Booking.com Scraper - Rate History, Alerts & PDP Enrichment

🧩 Part of the harvestlab MCP suite — 36 RAG-ready, AI-agent-payment-ready Apify actors covering ecommerce, social, travel, news, jobs, EU B2B, dev-tools, and government data. See the full suite →

Extract hotel listings, nightly prices, guest reviews, star ratings, and amenities from Booking.com search results — plus cross-run rate-history tracking, a rate-alert tier that fires only when a hotel hits your price-drop / volatility / new-low threshold, and an optional PDP enrichment mode that visits each hotel's detail page for descriptions, full amenities, check-in/out times, and house rules.

Whether you need hotel price comparison data for a travel app, competitive analysis for revenue management, or hospitality market research at scale, this actor delivers structured, ready-to-use hotel data from the world's largest travel platform. Re-run it on the same destination and dates — it remembers across runs with no external database required.

What it does

This actor scrapes Booking.com search results and hotel detail pages, then layers on rate intelligence that standard scrapers never ship. On every run it extracts hotel names, nightly prices, star ratings, guest review scores, amenity lists, and photos. Enable fetchDetails and it deep-crawls each hotel's PDP for full descriptions, check-in/out times, house rules, and languages spoken.

The real differentiator is cross-run rate-history tracking. Every price is persisted to a named Apify key-value store keyed by (destination, check-in, check-out), so each subsequent run automatically computes 7-day and 30-day price deltas, volatility flags, rolling min/max/avg, and a rate-movement digest that surfaces the biggest movers — with zero external database setup.

Pair that with the rate-alert tier and you have a standing price-watch service: set alertMode to price_drop, volatile, or new_low, and the actor only charges (and fires a dataset item) when a hotel actually breaches your threshold. You pay per actionable signal, not per page scraped.

Optional AI market analysis — backed by OpenRouter, Anthropic, Google AI, OpenAI, or self-hosted Ollama — delivers a structured narrative covering pricing trends, quality distribution, competitive positioning, and booking-window recommendations derived from your rate history. When rate-history is enabled, the AI report gets a dedicated Rate Dynamics section with 7/30-day delta commentary and booking-window advice.

How this compares to other Booking.com scrapers on the Apify Store

Actor	Price model	Rate-history	AI analysis
This actor	$0.005/hotel + events	Yes — 7/30-day deltas + alerts	Yes — 5-provider LLM
voyager/booking-scraper	$0.002/hotel	No	No
automation-lab/booking-scraper	$0.005/hotel + $0.05/run fee	No	No
scrapepilot/booking-com-hotel-scraper	Subscription	No	No

This is the only Booking.com scraper on the Store that bundles AI-powered market analysis AND cross-run rate-history tracking. Per-hotel pricing matches automation-lab but without the $0.05 run fee, and there is no subscription lock-in.

Pricing

Event	Price	When charged
hotel-scraped	$0.005	Per hotel listing extracted
detail-scraped	$0.01	Per hotel PDP enriched (fetchDetails=true)
rate-alert-triggered	$0.02	Per hotel matching the alertMode criterion
ai-analysis-completed	$0.05	Per AI market analysis report (one per run)

Cost examples:

Scenario	Hotels	PDP	AI	Alerts	Total
Quick price check	10	No	No	0	$0.05
Destination comparison	50	No	No	0	$0.25
Full market analysis	50	No	Yes	0	$0.30
Enriched market audit	50	Yes	Yes	0	$0.80
Daily rate-watch	50	No	No	3	$0.31
Premium revenue-mgmt stack	50	Yes	Yes	5	$0.90

vs. commercial alternatives: OTA Insight charges $200+/mo and RateGain uses subscription pricing for hotel rate intelligence APIs. This actor uses pay-per-event with no subscription: $0.005/hotel and zero monthly fees.

