{ "version": "1.0.0", "exported_at": "2026-06-02T20:20:00.000Z", "project": { "name": "Decathlonfr Data Scraper", "description": "Decathlon.fr listing scraper equivalent to the Octoparse template. Extracts current price, brand, product description, review/comment count, delivery text, image URL, and product detail URL from Decathlon France search/listing URLs such as https://www.decathlon.fr/search?Ntt=chaussure. Uses append mode and a next-page pagination loop so all reachable result pages are collected. Includes Didomi cookie-popup dismissal and JavaScript-based next-page navigation to avoid overlay click interception. Decathlon.fr may still show Cloudflare verification; a verified persistent browser session may be required.", "color": "bg-[#4589ff]", "template_id": "ai-generated" }, "blocks": [ { "block_id": "navigate-1", "block_type": "process", "title": "Navigate", "description": "Go to Decathlon.fr listing/search URL input", "position_x": 120, "position_y": 220, "config": { "urls": [ "https://www.decathlon.fr/search?Ntt=chaussure" ], "color": "bg-[#4589ff]", "tags": [ "decathlon", "input-url", "listing" ] } }, { "block_id": "wait-for-page-load-1", "block_type": "process", "title": "Wait for Page Load", "description": "Wait for the listing page to finish loading", "position_x": 480, "position_y": 220, "config": { "timeout": 45 } }, { "block_id": "sleep-1", "block_type": "process", "title": "Sleep", "description": "Allow Decathlon client-side content or verification redirect to settle", "position_x": 840, "position_y": 220, "config": { "duration": 5 } }, { "block_id": "inject-javascript-1", "block_type": "process", "title": "Inject JavaScript", "description": "Dismiss or remove Didomi cookie popup", "position_x": 1200, "position_y": 220, "config": { "jsCode": "(() => {\n const host = document.querySelector('#didomi-host');\n if (!host) return 'no didomi popup';\n const buttons = Array.from(host.querySelectorAll('button, a[role=\"button\"], [role=\"button\"]'));\n const preferred = buttons.find(el => /^(tout accepter|accepter|accept all|accept|j'accepte|continuer)$/i.test((el.textContent || '').trim())) || buttons.find(el => /accepter|accept/i.test((el.textContent || '').trim()));\n if (preferred) {\n preferred.click();\n return 'clicked didomi consent';\n }\n document.querySelectorAll('#didomi-host, .didomi-popup-backdrop, .didomi-notice-popup, .didomi-popup__backdrop').forEach(el => el.remove());\n document.documentElement.style.overflow = '';\n document.body.style.overflow = '';\n return 'removed didomi overlay';\n})()", "waitForCompletion": true, "timeout": 10 } }, { "block_id": "sleep-3", "block_type": "process", "title": "Sleep", "description": "Wait briefly after cookie popup handling", "position_x": 1560, "position_y": 220, "config": { "duration": 1 } }, { "block_id": "wait-for-element-1", "block_type": "process", "title": "Wait for Element", "description": "Wait for product cards to appear", "position_x": 1920, "position_y": 220, "config": { "selector": "[data-testid=\"product-card\"], [data-testid=\"product-tile\"], article:has(a[href*=\"/p/\"][href*=\"/c\"]), li:has(a[href*=\"/p/\"][href*=\"/c\"])", "timeout": 45, "visible": true } }, { "block_id": "structured-export-1", "block_type": "process", "title": "Structured Export", "description": "Export Decathlon product data with custom columns", "position_x": 2280, "position_y": 220, "config": { "rowSelector": "[data-testid=\"product-card\"], [data-testid=\"product-tile\"], article:has(a[href*=\"/p/\"][href*=\"/c\"])", "fileName": "decathlon-fr-data-scraper.csv", "saveLocation": "C:\\Users\\theskd\\Documents\\UScraper\\templates", "includeHeaders": true, "fileMode": "append", "columns": [ { "name": "prix_actuel", "selector": "(() => { const row = ROW; const txt = (row.innerText || '').replace(/\\s+/g, ' ').trim(); const m = txt.match(/\\b\\d+(?:[,.]