{
  "version": "1.0.0",
  "exported_at": "2026-06-03T00:00:00.000Z",
  "project": {
    "name": "Kompass annuaire des entreprises Scraper liste",
    "description": "Scrapes Kompass France company listing pages for URL_entree, company name, location, presentation, supplier categories, certification remark, phone, website, and Kompass detail URL. Pagination is handled with a click-next loop and structured export appends results across pages. Best-effort: Kompass may show CAPTCHA or hide phone/site data behind anti-bot, interaction, or login controls. Selector update: uses Kompass .rowTop result wrappers and waits for existence rather than visibility for better runtime compatibility.",
    "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": {
        "url": "https://fr.kompass.com/s/informatique-internet-r-d/12/",
        "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": "wait-for-element-1",
      "block_type": "process",
      "title": "Wait for Element",
      "description": "Wait until element appears",
      "position_x": 840,
      "position_y": 220,
      "config": {
        "selector": ".rowTop",
        "timeout": 30,
        "visible": false
      }
    },
    {
      "block_id": "inject-javascript-1",
      "block_type": "process",
      "title": "Inject JavaScript",
      "description": "Run custom JavaScript on the page",
      "position_x": 1200,
      "position_y": 220,
      "config": {
        "jsCode": "(() => { document.querySelectorAll('.contactphoneblock a, a.phoneCompany, [id^=\"switchPhone\"] a, .coordonneesItemLink.phoneCompany').forEach(el => { try { el.click(); } catch (e) {} }); })();",
        "waitForCompletion": true,
        "timeout": 10
      }
    },
    {
      "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": "structured-export-1",
      "block_type": "process",
      "title": "Structured Export",
      "description": "Export data with custom columns",
      "position_x": 1920,
      "position_y": 220,
      "config": {
        "rowSelector": ".rowTop",
        "fileName": "kompass_annuaire_des_entreprises_scraper_liste.csv",
        "saveLocation": "C:\\Users\\theskd\\Documents\\UScraper\\templates",
        "includeHeaders": true,
        "fileMode": "append",
        "columns": [
          {
            "name": "url_entree",
            "selector": "(() => { const card = ROW.closest('.company-container') || ROW.querySelector('.company-container') || ROW; const a = card.querySelector('a[href*=\"/c/\"]'); return a ? window.location.href : ''; })()",
            "attribute": "text",
            "isJs": true
          },
          {
            "name": "nom",
            "selector": "(() => { const card = ROW.closest('.company-container') || ROW.querySelector('.company-container') || ROW; const detail = card.querySelector('a[href*=\"/c/\"]'); if (!detail) return ''; const h = detail.closest('h2') || card.querySelector('h2'); return (h ? h.innerText : detail.innerText).replace(/\\s*Entreprise certifiée\\s*/ig, ' ').replace(/\\s+/g, ' ').trim(); })()",
            "attribute": "text",
            "isJs": true
          },
          {
            "name": "lieu",
            "selector": "(() => { const card = ROW.closest('.company-container') || ROW.querySelector('.company-container') || ROW; if (!card.querySelector('a[href*=\"/c/\"]')) return ''; const lines = card.innerText.split('\\n').map(t => t.trim()).filter(Boolean); return lines.find(t => /\\s-\\sFrance\\b/i.test(t)) || ''; })()",
            "attribute": "text",
            "isJs": true
          },
          {
            "name": "presentation",
            "selector": "(() => { const card = ROW.closest('.company-container') || ROW.querySelector('.company-container') || ROW; if (!card.querySelector('a[href*=\"/c/\"]')) return ''; const lines = card.innerText.split('\\n').map(t => t.trim()).filter(Boolean); const locIdx = lines.findIndex(t => /\\s-\\sFrance\\b/i.test(t)); let stop = lines.findIndex((t, i) => i > locIdx && /^Fournisseur de\\s*:/i.test(t)); if (stop < 0) stop = lines.findIndex((t, i) => i > locIdx && /^(Téléphone|Site|Email|Contacter|Voir la page)$/i.test(t)); const start = locIdx >= 0 ? locIdx + 1 : 1; const end = stop > start ? stop : Math.min(lines.length, start + 6); return lines.slice(start, end).filter(t => !/^Voir la page$/i.test(t) && !/Entreprise certifiée/i.test(t) && !/^Fournisseur de\\s*:/i.test(t)).join(' ').replace(/\\s+/g, ' ').trim(); })()",
            "attribute": "text",
            "isJs": true
          },
          {
            "name": "fourniture",
            "selector": "(() => { const card = ROW.closest('.company-container') || ROW.querySelector('.company-container') || ROW; if (!card.querySelector('a[href*=\"/c/\"]')) return ''; const lines = card.innerText.split('\\n').map(t => t.trim()).filter(Boolean); const idx = lines.findIndex(t => /^Fournisseur de\\s*:/i.test(t)); if (idx < 0) return ''; const nextStop = lines.findIndex((t, i) => i > idx && /^(Téléphone|Site|Email|Contacter|Voir la page)$/i.test(t)); const end = nextStop > idx ? nextStop : Math.min(lines.length, idx + 12); return lines.slice(idx + 1, end).filter(t => !/Entreprise certifiée/i.test(t) && !/\\s-\\sFrance\\b/i.test(t)).join(' | ').replace(/\\s+/g, ' ').trim(); })()",