Typical runtime

• 10 hotels without reviews: 1–2 minutes
• 50 hotels without reviews: 3–5 minutes
• 50 hotels with reviews: 8–12 minutes
• AI analysis adds ~15–30 seconds per run

Features

• Full hotel data extraction — name, price per night, currency, star rating, guest review score, review count, location, property type, amenities, and photos
• PDP enrichment mode — enable fetchDetails to deep-crawl each hotel's detail page for description, full amenities_full[], property_type, checkin_time, checkout_time, house_rules[], and languages_spoken[]. Charged separately at $0.01 per PDP
• Rate-alert tier — pick an alertMode (price_drop, volatile, new_low, or all), set alertThresholdPct, and the actor emits a dedicated hotel_rate_alert dataset item only when a hotel breaches the threshold. Pay per actionable alert ($0.02 each), not per scrape. Combine with Apify's scheduler for a standing rate-watch service
• Cross-run rate-history tracking — persist every run's prices to a named key-value store and emit delta_pct_7d, delta_pct_30d, direction, is_volatile, rate_min_30d, rate_max_30d, rate_avg_30d on every hotel. A rate-movement digest item per run surfaces the biggest 7-day hikes, drops, and most volatile properties. Free feature, no extra HTTP calls
• 5 sort options — sort results by popularity, price (low to high), price (high to low), guest rating, or star rating
• Guest review scraping — collect up to 50 reviews per hotel with reviewer name, score, positive/negative comments, and date
• Lazy-load handling — automatically scrolls through Booking.com's dynamically loaded search results to capture all listings
• Flexible search input — search by destination name or paste a full Booking.com search URL with pre-applied filters
• Check-in/check-out dates — get accurate nightly pricing for your specific travel dates
• AI market analysis with rate dynamics — optional LLM-powered report covering pricing trends, quality distribution, competitive positioning, strategic recommendations, and when rate-history is enabled, a dedicated Rate Dynamics section
• Multi-LLM support — choose between OpenRouter (recommended — 300+ models), Anthropic (Claude), Google AI (Gemini), OpenAI (GPT), or Ollama (self-hosted)
• Residential proxy support — built-in configuration for Apify residential proxies, critical for reliable Booking.com scraping

Use Cases

• Hotel revenue managers — track competitor pricing across your market daily. Identify pricing gaps, monitor rate parity, and inform dynamic pricing strategies with real data instead of manual checks. The rate-alert tier sends actionable signals only when a competitor actually moves price, so you are not buried in noise
• Travel tech companies — feed structured hotel data into price comparison engines, travel planning apps, and deal alert systems. Build fare trackers and accommodation aggregators without maintaining your own scraping infrastructure
• Hospitality market researchers — analyze pricing trends, quality distribution, and competitive positioning across destinations. Generate reports on market saturation and opportunity zones using the AI market analysis report
• Hotel owners and operators — understand how your property stacks up against competitors on price, reviews, and amenities. The rate-history tracking gives you a rolling 30-day baseline, so you can see whether competitor pricing is trending up or down over time
• Real estate investors in hospitality — evaluate hotel markets before acquiring properties. Compare revenue potential across locations using actual pricing and occupancy signals from Booking.com combined with AI investment analysis
• OTAs and travel aggregators — collect structured hotel data at scale. The PDP enrichment mode delivers full descriptions, amenity lists, house rules, and check-in/out windows — everything needed to populate a property listing without separate API contracts
• Travel bloggers and content creators — gather accurate, up-to-date accommodation data for destination guides, deal roundups, and travel recommendation content
• Academic researchers — collect hospitality pricing datasets for tourism economics studies, market efficiency research, and price discrimination analysis

Pair with the Hotel Reputation Suite

Booking.com Scraper covers the price + amenities + rate-history half of hotel intelligence. Pair it with harvestlab/ai-review-analyzer (publishing in the next quota window) for the review-quality half — AI sentiment scoring, SimHash duplicate detection, astroturfing scores, and cross-platform consistency analysis. Together they form a full-stack Hotel Reputation Suite: every property gets paired pricing/availability data and review-authenticity signals from one workflow.

This pairing is the buyer-curated context Apify highlighted in its Best hotel reputation management tools in 2026 blog post (2026-04-17), which positioned scraping plus review-intelligence as the canonical stack for hotel reputation work.