\\d{1,2})?\\s?€/); return m ? m[0].replace(/\\s+/g, '') : ''; })()", "attribute": "text", "isJs": true }, { "name": "marque", "selector": "(() => { const row = ROW; const direct = row.querySelector('[data-testid*=\"brand\" i], [class*=\"brand\" i], [aria-label*=\"marque\" i]'); if (direct && direct.textContent.trim() && !/[€()]|avis/i.test(direct.textContent)) return direct.textContent.trim(); const a = row.querySelector('a[href*=\"/p/\"][href*=\"/c\"]') || row.querySelector('a[href*=\"/p/\"]'); const img = row.querySelector('img'); const raw = [row.querySelector('[data-testid*=\"title\" i], [data-testid*=\"name\" i], [class*=\"title\" i], [class*=\"name\" i], h2, h3')?.textContent, a?.getAttribute('aria-label'), a?.getAttribute('title'), a?.textContent, img?.getAttribute('alt')].map(v => (v || '').replace(/\\s+/g, ' ').trim()).find(v => v && !/^\\d+(?:[,.]\\d{1,2})?\\s?€$/.test(v) && !/^https?:\\/\\//i.test(v)) || ''; const words = raw.split(/\\s+/); const brand = []; for (const w of words) { if (brand.length >= 3) break; if (/^[A-Z0-9À-ÖØ-Þ&'.-]+$/.test(w) && !/^\\(?[\\d\\s\\u202f\\u00a0]+\\)?$/.test(w) && !/€/.test(w)) brand.push(w); else break; } return brand.join(' '); })()", "attribute": "text", "isJs": true }, { "name": "description", "selector": "(() => { const row = ROW; const a = row.querySelector('a[href*=\"/p/\"][href*=\"/c\"]') || row.querySelector('a[href*=\"/p/\"]'); const img = row.querySelector('img'); let raw = [row.querySelector('[data-testid*=\"title\" i], [data-testid*=\"name\" i], [class*=\"title\" i], [class*=\"name\" i], h2, h3')?.textContent, a?.getAttribute('aria-label'), a?.getAttribute('title'), a?.textContent, img?.getAttribute('alt')].map(v => (v || '').replace(/\\s+/g, ' ').trim()).find(v => v && !/^\\d+(?:[,.]\\d{1,2})?\\s?€$/.test(v) && !/^https?:\\/\\//i.test(v)) || ''; raw = raw.replace(/^Voir le produit\\s*/i, '').trim(); const words = raw.split(/\\s+/); let i = 0; while (i < words.length && i < 3 && /^[A-Z0-9À-ÖØ-Þ&'.-]+$/.test(words[i]) && !/^\\(?[\\d\\s\\u202f\\u00a0]+\\)?$/.test(words[i]) && !/€/.test(words[i])) i++; const stripped = words.slice(i).join(' ').trim(); return stripped || raw; })()", "attribute": "text", "isJs": true }, { "name": "commentaire", "selector": "(() => { const txt = (ROW.innerText || '').replace(/\\s+/g, ' ').trim(); const paren = txt.match(/\\(\\s*[\\d\\s\\u202f\\u00a0]+\\s*\\)/); if (paren) return paren[0].replace(/\\s+/g, ' '); const review = txt.match(/\\b[\\d\\s\\u202f\\u00a0]+\\s*(?:avis|commentaires?)\\b/i); return review ? review[0].replace(/\\s+/g, ' ') : ''; })()", "attribute": "text", "isJs": true }, { "name": "livraison", "selector": "(() => { const lines = (ROW.innerText || '').split(/\\n+/).map(s => s.replace(/\\s+/g, ' ').trim()).filter(Boolean); const line = lines.find(s => /livraison|retrait|disponible|chez vous|24h|48h/i.test(s)); return line || ''; })()", "attribute": "text", "isJs": true }, { "name": "image_url", "selector": "(() => { const img = ROW.querySelector('img[src*=\"contents.mediadecathlon.com\"], img[data-src*=\"contents.mediadecathlon.com\"], img'); if (!img) return ''; return img.currentSrc || img.src || img.getAttribute('data-src') || img.getAttribute('src') || ''; })()", "attribute": "text", "isJs": true }, { "name": "url_de_la_page_detaillee", "selector": "(() => { const a = ROW.querySelector('a[href*=\"/p/\"][href*=\"/c\"]') || ROW.querySelector('a[href*=\"/p/\"]'); return a ? a.href : ''; })()", "attribute": "text", "isJs": true } ] } }, { "block_id": "element-exists-1", "block_type": "process", "title": "Element Exists", "description": "Check whether an enabled next-page pagination control exists", "position_x": 2640, "position_y": 220, "config": { "selector": "//a[(contains(@rel,'next') or