{ "version": "1.0.0", "exported_at": "2026-05-31T00:00:00.000Z", "project": { "name": "Bookingcom Listings Scraper", "description": "Scrapes Booking.com accommodation search/listing results for the keyword 北海道. Extracts keyword, hotel name, hotel URL, address/location when exposed in the card, rating label, review count, and review score. Pagination strategy: uses Booking.com's predictable search result offset URLs in a navigate.urls loop (offset=0,25,50...) and appends each page to one CSV, avoiding fragile Next-button/calendar overlay clicks. Best effort: Booking.com may show anti-bot/CAPTCHA, regional/language variations, or changed frontend selectors; some cards may not expose address text in search results.", "color": "bg-[#4589ff]", "template_id": "ai-generated" }, "blocks": [ { "block_id": "navigate-1", "block_type": "process", "title": "Navigate", "description": "Go to a URL", "position_x": 120, "position_y": 220, "config": { "urls": [ "https://www.booking.com/searchresults.html?ss=%E5%8C%97%E6%B5%B7%E9%81%93&dest_id=2347&dest_type=region&group_adults=2&no_rooms=1&group_children=0&sr_order=popularity&offset=0", "https://www.booking.com/searchresults.html?ss=%E5%8C%97%E6%B5%B7%E9%81%93&dest_id=2347&dest_type=region&group_adults=2&no_rooms=1&group_children=0&sr_order=popularity&offset=25", "https://www.booking.com/searchresults.html?ss=%E5%8C%97%E6%B5%B7%E9%81%93&dest_id=2347&dest_type=region&group_adults=2&no_rooms=1&group_children=0&sr_order=popularity&offset=50", "https://www.booking.com/searchresults.html?ss=%E5%8C%97%E6%B5%B7%E9%81%93&dest_id=2347&dest_type=region&group_adults=2&no_rooms=1&group_children=0&sr_order=popularity&offset=75", "https://www.booking.com/searchresults.html?ss=%E5%8C%97%E6%B5%B7%E9%81%93&dest_id=2347&dest_type=region&group_adults=2&no_rooms=1&group_children=0&sr_order=popularity&offset=100", "https://www.booking.com/searchresults.html?ss=%E5%8C%97%E6%B5%B7%E9%81%93&dest_id=2347&dest_type=region&group_adults=2&no_rooms=1&group_children=0&sr_order=popularity&offset=125", "https://www.booking.com/searchresults.html?ss=%E5%8C%97%E6%B5%B7%E9%81%93&dest_id=2347&dest_type=region&group_adults=2&no_rooms=1&group_children=0&sr_order=popularity&offset=150", "https://www.booking.com/searchresults.html?ss=%E5%8C%97%E6%B5%B7%E9%81%93&dest_id=2347&dest_type=region&group_adults=2&no_rooms=1&group_children=0&sr_order=popularity&offset=175", "https://www.booking.com/searchresults.html?ss=%E5%8C%97%E6%B5%B7%E9%81%93&dest_id=2347&dest_type=region&group_adults=2&no_rooms=1&group_children=0&sr_order=popularity&offset=200", "https://www.booking.com/searchresults.html?ss=%E5%8C%97%E6%B5%B7%E9%81%93&dest_id=2347&dest_type=region&group_adults=2&no_rooms=1&group_children=0&sr_order=popularity&offset=225" ], "color": "bg-[#4589ff]" } }, { "block_id": "wait-for-page-load-1", "block_type": "process", "title": "Wait for Page Load", "description": "Wait for page to finish loading", "position_x": 480, "position_y": 220, "config": { "timeout": 45 } }, { "block_id": "wait-for-element-1", "block_type": "process", "title": "Wait for Element", "description": "Wait until element appears", "position_x": 840, "position_y": 220, "config": { "selector": "[data-testid=\"property-card\"]", "timeout": 45, "visible": true } }, { "block_id": "structured-export-1", "block_type": "process", "title": "Structured Export", "description": "Export data with custom columns", "position_x": 1200, "position_y": 220, "config": { "rowSelector": "[data-testid=\"property-card\"]", "fileName": "booking-com-hotel-listings-scraper.csv", "saveLocation": "C:\\Users\\theskd\\Documents\\UScraper\\templates", "includeHeaders": true, "fileMode": "append", "columns": [ { "name": "keyword", "selector": "\"北海道\"", "attribute": "text", "isJs": true }, { "name": "hotel_name", "selector": "[data-testid=\"title\"]", "attribute": "text" }, { "name": "hotel_url", "selector": "a[data-testid=\"title-link\"]", "attribute": "href" }, { "name": "address", "selector": "(() => { const clean = s => (s || '').replace(/\\s+/g, ' ').replace(/\\s*(Show on map|show map|地図に表示).