Suite use cases

• Revenue managers reconcile rate-history shifts from this actor against review-sentiment trends from ai-review-analyzer — when a competitor's nightly price drops while their sentiment score deteriorates, you have a defensible signal to hold or raise your own rate instead of chasing the discount.
• Travel agencies and OTAs vet hotels before recommending them. Pull pricing and amenities here, then run the review feed through ai-review-analyzer to flag astroturfing or duplicate-review clusters. Hotels with clean reputation scores graduate to your recommended list; flagged ones get a second look.
• Hotel owners and operators benchmark their own property against direct competitors on both axes. This actor surfaces price gaps and amenity mismatches; ai-review-analyzer surfaces sentiment drivers and authenticity scores. The combined view answers "Are competitors winning on price, on perception, or both?"
• PR and comms teams track reputation crises with rate-impact analysis. When a hotel hits the news, the rate-alert tier here flags whether competitors are repricing in response, while ai-review-analyzer tracks the sentiment shift across platforms — letting communicators correlate narrative and revenue impact in near real time.

The two actors share the same input ergonomics (residential proxy recommended, 5-provider LLM stack, pay-per-event monetization), so existing booking-scraper users can layer the reputation half onto current schedules without retooling.

Use with AI agents

booking-scraper outputs hotels + 7/30-day rate-history deltas + amenities + AI market analysis as structured JSON — a RAG-ready agent tool for revenue-managers, travel-research agents, and reputation-monitoring workflows. Wrap it as a tool inside a hotel-revenue or travel-planning agent and replace manual rate-shopping or per-call STR/OTA Insight pulls.

LangChain — track_booking_hotels tool (revenue-manager / travel-agency alternative):

from langchain.tools import Tool
from apify_client import ApifyClient

client = ApifyClient("YOUR_APIFY_TOKEN")

def track_booking_hotels(params: dict) -> list:
    run = client.actor("harvestlab/booking-scraper").call(run_input={
        "destination": params["destination"],
        "checkIn": params.get("checkIn"),
        "checkOut": params.get("checkOut"),
        "fetchDetails": params.get("fetchDetails", True),
        "enableRateHistory": True,
        "enableAiAnalysis": True,
        "proxyConfiguration": {"useApifyProxy": True, "apifyProxyGroups": ["RESIDENTIAL"]},
    })
    return list(client.dataset(run["defaultDatasetId"]).iterate_items())

track_booking_hotels_tool = Tool(
    name="track_booking_hotels",
    description="Scrape Booking.com hotels with 7/30-day rate-history deltas, PDP amenities, and 5-provider AI market analysis. RAG-ready for revenue-management and travel-research agents.",
    func=track_booking_hotels,
)
# agent.invoke({"input": "Track Amsterdam hotels for 2026-06-01 to 2026-06-04 and flag any price drops"})

LangGraph — node in a hotel-revenue graph:

from langgraph.graph import StateGraph
from apify_client import ApifyClient

client = ApifyClient("YOUR_APIFY_TOKEN")

def hotels_node(state: dict) -> dict:
    run = client.actor("harvestlab/booking-scraper").call(run_input={
        "destination": state["city"],
        "checkIn": state["checkIn"],
        "checkOut": state["checkOut"],
        "maxListings": 50,
        "enableRateHistory": True,
        "alertMode": "price_drop",
        "alertThresholdPct": 10,
    })
    items = list(client.dataset(run["defaultDatasetId"]).iterate_items())
    hotels = [i for i in items if i.get("type") != "hotel_rate_alert" and i.get("type") != "rate_movement_digest"]
    ranked = sorted(hotels, key=lambda h: (h.get("review_score") or 0), reverse=True)
    price_drops = [h for h in hotels if (h.get("delta_pct_7d") or 0) <= -10]
    return {**state, "ranked_hotels": ranked, "price_drop_flagged": price_drops}

graph = StateGraph(dict)
graph.add_node("hotels", hotels_node)
# wire into downstream rate-recommendation / pace-vs-comp / Slack-alert nodes

See Apify's actor-templates/js-langchain and js-langgraph-agent for full reference setups.

Input

All parameters are optional except for at least one of searchUrl or destination.

