Greenhouse Job Ingestion

The workflow JSON

Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →

{
  "name": "Greenhouse Job Ingestion",
  "nodes": [
    {
      "parameters": {
        "rule": {
          "interval": [
            {
              "field": "hours",
              "hoursInterval": 6
            }
          ]
        }
      },
      "id": "schedule-greenhouse",
      "name": "Schedule Trigger",
      "type": "n8n-nodes-base.scheduleTrigger",
      "typeVersion": 1.3,
      "position": [
        -400,
        0
      ]
    },
    {
      "parameters": {
        "jsCode": "// Greenhouse public job board API \u2014 no auth required.\n// API: GET https://boards-api.greenhouse.io/v1/boards/{slug}/jobs?content=true\n// Add company slugs here. Find slugs at: https://boards.greenhouse.io/{slug}\nconst companies = [\n  'monzo',\n  'wise',\n  'starling-bank',\n  'cleo',\n  'revolut',\n  'curve',\n  'pismo',\n  'checkout-com',\n  'duolingo',\n  'intercom',\n  'notion',\n  'loom',\n  'plaid',\n  'brex',\n  'vercel',\n  'supabase',\n  'posthog',\n  'linear',\n];\nreturn companies.map(slug => ({ json: { slug } }));"
      },
      "id": "companies-greenhouse",
      "name": "Companies",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        -176,
        0
      ]
    },
    {
      "parameters": {
        "url": "=https://boards-api.greenhouse.io/v1/boards/{{ $json.slug }}/jobs",
        "sendQuery": true,
        "queryParameters": {
          "parameters": [
            {
              "name": "content",
              "value": "true"
            }
          ]
        },
        "options": {}
      },
      "id": "fetch-greenhouse",
      "name": "Fetch Jobs",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        48,
        0
      ],
      "continueOnFail": true,
      "onError": "continueRegularOutput"
    },
    {
      "parameters": {
        "jsCode": "function stripHtml(html) {\n  return (html || '').replace(/<[^>]*>/g, ' ').replace(/&amp;/g, '&').replace(/&lt;/g, '<').replace(/&gt;/g, '>').replace(/&nbsp;/g, ' ').replace(/&#39;/g, \"'\").replace(/&quot;/g, '\"').replace(/\\s+/g, ' ').trim();\n}\nconst jobs = $json.jobs || [];\nconst companyName = ($json.company || {}).name || '';\nreturn jobs.map(j => {\n  const loc = (j.location || {}).name || '';\n  const isRemote = loc.toLowerCase().includes('remote') || (j.content || '').toLowerCase().includes('remote');\n  return {\n    json: {\n      source: 'greenhouse',\n      external_id: String(j.id ?? ''),\n      company: companyName,\n      title: (j.title || '').trim(),\n      location: loc,\n      remote: isRemote ? 'remote' : 'unknown',\n      url: j.absolute_url || '',\n      description: stripHtml(j.content || '').slice(0, 8000),\n      posted_at: j.updated_at || null,\n    }\n  };\n});"
      },
      "id": "normalize-greenhouse",
      "name": "Normalize",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        272,
        0
      ]
    },
    {
      "parameters": {
        "jsCode": "function simpleHash(str) {\n  let hash = 0;\n  for (let i = 0; i < str.length; i++) {\n    hash = ((hash << 5) - hash) + str.charCodeAt(i);\n    hash |= 0;\n  }\n  return Math.abs(hash).toString(16).padStart(8, '0');\n}\nreturn items.map(({ json }) => {\n  const base = [json.source, json.external_id, json.company, json.title, json.url].join('|');\n  return { json: { ...json, content_hash: simpleHash(base) } };\n});"
      },
      "id": "hash-greenhouse",
      "name": "Hash",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        496,
        0
      ]
    },
    {
      "parameters": {
        "method": "POST",
        "url": "https://matchpilot-production-a08d.up.railway.app/api/ingest",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Content-Type",
              "value": "application/json"
            }
          ]
        },
        "sendBody": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "source",
              "value": "={{ $json.source }}"
            },
            {
              "name": "external_id",
              "value": "={{ $json.external_id }}"
            },
            {
              "name": "company",
              "value": "={{ $json.company }}"
            },
            {
              "name": "title",
              "value": "={{ $json.title }}"
            },
            {
              "name": "location",
              "value": "={{ $json.location }}"
            },
            {
              "name": "remote",
              "value": "={{ $json.remote }}"
            },
            {
              "name": "url",
              "value": "={{ $json.url }}"
            },
            {
              "name": "description",
              "value": "={{ $json.description }}"
            },
            {
              "name": "posted_at",
              "value": "={{ $json.posted_at }}"
            },
            {
              "name": "content_hash",
              "value": "={{ $json.content_hash }}"
            }
          ]
        },
        "options": {
          "timeout": 15000
        }
      },
      "id": "ingest-greenhouse",
      "name": "Ingest",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        720,
        0
      ],
      "continueOnFail": true,
      "onError": "continueRegularOutput"
    },
    {
      "parameters": {
        "jsCode": "return Array.from({length: 100}, (_, i) => ({ json: { i } }));"
      },
      "id": "loop-greenhouse",
      "name": "Loop 100",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        944,
        0
      ]
    },
    {
      "parameters": {
        "method": "POST",
        "url": "https://matchpilot-production-a08d.up.railway.app/api/worker/score",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "x-worker-secret",
              "value": "3eb2bf26e739c83044d5b6c7ea851c4e4c7e6f58afd401f267fa98f78445e6bf"
            }
          ]
        },
        "options": {
          "timeout": 60000
        }
      },
      "id": "worker-greenhouse",
      "name": "Trigger Worker",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        1168,
        0
      ],
      "continueOnFail": true,
      "onError": "continueRegularOutput"
    }
  ],
  "connections": {
    "Schedule Trigger": {
      "main": [
        [
          {
            "node": "Companies",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Companies": {
      "main": [
        [
          {
            "node": "Fetch Jobs",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Fetch Jobs": {
      "main": [
        [
          {
            "node": "Normalize",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Normalize": {
      "main": [
        [
          {
            "node": "Hash",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Hash": {
      "main": [
        [
          {
            "node": "Ingest",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Ingest": {
      "main": [
        [
          {
            "node": "Loop 100",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Loop 100": {
      "main": [
        [
          {
            "node": "Trigger Worker",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}

About this workflow

Greenhouse Job Ingestion. Uses httpRequest. Scheduled trigger; 8 nodes.

Source: https://github.com/OskarsZvingulis/MatchPilot/blob/b94053498fa3f8fe4a8479b24d74a099cb9dfe73/n8n-workflows/greenhouse.json — original creator credit. Request a take-down →

More Web Scraping workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.