{ "version": "1.0.0", "exported_at": "2026-06-02T02:20:00.000Z", "project": { "name": "Lamudi Post Details Scraper", "description": "Scrapes Lamudi Mexico property detail pages by URL, extracting title, price, address, technical specifications, description, amenities, up to five image URLs, page URL, publication date, and scrape timestamp. Navigation uses a multi-URL loop: add all target Lamudi detail URLs to the navigate.urls array; each successful page is appended to one CSV. Lamudi may show an anti-bot page with the text 'Let's confirm you are human'; this template detects that challenge and skips extraction for blocked pages to avoid writing invalid rows.", "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.lamudi.com.mx/detalle/41032-73-c184fc1ac04f-8b77-4e258a79-bd73-46ca", "https://www.lamudi.com.mx/detalle/41032-73-e4e47f9a0eca-81d1-6557ce60-bf43-46d3" ], "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": 456, "position_y": 220, "config": { "timeout": 30 } }, { "block_id": "wait-for-element-1", "block_type": "process", "title": "Wait for Element", "description": "Wait until element appears", "position_x": 792, "position_y": 220, "config": { "selector": "body", "timeout": 30, "visible": true } }, { "block_id": "text-contains-1", "block_type": "process", "title": "Text Contains", "description": "Check if page contains text", "position_x": 1128, "position_y": 220, "config": { "text": "Let's confirm you are human", "selector": "body", "caseSensitive": false } }, { "block_id": "inject-javascript-1", "block_type": "process", "title": "Inject JavaScript", "description": "Run custom JavaScript", "position_x": 1128, "position_y": 520, "config": { "jsCode": "window.scrollTo(0, document.body.scrollHeight);\nwindow.__US_LAMUDI_DETAIL__ = (() => {\n const norm = (v) => (v == null ? '' : String(v)).replace(/\\s+/g, ' ').trim();\n const bodyText = () => norm(document.body ? document.body.innerText : '');\n const meta = (name) => norm(document.querySelector(`meta[property=\"${name}\"], meta[name=\"${name}\"]`)?.content || '');\n const qText = (selectors) => {\n for (const sel of selectors) {\n const el = document.querySelector(sel);\n const txt = norm(el?.innerText || el?.textContent || el?.content || '');\n if (txt) return txt;\n }\n return '';\n };\n const parseJsonLd = () => {\n const out = [];\n document.querySelectorAll('script[type=\"application/ld+json\"]').forEach((s) => {\n try {\n const parsed = JSON.parse(s.textContent || '{}');\n if (Array.isArray(parsed)) out.push(...parsed); else out.push(parsed);\n } catch (_) {}\n });\n return out;\n };\n const findKey = (wanted) => {\n const seen = new Set();\n const walk = (x) => {\n if (!x || seen.has(x)) return '';\n if (typeof x === 'object') seen.add(x);\n if (Array.isArray(x)) {\n for (const item of x) {\n const got = walk(item);\n if (got) return got;\n }\n return '';\n }\n if (typeof x !== 'object') return '';\n for (const [k, v] of Object.entries(x)) {\n if (wanted.includes(String(k).toLowerCase())) {\n if (typeof v === 'string' || typeof v === 'number') return norm(v);\n if (v && typeof v === 'object') {\n if (v.streetAddress || v.addressLocality || v.addressRegion || v.postalCode) {\n return norm([v.streetAddress, v.addressLocality, v.addressRegion, v.postalCode].filter(Boolean).join(', '));\n }\n const compact = norm(Object.values(v).filter((z) => typeof z === 'string' || typeof z === 'number').join(', '));\n if (compact) return compact;\n }\n }\n }\n for (const v of Object.values(x)) {\n const got = walk(v);\n if (got) return got;\n }\n return '';\n };\n for (const root of parseJsonLd()) {\n const got = walk(root);\n if (got) return got;\n }\n return '';\n };\n const allImages = () => {\n const set = new Set();\n const addUrl = (u) => {\n u = norm(u);\n if (!u) return;\n if (u.startsWith('//')) u = location.protocol + u;\n if (u.startsWith('/')) u = location.origin + u;\n if (/lamudi|lifull|jpg|jpeg|png|webp/i.test(u)) set.add(u);\n };\n document.querySelectorAll('img').forEach((img) => {\n addUrl(img.currentSrc || img.src || img.getAttribute('data-src') || img.getAttribute('data-lazy-src'));\n const srcset = img.getAttribute('srcset') || img.getAttribute('data-srcset') || '';\n srcset.split(',').forEach((part) => addUrl(part.trim().split(/\\s+/)[0]));\n });\n document.querySelectorAll('source').forEach((source) => {\n const srcset = source.getAttribute('srcset') || '';\n srcset.split(',').forEach((part) => addUrl(part.trim().split(/\\s+/)[0]));\n });\n document.querySelectorAll('*').forEach((el) => {\n const bg = getComputedStyle(el).backgroundImage || '';\n const matches = bg.match(/url\\([\"']?([^\"')]+)[\"']?\\)/g) || [];\n matches.forEach((m) => addUrl(m.replace(/^url\\([\"']?/, '').replace(/[\"']?\\)$/, '')));\n });\n return Array.from(set).filter((u) => !/logo|icon|sprite/i.test(u));\n };\n const spec = (patterns) => {\n const txt = bodyText();\n for (const p of patterns) {\n const m = txt.match(p);\n if (m) return norm(m[0]);\n }\n return '';\n };\n const amenities = () => {\n const keywords = /garaje|cocina|agua|gas|electricidad|internet|muebles|dep[oó]sito|televisi[oó]n|armario|servicio|alberca|jard[ií]n|seguridad|terraza|balc[oó]n|elevador|mascotas|gimnasio/i;\n const vals = [];\n document.querySelectorAll('li, span, p, div, button').forEach((el) => {\n const t = norm(el.innerText || el.textContent || '');\n if (t && t.length <= 60 && keywords.test(t) && !vals.includes(t)) vals.push(t);\n });\n return vals.slice(0, 40).join('\\n');\n };\n const description = () => {\n const bySelector = qText(['[data-testid*=\"description\" i]', '[class*=\"description\" i]', '[id*=\"description\" i]', 'section[aria-label*=\"description\" i]']);\n if (bySelector && bySelector.length > 40) return bySelector;\n const json = findKey(['description']);\n if (json && json.length > 40) return json;\n return meta('description');\n };\n const price = () => {\n const bySelector = qText(['[data-testid*=\"price\" i]', '[class*=\"price\" i]', '[id*=\"price\" i]']);\n if (bySelector && /\\$/.test(bySelector)) return bySelector;\n const txt = bodyText();\n const m = txt.match(/\\$\\s*[\\d.,]+\\s*(?:MXN)?(?:\\s*Gastos de comunidad\\s*\\$?\\s*[\\d.,]+\\s*MXN)?/i);\n return m ? norm(m[0]) : findKey(['price']);\n };\n const address = () => {\n const bySelector = qText(['[data-testid*=\"address\" i]', '[class*=\"address\" i]', '[id*=\"address\" i]', '[data-testid*=\"location\" i]', '[class*=\"location\" i]']);\n if (bySelector && bySelector.length > 5) return bySelector;\n return findKey(['address', 'streetaddress', 'addresslocality', 'addressregion']) || meta('og:street-address');\n };\n const title = () => qText(['h1', '[data-testid*=\"title\" i]', '[class*=\"title\" i]']) || findKey(['name', 'headline', 'title']) || meta('og:title') || document.title;\n const published = () => qText(['time[datetime]', 'time', '[data-testid*=\"date\" i]', '[class*=\"date\" i]']) || document.querySelector('time')?.getAttribute('datetime') || findKey(['datepublished', 'dateposted', 'uploaddate']);\n return {\n get: (field) => {\n const imgs = allImages();\n const map = {\n titulo: title(),\n precio: price(),\n direccion: address(),\n recamaras: spec([/\\d+\\s*rec[aá]maras?