Parameter	Type	Default	Description
searchUrl	string	—	Full Booking.com search URL (overrides destination/date params)
destination	string	—	City or area name (e.g. "Amsterdam", "Paris 6th arrondissement")
checkIn	string	—	Check-in date in YYYY-MM-DD format
checkOut	string	—	Check-out date in YYYY-MM-DD format
currency	string	EUR	3-letter ISO 4217 currency code for prices
maxListings	integer	25	Maximum hotels to scrape (1–100)
includeReviews	boolean	false	Scrape top guest reviews per hotel
maxReviewsPerHotel	integer	10	Reviews to collect per hotel (1–50)
sortBy	string	popularity	Sort order: popularity, price_low, price_high, rating, stars_high
enableRateHistory	boolean	true	Track prices across runs and emit 7/30-day deltas and volatility flags. Free feature
fetchDetails	boolean	false	Visit each hotel's PDP to enrich with description, full amenities, check-in/out times, house rules, and languages. $0.01 per PDP
alertMode	string	off	Rate-alert mode: off, price_drop, volatile, new_low, or all. Requires rate-history. $0.02 per alert fired
alertThresholdPct	integer	10	Percentage threshold for price_drop and volatile alert modes
enableAiAnalysis	boolean	false	Generate AI-powered market analysis report
llmProvider	string	openrouter	LLM provider: openrouter, anthropic, google, openai, or ollama
llmModel	string	—	Specific model identifier (leave empty for recommended default)
openrouterApiKey	string	—	OpenRouter API key
anthropicApiKey	string	—	Anthropic API key
googleApiKey	string	—	Google AI API key
openaiApiKey	string	—	OpenAI API key
ollamaBaseUrl	string	http://localhost:11434	Base URL for self-hosted Ollama
proxyConfiguration	object	—	Proxy settings (residential strongly recommended)

Provide either searchUrl (a full Booking.com search URL with filters pre-applied) or destination (a city/area name). When using destination, set checkIn and checkOut for accurate pricing — without dates, Booking.com may show estimated prices or no prices at all.

Full example input

{
    "destination": "Amsterdam",
    "checkIn": "2026-06-01",
    "checkOut": "2026-06-04",
    "maxListings": 30,
    "includeReviews": true,
    "maxReviewsPerHotel": 5,
    "sortBy": "rating",
    "enableRateHistory": true,
    "alertMode": "price_drop",
    "alertThresholdPct": 10,
    "fetchDetails": true,
    "enableAiAnalysis": true,
    "llmProvider": "openrouter",
    "openrouterApiKey": "sk-or-...",
    "proxyConfiguration": {
        "useApifyProxy": true,
        "apifyProxyGroups": ["RESIDENTIAL"]
    }
}

CLI aliases

The following hidden fields accept the same values as their canonical counterparts and are accepted via the Apify CLI or API for backward compatibility: searchQuery, query, city, location (alias for destination); checkInDate (alias for checkIn); checkOutDate (alias for checkOut); maxHotels, maxResults, maxItems (aliases for maxListings); includeDetails (alias for fetchDetails).

Output

Each hotel is pushed as a separate dataset item. Below is a complete example including rate-history and PDP fields:

{
    "name": "Hotel V Nesplein",
    "url": "https://www.booking.com/hotel/nl/v-nesplein.html",
    "price_per_night": 189.0,
    "currency": "EUR",
    "stars": 4,
    "review_score": 9.1,
    "review_count": 4521,
    "location": "Amsterdam City Center",
    "distance_from_center": "0.6 km from downtown",
    "property_type": "Hotel",
    "breakfast_included": true,
    "free_cancellation": true,
    "amenities": ["Free WiFi", "Breakfast included", "Bar", "24-hour front desk"],
    "image_url": "https://cf.bstatic.com/xdata/images/hotel/...",
    "reviews": [
        {
            "reviewer": "John",
            "score": 9.0,
            "positive": "Perfect location, very friendly staff",
            "negative": "Room was a bit small",
            "date": "March 2026"
        }
    ],
    "direction": "up",
    "delta_pct_7d": 7.14,
    "delta_pct_30d": 50.0,
    "is_volatile": false,
    "rate_previous": 145.0,
    "rate_min_30d": 100.0,
    "rate_max_30d": 189.0,
    "rate_avg_30d": 161.25,
    "history_sample_count": 12,
    "description": "Hotel V Nesplein enjoys a central location in the heart of Amsterdam...",
    "amenities_full": ["Free WiFi", "Bar", "Restaurant", "Room service", "24-hour front desk", "Airport shuttle", "Spa", "Fitness centre"],
    "checkin_time": "From 15:00",
    "checkout_time": "Until 11:00",
    "house_rules": ["No pets allowed", "Children under 12 stay free when using existing beds"],
    "languages_spoken": ["English", "Dutch", "German", "French"],
    "details_scraped": true,
    "scraped_at": "2026-04-10T12:00:00+00:00"
}

