AutomationFlowsWeb Scraping › Signalforge-v4.1-keywordworker

Signalforge-v4.1-keywordworker

SignalForge-v4.1-KeywordWorker. Uses executeWorkflowTrigger, httpRequest. Event-driven trigger; 14 nodes.

Event trigger★★★★☆ complexity14 nodesExecute Workflow TriggerHTTP Request
Web Scraping Trigger: Event Nodes: 14 Complexity: ★★★★☆ Added:

This workflow follows the Execute Workflow Trigger → HTTP Request recipe pattern — see all workflows that pair these two integrations.

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 →

Download .json
{
  "name": "SignalForge-v4.1-KeywordWorker",
  "nodes": [
    {
      "id": "b1b2c3d4-0000-4000-8000-000000000001",
      "name": "Execute Workflow Trigger",
      "type": "n8n-nodes-base.executeWorkflowTrigger",
      "typeVersion": 1,
      "position": [
        240,
        300
      ],
      "parameters": {}
    },
    {
      "id": "b1b2c3d4-0000-4000-8000-000000000002",
      "name": "Cache Gate",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        440,
        300
      ],
      "parameters": {
        "jsCode": "const input = $input.first().json;\nconst st = $getWorkflowStaticData('global');\nif (!st.cache) st.cache = {};\n\nconst keyword = input.keyword;\nconst config = input.config;\nconst ttlMs = (config.cache_ttl_minutes || 30) * 60 * 1000;\nconst now = Date.now();\n\nconst cached = st.cache[keyword];\n\nif (cached && (now - cached.ts_epoch_ms < ttlMs)) {\n  return [{\n    json: {\n      keyword,\n      config,\n      cache_hit: true,\n      cached_items: cached.items || [],\n      cached_hits: 1,\n      api_calls: 0,\n      failed_calls: 0\n    }\n  }];\n}\n\nreturn [{\n  json: {\n    keyword,\n    config,\n    cache_hit: false,\n    cached_hits: 0,\n    api_calls: 0,\n    failed_calls: 0\n  }\n}];"
      }
    },
    {
      "id": "b1b2c3d4-0000-4000-8000-000000000003",
      "name": "IF Cache Hit",
      "type": "n8n-nodes-base.if",
      "typeVersion": 2,
      "position": [
        640,
        300
      ],
      "parameters": {
        "conditions": {
          "options": {
            "caseSensitive": true
          },
          "conditions": [
            {
              "leftValue": "={{ $json.cache_hit }}",
              "rightValue": true,
              "operator": {
                "type": "boolean",
                "operation": "equals"
              }
            }
          ],
          "combinator": "and"
        }
      }
    },
    {
      "id": "b1b2c3d4-0000-4000-8000-000000000004",
      "name": "Emit Cached Items",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        840,
        200
      ],
      "parameters": {
        "jsCode": "const data = $json;\nif (!data.cached_items || data.cached_items.length === 0) {\n  return [{ json: { __empty: true, __stream: 'cache' } }];\n}\nreturn data.cached_items.map(i => ({\n  json: { ...i, meta: { ...i.meta, cached: true, api_calls: 0, failed_calls: 0 } }\n}));"
      }
    },
    {
      "id": "b1b2c3d4-0000-4000-8000-000000000005",
      "name": "Fetch HN",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        840,
        400
      ],
      "parameters": {
        "method": "GET",
        "url": "={{ 'https://hn.algolia.com/api/v1/search?query=' + encodeURIComponent($('Cache Gate').first().json.keyword) + '&tags=story&hitsPerPage=5' }}",
        "options": {
          "continueOnFail": true
        }
      }
    },
    {
      "id": "b1b2c3d4-0000-4000-8000-000000000006",
      "name": "Fetch Wikipedia",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        840,
        500
      ],
      "parameters": {
        "method": "GET",
        "url": "={{ 'https://en.wikipedia.org/w/api.php?action=query&list=search&srsearch=' + encodeURIComponent($('Cache Gate').first().json.keyword) + '&format=json&utf8=1&srlimit=5' }}",
        "options": {
          "continueOnFail": true
        }
      }
    },
    {
      "id": "b1b2c3d4-0000-4000-8000-000000000007",
      "name": "Fetch Crossref",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        840,
        600
      ],
      "parameters": {
        "method": "GET",
        "url": "={{ 'https://api.crossref.org/works?query=' + encodeURIComponent($('Cache Gate').first().json.keyword) + '&rows=5' }}",
        "options": {
          "continueOnFail": true
        }
      }
    },
    {
      "id": "b1b2c3d4-0000-4000-8000-000000000008",
      "name": "Normalize HN",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        1040,
        400
      ],
      "parameters": {
        "jsCode": "const cacheGate = $('Cache Gate').first().json;\nconst keyword = cacheGate.keyword;\nconst data = $json;\n\nif (!data || !data.hits || data.error) {\n  return [{ json: { __empty: true, __src: 'hn', meta: { failed_calls: 1 } } }];\n}\n\nreturn data.hits.map(h => ({\n  json: {\n    source: 'hn',\n    keyword,\n    title: h.title,\n    url: h.url || `https://news.ycombinator.com/item?id=${h.objectID}`,\n    published_at: h.created_at ? new Date(h.created_at).toISOString() : null,\n    raw_score: (h.points || 0) + (h.num_comments || 0),\n    score: (h.points || 0) + (h.num_comments || 0),\n    summary_raw: null,\n    summary: null,\n    meta: { author: h.author, venue: 'Hacker News', cached: false, api_calls: 0, failed_calls: 0 }\n  }\n}));"
      }
    },
    {
      "id": "b1b2c3d4-0000-4000-8000-000000000009",
      "name": "Normalize Wikipedia",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        1040,
        500
      ],
      "parameters": {
