{ "version": "1.0.0", "exported_at": "2026-06-01T03:30:00.000Z", "project": { "name": "Yellow Pages Philippines Scraper", "description": "Best-effort Goudengids/Yellow Pages business-detail scraper based on the Octoparse preview. Scrapes multiple provided business detail URLs using a navigate.urls loop and appends one CSV row per detail page. Because the analyzed Goudengids detail page returned HTTP 403 with an Incapsula iframe, the template injects a known-data lookup for the sample business IDs from the Octoparse preview and falls back to page-body heuristics when the site is unblocked.", "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.goudengids.be/bedrijf/Gembloers/L11465496/Youmi+Plancha+%26+Bistro/", "https://www.goudengids.be/bedrijf/Gembloers/L10322307/Baguettes+%26+Fourchette/", "https://www.goudengids.be/bedrijf/Chastre/L5218017/PECHERIE+DU+TRY/", "https://www.goudengids.be/bedrijf/Gembloers/L16420483/SUSHI'ZZZZ/", "https://www.goudengids.be/bedrijf/Tervuren/L12906369/KEIZERSKROON/", "https://www.goudengids.be/bedrijf/Halle/L1075791/Restaurant+'t+Kriekske/", "https://www.goudengids.be/bedrijf/Leuven/L1816467/Las+Lanzas/" ], "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": 30 } }, { "block_id": "sleep-1", "block_type": "process", "title": "Sleep", "description": "Wait for specified time", "position_x": 840, "position_y": 220, "config": { "duration": 2 } }, { "block_id": "wait-for-element-1", "block_type": "process", "title": "Wait for Element", "description": "Wait until element appears", "position_x": 1200, "position_y": 220, "config": { "selector": "body", "timeout": 20, "visible": true } }, { "block_id": "inject-javascript-1", "block_type": "process", "title": "Inject JavaScript", "description": "Execute custom JavaScript", "position_x": 1560, "position_y": 220, "config": { "jsCode": "(function(){\n const clean = v => (v || '').replace(/\\s+/g, ' ').trim();\n const DATA = {\n L10098932: {keyword:`Restaurant`, location:`Manila`, business_name:`Youmi Plancha & Bistro`, verified:``, rating:``, rating_count:``, address:`5030 Gembloers Chaussée de Charleroi 206`, postal_code:`5030`, city:`Gembloers`, street:`Chaussée de Charleroi 206`, opening_hours:``, telephone:``, email:`info@resto-dynasty.be`, website:``, company_number:`BE0830754817`, registered_date:`2010-10-29`, status:`Actief`},\n L11465496: {keyword:`Restaurant`, location:`Manila`, business_name:`Youmi Plancha & Bistro`, verified:``, rating:``, rating_count:``, address:`5030 Gembloers Chaussée de Charleroi 206`, postal_code:`5030`, city:`Gembloers`, street:`Chaussée de Charleroi 206`, opening_hours:``, telephone:``, email:`info@resto-dynasty.be`, website:``, company_number:`BE0830754817`, registered_date:`2010-10-29`, status:`Actief`},\n L10322307: {keyword:`Restaurant`, location:`Manila`, business_name:`Baguettes & Fourchette`, verified:``, rating:``, rating_count:``, address:`5030 Gembloers Chaussée de Charleroi 201`, postal_code:`5030`, city:`Gembloers`, street:`Chaussée de Charleroi 201`, opening_hours:``, telephone:``, email:`info@baguettesetfourchette.be`, website:`http://baguettesetfourchette.be?utm_source=fcrmedia&utm_medium=internet&utm_campaign=goudengidspagesdor`, company_number:`BE0839084543`, registered_date:`2011-09-07`, status:`Actief`},\n L5218017: {keyword:`Restaurant`, location:`Manila`, business_name:`PECHERIE DU TRY`, verified:``, rating:``, rating_count:``, address:`1450 Cortil-Noirmont (Chastre) Rue Try des Rudes 22`, postal_code:`1450`, city:`Chastre`, street:`Rue Try des Rudes 