Field reference

Field	Type	Description
name	string	Hotel name as shown on Booking.com
url	string	Canonical Booking.com hotel page URL (tracking params stripped)
price_per_night	float	Nightly price in the selected currency (null if dates not provided)
currency	string	3-letter ISO 4217 currency code (e.g. EUR, USD)
stars	int	Official star rating 1–5 (null for apartments / hostels)
review_score	float	Guest review score 0.0–10.0
review_count	int	Total number of guest reviews
location	string	Neighborhood or area, falls back to distance from center
distance_from_center	string	Human-readable distance from downtown
property_type	string	Hotel, Apartment, Hostel, Resort, etc.
breakfast_included	bool	Whether breakfast is included in the listed price
free_cancellation	bool	Whether the rate offers free cancellation
amenities	list[string]	Up to 10 amenity tags from the search card
image_url	string	First hero image URL
reviews	list[object]	Top guest reviews (only when includeReviews=true)
direction	string	Rate direction vs last scrape: up, down, flat, new
delta_pct_7d	float	% price change vs scrape ~7 days ago (null on first run)
delta_pct_30d	float	% price change vs scrape ~30 days ago (null on first run)
is_volatile	bool	True when 7-day stddev/mean exceeds 12%
rate_previous	float	Most recent prior price from rate history
rate_min_30d	float	Minimum observed price in the last 30 days
rate_max_30d	float	Maximum observed price in the last 30 days
rate_avg_30d	float	Average observed price in the last 30 days
history_sample_count	int	Number of historical snapshots stored for this hotel
description	string	Hotel description from PDP (fetchDetails=true only)
amenities_full	list[string]	Full amenity list from PDP (up to 40 items)
checkin_time	string	Check-in window (e.g. "From 15:00") — PDP only
checkout_time	string	Check-out time (e.g. "Until 11:00") — PDP only
house_rules	list[string]	Bullet list of hotel policies from PDP (up to 20 items)
languages_spoken	list[string]	Languages spoken at reception — PDP only
details_scraped	bool	True when PDP enrichment was applied to this row
scraped_at	string	ISO-8601 UTC timestamp of the scrape

Rate-alert items (when alertMode != "off")

A dedicated hotel_rate_alert item is pushed for each hotel that matches the threshold criterion. One alert = one rate-alert-triggered event at $0.02:

{
    "type": "hotel_rate_alert",
    "alert_mode": "price_drop",
    "alert_threshold_pct": 10,
    "alert_reasons": ["price_drop:18.3%_below_30d_avg", "new_low:at_or_below_30d_min=95.0"],
    "hotel_name": "YOTEL Amsterdam",
    "hotel_url": "https://www.booking.com/hotel/nl/yotel-amsterdam.html",
    "currency": "EUR",
    "rate_now": 95.0,
    "rate_previous": 140.0,
    "rate_avg_30d": 116.3,
    "rate_min_30d": 95.0,
    "rate_max_30d": 150.0,
    "delta_pct_7d": -32.1,
    "delta_pct_30d": -18.3,
    "direction": "down",
    "scraped_at": "2026-04-22T12:00:00+00:00"
}

Hotels with zero history (first run for a new slot) never fire alerts — seeding runs are silent. Combine with Apify's scheduler and webhooks to receive email or Slack notifications only when a competitor genuinely moves price.