*$/i, '').trim(); const directSelectors = ['[data-testid=\"address\"]', '[data-testid=\"location\"]', '[data-testid=\"location-link\"]', '[data-testid=\"property-card-location\"]', '[data-testid=\"distance\"]']; for (const sel of directSelectors) { const v = clean(ROW.querySelector(sel)?.innerText || ROW.querySelector(sel)?.getAttribute('aria-label') || ROW.querySelector(sel)?.getAttribute('title')); if (v) return v; } const aria = Array.from(ROW.querySelectorAll('[aria-label], [title]')).map(e => clean(e.getAttribute('aria-label') || e.getAttribute('title'))).find(v => v && /(show map|show on map|地図|location|map|中心|centre|center|駅|station|北海道|hokkaido|japan|市|町|区|郡)/i.test(v)); if (aria) return clean(aria); const title = clean(ROW.querySelector('[data-testid=\"title\"]')?.innerText); const lines = (ROW.innerText || '').split(/\\n+/).map(clean).filter(Boolean); for (let i = 0; i < lines.length; i++) { if (/^(Show on map|show map|地図に表示)$/i.test(lines[i]) && i > 0) return clean(lines[i - 1]); if (/(Show on map|show map|地図に表示)/i.test(lines[i])) { const v = clean(lines[i]); if (v) return v; } } const bad = /(Scored|Rated|reviews?|クチコミ|件|Excellent|Very Good|Good|Wonderful|Superb|Pleasant|Review score|Price|night|料金|Sign in|Genius|Travel Sustainable|Breakfast|Show prices|See availability|Only \\d+|left|Free cancellation|No prepayment|Reserve|stars?|ホテル|Hotel)$/i; const candidates = lines.filter(l => l !== title && l.length > 1 && l.length < 120 && !bad.test(l) && !/^\\d+(\\.\\d+)?$/.test(l) && !/^[¥$€£]/.test(l)); const locationLike = candidates.find(l => /(中心|centre|center|駅|Station|Otaru|Sapporo|Hakodate|Furano|Asahikawa|Abashiri|Hokuto|Tomakomai|Hokkaido|北海道|Japan|市|町|区|郡|km|miles?)/i.test(l)); return locationLike || ''; })()", "attribute": "text", "isJs": true }, { "name": "rating", "selector": "(() => { const t = (ROW.querySelector('[data-testid=\"review-score\"]')?.innerText || '').replace(/\\s+/g, ' ').trim(); const direct = Array.from(ROW.querySelectorAll('[data-testid=\"review-score\"] div, [data-testid=\"review-score\"] span')).map(e => e.innerText.trim()).filter(Boolean).find(v => /^(Very Good|Excellent|Good|Wonderful|Superb|Pleasant|Review score|とても良い|すばらしい|良い|最高|満足)$/i.test(v)); if (direct) return direct; const m = t.match(/Rated\\s+([A-Za-z ]+?)(?:\\s+\\d|$)/i) || t.match(/(Very Good|Excellent|Good|Wonderful|Superb|Pleasant|Review score|とても良い|すばらしい|良い|最高|満足)/i); return m ? (m[1] || m[0]).trim() : ''; })()", "attribute": "text", "isJs": true }, { "name": "reviews", "selector": "(() => { const t = (ROW.querySelector('[data-testid=\"review-score\"]')?.innerText || ROW.innerText || '').replace(/\\s+/g, ' ').trim(); const m = t.match(/([\\d,]+)\\s*(?:reviews|件|クチコミ)/i); return m ? m[1] : ''; })()", "attribute": "text", "isJs": true }, { "name": "review_score", "selector": "(() => { const t = (ROW.querySelector('[data-testid=\"review-score\"]')?.innerText || '').replace(/\\s+/g, ' ').trim(); const m = t.match(/Scored\\s*([\\d.]+)/i) || t.match(/(?:スコア|評価)\\s*([\\d.]+)/i) || t.match(/\\b(\\d+(?:\\.\\d+)?)