Jd Scraper

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": "JD Scraper",
  "nodes": [
    {
      "parameters": {
        "httpMethod": "POST",
        "path": "jd-scraper",
        "responseMode": "responseNode",
        "options": {}
      },
      "id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
      "name": "Webhook",
      "type": "n8n-nodes-base.webhook",
      "typeVersion": 2,
      "position": [
        240,
        300
      ]
    },
    {
      "parameters": {
        "mode": "runOnceForAllItems",
        "jsCode": "// Normalise input: support both direct JSON and webhook body wrapper\nconst raw = $input.first().json;\nconst body = raw.body || raw;\n\nconst url  = (body.url  || '').trim();\nconst text = (body.text || '').trim();\n\nif (!url && !text) {\n  throw new Error('Provide either url or text in the request body');\n}\n\nreturn [{ json: { url, text, hasText: text.length > 0 } }];\n"
      },
      "id": "jds-validate-01",
      "name": "Validate Input",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        460,
        300
      ]
    },
    {
      "parameters": {
        "conditions": {
          "options": {
            "caseSensitive": true,
            "leftValue": "",
            "typeValidation": "strict"
          },
          "conditions": [
            {
              "id": "cond-has-text",
              "leftValue": "={{ $json.hasText }}",
              "rightValue": true,
              "operator": {
                "type": "boolean",
                "operation": "equals"
              }
            }
          ],
          "combinator": "and"
        },
        "options": {}
      },
      "id": "b2c3d4e5-f6a7-8901-bcde-f12345678901",
      "name": "Has Text?",
      "type": "n8n-nodes-base.if",
      "typeVersion": 2,
      "position": [
        700,
        300
      ]
    },
    {
      "parameters": {
        "method": "POST",
        "url": "={{ \"https://api.cloudflare.com/client/v4/accounts/\" + $env.CF_ACCOUNT_ID + \"/browser-rendering/content\" }}",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Authorization",
              "value": "=Bearer {{ $env.CF_API_TOKEN }}"
            },
            {
              "name": "Content-Type",
              "value": "application/json"
            }
          ]
        },
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "={{ { url: $('Validate Input').item.json.url, rejectResourceTypes: ['image', 'font', 'media'] } }}",
        "options": {
          "timeout": 30000,
          "response": {
            "response": {
              "fullResponse": true
            }
          }
        }
      },
      "id": "c3d4e5f6-a7b8-9012-cdef-123456789012",
      "name": "Cloudflare Scrape",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4,
      "position": [
        940,
        420
      ],
      "continueOnFail": true
    },
    {
      "parameters": {
        "conditions": {
          "options": {
            "caseSensitive": true,
            "leftValue": "",
            "typeValidation": "loose"
          },
          "conditions": [
            {
              "id": "cond-cf-success",
              "leftValue": "={{ $json.body && $json.body.result && $json.body.result.markdown && $json.body.result.markdown.trim().length > 100 }}",
              "rightValue": true,
              "operator": {
                "type": "boolean",
                "operation": "equals"
              }
            }
          ],
          "combinator": "and"
        },
        "options": {}
      },
      "id": "d4e5f6a7-b8c9-0123-defa-234567890123",
      "name": "CF Success?",
      "type": "n8n-nodes-base.if",
      "typeVersion": 2,
      "position": [
        1180,
        420
      ]
    },
    {
      "parameters": {
        "method": "GET",
        "url": "={{ \"https://r.jina.ai/\" + $('Validate Input').item.json.url }}",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "Accept",
              "value": "text/plain"
            },
            {
              "name": "X-Return-Format",
              "value": "text"
            }
          ]
        },
        "options": {
          "timeout": 25000
        }
      },
      "id": "e5f6a7b8-c9d0-1234-efab-345678901234",
      "name": "Jina AI Fallback",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4,
      "position": [
        1420,
        540
      ],
      "continueOnFail": true
    },
    {
      "parameters": {
        "mode": "runOnceForAllItems",
        "jsCode": "// Unify output from all three branches into { jd_raw, source }\nconst item = $input.first().json;\n\nlet jd_raw = '';\nlet source  = 'unknown';\n\n// Branch 1: manual text passed directly from Has Text? node\nif (item.hasText === true) {\n  jd_raw = item.text || '';\n  source  = 'manual';\n}\n// Branch 2: Cloudflare returned valid markdown\nelse if (item.body && item.body.result && item.body.result.markdown) {\n  jd_raw = item.body.result.markdown.trim();\n  source  = 'cloudflare';\n}\n// Branch 3: Jina AI returned plain text (various n8n response shapes)\nelse if (typeof item.data === 'string' && item.data.trim().length > 50) {\n  jd_raw = item.data.trim();\n  source  = 'jina';\n}\nelse if (typeof item === 'string' && item.trim().length > 50) {\n  jd_raw = item.trim();\n  source  = 'jina';\n}\n\n// Trim to a reasonable token budget (first ~12 000 chars \u2248 3 000 tokens)\njd_raw = jd_raw.slice(0, 12000);\n\nif (!jd_raw.trim()) {\n  throw new Error('Failed to retrieve job description from any source. Check CF credentials or paste JD text directly.');\n}\n\nreturn [{ json: { jd_raw, source } }];\n"
      },
      "id": "f6a7b8c9-d0e1-2345-fabc-456789012345",
      "name": "Normalize Output",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        1660,
        300
      ]
    },
    {
      "parameters": {
        "respondWith": "allIncomingItems",
        "options": {}
      },
      "id": "a7b8c9d0-e1f2-3456-abcd-567890123456",
      "name": "Respond to Webhook",
      "type": "n8n-nodes-base.respondToWebhook",
      "typeVersion": 1.1,
      "position": [
        1900,
        300
      ]
    }
  ],
  "connections": {
    "Webhook": {
      "main": [
        [
          {
            "node": "Validate Input",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Validate Input": {
      "main": [
        [
          {
            "node": "Has Text?",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Has Text?": {
      "main": [
        [
          {
            "node": "Normalize Output",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Cloudflare Scrape",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Cloudflare Scrape": {
      "main": [
        [
          {
            "node": "CF Success?",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "CF Success?": {
      "main": [
        [
          {
            "node": "Normalize Output",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Jina AI Fallback",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Jina AI Fallback": {
      "main": [
        [
          {
            "node": "Normalize Output",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Normalize Output": {
      "main": [
        [
          {
            "node": "Respond to Webhook",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "settings": {
    "executionOrder": "v1"
  },
  "staticData": null,
  "tags": [],
  "id": 1,
  "active": true
}

About this workflow

JD Scraper. Uses httpRequest. Webhook trigger; 8 nodes.

Source: https://github.com/1Mangesh1/resume-gen/blob/5e25f2cb1d4429abd1677088fec426394eef0c6b/workflows/jd-scraper.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.