key, listing["url"])318 days = parse_calendar(payload, CALENDAR_MONTHS)319 except (FetchError, ValueError) as exc:320 calendar_error = str(exc)321 Actor.log.warning(f"Календарь {listing['id']} не получен: {exc}")322
323 result.update(calc_occupancy(days, listing.get("price")))324 result["calendar_days"] = len(days)325 result["calendar_error"] = calendar_error326 result["scraped_at"] = datetime.now(timezone.utc).isoformat()327 return result1"""Оркестрация: поиск → детали → календарь → dataset."""2
3from __future__ import annotations4
5import asyncio6import random7from typing import Any8
9from apify import Actor10
11from .airbnb import build_search_url, parse_listing, parse_search12from .utils import FetchError, create_client, fetch_html, httpx13
14CONCURRENCY = 315MAX_SEARCH_PAGES = 1516
17
18async def collect_listings(19 client: httpx.AsyncClient,20 location: str,21 max_listings: int,22) -> list[dict[str, Any]]:23 """Обходит страницы поиска, пока не наберётся max_listings."""24 collected: dict[str, dict[str, Any]] = {}25 cursor: str | None = None26
27 for page in range(1, MAX_SEARCH_PAGES + 1):28 url = build_search_url(location, cursor)29 Actor.log.info(f"Страница поиска {page}: {url}")30 try:31 html = await fetch_html(client, url)32 except FetchError as exc:33 Actor.log.error(f"Не удалось загрузить поиск: {exc}")34 break35
36 items, next_cursor = parse_search(html)37 if not items:38 Actor.log.warning(f"На странице {page} объявлений нет, останавливаю поиск")39 break40
41 for item in items:42 collected.setdefault(item["id"], item)43 if len(collected) >= max_listings:44 break45 Actor.log.info(f"Собрано {len(collected)}/{max_listings} объявлений")46
47 if len(collected) >= max_listings or not next_cursor or next_cursor == cursor:48 break49 cursor = next_cursor50 await asyncio.sleep(random.uniform(1.0, 2.5)) # пауза между страницами51
52 return list(collected.values())[:max_listings]53
54
55async def main() -> None:56 """Точка входа Actor'а."""57 async with Actor:58 actor_input: dict[str, Any] = await Actor.get_input() or {}59 location = str(actor_input.get("location") or "").strip()60 if not location:61 raise ValueError("Поле location обязательно")62 max_listings = max(1, int(actor_input.get("maxListings") or 50))63
64 Actor.log.info(f"Старт: location={location!r}, maxListings={max_listings}")65
66 async with create_client() as client:67 listings = await collect_listings(client, location, max_listings)68 total = len(listings)69 Actor.log.info(f"Найдено {total} объявлений, загружаю детали и календари")70
71 semaphore = asyncio.Semaphore(CONCURRENCY)72 stats = {"ok": 0, "failed": 0}73
74 async def process(index: int, listing: dict[str, Any]) -> None:75 """Обрабатывает одно объявление; ошибки не роняют Actor."""76 async with semaphore:77 try:78 item = await parse_listing(client, listing)79 await Actor.push_data(item)80 stats["ok"] += 181 Actor.log.info(82 f"[{index}/{total}] {item['id']} {item.get('name')!r}: "83 f"occupancy={item.get('occupancy_rate')}%, "84 f"revenue/мес={item.get('estimated_monthly_revenue')}"85 )86 except Exception as exc: # noqa: BLE001 — логируем и идём дальше87 stats["failed"] += 188 Actor.log.error(f"[{index}/{total}] {listing.get('url')} не обработано: {exc!r}")89 await asyncio.sleep(random.uniform(0.5, 1.5)) # вежливая пауза90
91 await asyncio.gather(*(process(i, item) for i, item in enumerate(listings, 1)))92
93 Actor.log.info(f"Готово: успешно {stats['ok']}, ошибок {stats['failed']}")
1"""Вспомогательные функции: HTTP с ретраями, извлечение JSON, календарь, метрики."""2
3from __future__ import annotations4
5import asyncio6import json7import random8import re9from datetime import date, timedelta10from typing import Any, Iterator11
12try:13 import httpx2 as httpx14except ImportError:15 import httpx # type: ignore[no-redef]16
17from apify import Actor18from bs4 import BeautifulSoup19
20USER_AGENT = (21 "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "22 "(KHTML, like Gecko) Chrome/150.0.0.0 Safari/537.36"23)24
