booking-com

<script src="https://www.booking.com/__challenge_{KEY}/{HASH}/challenge.js"></script>
<script>
  AwsWafIntegration.getToken().then(() => { window.location.href = newHref; });
</script>

def is_waf_blocked(html: str) -> bool:
    return (
        'AwsWafIntegration' in html
        or 'awsWafCookieDomainList' in html
        or 'challenge.js' in html
        or len(html) < 10_000 and '<title></title>' in html
    )

import gzip, re, urllib.request

GOOGLEBOT = {"User-Agent": "Googlebot/2.1 (+http://www.google.com/bot.html)"}

def fetch_sitemap_index(url: str) -> list[str]:
    """Returns list of child sitemap URLs from an index sitemap."""
    xml = http_get(url, headers=GOOGLEBOT)
    return re.findall(r'<loc>(https://[^<]+)</loc>', xml)

def fetch_sitemap_gz(gz_url: str) -> list[str]:
    """Decompresses a gzipped sitemap and returns all <loc> URLs."""
    req = urllib.request.Request(gz_url, headers=GOOGLEBOT)
    with urllib.request.urlopen(req, timeout=30) as r:
        data = gzip.decompress(r.read())
    return re.findall(r'<loc>(https://[^<]+)</loc>', data.decode())

# Example: get all en-gb hotel URLs
hotel_idx = http_get(
    "https://www.booking.com/sitembk-hotel-index.xml",
    headers=GOOGLEBOT
)
# 74 shards for en-gb; each shard has ~45,000-50,000 property URLs
en_gb_shards = re.findall(
    r'<loc>(https://www\.booking\.com/sitembk-hotel-en-gb\.\d+\.xml\.gz)</loc>',
    hotel_idx
)
# hotel_urls = fetch_sitemap_gz(en_gb_shards[0])  # ~50K URLs per shard

robots = http_get("https://www.booking.com/robots.txt", headers={"User-Agent": "Mozilla/5.0"})

import json, urllib.request, gzip

GQL_URL = "https://www.booking.com/dml/graphql?lang=en-gb"
GQL_HEADERS = {
    "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36",
    "Accept": "application/json",
    "Content-Type": "application/json",
    "Origin": "https://www.booking.com",
    "Referer": "https://www.booking.com/searchresults.html",
    "x-booking-context-action-name": "searchresults",
    "x-booking-context-aid": "376510",
    "x-booking-site-type-id": "1",
}

def gql(operation_name: str, query: str, variables: dict = None) -> dict:
    payload = {"operationName": operation_name, "query": query}
    if variables:
        payload["variables"] = variables
    req = urllib.request.Request(
        GQL_URL,
        data=json.dumps(payload).encode(),
        headers=GQL_HEADERS,
        method="POST"
    )
    with urllib.request.urlopen(req, timeout=20) as r:
        data = r.read()
        if r.headers.get("Content-Encoding") == "gzip":
            data = gzip.decompress(data)
        return json.loads(data.decode())

query SearchResultsPage($input: SearchQueryInput!) {
    searchQueries {
        search(input: $input) {
            __typename  # Returns SearchQueryResult type
        }
    }
}

{
  "dest_id": "-1456928",
  "dest_type": "CITY",
  "checkin": "2026-05-01",
  "checkout": "2026-05-03",
  "group_adults": "2",
  "no_rooms": "1",
  "group_children": "0",
  "selected_currency": "USD"
}

https://www.booking.com/hotel/{cc}/{slug}.html
https://www.booking.com/hotel/{cc}/{slug}.en-gb.html
https://www.booking.com/hotel/{cc}/{slug}.{lang}.html

https://www.booking.com/city/{cc}/{city-slug}.html
https://www.booking.com/region/{cc}/{region-slug}.html
https://www.booking.com/country/{cc}.html

# Always use new_tab() for the first Booking.com load in a session
tid = new_tab("https://www.booking.com/searchresults.html?ss=Paris&checkin=2026-05-01&checkout=2026-05-03&group_adults=2&no_rooms=1&selected_currency=USD")
wait_for_load()
wait(3)  # React hydration takes ~3s after readyState=complete

# Check for WAF challenge still running (rare in real Chrome)
url = page_info()["url"]
if "chal_t=" in url:
    wait(5)  # WAF challenge resolving
    wait_for_load()

def dismiss_cookie_banner():
    # Booking.com uses data-testid="accept" on the Accept button
    accepted = js("""
        (function() {
            var btn = document.querySelector('[data-testid="accept"]')
                   || document.querySelector('#onetrust-accept-btn-handler')
                   || document.querySelector('[aria-label*="Accept"]');
            if (btn) { btn.click(); return true; }
            return false;
        })()
    """)
    return accepted

# Call immediately after load if you have an EU IP
if dismiss_cookie_banner():
    wait(1)

results = js("""
  Array.from(document.querySelectorAll('[data-testid="property-card"]')).map(el => ({
    name: el.querySelector('[data-testid="title"]')?.innerText?.trim(),
    url: el.querySelector('[data-testid="title-link"]')?.href,
    price: el.querySelector('[data-testid="price-and-discounted-price"]')?.innerText?.trim(),
    rating: el.querySelector('[data-testid="review-score"]')?.innerText?.trim(),
    stars: el.querySelectorAll('[data-testid="rating-stars"] svg').length,
    location: el.querySelector('[data-testid="address"]')?.innerText?.trim(),
    availability_note: el.querySelector('[data-testid="availability-rate-information"]')?.innerText?.trim(),
    is_genius: !!el.querySelector('[data-testid="genius-label"]'),
  }))
""")

# Method 1: Next page button
next_btn = js("document.querySelector('[data-testid=\"pagination-next\"]')?.href")
if next_btn:
    goto_url(next_btn)
    wait_for_load()
    wait(3)

