{ "name": "Leadgen: enrich a CSV of Romanian firms (lookup_companies + match_companies + find_company_by_domain)", "nodes": [ { "parameters": {}, "id": "6f1c1e2a-1b1a-4d0e-9a51-0c0a3b7e0001", "name": "Start", "type": "n8n-nodes-base.manualTrigger", "typeVersion": 1, "position": [ 0, 300 ] }, { "parameters": { "fileSelector": "/files/leadgen-input.csv", "options": {} }, "id": "6f1c1e2a-1b1a-4d0e-9a51-0c0a3b7e0002", "name": "Read the CSV file", "type": "n8n-nodes-base.readWriteFile", "typeVersion": 1, "position": [ 220, 300 ], "notes": "Your list: one firm per row, first row = column names. Recognised columns (any case, RO or EN): cui / cif / cod fiscal; name / company / denumire / firma / client / cont; county / judet; website / domain / site / email. To read a Google Sheet instead, replace this node and the next one with a Google Sheets 'Get rows' node." }, { "parameters": { "operation": "csv", "options": { "headerRow": true } }, "id": "6f1c1e2a-1b1a-4d0e-9a51-0c0a3b7e0003", "name": "Rows from the CSV", "type": "n8n-nodes-base.extractFromFile", "typeVersion": 1, "position": [ 440, 300 ] }, { "parameters": { "mode": "runOnceForAllItems", "jsCode": "// Rows WITH a CUI -> POST /lookup_companies, up to 100 CUIs per request.\n// Each CUI counts as one lookup on your key (free key: 25 a day). A batch larger\n// than what is left today answers the CUIs that fit; the rest come back\n// not_processed (not counted) and go to leadgen-pending.csv for the next run.\nconst pick = (row, names) => {\n for (const [k, v] of Object.entries(row)) {\n const h = k.normalize('NFD').replace(/[\\u0300-\\u036f]/g, '').toLowerCase().trim();\n if (names.some((n) => h === n || h.startsWith(n + ' '))) return String(v ?? '').trim();\n }\n return '';\n};\nconst CUI = ['cui', 'cif', 'cod fiscal', 'cod_fiscal', 'tax id', 'vat number'];\nconst cuis = [];\nfor (const item of $input.all()) {\n const cui = pick(item.json, CUI);\n if (cui) cuis.push(cui);\n}\nconst out = [];\nfor (let i = 0; i < cuis.length; i += 100) {\n out.push({ json: { cuis: cuis.slice(i, i + 100), compact: true } });\n}\nreturn out;" }, "id": "6f1c1e2a-1b1a-4d0e-9a51-0c0a3b7e0004", "name": "Batches of CUIs", "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 680, 180 ] }, { "parameters": { "mode": "runOnceForAllItems", "jsCode": "// Rows WITHOUT a CUI but with a name -> POST /match_companies (name, county,\n// website), up to 500 rows per request. Each row counts as one lookup on your key. `ref` is the\n// row number, echoed back so the answer joins the right row.\nconst pick = (row, names) => {\n for (const [k, v] of Object.entries(row)) {\n const h = k.normalize('NFD').replace(/[\\u0300-\\u036f]/g, '').toLowerCase().trim();\n if (names.some((n) => h === n || h.startsWith(n + ' '))) return String(v ?? '').trim();\n }\n return '';\n};\nconst CUI = ['cui', 'cif', 'cod fiscal', 'cod_fiscal', 'tax id', 'vat number'];\nconst NAME = ['name', 'company', 'company name', 'account', 'denumire', 'firma', 'client', 'cont', 'nume'];\nconst COUNTY = ['county', 'judet', 'judetul'];\nconst SITE = ['website', 'domain', 'site', 'web', 'url', 'email', 'e-mail'];\nconst rows = [];\n$input.all().forEach((item, i) => {\n if (pick(item.json, CUI)) return;\n const name = pick(item.json, NAME);\n const domain = pick(item.json, SITE);\n if (!name) return; // a website alone goes to /find_company_by_domain (Websites)\n rows.push({ name: name || null, county: pick(item.json, COUNTY) || null, domain: domain || null, ref: String(i) });\n});\nconst out = [];\nfor (let i = 0; i < rows.length; i += 500) {\n out.push({ json: { rows: rows.slice(i, i + 500), compact: true } });\n}\nreturn out;" }, "id": "6f1c1e2a-1b1a-4d0e-9a51-0c0a3b7e0005", "name": "Batches of names", "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 680, 420 ] }, { "parameters": { "method": "POST", "url": "https://leadgen.adrianhomelab.com/lookup_companies", "authentication": "genericCredentialType", "genericAuthType": "httpHeaderAuth", "sendBody": true, "specifyBody": "json", "jsonBody": "={{ JSON.stringify($json) }}", "options": { "response": { "response": { "neverError": true } } } }, "id": "6f1c1e2a-1b1a-4d0e-9a51-0c0a3b7e0006", "name": "Leadgen /lookup_companies", "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [ 920, 180 ], "credentials": { "httpHeaderAuth": { "id": "", "name": "Leadgen API key" } }, "notes": "Credential: Header Auth, Name = X-API-Key, Value = your key (free at https://leadgen.adrianhomelab.com/start). A batch larger than what is left today answers the rows that fit (partial: true, processed, remaining); a refusal (nothing left today: 429) comes back as the rows' status instead of stopping the run." }, { "parameters": { "method": "POST", "url": "https://leadgen.adrianhomelab.com/match_companies", "authentication": "genericCredentialType", "genericAuthType": "httpHeaderAuth", "sendBody": true, "specifyBody": "json", "jsonBody": "={{ JSON.stringify($json) }}", "options": { "response": { "response": { "neverError": true } } } }, "id": "6f1c1e2a-1b1a-4d0e-9a51-0c0a3b7e0007", "name": "Leadgen /match_companies", "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [ 920, 420 ], "credentials": { "httpHeaderAuth": { "id": "", "name": "Leadgen API key" } }, "notes": "Same credential as /lookup_companies. A batch larger than what is left today answers the rows that fit; the rest come back not_processed." }, { "parameters": { "mode": "runOnceForAllItems", "jsCode": "// One output row per CUI asked: the firm, or found=false with the reason. A CUI\n// today's allowance did not cover is \"not_processed\" (not run, not counted): the\n// answer says partial: true and `remaining`, and a request refused because nothing\n// was left (429) covers every CUI it carried. Those rows go to leadgen-pending.csv.\nconst asked = typeof $ === 'function' ? $('Batches of CUIs').all() : [];\nconst out = [];\n$input.all().forEach((item, i) => {\n const b = item.json || {};\n let results = b.results;\n if (!Array.isArray(results)) {\n const status = b.error === 'daily_limit_reached' ? 'not_processed' : (b.error || 'error');\n results = (((asked[i] || {}).json || {}).cuis || []).map((c) => ({ input: c, found: false, status }));\n }\n for (const r of results) {\n const c = r.company || {};\n const fin = c.latestFinancials || {};\n const pending = r.status === 'not_processed';\n out.push({ json: {\n input: r.input, leadgen_status: r.found ? 'found' : (r.status || r.reason || r.error || 'not_found'),\n cui: r.cui || (pending ? String(r.input ?? '') : ''), company: c.companyName || '', county: c.county || '', city: c.city || '',\n legal_form: c.legalForm || '', risk: (c.risk || {}).level || '', is_lead: (c.risk || {}).isLead ?? '',\n phone: c.phone || '', website: c.website || '', revenue: fin.revenue ?? '', employees: fin.employees ?? '',\n financial_year: fin.year ?? '', confidence: r.found ? 1 : '', matched_on: r.found ? 