contains(translate(@aria-label,'ABCDEFGHIJKLMNOPQRSTUVWXYZ','abcdefghijklmnopqrstuvwxyz'),'page suivante') or contains(translate(@aria-label,'ABCDEFGHIJKLMNOPQRSTUVWXYZ','abcdefghijklmnopqrstuvwxyz'),'suivant') or contains(translate(normalize-space(.),'ABCDEFGHIJKLMNOPQRSTUVWXYZ','abcdefghijklmnopqrstuvwxyz'),'suivant')) and not(@aria-disabled='true') and not(contains(translate(@class,'ABCDEFGHIJKLMNOPQRSTUVWXYZ','abcdefghijklmnopqrstuvwxyz'),'disabled'))] | //button[(contains(translate(@aria-label,'ABCDEFGHIJKLMNOPQRSTUVWXYZ','abcdefghijklmnopqrstuvwxyz'),'page suivante') or contains(translate(@aria-label,'ABCDEFGHIJKLMNOPQRSTUVWXYZ','abcdefghijklmnopqrstuvwxyz'),'suivant') or contains(translate(normalize-space(.),'ABCDEFGHIJKLMNOPQRSTUVWXYZ','abcdefghijklmnopqrstuvwxyz'),'suivant')) and not(@disabled) and not(@aria-disabled='true') and not(contains(translate(@class,'ABCDEFGHIJKLMNOPQRSTUVWXYZ','abcdefghijklmnopqrstuvwxyz'),'disabled'))]" } }, { "block_id": "inject-javascript-2", "block_type": "process", "title": "Inject JavaScript", "description": "Navigate to next page by href instead of physical click", "position_x": 2640, "position_y": 540, "config": { "jsCode": "(() => {\n document.querySelectorAll('#didomi-host, .didomi-popup-backdrop, .didomi-notice-popup, .didomi-popup__backdrop').forEach(el => el.remove());\n const xpath = \"//a[(contains(@rel,'next') or contains(translate(@aria-label,'ABCDEFGHIJKLMNOPQRSTUVWXYZ','abcdefghijklmnopqrstuvwxyz'),'page suivante') or contains(translate(@aria-label,'ABCDEFGHIJKLMNOPQRSTUVWXYZ','abcdefghijklmnopqrstuvwxyz'),'suivant') or contains(translate(normalize-space(.),'ABCDEFGHIJKLMNOPQRSTUVWXYZ','abcdefghijklmnopqrstuvwxyz'),'suivant')) and not(@aria-disabled='true') and not(contains(translate(@class,'ABCDEFGHIJKLMNOPQRSTUVWXYZ','abcdefghijklmnopqrstuvwxyz'),'disabled'))] | //button[(contains(translate(@aria-label,'ABCDEFGHIJKLMNOPQRSTUVWXYZ','abcdefghijklmnopqrstuvwxyz'),'page suivante') or contains(translate(@aria-label,'ABCDEFGHIJKLMNOPQRSTUVWXYZ','abcdefghijklmnopqrstuvwxyz'),'suivant') or contains(translate(normalize-space(.),'ABCDEFGHIJKLMNOPQRSTUVWXYZ','abcdefghijklmnopqrstuvwxyz'),'suivant')) and not(@disabled) and not(@aria-disabled='true') and not(contains(translate(@class,'ABCDEFGHIJKLMNOPQRSTUVWXYZ','abcdefghijklmnopqrstuvwxyz'),'disabled'))]\";\n const node = document.evaluate(xpath, document, null, XPathResult.FIRST_ORDERED_NODE_TYPE, null).singleNodeValue;\n if (!node) return 'no next page node';\n const href = node.href || node.getAttribute('href');\n if (href) {\n window.location.href = new URL(href, window.location.href).href;\n return 'navigating to ' + href;\n }\n node.click();\n return 'clicked next button via js';\n})()", "waitForCompletion": true, "timeout": 10 } }, { "block_id": "wait-for-page-load-2", "block_type": "process", "title": "Wait for Page Load", "description": "Wait after pagination navigation", "position_x": 3000, "position_y": 540, "config": { "timeout": 45 } }, { "block_id": "sleep-2", "block_type": "process", "title": "Sleep", "description": "Allow Decathlon product results to refresh after pagination", "position_x": 3360, "position_y": 540, "config": { "duration": 3 } }, { "block_id": "wait-for-element-2", "block_type": "process", "title": "Wait for Element", "description": "Wait for product cards on the next page before extracting again", "position_x": 3720, "position_y": 540, "config": { "selector": "[data-testid=\"product-card\"], [data-testid=\"product-tile\"], article:has(a[href*=\"/p/\"][href*=\"/c\"]), li:has(a[href*=\"/p/\"][href*=\"/c\"])", "timeout": 45, "visible": true } }, { "block_id": "loop-continue-1", "block_type": "process", "title": "Loop Continue", "description": "Continue to the next configured Decathlon listing URL", "position_x": 2640, "position_y": 