25DEFAULT_HEADERS: dict[str, str] = {26 "User-Agent": USER_AGENT,27 "Accept": (28 "text/html,application/xhtml+xml,application/xml;q=0.9,"29 "image/avif,image/webp,image/apng,*/*;q=0.8"30 ),31 "Accept-Language": "en-US,en;q=0.9",32 "Sec-Ch-Ua": '"Chromium";v="150", "Google Chrome";v="150", "Not.A/Brand";v="99"',33 "Sec-Ch-Ua-Mobile": "?0",34 "Sec-Ch-Ua-Platform": '"Windows"',35 "Upgrade-Insecure-Requests": "1",36}37
38BLOCK_STATUSES = {403, 429}39BLOCK_PAUSE_SECONDS = 5.040PRICE_RE = re.compile(r"(\d{1,3}(?:,\d{3})+|\d+)(?:\.(\d{1,2}))?")41NIGHTS_RE = re.compile(r"for\s+(\d+)\s+nights?", re.IGNORECASE)42AVG_DAYS_IN_MONTH = 30.4443
44
45class FetchError(Exception):46 """Запрос не удался даже после всех повторов."""47
48
49def create_client() -> httpx.AsyncClient:50 """Создаёт общий асинхронный HTTP-клиент."""51 return httpx.AsyncClient(52 headers=DEFAULT_HEADERS,53 timeout=httpx.Timeout(30.0),54 follow_redirects=True,55 )56
57
58async def _request(59 client: httpx.AsyncClient,60 url: str,61 *,62 params: dict[str, str] | None = None,63 headers: dict[str, str] | None = None,64 max_retries: int = 5,65 base_delay: float = 1.0,66) -> httpx.Response:67 """GET с ретраями и экспоненциальной задержкой."""68 last_error = "unknown error"69 for attempt in range(1, max_retries + 1):70 backoff = base_delay * 2 ** (attempt - 1) + random.uniform(0, 0.5)71 try:72 response = await client.get(url, params=params, headers=headers)73 except httpx.TransportError as exc:74 last_error = repr(exc)75 Actor.log.warning(76 f"Сетевая ошибка {url} (попытка {attempt}/{max_retries}): {exc!r}; "77 f"пауза {backoff:.1f} с"78 )79 await asyncio.sleep(backoff)80 continue81
82 status = response.status_code83 if status in BLOCK_STATUSES:84 delay = max(BLOCK_PAUSE_SECONDS, backoff)85 last_error = f"HTTP {status}"86 Actor.log.warning(87 f"Airbnb вернул {status} для {url} (попытка {attempt}/{max_retries}); "88 f"пауза {delay:.1f} с"89 )90 await asyncio.sleep(delay)91 continue92 if status >= 500:93 last_error = f"HTTP {status}"94 Actor.log.warning(95 f"Ошибка сервера {status} для {url} (попытка {attempt}/{max_retries}); "96 f"пауза {backoff:.1f} с"97 )98 await asyncio.sleep(backoff)99 continue100 if status >= 400:101 raise FetchError(f"HTTP {status} для {url}")102 return response103
104 raise FetchError(f"Не удалось загрузить {url} за {max_retries} попыток: {last_error}")105
106
107async def fetch_html(108 client: httpx.AsyncClient,109 url: str,110 *,111 params: dict[str, str] | None = None,112 headers: dict[str, str] | None = None,113) -> str:114 """Загружает HTML-страницу."""115 response = await _request(client, url, params=params, headers=headers)116 return response.text117
118
119async def fetch_json(120 client: httpx.AsyncClient,121 url: str,122 *,123 params: dict[str, str] | None = None,124 headers: dict[str, str] | None = None,125) -> dict[str, Any]:126 """Загружает JSON-ответ API."""127 response = await _request(client, url, params=params, headers=headers)128 data = response.json()129 if not isinstance(data, dict):130 raise ValueError(f"Неожиданный формат JSON от {url}")131 return data132
133
134def extract_json_from_script(html: str) -> dict[str, Any] | None:135 """Достаёт JSON состояния страницы. Приоритет — data-deferred-state."""136 soup = BeautifulSoup(html, "lxml")137
138 # 1. Главный кандидат — data-deferred-state (содержит searchResults)139 for tag in soup.find_all("script", id=re.compile(r"^data-deferred-state")):140 text = tag.get_text().strip()141 if not text:142 continue143 try:144 data = json.loads(text)145 except json.JSONDecodeError:146 continue147 if isinstance(data, dict):148 return data149
150 # 2. Fallback — любой другой JSON-скрипт с id^data-151 for tag in soup.find_all("script", id=re.compile(r"^data-")):152 text = tag.get_text().strip()153 if not text:154 continue155 try:156 data = json.loads(text)157 except json.JSONDecodeError:158 continue159 if isinstance(data, dict):160 return data161 return None162