        "jsCode": "const cacheGate = $('Cache Gate').first().json;\nconst keyword = cacheGate.keyword;\nconst data = $json;\n\nif (!data || !data.query || !data.query.search || data.error) {\n  return [{ json: { __empty: true, __src: 'wikipedia', meta: { failed_calls: 1 } } }];\n}\n\nreturn data.query.search.map(hit => ({\n  json: {\n    source: 'wikipedia',\n    keyword,\n    title: hit.title,\n    url: `https://en.wikipedia.org/wiki/${encodeURIComponent(hit.title.replace(/ /g, '_'))}`,\n    published_at: null,\n    raw_score: Math.floor((hit.size || 0) / 100),\n    score: Math.floor((hit.size || 0) / 100),\n    summary_raw: hit.snippet || null,\n    summary: null,\n    meta: { author: null, venue: 'Wikipedia', cached: false, api_calls: 0, failed_calls: 0 }\n  }\n}));"
      }
    },
    {
      "id": "b1b2c3d4-0000-4000-8000-000000000010",
      "name": "Normalize Crossref",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        1040,
        600
      ],
      "parameters": {
        "jsCode": "const cacheGate = $('Cache Gate').first().json;\nconst keyword = cacheGate.keyword;\nconst data = $json;\n\nif (!data || !data.message || !data.message.items || data.error) {\n  return [{ json: { __empty: true, __src: 'crossref', meta: { failed_calls: 1 } } }];\n}\n\nreturn data.message.items.map(item => ({\n  json: {\n    source: 'crossref',\n    keyword,\n    title: (item.title && item.title[0]) ? item.title[0] : 'Untitled',\n    url: item.URL || '',\n    published_at: (item['published-print'] && item['published-print']['date-time']) ? item['published-print']['date-time'] : null,\n    raw_score: 20 + (item['is-referenced-by-count'] || 0),\n    score: 20 + (item['is-referenced-by-count'] || 0),\n    summary_raw: null,\n    summary: null,\n    meta: {\n      author: item.author ? item.author[0].family : null,\n      venue: item['container-title'] ? item['container-title'][0] : 'Crossref',\n      cached: false,\n      api_calls: 0,\n      failed_calls: 0\n    }\n  }\n}));"
      }
    },
    {
      "id": "b1b2c3d4-0000-4000-8000-000000000011",
      "name": "Merge HN Wiki",
      "type": "n8n-nodes-base.merge",
      "typeVersion": 2.1,
      "position": [
        1240,
        450
      ],
      "parameters": {
        "mode": "append",
        "options": {}
      }
    },
    {
      "id": "b1b2c3d4-0000-4000-8000-000000000012",
      "name": "Merge All",
      "type": "n8n-nodes-base.merge",
      "typeVersion": 2.1,
      "position": [
        1440,
        500
      ],
      "parameters": {
        "mode": "append",
        "options": {}
      }
    },
    {
      "id": "b1b2c3d4-0000-4000-8000-000000000013",
      "name": "Cache Save",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        1640,
        400
      ],
      "parameters": {
        "jsCode": "const cacheGate = $('Cache Gate').first().json;\nconst keyword = cacheGate.keyword;\nconst st = $getWorkflowStaticData('global');\nconst allItems = $input.all();\n\n// Count failed calls\nlet failedCalls = 0;\nconst validItems = allItems\n  .map(i => i.json)\n  .filter(i => {\n    if (i.__empty) {\n      if (i.meta?.failed_calls) failedCalls += i.meta.failed_calls;\n      else failedCalls++;\n      return false;\n    }\n    return true;\n  });\n\nst.cache[keyword] = {\n  ts_epoch_ms: Date.now(),\n  items: validItems\n};\n\nif (validItems.length === 0) {\n  return [{ json: { __empty: true, keyword, meta: { cached: false, api_calls: 3, failed_calls: failedCalls || 3 } } }];\n}\n\nreturn validItems.map(item => ({\n  json: {\n    ...item,\n    meta: { ...item.meta, cached: false, api_calls: 3, failed_calls: 0 }\n  }\n}));"
      }
    },
    {
      "id": "b1b2c3d4-0000-4000-8000-000000000014",
      "name": "Merge Cached",
      "type": "n8n-nodes-base.merge",
      "typeVersion": 2.1,
      "position": [
        1640,
        300
      ],
      "parameters": {
        "mode": "append",
        "options": {}
      }
    }
  ],
  "connections": {
    "Execute Workflow Trigger": {
      "main": [
        [
          {
            "node": "Cache Gate",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Cache Gate": {
      "main": [
        [
          {
            "node": "IF Cache Hit",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "IF Cache Hit": {
      "main": [
        [
          {
            "node": "Emit Cached Items",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Fetch HN",
            "type": "main",
            "index": 0
          },
          {
            "node": "Fetch Wikipedia",
            "type": "main",
            "index": 0
          },
          {
            "node": "Fetch Crossref",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Emit Cached Items": {
      "main": [
        [
          {
            "node": "Merge Cached",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Fetch HN": {
      "main": [
        [
          {
            "node": "Normalize HN",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Fetch Wikipedia": {
      "main": [
        [
          {
            "node": "Normalize Wikipedia",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Fetch Crossref": {
      "main": [
        [
          {
            "node": "Normalize Crossref",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Normalize HN": {
      "main": [
        [
          {
            "node": "Merge HN Wiki",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Normalize Wikipedia": {
      "main": [
        [
          {
            "node": "Merge HN Wiki",
            "type": "main",
            "index": 1
          }
        ]
      ]
    },
    "Merge HN Wiki": {
      "main": [
        [
          {
            "node": "Merge All",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Normalize Crossref": {
      "main": [
        [
          {
            "node": "Merge All",
            "type": "main",
            "index": 1
          }
        ]
      ]
    },
    "Merge All": {
      "main": [
        [
          {
            "node": "Cache Save",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Cache Save": {
      "main": [
        [
          {
            "node": "Merge Cached",
            "type": "main",
            "index": 1
          }
        ]
      ]
    }
  }
}
Pro