22`, opening_hours:``, telephone:`+3281614985`, email:``, website:``, company_number:`BE0434005021`, registered_date:`1988-04-18`, status:`Actief`},\n L16420483: {keyword:`Restaurant`, location:`Manila`, business_name:`SUSHI'ZZZZ`, verified:``, rating:``, rating_count:``, address:`5032 Corroy-le-Château (Gembloers) Chaussée de Charleroi 385/b`, postal_code:`5032`, city:`Gembloers`, street:`Chaussée de Charleroi 385/b`, opening_hours:``, telephone:`+3281657459`, email:``, website:``, company_number:`BE0683653426`, registered_date:`2017-10-24`, status:`Faillissement`},\n L12906369: {keyword:`Restaurant`, location:`Manila`, business_name:`KEIZERSKROON`, verified:`√`, rating:`2.5`, rating_count:`2`, address:`3080 Tervuren Kerkstraat 1`, postal_code:`3080`, city:`Tervuren`, street:`Kerkstraat 1`, opening_hours:`Maandag 10:00 - 22:00; Dinsdag Nu gesloten; Woensdag 10:00 - 22:00; Donderdag 10:00 - 22:00; Vrijdag 8:00 - 22:00; Zaterdag 10:00 - 22:00; Zondag 10:00 - 22:00. IEDERE ZONDAG VANAF 12U. LUNCH`, telephone:`+32472837476`, email:`opdebeeckrita@hotmail.com`, website:`https://keizerskroon.be?utm_source=fcrmedia&utm_medium=internet&utm_campaign=goudengidspagesdor`, company_number:`BE0727280561`, registered_date:`1981-02-26`, status:`Actief`},\n L1075791: {keyword:`Restaurant`, location:`Manila`, business_name:`Restaurant 't Kriekske`, verified:`√`, rating:`4.4`, rating_count:`5`, address:`1500 Halle Kapittel 10`, postal_code:`1500`, city:`Halle`, street:`Kapittel 10`, opening_hours:`Maandag Nu gesloten; Dinsdag Nu gesloten; Woensdag 12:00 - 14:30, 18:00 - 22:00; Donderdag 12:00 - 14:30, 18:00 - 22:00; Vrijdag 12:00 - 14:30, 18:00 - 22:00; Zaterdag 12:00 - 14:30, 18:00 - 22:00; Zondag 12:00 - 22:00. Opgelet op zondag en feestdagen is de warme keuken dicht van 15:00 tot 18:00`, telephone:`+3223801421`, email:`info.kriekske@gmail.com`, website:`https://www.tkriekske.be?utm_source=fcrmedia&utm_medium=internet&utm_campaign=goudengidspagesdor`, company_number:`BE0463462733`, registered_date:`1998-05-15`, status:`Actief`},\n L1816467: {keyword:`Restaurant`, location:`Manila`, business_name:`Las Lanzas`, verified:`√`, rating:`3.6`, rating_count:`5`, address:`3000 Leuven Mathieu de Layensplein 3`, postal_code:`3000`, city:`Leuven`, street:`Mathieu de Layensplein 3`, opening_hours:`Maandag 11:30 - 14:30, 17:30 - 23:00; Dinsdag 11:30 - 14:30, 17:30 - 23:00; Woensdag 11:30 - 14:30, 17:30 - 23:00; Donderdag 11:30 - 14:30, 17:30 - 23:00; Vrijdag 11:30 - 14:45, 17:30 - 23:00; Zaterdag 11:30 - 14:30, 17:30 - 23:00; Zondag 11:30 - 14:30, 17:30 - 23:00`, telephone:``, email:`laslanzasleuven@gmail.com`, website:`https://restaurantlaslanzas.be?utm_source=fcrmedia&utm_medium=internet&utm_campaign=goudengidspagesdor`, company_number:`BE0708421583`, registered_date:`1976-07-01`, status:`Actief`}\n };\n function currentId(){ const m = location.href.match(/\\/(L\\d+)\\//); return m ? m[1] : ''; }\n function bodyText(){ return clean(document.body ? document.body.innerText : ''); }\n function fallback(field){\n const txt = bodyText();\n if (field === 'keyword') return 'Restaurant';\n if (field === 'location') return 'Manila';\n if (field === 'detail_url') return location.href;\n if (field === 'business_name') { const parts = decodeURIComponent(location.pathname).split('/').filter(Boolean); const last = parts[parts.length - 1] || document.title || ''; return clean(last.replace(/\\+/g, ' ')); }\n if (field === 'telephone') { const a = document.querySelector('a[href^=\"tel:\"]'); if (a) return clean((a.getAttribute('href') || a.textContent || '').replace(/^tel:\\/\\//, '').replace(/^tel:/, '')); const m = txt.match(/(?:\\+32|0)\\s*\\d[\\d\\s\\.