            "attribute": "text",
            "isJs": true
          },
          {
            "name": "remarque",
            "selector": "(() => { const card = ROW.closest('.company-container') || ROW.querySelector('.company-container') || ROW; if (!card.querySelector('a[href*=\"/c/\"]')) return ''; return card.innerText.includes('Entreprise certifiée') ? 'Entreprise certifiée' : ''; })()",
            "attribute": "text",
            "isJs": true
          },
          {
            "name": "telephone",
            "selector": "(() => { const card = ROW.closest('.company-container') || ROW.querySelector('.company-container') || ROW; if (!card.querySelector('a[href*=\"/c/\"]')) return ''; const hrefTel = Array.from(card.querySelectorAll('a[href^=\"tel:\"]')).map(a => a.getAttribute('href').replace(/^tel:/i, '').trim()).find(Boolean); if (hrefTel) return hrefTel; const txt = card.innerText.replace(/\\u00a0/g, ' '); const m = txt.match(/(?:\\+33|0)\\s?\\d(?:[\\s.\\-]?\\d{2}){4}/); return m ? m[0].trim() : ''; })()",
            "attribute": "text",
            "isJs": true
          },
          {
            "name": "site",
            "selector": "(() => { const card = ROW.closest('.company-container') || ROW.querySelector('.company-container') || ROW; if (!card.querySelector('a[href*=\"/c/\"]')) return ''; const links = Array.from(card.querySelectorAll('a[href]')).map(a => a.href).filter(h => /^https?:/i.test(h)); const direct = links.find(h => !/kompass\\.com/i.test(h) && !/solutions\\.kompass/i.test(h)); if (direct) return direct; const attrs = Array.from(card.querySelectorAll('[data-href], [data-url], [data-website]')).map(el => el.getAttribute('data-href') || el.getAttribute('data-url') || el.getAttribute('data-website')).filter(Boolean); return attrs.find(h => /^https?:/i.test(h) && !/kompass\\.com/i.test(h)) || ''; })()",
            "attribute": "text",
            "isJs": true
          },
          {
            "name": "url_detail",
            "selector": "(() => { const card = ROW.closest('.company-container') || ROW.querySelector('.company-container') || ROW; const a = card.querySelector('h2 a[href*=\"/c/\"], a[href*=\"/c/\"]'); return a ? a.href : ''; })()",
            "attribute": "text",
            "isJs": true
          }
        ]
      }
    },
    {
      "block_id": "element-exists-1",
      "block_type": "process",
      "title": "Element Exists",
      "description": "Check if element exists",
      "position_x": 2280,
      "position_y": 220,
      "config": {
        "selector": ".pagination li.active + li a, .pagination .active + li a, .pagination a[rel=\"next\"], .pagination a[aria-label*=\"next\" i], .pagination a[aria-label*=\"suivant\" i]"
      }
    },
    {
      "block_id": "click-1",
      "block_type": "process",
      "title": "Click",
      "description": "Click on element",
      "position_x": 2640,
      "position_y": 560,
      "config": {
        "selector": ".pagination li.active + li a, .pagination .active + li a, .pagination a[rel=\"next\"], .pagination a[aria-label*=\"next\" i], .pagination a[aria-label*=\"suivant\" i]",
        "timeout": 15
      }
    },
    {
      "block_id": "wait-for-page-load-2",
      "block_type": "process",
      "title": "Wait for Page Load",
      "description": "Wait for page to finish loading",
      "position_x": 3000,
      "position_y": 560,
      "config": {
        "timeout": 30
      }
    },
    {
      "block_id": "wait-for-element-2",
      "block_type": "process",
      "title": "Wait for Element",
      "description": "Wait until element appears",
      "position_x": 3360,
      "position_y": 560,
      "config": {
        "selector": ".rowTop",
        "timeout": 30,
        "visible": false
      }
    },
    {
      "block_id": "inject-javascript-2",
      "block_type": "process",
      "title": "Inject JavaScript",
      "description": "Run custom JavaScript on the page",
      "position_x": 3720,
      "position_y": 560,
      "config": {
        "jsCode": "(() => { document.querySelectorAll('.contactphoneblock a, a.phoneCompany, [id^=\"switchPhone\"] a, .coordonneesItemLink.phoneCompany').forEach(el => { try { el.click(); } catch (e) {} }); })();",
        "waitForCompletion": true,
        "timeout": 10
      }
    },
    {
      "block_id": "sleep-2",
      "block_type": "process",
      "title": "Sleep",
      "description": "Wait for specified time",
      "position_x": 4080,
      "position_y": 560,
      "config": {
        "duration": 2
      }
    },
    {
      "block_id": "end-1",