Rate-movement digest

Once per run, a rollup item highlights the biggest 7-day movers and any hotels with volatile pricing:

{
    "type": "rate_movement_digest",
    "destination": "Amsterdam",
    "check_in": "2026-06-01",
    "check_out": "2026-06-03",
    "hotels_with_history": 6,
    "biggest_hikes_7d": [
        {"name": "Hotel V Nesplein", "url": "...", "rate_now": 189.0, "rate_previous": 160.0, "delta_pct_7d": 18.1, "currency": "EUR"}
    ],
    "biggest_drops_7d": [
        {"name": "YOTEL Amsterdam", "url": "...", "rate_now": 112.0, "rate_previous": 140.0, "delta_pct_7d": -20.0, "currency": "EUR"}
    ],
    "volatile_hotels": [
        {"name": "Zoku Amsterdam", "url": "...", "rate_now": 210.0, "rate_avg_30d": 180.0, "rate_min_30d": 120.0, "rate_max_30d": 260.0, "currency": "EUR"}
    ],
    "generated_at": "2026-04-10T12:00:00+00:00"
}

AI analysis output

When AI analysis is enabled, an additional dataset item is pushed containing a comprehensive market report:

{
    "type": "ai_analysis_report",
    "provider": "openrouter",
    "model": "google/gemini-2.0-flash-001",
    "analysis": "## Market Overview\n\nAnalyzing 30 properties in Amsterdam...",
    "hotels_analyzed": 30,
    "generated_at": "2026-04-10T12:00:00+00:00"
}

The AI analysis covers market overview, pricing distribution, quality segmentation, competitive positioning, top value picks, strategic recommendations, and — when rate-history is enabled — a Rate Dynamics section with booking-window advice derived from 30-day rolling price data.

Quick Start

The simplest run — just provide a destination:

{
    "destination": "Amsterdam",
    "maxListings": 10
}

This scrapes the top 10 hotels in Amsterdam sorted by popularity. Set a residential proxy in proxyConfiguration for reliable results.

Rate-surveillance setup (recommended for revenue managers)

Schedule the actor daily against the same destination and dates to build 30-day rolling history, then layer on alerts:

{
    "destination": "Amsterdam",
    "checkIn": "2026-06-01",
    "checkOut": "2026-06-04",
    "maxListings": 50,
    "enableRateHistory": true,
    "alertMode": "price_drop",
    "alertThresholdPct": 10,
    "proxyConfiguration": {
        "useApifyProxy": true,
        "apifyProxyGroups": ["RESIDENTIAL"]
    }
}

On the first run every hotel shows direction: "new" — it is seeding the history. From the second run onward the deltas and alerts populate.

Full revenue-management stack

Combine PDP enrichment, rate-alerts, and AI analysis for the maximum signal-per-run ratio:

{
    "destination": "Amsterdam",
    "checkIn": "2026-06-01",
    "checkOut": "2026-06-04",
    "maxListings": 50,
    "enableRateHistory": true,
    "alertMode": "all",
    "alertThresholdPct": 10,
    "fetchDetails": true,
    "enableAiAnalysis": true,
    "llmProvider": "openrouter",
    "openrouterApiKey": "sk-or-...",
    "proxyConfiguration": {
        "useApifyProxy": true,
        "apifyProxyGroups": ["RESIDENTIAL"]
    }
}

Tips for best results

• Start with 10–15 hotels to verify output before scaling to larger runs
• Sort by rating when running competitive analysis to surface the strongest competitors first
• Use AI analysis with 15+ hotels — the market report is significantly more insightful with a larger dataset
• Always provide both checkIn and checkOut dates for accurate pricing
• Keep destination, checkIn, and checkOut identical across runs for consistent rate-history keys
• The actor uses Playwright (Chromium) to render Booking.com's JavaScript-heavy pages and handles lazy-loaded content by scrolling automatically

Troubleshooting

Actor returns 403 or scrapes 0 hotels despite a valid destination

Booking.com blocks datacenter IP addresses aggressively. Without a residential proxy, almost every request ends in a 403 or an empty result set. Set proxyConfiguration.useApifyProxy: true with apifyProxyGroups: ["RESIDENTIAL"]. Datacenter proxies are insufficient — residential is a hard requirement.