'cui' : '',\n attribution: b.attribution || '',\n } });\n }\n});\nreturn out;" }, "id": "6f1c1e2a-1b1a-4d0e-9a51-0c0a3b7e0008", "name": "Firms by CUI", "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 1160, 180 ] }, { "parameters": { "mode": "runOnceForAllItems", "jsCode": "// One output row per name asked: the matched firm with its confidence, or\n// UNMATCHED with up to 3 candidates (never a guess). A row flagged ambiguous or\n// countyMismatch is matched but worth a look. A row today's allowance did not\n// cover is \"not_processed\" (not run, not counted; a 429 covers its whole request)\n// and keeps the name, county and website you gave, for leadgen-pending.csv.\nconst asked = typeof $ === 'function' ? $('Batches of names').all() : [];\nconst out = [];\n$input.all().forEach((item, i) => {\n const b = item.json || {};\n let results = b.results;\n if (!Array.isArray(results)) {\n const status = b.error === 'daily_limit_reached' ? 'not_processed' : (b.error || 'error');\n results = (((asked[i] || {}).json || {}).rows || []).map((row) => ({ status, input: row, ref: row.ref }));\n }\n for (const r of results) {\n const m = r.match || {};\n const c = r.company || {};\n const inp = r.input || {};\n const fin = c.latestFinancials || {};\n const pending = r.status === 'not_processed';\n const flags = [r.ambiguous ? 'ambiguous' : '', r.countyMismatch ? 'county_mismatch' : ''].filter(Boolean).join(' ');\n const status = r.status === 'matched' ? ('matched' + (flags ? ' (' + flags + ')' : ''))\n : (r.status === 'no_match' || r.status === 'error' ? 'UNMATCHED' : (r.status || 'UNMATCHED'));\n out.push({ json: {\n input: [inp.name, inp.county, inp.domain].filter(Boolean).join(' / '),\n leadgen_status: status,\n cui: m.cui || '', company: m.companyName || c.companyName || (pending ? inp.name || '' : ''),\n county: c.county || (pending ? inp.county || '' : ''), city: c.city || '',\n legal_form: c.legalForm || '', risk: (c.risk || {}).level || '', is_lead: (c.risk || {}).isLead ?? '',\n phone: c.phone || '', website: c.website || (pending ? inp.domain || '' : ''), revenue: fin.revenue ?? '',\n employees: fin.employees ?? '', financial_year: fin.year ?? '', confidence: m.confidence ?? '', matched_on: m.matchedOn || '',\n candidates: (r.candidates || []).slice(0, 3).map((x) => `${x.companyName} (${x.cui}, ${x.county || ''})`).join('; '),\n attribution: b.attribution || '',\n } });\n }\n});\nreturn out;" }, "id": "6f1c1e2a-1b1a-4d0e-9a51-0c0a3b7e0009", "name": "Firms by name", "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 1160, 420 ] }, { "parameters": { "jsCode": "// Rows with ONLY a website (no CUI, no name) -> GET /find_company_by_domain, one\n// request per row: the registry's website field first, else the site's own pages\n// are read for the CUI they show (emag.ro -> DANTE INTERNATIONAL SA). One lookup\n// per row. `ref` is the row number.\nconst pick = (row, names) => {\n for (const [k, v] of Object.entries(row)) {\n const h = k.normalize('NFD').replace(/[\\u0300-\\u036f]/g, '').toLowerCase().trim();\n if (names.some((n) => h === n || h.startsWith(n + ' '))) return String(v ?? '').trim();\n }\n return '';\n};\nconst CUI = ['cui', 'cif', 'cod fiscal', 'cod_fiscal', 'tax id', 'vat number'];\nconst NAME = ['name', 'company', 'company name', 'account', 'denumire', 'firma', 'client', 'cont', 'nume'];\nconst SITE = ['website', 'domain', 'site', 'web', 'url', 'email', 'e-mail'];\nconst out = [];\n$input.all().forEach((item, i) => {\n if (pick(item.json, CUI) || pick(item.json, NAME)) return;\n let domain = pick(item.json, SITE);\n if (domain.includes('@')) domain = domain.split('@').pop(); // an