/i, /\\d+\\s*habitaciones?/i]),\n banos: spec([/\\d+\\s*bañ(?:o|os)/i, /\\d+\\s*ban(?:o|os)/i]),\n construidos: spec([/\\d+[\\d.,]*\\s*m²/i, /\\d+[\\d.,]*\\s*m2/i, /\\d+[\\d.,]*\\s*metros cuadrados/i]),\n descripcion: description(),\n amenidades: amenities(),\n imagen1_url: imgs[0] || '',\n imagen2_url: imgs[1] || '',\n imagen3_url: imgs[2] || '',\n imagen4_url: imgs[3] || '',\n imagen5_url: imgs[4] || '',\n pagina_url: location.href,\n fecha_publicacion: published(),\n hora_actual: new Date().toISOString()\n };\n return map[field] || '';\n }\n };\n})();", "waitForCompletion": true, "timeout": 10 } }, { "block_id": "sleep-1", "block_type": "process", "title": "Sleep", "description": "Wait for specified time", "position_x": 1632, "position_y": 800, "config": { "duration": 2 } }, { "block_id": "structured-export-1", "block_type": "process", "title": "Structured Export", "description": "Export data with custom columns", "position_x": 1968, "position_y": 800, "config": { "rowSelector": "body", "fileName": "lamudi-detalles-scraper.csv", "saveLocation": "C:\\Users\\theskd\\Documents\\UScraper\\templates", "includeHeaders": true, "fileMode": "append", "columns": [ { "name": "titulo", "selector": "window.__US_LAMUDI_DETAIL__ ? window.__US_LAMUDI_DETAIL__.get('titulo') : ''", "attribute": "text", "isJs": true }, { "name": "precio", "selector": "window.__US_LAMUDI_DETAIL__ ? window.__US_LAMUDI_DETAIL__.get('precio') : ''", "attribute": "text", "isJs": true }, { "name": "direccion", "selector": "window.__US_LAMUDI_DETAIL__ ? window.__US_LAMUDI_DETAIL__.get('direccion') : ''", "attribute": "text", "isJs": true }, { "name": "recamaras", "selector": "window.__US_LAMUDI_DETAIL__ ? window.__US_LAMUDI_DETAIL__.get('recamaras') : ''", "attribute": "text", "isJs": true }, { "name": "banos", "selector": "window.__US_LAMUDI_DETAIL__ ? window.__US_LAMUDI_DETAIL__.get('banos') : ''", "attribute": "text", "isJs": true }, { "name": "construidos", "selector": "window.__US_LAMUDI_DETAIL__ ? window.__US_LAMUDI_DETAIL__.get('construidos') : ''", "attribute": "text", "isJs": true }, { "name": "descripcion", "selector": "window.__US_LAMUDI_DETAIL__ ? window.__US_LAMUDI_DETAIL__.get('descripcion') : ''", "attribute": "text", "isJs": true }, { "name": "amenidades", "selector": "window.__US_LAMUDI_DETAIL__ ? window.__US_LAMUDI_DETAIL__.get('amenidades') : ''", "attribute": "text", "isJs": true }, { "name": "imagen1_url", "selector": "window.__US_LAMUDI_DETAIL__ ? window.__US_LAMUDI_DETAIL__.get('imagen1_url') : ''", "attribute": "text", "isJs": true }, { "name": "imagen2_url", "selector": "window.__US_LAMUDI_DETAIL__ ? window.__US_LAMUDI_DETAIL__.get('imagen2_url') : ''", "attribute": "text", "isJs": true }, { "name": "imagen3_url", "selector": "window.__US_LAMUDI_DETAIL__ ? window.__US_LAMUDI_DETAIL__.get('imagen3_url') : ''", "attribute": "text", "isJs": true }, { "name": "imagen4_url", "selector": "window.__US_LAMUDI_DETAIL__ ? window.__US_LAMUDI_DETAIL__.get('imagen4_url') : ''", "attribute": "text", "isJs": true }, { "name": "imagen5_url", "selector": "window.__US_LAMUDI_DETAIL__ ? window.__US_LAMUDI_DETAIL__.get('imagen5_url') : ''", "attribute": "text", "isJs": true }, { "name": "pagina_url", "selector": "window.__US_LAMUDI_DETAIL__ ? window.__US_LAMUDI_DETAIL__.get('pagina_url') : location.href", "attribute": "text", "isJs": true }, { "name": "fecha_publicacion", "selector": "window.__US_LAMUDI_DETAIL__ ? window.