# Method 2: Offset parameter (25 results per page)
current_url = page_info()["url"]
offset = 25  # next page
goto_url(current_url + f"&offset={offset}")
wait_for_load()
wait(3)

detail = js("""
  ({
    name: document.querySelector('[data-testid="property-name"]')?.innerText?.trim()
       || document.querySelector('h2.hp__hotel-name, h1.pp-hotel-name-title')?.innerText?.trim(),
    rating: document.querySelector('[data-testid="rating-squares"]')
              ? document.querySelectorAll('[data-testid="rating-squares"] svg').length
              : null,
    score: document.querySelector('[data-testid="review-score-right-component"] .ac4a7896c7')?.innerText
        || document.querySelector('[aria-label*="Scored"]')?.getAttribute('aria-label'),
    address: document.querySelector('[data-testid="PropertyHeaderAddressDesktop"]')?.innerText?.trim()
          || document.querySelector('[id="hotel_address"]')?.innerText?.trim(),
    description: document.querySelector('[data-testid="property-description-content"]')?.innerText?.trim()
              || document.querySelector('#property_description_content')?.innerText?.trim(),
    amenities: Array.from(document.querySelectorAll('[data-testid="facility-list-item"]'))
                    .map(e => e.innerText?.trim()).filter(Boolean),
    room_types: Array.from(document.querySelectorAll('[data-testid="roomstable-accordion"]'))
                     .map(el => ({
                       name: el.querySelector('[data-testid="room-type-name"]')?.innerText?.trim(),
                       price: el.querySelector('[data-testid="price-and-discounted-price"]')?.innerText?.trim(),
                     })),
    lat: document.querySelector('a[href*="maps.google"]')
           ?.href?.match(/[?&]q=([^&]+)/)?.[1]?.split(',')[0],
    lon: document.querySelector('a[href*="maps.google"]')
           ?.href?.match(/[?&]q=([^&]+)/)?.[1]?.split(',')[1],
  })
""")

ld_json = js("""
  (function() {
    for (var s of document.querySelectorAll('script[type="application/ld+json"]')) {
      try {
        var d = JSON.parse(s.textContent);
        if (d['@type'] === 'Hotel' || d['@type'] === 'LodgingBusiness') return d;
      } catch(e) {}
    }
    return null;
  })()
""")
# Returns:
# {
#   "@type": "Hotel",
#   "name": "Hotel de Crillon",
#   "aggregateRating": {"ratingValue": "9.2", "reviewCount": "1423"},
#   "address": {"streetAddress": "10 Place de la Concorde", "addressLocality": "Paris", ...},
#   "geo": {"latitude": 48.865, "longitude": 2.321},
#   "starRating": {"ratingValue": 5}
# }

next_data = js("window.__NEXT_DATA__")    # dict or None
b_hotel   = js("window.b_hotel_data")    # dict or None — legacy pages

price_patterns = js("""
  ({
    // Search results card price
    search_price: document.querySelector('[data-testid="price-and-discounted-price"]')?.innerText,
    // Property page room price
    room_price: document.querySelector('[data-testid="price-and-discounted-price"]')?.innerText,
    // Original (crossed-out) price before discount
    original_price: document.querySelector('[data-testid="recommended-units-price"] s')?.innerText
                 || document.querySelector('.prco-valign-middle-helper del')?.innerText,
    // "Price for X nights" summary
    total_price: document.querySelector('[data-testid="checkout-price-summary"]')?.innerText,
    // Genius discount tag
    genius_discount: document.querySelector('[data-testid="genius-rate-badge"]')?.innerText,
  })
""")

def check_booking_waf():
    url = page_info()["url"]
    html_snippet = js("document.body?.innerHTML?.slice(0, 500)") or ""
    return (
        "chal_t=" in url
        or "AwsWafIntegration" in html_snippet
        or "challenge-container" in html_snippet
    )

def wait_past_waf(timeout=15):
    import time
    deadline = time.time() + timeout
    while time.time() < deadline:
        if not check_booking_waf():
            return True
        wait(1)
    return False  # timed out — WAF didn't resolve

# Use after goto_url():
goto_url("https://www.booking.com/searchresults.html?ss=London&checkin=2026-06-01&checkout=2026-06-03&group_adults=2&no_rooms=1")
wait_for_load()
wait_past_waf()
wait(2)  # hydration

import gzip, re, urllib.request

GOOGLEBOT = {"User-Agent": "Googlebot/2.1 (+http://www.google.com/bot.html)"}

def get_hotel_urls_for_country(cc: str, lang: str = "en-gb", max_shards: int = 2) -> list[str]:
    """Returns property page URLs for a country from sitemaps. No browser needed."""
    idx_url = f"https://www.booking.com/sitembk-hotel-index.xml"
    idx = http_get(idx_url, headers=GOOGLEBOT)
    pattern = rf'<loc>(https://www\.booking\.com/sitembk-hotel-{lang}\.\d+\.xml\.gz)</loc>'
    shards = re.findall(pattern, idx)[:max_shards]
    
    urls = []
    for shard_url in shards:
        req = urllib.request.Request(shard_url, headers=GOOGLEBOT)
        with urllib.request.urlopen(req, timeout=60) as r:
            xml = gzip.decompress(r.read()).decode()
        all_urls = re.findall(r'<loc>(https://[^<]+)</loc>', xml)
        # Filter by country code
        country_urls = [u for u in all_urls if f"/hotel/{cc}/" in u]
        urls.extend(country_urls)
    return urls

# Example: get French hotel URLs (no browser needed, instant)
# french_hotels = get_hotel_urls_for_country("fr", max_shards=1)
# len(french_hotels) -> ~8,000+ URLs from one shard