Prices differ from what I see on Booking.com

Booking.com personalizes prices based on login status, Genius loyalty tier, country of origin, and device type. The actor fetches as an anonymous visitor. Use a RESIDENTIAL proxy in the target country to get representative local pricing — a US residential proxy returns USD prices, a UK residential proxy returns GBP. Genius discounts (up to 20%) are not accessible without an authenticated session.

Date format rejected or no results returned for specific dates

Dates must be in YYYY-MM-DD format (e.g. 2026-06-01). Formats like 06/01/2026 or June 1 are silently ignored and the actor falls back to a default near-future date. Verify that the check-out date is at least one day after check-in — same-day values produce no results.

No hotels returned even though the destination exists

Booking.com search can return empty results if your dates are too far in the future (beyond ~18 months), the destination string is ambiguous, or there are no available properties meeting Booking's availability criteria for those dates. Try a nearby major city to confirm the actor is working, then narrow to your target. Omitting dates is also a common cause — always provide both checkIn and checkOut.

Actor slows down or times out on large runs with reviews enabled

Review scraping requires visiting each hotel's individual detail page, which multiplies the number of HTTP requests by maxListings. Start with maxReviewsPerHotel: 5 and maxListings: 20 when testing. For large runs, disable reviews on the first pass, then re-run targeted hotel URLs with reviews enabled.

Rate history shows no deltas on the second run

Cross-run history requires the same hotel IDs to appear in both runs. If you change the destination, dates, or sort order between runs, a new KV-store slot is created and no prior baseline exists. Keep destination, checkIn, and checkOut identical across runs. The first run for any slot produces direction: "new" — deltas appear from the second run onward. History is capped at 90 snapshots per hotel, giving roughly 3 months of lookback on a daily schedule.

AI analysis fails with "API key missing"

Set openrouterApiKey (or your chosen provider's key field) in the actor input, or set the corresponding environment variable (OPENROUTER_API_KEY, ANTHROPIC_API_KEY, GOOGLE_API_KEY, or OPENAI_API_KEY). AI analysis is optional — set enableAiAnalysis: false to run without it. The actor will skip AI silently if no key is provided and will not abort the scrape.

PDP enrichment returns null for some fields

property_type, amenities, breakfast_included, and free_cancellation are only populated when Booking exposes them in the search card DOM. In some A/B variants these fields appear only on the hotel detail page. When missing they are returned as null / [] rather than falsified. Enable fetchDetails=true for the most complete amenity data.

Rate alerts not firing even though prices have changed

Alerts require at least one prior snapshot in history, so the very first run for a new (destination, check-in, check-out) slot is always silent — it is seeding the data. Check that alertMode is not off and that alertThresholdPct is set appropriately. The rate_movement_digest item on each run shows which hotels have history and which do not.

Legal and Compliance

This actor scrapes publicly available data. By using this actor, you agree to the following:

• Your responsibility: You are solely responsible for ensuring your use complies with all applicable laws, regulations, and the target website's terms of service. This includes but is not limited to GDPR (EU), CCPA (California), and other data protection laws in your jurisdiction.
• No legal advice: This actor does not constitute legal advice. Consult a qualified attorney if you have questions about the legality of your specific use case.
• Intended use: This actor is designed for legitimate business purposes such as market research, competitive analysis, and academic research using publicly accessible data.
• Data handling: You are responsible for how you store, process, and share any data collected. Ensure you have a lawful basis for processing any personal data under applicable privacy laws.
• Rate limiting: This actor implements polite crawling practices including request delays and retry backoff to minimize impact on target servers.
• No warranty: This actor is provided "as is" without warranty. Data accuracy depends on the target website's content and structure.
• Booking.com terms: Booking.com's terms of service restrict automated data collection. Use residential proxies and moderate request volumes to reduce detection risk and server load.
• Personal data notice: Hotel review data may contain reviewer names which constitute personal data under GDPR. Ensure you have a lawful basis for processing. Do not use reviewer data for direct marketing or unsolicited contact.
• Related actors: Zillow Scraper for US real estate · Funda Scraper for Dutch real estate · Review Analyzer for AI sentiment · Trustpilot Scraper for brand reputation · News Monitor for travel industry news