email's domain\n if (domain) out.push({ json: { domain, ref: String(i) } });\n});\nreturn out;" }, "id": "6f1c1e2a-1b1a-4d0e-9a51-0c0a3b7e0013", "name": "Websites", "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 680, 660 ] }, { "parameters": { "method": "GET", "url": "https://leadgen.adrianhomelab.com/find_company_by_domain", "authentication": "genericCredentialType", "genericAuthType": "httpHeaderAuth", "sendQuery": true, "queryParameters": { "parameters": [ { "name": "domain", "value": "={{ $json.domain }}" }, { "name": "compact", "value": "true" } ] }, "options": { "response": { "response": { "neverError": true } } } }, "id": "6f1c1e2a-1b1a-4d0e-9a51-0c0a3b7e0014", "name": "Leadgen /find_company_by_domain", "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [ 920, 660 ], "credentials": { "httpHeaderAuth": { "id": "", "name": "Leadgen API key" } }, "notes": "Same credential as /lookup_companies. One request per website; a refusal (bad domain, daily limit) comes back as the row's status instead of stopping the run." }, { "parameters": { "jsCode": "// One output row per website asked: the firm behind it (matched_on says how:\n// registry_website or site_cui), or UNMATCHED with up to 3 name candidates from\n// the page title, or the refusal (invalid_domain; not_processed when nothing was\n// left today: the website goes to leadgen-pending.csv).\nconst asked = typeof $ === 'function' ? $('Websites').all() : [];\nconst out = [];\n$input.all().forEach((item, i) => {\n const b = item.json || {};\n const c = (b.results || [])[0] || {};\n const m = b.match || {};\n const fin = c.latestFinancials || {};\n const domain = ((asked[i] || {}).json || {}).domain || b.domain || '';\n const pending = b.error === 'daily_limit_reached'; // nothing left today: resend tomorrow\n out.push({ json: {\n input: domain,\n leadgen_status: pending ? 'not_processed' : (b.error ? b.error : (b.found ? 'matched' : 'UNMATCHED')),\n cui: m.cui || '', company: m.companyName || c.companyName || '', county: c.county || '', city: c.city || '',\n legal_form: c.legalForm || '', risk: (c.risk || {}).level || '', is_lead: (c.risk || {}).isLead ?? '',\n phone: c.phone || '', website: c.website || (pending ? domain : ''), revenue: fin.revenue ?? '', employees: fin.employees ?? '',\n financial_year: fin.year ?? '', confidence: '', matched_on: b.matchedOn || '',\n candidates: (b.candidates || []).slice(0, 3).map((x) => `${x.companyName} (${x.cui}, ${x.county || ''})`).join('; '),\n attribution: b.attribution || '',\n } });\n});\nreturn out;" }, "id": "6f1c1e2a-1b1a-4d0e-9a51-0c0a3b7e0015", "name": "Firms by website", "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 1160, 660 ] }, { "parameters": { "numberInputs": 3 }, "id": "6f1c1e2a-1b1a-4d0e-9a51-0c0a3b7e0010", "name": "All rows", "type": "n8n-nodes-base.merge", "typeVersion": 3, "position": [ 1400, 300 ] }, { "parameters": { "options": { "fileName": "leadgen-enriched.csv" } }, "id": "6f1c1e2a-1b1a-4d0e-9a51-0c0a3b7e0011", "name": "To CSV", "type": "n8n-nodes-base.convertToFile", "typeVersion": 1.1, "position": [ 1620, 300 ] }, { "parameters": { "operation": "write", "fileName": "/files/leadgen-enriched.csv", "options": {} }, "id": "6f1c1e2a-1b1a-4d0e-9a51-0c0a3b7e0012", "name": "Write the enriched CSV", "type": "n8n-nodes-base.readWriteFile", "typeVersion": 1, "position": [ 1840, 300 ], "notes": "Or send it on: Google Sheets 'Append row', email, your CRM. Keep the attribution column (CC BY 4.0) when you redistribute the data." }, { "parameters": { "mode": "runOnceForAllItems", "jsCode": "// The rows today's allowance did not cover (leadgen_status \"not_processed\": not\n// run, not counted), in column names \"Read the CSV file\" recognises. After the\n// reset (00:00 UTC, 03:00 Romanian time) run the workflow on leadgen-pending.csv.