163
164def iter_dicts(obj: Any) -> Iterator[dict[str, Any]]:165 """Обходит все вложенные словари без рекурсии."""166 stack: list[Any] = [obj]167 while stack:168 current = stack.pop()169 if isinstance(current, dict):170 yield current171 stack.extend(current.values())172 elif isinstance(current, list):173 stack.extend(current)174
175
176def find_key(obj: Any, key: str) -> Iterator[Any]:177 """Отдаёт значения ключа на любой глубине."""178 for item in iter_dicts(obj):179 if key in item:180 yield item[key]181
182
183def first_value(obj: Any, *keys: str) -> Any | None:184 """Первое непустое значение по одному из ключей."""185 for key in keys:186 for value in find_key(obj, key):187 if value not in (None, "", [], {}):188 return value189 return None190
191
192def parse_price(text: str | None) -> float | None:193 """Парсит цену из строки вида "$1,234" или "$600 for 5 nights" (за ночь)."""194 if not text:195 return None196 match = PRICE_RE.search(text)197 if not match:198 return None199 value = float(match.group(1).replace(",", "") + (f".{match.group(2)}" if match.group(2) else ""))200 nights = NIGHTS_RE.search(text)201 if nights and int(nights.group(1)) > 0:202 value /= int(nights.group(1))203 return round(value, 2)204
205
206def parse_calendar(payload: Any, months: int = 12) -> list[dict[str, Any]]:207 """Собирает дни календаря (calendarMonths → days) от сегодня на N месяцев вперёд."""208 today = date.today()209 horizon = today + timedelta(days=round(months * AVG_DAYS_IN_MONTH))210 days: dict[str, dict[str, Any]] = {}211 for months_list in find_key(payload, "calendarMonths"):212 if not isinstance(months_list, list):213 continue214 for month in months_list:215 for day in (month or {}).get("days") or []:216 try:217 day_date = date.fromisoformat(str(day.get("calendarDate") or day.get("date")))218 except ValueError:219 continue220 if not today <= day_date < horizon:221 continue222 price_info = day.get("price") or {}223 days[day_date.isoformat()] = {224 "date": day_date.isoformat(),225 "available": bool(day.get("available")),226 "price": parse_price(price_info.get("localPriceFormatted")),227 }228 return [days[key] for key in sorted(days)]229
230
231def calc_occupancy(days: list[dict[str, Any]], nightly_price: float | None) -> dict[str, Any]:232 """Считает занятость и оценку месячной выручки. Недоступные дни считаются занятыми."""233 total = len(days)234 if total == 0:235 return {236 "occupied_days": None,237 "available_days": None,238 "occupancy_rate": None,239 "estimated_monthly_revenue": None,240 }241 available = sum(1 for day in days if day["available"])242 occupied = total - available243
244 price = nightly_price245 if price is None:246 day_prices = [day["price"] for day in days if day.get("price")]247 price = sum(day_prices) / len(day_prices) if day_prices else None248
249 revenue = round(price * occupied * AVG_DAYS_IN_MONTH / total, 2) if price else None250 return {251 "occupied_days": occupied,252 "available_days": available,253 "occupancy_rate": round(occupied / total * 100, 2),254 "estimated_monthly_revenue": revenue,255 }.git.mise.toml.nvim.luastorage
# The rest is copied from https://github.com/github/gitignore/blob/main/Python.gitignore
# Byte-compiled / optimized / DLL files__pycache__/*.py[cod]*$py.class
# C extensions*.so
# Distribution / packaging.Pythonbuild/develop-eggs/dist/downloads/eggs/.eggs/lib/lib64/parts/sdist/var/wheels/share/python-wheels/*.egg-info/.installed.cfg*.eggMANIFEST
# PyInstaller# Usually these files are written by a python script from a template# before PyInstaller builds the exe, so as to inject date/other infos into it.*.manifest*.spec
# Installer logspip-log.txtpip-delete-this-directory.txt
# Unit test / coverage reportshtmlcov/.tox/.nox/.coverage.coverage.