\\b/); return m ? m[1] : ''; })()", "attribute": "text", "isJs": true } ] } }, { "block_id": "sleep-1", "block_type": "process", "title": "Sleep", "description": "Wait for specified time", "position_x": 1560, "position_y": 220, "config": { "duration": 2 } }, { "block_id": "loop-continue-1", "block_type": "process", "title": "Loop Continue", "description": "Continue multi-input loop", "position_x": 1920, "position_y": 220, "config": {} } ], "connections": [ { "from_block_id": "navigate-1", "from_connector_id": "right", "to_block_id": "wait-for-page-load-1", "to_connector_id": "left" }, { "from_block_id": "wait-for-page-load-1", "from_connector_id": "right", "to_block_id": "wait-for-element-1", "to_connector_id": "left" }, { "from_block_id": "wait-for-element-1", "from_connector_id": "right", "to_block_id": "structured-export-1", "to_connector_id": "left" }, { "from_block_id": "structured-export-1", "from_connector_id": "right", "to_block_id": "sleep-1", "to_connector_id": "left" }, { "from_block_id": "sleep-1", "from_connector_id": "right", "to_block_id": "loop-continue-1", "to_connector_id": "left" } ], "canvas_elements": [ { "id": "group-load", "element_type": "group", "title": "Page Load", "color": "#08bdba", "position_x": 48, "position_y": 116, "width": 1760, "height": 296, "z_index": 20, "data": { "memberBlockIds": [ "navigate-1", "wait-for-page-load-1", "wait-for-element-1", "sleep-1" ] } }, { "id": "group-extract", "element_type": "group", "title": "Data Extraction", "color": "#42be65", "position_x": 1128, "position_y": 116, "width": 380, "height": 296, "z_index": 20, "data": { "memberBlockIds": [ "structured-export-1" ] } }, { "id": "group-pagination", "element_type": "group", "title": "Pagination Loop", "color": "#ff832b", "position_x": 1848, "position_y": 116, "width": 380, "height": 296, "z_index": 20, "data": { "memberBlockIds": [ "loop-continue-1" ] } }, { "id": "note-overview", "element_type": "note", "title": "Overview", "content": "Scrapes Booking.com accommodation search/listing results for the keyword 北海道. Extracts keyword, hotel name, hotel URL, address/location when exposed in the card, rating label, review count, and review score. Pagination strategy: uses Booking.com's predictable search result offset URLs in a navigate.urls loop (offset=0,25,50...) and appends each page to one CSV, avoiding fragile Next-button/calendar overlay clicks. Best effort: Booking.com may show anti-bot/CAPTCHA, regional/language variations, or changed frontend selectors; some cards may not expose address text in search results.", "color": "#f1c21b", "position_x": 80, "position_y": 20, "width": 480, "height": 160, "z_index": 22, "data": {} }, { "id": "note-block-navigate-1", "element_type": "note", "title": "Note: Navigate", "content": "Multi-URL loop over 10 pages. Pair with loop-continue at the end of each iteration.", "color": "#ee5396", "position_x": 320, "position_y": 200, "width": 332, "height": 107, "z_index": 22, "data": { "block_id": "navigate-1" } }, { "id": "note-block-structured-export-1", "element_type": "note", "title": "Note: Structured Export", "content": "Structured export with JS columns (keyword, address, rating, reviews, review_score). These selectors are fragile — update if the site layout changes.", "color": "#ee5396", "position_x": 1400, "position_y": 200, "width": 340, "height": 129, "z_index": 22, "data": { "block_id": "structured-export-1" } }, { "id": "note-block-loop-continue-1", "element_type": "note", "title": "Note: Loop Continue", "content": "Loop Continue advances a multi-URL or multi-text loop. Place at the end of the loop body with a clear back-edge to the loop start.", "color": "#ee5396", "position_x": 2120, "position_y": 200, "width": 340, "height": 123, "z_index": 22, "data": { "block_id": "loop-continue-1" } } ] }