{
  "name": "Extract Article Text",
  "nodes": [
    {
      "parameters": {
        "content": "## Extract Article Text\n\nContent aggregators and newsletter platforms use this recipe to extract clean article content from PDFs, Word documents, and saved web pages. Define fields for title, author, date, body, and summary \u2014 the parser pulls the content and ignores headers, footers, navigation, and sidebars.\n\n**Note:** This workflow uses the Iteration Layer community node (`n8n-nodes-iterationlayer`). Install it via Settings > Community Nodes on self-hosted n8n, or add it directly on n8n Cloud with Verified Community Nodes enabled.",
        "height": 280,
        "width": 500,
        "color": 2
      },
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        200,
        40
      ],
      "id": "97f247db-41d8-4eae-95c9-d65cc3b2124d",
      "name": "Overview"
    },
    {
      "parameters": {
        "content": "### Step 1: Extract Data\nResource: **Document Extraction**\n\nConfigure the Document Extraction parameters below, then connect your credentials.",
        "height": 160,
        "width": 300,
        "color": 6
      },
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        475,
        100
      ],
      "id": "a0acbdab-4287-4466-8b64-95bd9d4e3e49",
      "name": "Step 1 Note"
    },
    {
      "parameters": {},
      "type": "n8n-nodes-base.manualTrigger",
      "typeVersion": 1,
      "position": [
        250,
        300
      ],
      "id": "c3d4e5f6-a7b8-9012-cdef-123456789012",
      "name": "Manual Trigger"
    },
    {
      "parameters": {
        "resource": "documentExtraction",
        "schemaInputMode": "rawJson",
        "schemaJson": "{\"fields\":[{\"name\":\"title\",\"type\":\"TEXT\",\"description\":\"Article title or headline\",\"is_required\":true},{\"name\":\"author\",\"type\":\"TEXT\",\"description\":\"Author name\"},{\"name\":\"publish_date\",\"type\":\"DATE\",\"description\":\"Publication date of the article\"},{\"name\":\"body\",\"type\":\"TEXTAREA\",\"description\":\"Main article text content, excluding headers, footers, sidebars, and navigation\",\"is_required\":true},{\"name\":\"summary\",\"type\":\"TEXT\",\"description\":\"Brief summary or abstract\",\"max_length\":500},{\"name\":\"category\",\"type\":\"TEXT\",\"description\":\"Article category or section\"}]}",
        "files": {
          "fileValues": [
            {
              "fileInputMode": "url",
              "fileName": "article.pdf",
              "fileUrl": "https://example.com/article.pdf"
            }
          ]
        }
      },
      "type": "n8n-nodes-iterationlayer.iterationLayer",
      "typeVersion": 1,
      "position": [
        500,
        300
      ],
      "id": "d4e5f6a7-b8c9-0123-defa-234567890123",
      "name": "Extract Data",
      "credentials": {
        "iterationLayerApi": {
          "name": "<your credential>"
        }
      }
    }
  ],
  "connections": {
    "Manual Trigger": {
      "main": [
        [
          {
            "node": "Extract Data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "settings": {
    "executionOrder": "v1"
  }
}