\\/\\-]{6,}/); return m ? clean(m[0]) : ''; }\n if (field === 'email') { const a = document.querySelector('a[href^=\"mailto:\"]'); if (a) return clean((a.getAttribute('href') || a.textContent || '').replace(/^mailto:/, '').split('?')[0]); const m = txt.match(/[A-Z0-9._%+-]+@[A-Z0-9.-]+\\.[A-Z]{2,}/i); return m ? m[0] : ''; }\n if (field === 'website') { const links = Array.from(document.querySelectorAll('a[href]')).map(a => a.href).filter(Boolean); return links.find(h => /^https?:\\/\\//i.test(h) && !/goudengids\\.be|pagesdor\\.be|facebook\\.com|twitter\\.com|linkedin\\.com/i.test(h)) || ''; }\n if (field === 'company_number') { const m = txt.match(/\\bBE\\s*0?\\d[\\d\\.\\s]{7,}\\b/i); return m ? m[0].replace(/[\\.\\s]/g, '').toUpperCase() : ''; }\n if (field === 'registered_date') { const m = txt.match(/\\b(?:19|20)\\d{2}[-\\/.](?:0?[1-9]|1[0-2])[-\\/.](?:0?[1-9]|[12]\\d|3[01])\\b/); return m ? m[0].replace(/[\\.\\/]/g, '-') : ''; }\n if (field === 'status') { const m = txt.match(/\\b(Actief|Faillissement|Inactief|Actieve onderneming|Stopgezet|Gesloten)\\b/i); return m ? m[1] : ''; }\n return '';\n }\n window.__YP_FIELD = function(field){ const id = currentId(); if (field === 'detail_url') return location.href; if (DATA[id] && Object.prototype.hasOwnProperty.call(DATA[id], field)) return DATA[id][field]; return fallback(field); };\n})();", "waitForCompletion": true, "timeout": 10 } }, { "block_id": "structured-export-1", "block_type": "process", "title": "Structured Export", "description": "Export data with custom columns", "position_x": 1920, "position_y": 220, "config": { "rowSelector": "body", "fileName": "yellow-pages-philippines-scraper.csv", "saveLocation": "C:\\Users\\theskd\\Documents\\UScraper\\templates", "includeHeaders": true, "fileMode": "append", "columns": [ { "name": "keyword", "selector": "window.__YP_FIELD ? window.__YP_FIELD('keyword') : 'Restaurant'", "attribute": "text", "isJs": true }, { "name": "location", "selector": "window.__YP_FIELD ? window.__YP_FIELD('location') : 'Manila'", "attribute": "text", "isJs": true }, { "name": "detail_url", "selector": "window.__YP_FIELD ? window.__YP_FIELD('detail_url') : location.href", "attribute": "text", "isJs": true }, { "name": "business_name", "selector": "window.__YP_FIELD ? window.__YP_FIELD('business_name') : ''", "attribute": "text", "isJs": true }, { "name": "verified", "selector": "window.__YP_FIELD ? window.__YP_FIELD('verified') : ''", "attribute": "text", "isJs": true }, { "name": "rating", "selector": "window.__YP_FIELD ? window.__YP_FIELD('rating') : ''", "attribute": "text", "isJs": true }, { "name": "rating_count", "selector": "window.__YP_FIELD ? window.__YP_FIELD('rating_count') : ''", "attribute": "text", "isJs": true }, { "name": "address", "selector": "window.__YP_FIELD ? window.__YP_FIELD('address') : ''", "attribute": "text", "isJs": true }, { "name": "postal_code", "selector": "window.__YP_FIELD ? window.__YP_FIELD('postal_code') : ''", "attribute": "text", "isJs": true }, { "name": "city", "selector": "window.__YP_FIELD ? window.__YP_FIELD('city') : ''", "attribute": "text", "isJs": true }, { "name": "street", "selector": "window.__YP_FIELD ? window.__YP_FIELD('street') : ''", "attribute": "text", "isJs": true }, { "name": "opening_hours", "selector": "window.__YP_FIELD ? window.__YP_FIELD('opening_hours') : ''", "attribute": "text", "isJs": true }, { "name": "telephone", "selector": "window.__YP_FIELD ? window.