860, "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": "inject-javascript-1", "to_connector_id": "left" }, { "from_block_id": "inject-javascript-1", "from_connector_id": "right", "to_block_id": "sleep-3", "to_connector_id": "left" }, { "from_block_id": "sleep-3", "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": "element-exists-1", "to_connector_id": "left" }, { "from_block_id": "element-exists-1", "from_connector_id": "true", "to_block_id": "inject-javascript-2", "to_connector_id": "left" }, { "from_block_id": "inject-javascript-2", "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": "sleep-2", "to_connector_id": "left" }, { "from_block_id": "sleep-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": "structured-export-1", "to_connector_id": "left" }, { "from_block_id": "element-exists-1", "from_connector_id": "false", "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": 3920, "height": 616, "z_index": 20, "data": { "memberBlockIds": [ "navigate-1", "wait-for-page-load-1", "sleep-1", "sleep-3", "wait-for-element-1", "wait-for-page-load-2", "sleep-2", "wait-for-element-2" ] } }, { "id": "group-interaction", "element_type": "group", "title": "Interaction", "color": "#a56eff", "position_x": 1128, "position_y": 116, "width": 1760, "height": 616, "z_index": 20, "data": { "memberBlockIds": [ "inject-javascript-1", "inject-javascript-2" ] } }, { "id": "group-extract", "element_type": "group", "title": "Data Extraction", "color": "#42be65", "position_x": 2208, "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": 2568, "position_y": 116, "width": 380, "height": 936, "z_index": 20, "data": { "memberBlockIds": [ "element-exists-1", "loop-continue-1" ] } }, { "id": "note-overview", "element_type": "note", "title": "Overview", "content": "Decathlon.fr listing scraper equivalent to the Octoparse template. Extracts current price, brand, product description, review/comment count, delivery text, image URL, and product detail URL from Decathlon France search/listing URLs such as https://www.decathlon.fr/search?Ntt=chaussure. Uses append mode and a next-page pagination loop so all reachable result pages are collected. Includes Didomi cookie-popup dismissal and JavaScript-based next-page navigation to avoid overlay click interception. Decathlon.fr may still show Cloudflare verification; a verified persistent browser session may be required.", "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: `(() => {\n const host = document.querySelector('#didomi-host');\n if (!host) return 'no didomi popup...` 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 (prix_actuel, marque, description, commentaire, livraison). These selectors are fragile — update if the site layout changes.", "color": "#ee5396", "position_x": 2480, "position_y": 200, "width": 340, "height": 132, "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 `//a[(contains(@rel,'next') or contains(translate(@aria-label,'ABCDEFGHIJKLMNOPQRSTUVWXYZ','abcdefghijklmnopqrstuvwxyz'),`. True / False branches control which path runs next. Keep enough space between branches so both connector lines are visible.", "color": "#ee5396", "position_x": 2840, "position_y": 200, "width": 340, "height": 170, "z_index": 22, "data": { "block_id": "element-exists-1" } }, { "id": "note-block-inject-javascript-2", "element_type": "note", "title": "Note: Inject JavaScript", "content": "Runs custom JavaScript in the page: `(() => {\n document.querySelectorAll('#didomi-host, .didomi-popup-backdrop, .didomi-notice-popup, .d...` Verify in browser if results are empty.", "color": "#ee5396", "position_x": 2840, "position_y": 520, "width": 340, "height": 140, "z_index": 22, "data": { "block_id": "inject-javascript-2" } }, { "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": 2840, "position_y": 840, "width": 340, "height": 123, "z_index": 22, "data": { "block_id": "loop-continue-1" } } ] }