\n// Nothing pending: this node outputs nothing and no file is written.\nconst out = [];\nfor (const item of $input.all()) {\n const r = item.json || {};\n if (r.leadgen_status !== 'not_processed') continue;\n out.push({ json: { cui: r.cui || '', name: r.cui ? '' : (r.company || ''), county: r.cui ? '' : (r.county || ''),\n website: r.cui ? '' : (r.website || '') } });\n}\nreturn out;" }, "id": "6f1c1e2a-1b1a-4d0e-9a51-0c0a3b7e0016", "name": "Rows for tomorrow", "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 1620, 520 ] }, { "parameters": { "options": { "fileName": "leadgen-pending.csv" } }, "id": "6f1c1e2a-1b1a-4d0e-9a51-0c0a3b7e0017", "name": "Pending to CSV", "type": "n8n-nodes-base.convertToFile", "typeVersion": 1.1, "position": [ 1840, 520 ] }, { "parameters": { "operation": "write", "fileName": "/files/leadgen-pending.csv", "options": {} }, "id": "6f1c1e2a-1b1a-4d0e-9a51-0c0a3b7e0018", "name": "Write the rows for tomorrow", "type": "n8n-nodes-base.readWriteFile", "typeVersion": 1, "position": [ 2060, 520 ], "notes": "Written only when today's allowance ran out partway. After 00:00 UTC (03:00 Romanian time) point 'Read the CSV file' at /files/leadgen-pending.csv (or copy it over leadgen-input.csv) and run again; keep this run's enriched CSV first, the next run writes a new one." } ], "connections": { "Start": { "main": [ [ { "node": "Read the CSV file", "type": "main", "index": 0 } ] ] }, "Read the CSV file": { "main": [ [ { "node": "Rows from the CSV", "type": "main", "index": 0 } ] ] }, "Rows from the CSV": { "main": [ [ { "node": "Batches of CUIs", "type": "main", "index": 0 }, { "node": "Batches of names", "type": "main", "index": 0 }, { "node": "Websites", "type": "main", "index": 0 } ] ] }, "Batches of CUIs": { "main": [ [ { "node": "Leadgen /lookup_companies", "type": "main", "index": 0 } ] ] }, "Batches of names": { "main": [ [ { "node": "Leadgen /match_companies", "type": "main", "index": 0 } ] ] }, "Leadgen /lookup_companies": { "main": [ [ { "node": "Firms by CUI", "type": "main", "index": 0 } ] ] }, "Leadgen /match_companies": { "main": [ [ { "node": "Firms by name", "type": "main", "index": 0 } ] ] }, "Firms by CUI": { "main": [ [ { "node": "All rows", "type": "main", "index": 0 } ] ] }, "Firms by name": { "main": [ [ { "node": "All rows", "type": "main", "index": 1 } ] ] }, "All rows": { "main": [ [ { "node": "To CSV", "type": "main", "index": 0 }, { "node": "Rows for tomorrow", "type": "main", "index": 0 } ] ] }, "To CSV": { "main": [ [ { "node": "Write the enriched CSV", "type": "main", "index": 0 } ] ] }, "Websites": { "main": [ [ { "node": "Leadgen /find_company_by_domain", "type": "main", "index": 0 } ] ] }, "Leadgen /find_company_by_domain": { "main": [ [ { "node": "Firms by website", "type": "main", "index": 0 } ] ] }, "Firms by website": { "main": [ [ { "node": "All rows", "type": "main", "index": 2 } ] ] }, "Rows for tomorrow": { "main": [ [ { "node": "Pending to CSV", "type": "main", "index": 0 } ] ] }, "Pending to CSV": { "main": [ [ { "node": "Write the rows for tomorrow", "type": "main", "index": 0 } ] ] } }, "pinData": {}, "settings": { "executionOrder": "v1" }, "meta": { "templateCredsSetupCompleted": false }, "tags": [] }