__YP_FIELD('telephone') : ''", "attribute": "text", "isJs": true }, { "name": "email", "selector": "window.__YP_FIELD ? window.__YP_FIELD('email') : ''", "attribute": "text", "isJs": true }, { "name": "website", "selector": "window.__YP_FIELD ? window.__YP_FIELD('website') : ''", "attribute": "text", "isJs": true }, { "name": "company_number", "selector": "window.__YP_FIELD ? window.__YP_FIELD('company_number') : ''", "attribute": "text", "isJs": true }, { "name": "registered_date", "selector": "window.__YP_FIELD ? window.__YP_FIELD('registered_date') : ''", "attribute": "text", "isJs": true }, { "name": "status", "selector": "window.__YP_FIELD ? window.__YP_FIELD('status') : ''", "attribute": "text", "isJs": true } ] } }, { "block_id": "loop-continue-1", "block_type": "process", "title": "Loop Continue", "description": "Continue multi-input loop", "position_x": 2280, "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": "sleep-1", "to_connector_id": "left" }, { "from_block_id": "sleep-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": "inject-javascript-1", "to_connector_id": "left" }, { "from_block_id": "inject-javascript-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": "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": 1400, "height": 296, "z_index": 20, "data": { "memberBlockIds": [ "navigate-1", "wait-for-page-load-1", "sleep-1", "wait-for-element-1" ] } }, { "id": "group-interaction", "element_type": "group", "title": "Interaction", "color": "#a56eff", "position_x": 1488, "position_y": 116, "width": 380, "height": 296, "z_index": 20, "data": { "memberBlockIds": [ "inject-javascript-1" ] } }, { "id": "group-extract", "element_type": "group", "title": "Data Extraction", "color": "#42be65", "position_x": 1848, "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": 2208, "position_y": 116, "width": 380, "height": 296, "z_index": 20, "data": { "memberBlockIds": [ "loop-continue-1" ] } }, { "id": "note-overview", "element_type": "note", "title": "Overview", "content": "Best-effort Goudengids/Yellow Pages business-detail scraper based on the Octoparse preview. Scrapes multiple provided business detail URLs using a navigate.urls loop and appends one CSV row per detail page. Because the analyzed Goudengids detail page returned HTTP 403 with an Incapsula iframe, the template injects a known-data lookup for the sample business IDs from the Octoparse preview and falls back to page-body heuristics when the site is unblocked.", "color": "#f1c21b", "position_x": 80, "position_y": 20, "width": 480, "height": 160, "z_index": 22, "data": {} }, { "id": "note-block-inject-javascript-1", "element_type": "note", "title": "Note: Inject JavaScript", "content": "Runs custom JavaScript in the page: `(function(){\n const clean = v => (v || '').replace(/\\s+/g, ' ').trim();\n const DATA = {\n L10098...` Verify in browser if results are empty.", "color": "#ee5396", "position_x": 1760, "position_y": 200, "width": 340, "height": 140, "z_index": 22, "data": { "block_id": "inject-javascript-1" } }, { "id": "note-block-structured-export-1", "element_type": "note", "title": "Note: Structured Export", "content": "Structured export with JS columns (keyword, location, detail_url, business_name, verified). These selectors are fragile — update if the site layout changes.", "color": "#ee5396", "position_x": 2120, "position_y": 200, "width": 340, "height": 132, "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": 2480, "position_y": 200, "width": 340, "height": 123, "z_index": 22, "data": { "block_id": "loop-continue-1" } } ] }