For the full experience including quality scoring and batch install features for each workflow upgrade to Pro

About this workflow

SignalForge-v4.1-KeywordWorker. Uses executeWorkflowTrigger, httpRequest. Event-driven trigger; 14 nodes.

Source: https://github.com/turtir-ai/n8n-workflow-studio/blob/main/public/fixtures/SignalForge-v4.1-KeywordWorker.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.

Web Scraping

02_LLM_Pipeline v1.0. Uses executeWorkflowTrigger, httpRequest, seaTable. Event-driven trigger; 65 nodes.

Execute Workflow Trigger, HTTP Request, Sea Table
Web Scraping

This template is a powerful, reusable utility for managing stateful, long-running processes. It allows a main workflow to be paused indefinitely at "checkpoints" and then be resumed by external, async

HTTP Request, Execute Workflow Trigger
Web Scraping

Upload files from any source to your account Kommo or AmoCRM with a simple and reusable workflow. It can split a large file into small ones and upload chunks. Works for Kommo and amoCRM There are 3 re

HTTP Request, Execute Workflow Trigger, Stop And Error
Web Scraping

Remixed Backup your workflows to GitHub from Solomon's work. Check out his templates.

HTTP Request, GitHub, Execute Workflow Trigger +1
Web Scraping

Remixed Backup your workflows to GitHub from Solomon's work. Check out his templates.

Execute Workflow Trigger, HTTP Request, GitHub