*.cachenosetests.xmlcoverage.xml*.cover*.py,cover.hypothesis/.pytest_cache/cover/
# Translations*.mo*.pot
# Django stuff:*.loglocal_settings.pydb.sqlite3db.sqlite3-journal
# Flask stuff:instance/.webassets-cache
# Scrapy stuff:.scrapy
# Sphinx documentationdocs/_build/
# PyBuilder.pybuilder/target/
# Jupyter Notebook.ipynb_checkpoints
# IPythonprofile_default/ipython_config.py
# pyenv# For a library or package, you might want to ignore these files since the code is# intended to run in multiple environments; otherwise, check them in:.python-version
# pdm# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.#pdm.lock# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it# in version control.# https://pdm.fming.dev/latest/usage/project/#working-with-version-control.pdm.toml.pdm-python.pdm-build/
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm__pypackages__/
# Celery stuffcelerybeat-schedulecelerybeat.pid
# SageMath parsed files*.sage.py
# Environments.env.venvenv/venv/ENV/env.bak/venv.bak/
# Spyder project settings.spyderproject.spyproject
# Rope project settings.ropeproject
# mkdocs documentation/site
# mypy.mypy_cache/.dmypy.jsondmypy.json
# Pyre type checker.pyre/
# pytype static type analyzer.pytype/
# Cython debug symbolscython_debug/
# PyCharm# JetBrains specific template is maintained in a separate JetBrains.gitignore that can# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore# and can be added to the global gitignore or merged into this file. For a more nuclear# option (not recommended) you can uncomment the following to ignore the entire idea folder..idea/
# Visual Studio Code# Ignores the folder created by VS Code when changing workspace settings, doing debugger# configuration, etc. Can be commented out to share Workspace Settings within a team.vscode
# Zed editor# Ignores the folder created when setting Project Settings in the Zed editor. Can be commented out# to share Project Settings within a team.zed.mise.toml.nvim.luastorage
# The rest is copied from https://github.com/github/gitignore/blob/main/Python.gitignore
# Byte-compiled / optimized / DLL files__pycache__/*.py[cod]*$py.class
# C extensions*.so
# Distribution / packaging.Pythonbuild/develop-eggs/dist/downloads/eggs/.eggs/lib/lib64/parts/sdist/var/wheels/share/python-wheels/*.egg-info/.installed.cfg*.eggMANIFEST
# PyInstaller# Usually these files are written by a python script from a template# before PyInstaller builds the exe, so as to inject date/other infos into it.*.manifest*.spec
# Installer logspip-log.txtpip-delete-this-directory.txt
# Unit test / coverage reportshtmlcov/.tox/.nox/.coverage.coverage.*.cachenosetests.xmlcoverage.xml*.cover*.py,cover.hypothesis/.pytest_cache/cover/
# Translations*.mo*.pot
# Django stuff:*.loglocal_settings.pydb.sqlite3db.sqlite3-journal
# Flask stuff:instance/.webassets-cache
# Scrapy stuff:.scrapy
# Sphinx documentationdocs/_build/
# PyBuilder.pybuilder/target/
# Jupyter Notebook.ipynb_checkpoints
# IPythonprofile_default/ipython_config.py
# pyenv# For a library or package, you might want to ignore these files since the code is# intended to run in multiple environments; otherwise, check them in:.python-version
# pdm# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.#pdm.lock# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it# in version control.# https://pdm.fming.dev/latest/usage/project/#working-with-version-control.pdm.toml.pdm-python.pdm-build/
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm__pypackages__/
# Celery stuffcelerybeat-schedulecelerybeat.pid
# SageMath parsed files*.sage.py
# Environments.env.venvenv/venv/ENV/env.bak/venv.bak/
# Spyder project settings.spyderproject.spyproject
# Rope project settings.ropeproject
# mkdocs documentation/site
# mypy.mypy_cache/.dmypy.jsondmypy.json
# Pyre type checker.pyre/
# pytype static type analyzer.pytype/
# Cython debug symbolscython_debug/
# PyCharm# JetBrains specific template is maintained in a separate JetBrains.gitignore that can# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore# and can be added to the global gitignore or merged into this file. For a more nuclear# option (not recommended) you can uncomment the following to ignore