__US_LAMUDI_DETAIL__.get('fecha_publicacion') : ''", "attribute": "text", "isJs": true }, { "name": "hora_actual", "selector": "window.__US_LAMUDI_DETAIL__ ? window.__US_LAMUDI_DETAIL__.get('hora_actual') : new Date().toISOString()", "attribute": "text", "isJs": true } ] } }, { "block_id": "loop-continue-1", "block_type": "process", "title": "Loop Continue", "description": "Continue multi-input loop", "position_x": 1464, "position_y": 520, "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": "text-contains-1", "to_connector_id": "left" }, { "from_block_id": "text-contains-1", "from_connector_id": "true", "to_block_id": "loop-continue-1", "to_connector_id": "left" }, { "from_block_id": "text-contains-1", "from_connector_id": "false", "to_block_id": "inject-javascript-1", "to_connector_id": "left" }, { "from_block_id": "inject-javascript-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": "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": 1832, "height": 876, "z_index": 20, "data": { "memberBlockIds": [ "navigate-1", "wait-for-page-load-1", "wait-for-element-1", "sleep-1" ] } }, { "id": "group-pagination", "element_type": "group", "title": "Pagination Loop", "color": "#ff832b", "position_x": 1056, "position_y": 116, "width": 656, "height": 596, "z_index": 20, "data": { "memberBlockIds": [ "text-contains-1", "loop-continue-1" ] } }, { "id": "group-interaction", "element_type": "group", "title": "Interaction", "color": "#a56eff", "position_x": 1056, "position_y": 416, "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": 1896, "position_y": 696, "width": 380, "height": 296, "z_index": 20, "data": { "memberBlockIds": [ "structured-export-1" ] } }, { "id": "note-overview", "element_type": "note", "title": "Overview", "content": "Scrapes Lamudi Mexico property detail pages by URL, extracting title, price, address, technical specifications, description, amenities, up to five image URLs, page URL, publication date, and scrape timestamp. Navigation uses a multi-URL loop: add all target Lamudi detail URLs to the navigate.urls array; each successful page is appended to one CSV. Lamudi may show an anti-bot page with the text 'Let's confirm you are human'; this template detects that challenge and skips extraction for blocked pages to avoid writing invalid rows.", "color": "#f1c21b", "position_x": 80, "position_y": 20, "width": 480, "height": 160, "z_index": 22, "data": {} }, { "id": "note-block-text-contains-1", "element_type": "note", "title": "Note: Text Contains", "content": "Condition block: checks `body`. True / False branches control which path runs next. Keep enough space between branches so both connector lines are visible.", "color": "#ee5396", "position_x": 1328, "position_y": 200, "width": 340, "height": 131, "z_index": 22, "data": { "block_id": "text-contains-1" } }, { "id": "note-block-inject-javascript-1", "element_type": "note", "title": "Note: Inject JavaScript", "content": "Runs custom JavaScript in the page: `window.scrollTo(0, document.body.scrollHeight);\nwindow.__US_LAMUDI_DETAIL__ = (() => {\n const norm ...` Verify in browser if results are empty.", "color": "#ee5396", "position_x": 1328, "position_y": 500, "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 (titulo, precio, direccion, recamaras, banos). These selectors are fragile — update if the site layout changes.", "color": "#ee5396", "position_x": 2168, "position_y": 780, "width": 340, "height": 128, "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": 1664, "position_y": 500, "width": 340, "height": 123, "z_index": 22, "data": { "block_id": "loop-continue-1" } } ] }