      "block_type": "output",
      "title": "End",
      "description": "Terminate execution flow",
      "position_x": 2280,
      "position_y": 880,
      "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": "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": "element-exists-1",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "element-exists-1",
      "from_connector_id": "true",
      "to_block_id": "click-1",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "element-exists-1",
      "from_connector_id": "false",
      "to_block_id": "end-1",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "click-1",
      "from_connector_id": "right",
      "to_block_id": "wait-for-page-load-2",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "wait-for-page-load-2",
      "from_connector_id": "right",
      "to_block_id": "wait-for-element-2",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "wait-for-element-2",
      "from_connector_id": "right",
      "to_block_id": "inject-javascript-2",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "inject-javascript-2",
      "from_connector_id": "right",
      "to_block_id": "sleep-2",
      "to_connector_id": "left"
    },
    {
      "from_block_id": "sleep-2",
      "from_connector_id": "right",
      "to_block_id": "structured-export-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": 4280,
      "height": 636,
      "z_index": 20,
      "data": {
        "memberBlockIds": [
          "navigate-1",
          "wait-for-page-load-1",
          "wait-for-element-1",
          "sleep-1",
          "wait-for-page-load-2",
          "wait-for-element-2",
          "sleep-2"
        ]
      }
    },
    {
      "id": "group-interaction",
      "element_type": "group",
      "title": "Interaction",
      "color": "#a56eff",
      "position_x": 1128,
      "position_y": 116,
      "width": 2840,
      "height": 636,
      "z_index": 20,
      "data": {
        "memberBlockIds": [
          "inject-javascript-1",
          "inject-javascript-2"
        ]
      }
    },
    {
      "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": 680,
      "height": 636,
      "z_index": 20,
      "data": {
        "memberBlockIds": [
          "element-exists-1",
          "click-1"
        ]
      }
    },
    {
      "id": "group-control",
      "element_type": "group",
      "title": "Control Flow",
      "color": "#8d8d8d",
      "position_x": 2208,
      "position_y": 776,
      "width": 380,
      "height": 296,
      "z_index": 20,
      "data": {
        "memberBlockIds": [
          "end-1"
        ]
      }
    },
    {
      "id": "note-overview",
      "element_type": "note",
      "title": "Overview",
      "content": "Scrapes Kompass France company listing pages for URL_entree, company name, location, presentation, supplier categories, certification remark, phone, website, and Kompass detail URL. Pagination is handled with a click-next loop and structured export appends results across pages. Best-effort: Kompass may show CAPTCHA or hide phone/site data behind anti-bot, interaction, or login controls. Selector update: uses Kompass .rowTop result wrappers and waits for existence rather than visibility for better runtime compatibility.",
      "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: `(() => { document.querySelectorAll('.contactphoneblock a, a.phoneCompany, [id^=\"switchPhone\"] a, .co...` Verify in browser if results are empty.",
      "color": "#ee5396",
      "position_x": 1400,
      "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 (url_entree, nom, lieu, presentation, fourniture). These selectors are fragile — update if the site layout changes.",
      "color": "#ee5396",
      "position_x": 2120,
      "position_y": 200,
      "width": 340,
      "height": 129,
      "z_index": 22,
      "data": {
        "block_id": "structured-export-1"
      }
    },
    {
      "id": "note-block-element-exists-1",
      "element_type": "note",
      "title": "Note: Element Exists",
      "content": "Condition block: checks `.pagination li.active + li a, .pagination .active + li a, .pagination a[rel=\"next\"], .pagination a[aria-label*=\"next\" i]`. True / False branches control which path runs next. Keep enough space between branches so both connector lines are visible.",
      "color": "#ee5396",
      "position_x": 2480,
      "position_y": 200,
      "width": 340,
      "height": 170,
      "z_index": 22,
      "data": {
        "block_id": "element-exists-1"
      }
    },
    {
      "id": "note-block-click-1",
      "element_type": "note",
      "title": "Note: Click",
      "content": "Pagination click — add waits after this block; the page reloads asynchronously.",
      "color": "#ee5396",
      "position_x": 2840,
      "position_y": 540,
      "width": 316,
      "height": 106,
      "z_index": 22,
      "data": {
        "block_id": "click-1"
      }
    }
  ]
}