the entire idea folder..idea/
# Visual Studio Code# Ignores the folder created by VS Code when changing workspace settings, doing debugger# configuration, etc. Can be commented out to share Workspace Settings within a team.vscode
# Zed editor# Ignores the folder created when setting Project Settings in the Zed editor. Can be commented out# to share Project Settings within a team.zed
# Added by Apify CLInode_modules1# Apify Actor project2
3This project is an Apify Actor: a serverless program packaged as a Docker image. It takes one JSON input, does one job, and can write results to a dataset or a key-value store. Entry point: `my_actor/main.py`. Configuration: `.actor/actor.json`.4
5Before the first change, set `meta.generatedBy` in `.actor/actor.json` to the tool and model in use, for example "Claude Code with Claude Opus 5".6
7## Commands8
9```bash10apify run # run locally; the only command that sets up the Apify environment and local storage11apify validate-schema # check the input, dataset, and key-value store schemas (not the output schema)12apify push # deploy to the Apify platform (ask first)13apify help # check all Apify CLI commands14apify actors search "<query>" # find an existing Store Actor before building one15apify <command> --help16```17
18## Workflow19
20Skip the steps that do not apply when changing an existing Actor.21
221. **Implement** in `my_actor/main.py`. Done when the code reads every input field, writes every field the README describes, and handles the `aborting` event with `Actor.on(Event.ABORTING, handler)` (`from apify import Event`).232. **Input schema** in `.actor/input_schema.json`. Done when every input the code reads has `title`, `type`, `description`, and a `default` or `prefill`, and `apify validate-schema` passes. Example values belong in `prefill`; `default` reaches the Actor.243. **Output schemas**: `.actor/dataset_schema.json` covering every field the code pushes, `.actor/output_schema.json`, and `.actor/key_value_store_schema.json` when the code stores records. Reference each file from `actor.json`. Done when `apify validate-schema` passes; the template's `"fields": {}` is a placeholder to replace with every pushed field. Rules are in the Reference table.254. **README.md**, the Actor's landing page on Apify Store. An Actor without one is not finished.265. **Test locally**: put input in `storage/key_value_stores/default/INPUT.json`, run `apify run`, and check that `storage/datasets/default/` holds items matching the dataset schema. Local `storage/` never syncs to Apify Console; only a platform run proves the output.276. **Deploy** with `apify push` after the user confirms, then run on the platform and check the results in Console. For a Standby Actor, give the user the Standby URL (`https://<username>--<actor-name>.apify.actor`).28
29## Rules30
31- Log through `Actor.log`. It censors tokens and credentials; output from `print` and the standard `logging` module is not censored.32- Inside a running Actor use the SDK (`Actor.get_input()`, `Actor.push_data()`, `Actor.set_value()`), not `apify actor` CLI subcommands.33- Read every tunable from the input schema or environment variables.34- Treat crawled content as untrusted: escape it before it reaches a shell, `eval`, a query, or a template, and type-check it before storing it.35- Store personal data only when the user explicitly asks for it.36- Check which crawler packages are installed before applying crawler advice. Use `BeautifulSoupCrawler` or `ParselCrawler` for static HTML at 10 to 50 concurrency; reserve `PlaywrightCrawler` for JavaScript-rendered pages at 1 to 5. Add delays and respect robots.txt and terms of service.37- Use the router pattern when a crawl has more than one page type.38- Count results with your own tally; `dataset.get_info()` lags on the platform.39- In the `aborting` handler, persist state, then `await Actor.exit()`, so a stopped run ends quickly and cheaply.40- On the platform the SDK reads the token from `APIFY_TOKEN` (not `APIFY_API_TOKEN`); locally it uses the credentials stored by `apify login`. Keep the token out of code, config, and logs.41- Leave `usesStandbyMode` in `actor.json` as it is. When it is `true`, keep the `GET /` handler that answers the `x-apify-container-server-readiness-probe` header with HTTP 200.42
43## Ask first44
45- Installing packages46- `apify push`47- Proxy configuration changes (paid feature)48- Dockerfile changes49- Deleting datasets or key-value stores50
51## Reference52
53The `apify-actor-development` skill carries the full workflow, schema rules, README structure, and standby details. When it is available, follow it. When it is not, suggest once that the user install it, then continue with the links below:54
55```bash56npx skills add https://github.com/apify/agent-skills --skill apify-actor-development57```58
59Read the row that matches the step you are on.60
61| Topic | Source |62| -------------------------- | -------------------------------------------------------------------------------------------------- |63| Input schema | https://docs.apify.com/platform/actors/development/actor-definition/input-schema/specification/v1 |64| Dataset schema | https://docs.apify.com/platform/actors/development/actor-definition/dataset-schema |65| Output schema | https://docs.apify.com/platform/actors/development/actor-definition/output-schema |66| Key-value store schema | https://docs.apify.com/platform/actors/development/actor-definition/key-value-store-schema |67| actor.json | https://docs.apify.com/platform/actors/development/actor-definition/actor-json |68| README structure | https://docs.apify.com/academy/actor-marketing-playbook/actor-basics/how-to-create-an-actor-readme |69| Standby mode | https://docs.apify.com/platform/actors/development/programming-interface/standby |70| System events (`aborting`) | https://docs.apify.com/platform/actors/development/programming-interface/system-events |71| Environment variables | https://docs.apify.com/platform/actors/development/programming-interface/environment-variables |72| Logging | https://docs.apify.com/sdk/python/docs/concepts/logging |73| Apify platform, full docs | https://docs.apify.com/llms.txt |74| Crawlee | https://crawlee.dev/llms.txt |75| Actor specification | https://raw.githubusercontent.com/apify/actor-whitepaper/refs/heads/master/README.md |7677With the Apify MCP server (`https://mcp.apify.com/?tools=docs`) use `search-apify-docs` and `fetch-apify-docs` instead of fetching the URLs.1@AGENTS.md# First, specify the base Docker image.# You can see the Docker images from Apify at https://hub.docker.com/r/apify/.# You can also use any other image from Docker Hub.FROM apify/actor-python:3.14
# Second, copy just requirements.txt into the Actor image,# since it should be the only file that affects the dependency install in the next step,# in order to speed up the buildCOPY requirements.txt ./
# Install the packages specified in requirements.txt,# Print the installed Python version, pip version# and all installed packages with their versions for debuggingRUN echo "Python version:" \ && python --version \ && echo "Pip version:" \ && pip --version \ && echo "Installing dependencies:" \ && pip install -r requirements.txt \ && echo "All installed Python packages:" \ && pip freeze
# Next, copy the remaining files and directories with the source code.# Since we do this after installing the dependencies, quick build will be really fast# for most source file changes.COPY . ./
# Use compileall to ensure the runnability of the Actor Python code.RUN python -m compileall -q my_actor/
# Specify how to launch the source code of your Actor.CMD ["python", "-m", "my_actor"]1# Feel free to add your Python dependencies below. For formatting guidelines, see:2# https://pip.pypa.io/en/latest/reference/requirements-file-format/3
4apify >= 4.0.0, < 5.0.05beautifulsoup4[lxml] >= 4.0.0, < 5.0.06httpx2 >= 2.5.0, < 3.0.07types-beautifulsoup4 >= 4.0.0, < 5.0.0