> Markdown versions of all pages of this connector library are available by appending `.md` to the page URL. For the full index of connectors, see [llms.txt](https://connectors.appmixer.com/llms.txt).

# Extract Page Contents

- Component: `appmixer.ai.exa.FindExtractedPages`
- Kind: Action
- Version: 1.0.0
- Visibility: Public
- Connector: [appmixer.ai.exa 1.0.2](https://connectors.appmixer.com/connector/appmixer.ai.exa/1.0.2.md)
- Component page: <https://connectors.appmixer.com/connector/appmixer.ai.exa/1.0.2/component/appmixer.ai.exa.FindExtractedPages>

Extract clean, LLM-ready content from a list of URLs — full text, relevant highlights, a focused summary and page metadata.

## Input ports

### Port `in`

| Field | Type | Description |
| --- | --- | --- |
| URLs (`urls`) | textarea | Comma or newline separated list of page URLs to extract, up to 100 per call. |
| Include Page Text (`includeText`) | toggle | Return the cleaned full text of each page. |
| Include Highlights (`includeHighlights`) | toggle | Also return the snippets of each page an LLM judged most relevant. |
| Summary Query (`summaryQuery`) | text | Ask Exa to summarise each page with this question in mind, e.g. `What is the pricing?`. Leave empty for no summary. |
| Max Cache Age (hours) (`maxAgeHours`) | number | Use Exa's cached copy when it is newer than this many hours. `0` forces a fresh crawl, `-1` serves cache only. Maximum 720. |
| Subpages (`subpages`) | number | Also crawl up to this many linked subpages of each URL, between 0 and 100. |
| Subpage Target (`subpageTarget`) | text | Comma separated terms that steer which subpages are picked, e.g. `pricing, about`. Only applies when Subpages is set. |
| Output Type (`outputType`) | select | Choose whether you want to receive the result set as one complete list, or first item only or one item at a time or stream the items to a file. |

## Output ports

### Port `out`

Variables are loaded dynamically from `/component/appmixer/ai/exa/FindExtractedPages?outPort=out&ignoreAuth=true`.

### Port `notFound`

| Field | Type | Description |
| --- | --- | --- |
| URLs (`urls`) | array | - |

## Full metadata (component.json)

```json
{
  "name": "appmixer.ai.exa.FindExtractedPages",
  "label": "Extract Page Contents",
  "description": "Extract clean, LLM-ready content from a list of URLs — full text, relevant highlights, a focused summary and page metadata.",
  "author": "Appmixer <info@appmixer.com>",
  "version": "1.0.0",
  "auth": {
    "service": "appmixer:ai:exa"
  },
  "quota": {
    "manager": "appmixer:ai:exa",
    "resources": "requests",
    "scope": {
      "userId": "{{userId}}"
    }
  },
  "inPorts": [
    {
      "name": "in",
      "schema": {
        "type": "object",
        "properties": {
          "urls": {
            "type": "string"
          },
          "includeText": {
            "type": "boolean"
          },
          "includeHighlights": {
            "type": "boolean"
          },
          "summaryQuery": {
            "type": "string"
          },
          "maxAgeHours": {
            "type": "integer",
            "minimum": -1,
            "maximum": 720
          },
          "subpages": {
            "type": "integer",
            "minimum": 0,
            "maximum": 100
          },
          "subpageTarget": {
            "type": "string"
          },
          "outputType": {
            "type": "string"
          }
        },
        "required": [
          "urls"
        ]
      },
      "inspector": {
        "inputs": {
          "urls": {
            "type": "textarea",
            "index": 1,
            "label": "URLs",
            "tooltip": "Comma or newline separated list of page URLs to extract, up to 100 per call."
          },
          "includeText": {
            "type": "toggle",
            "index": 2,
            "label": "Include Page Text",
            "defaultValue": true,
            "tooltip": "Return the cleaned full text of each page."
          },
          "includeHighlights": {
            "type": "toggle",
            "index": 3,
            "label": "Include Highlights",
            "tooltip": "Also return the snippets of each page an LLM judged most relevant."
          },
          "summaryQuery": {
            "type": "text",
            "index": 4,
            "label": "Summary Query",
            "tooltip": "Ask Exa to summarise each page with this question in mind, e.g. <code>What is the pricing?</code>. Leave empty for no summary."
          },
          "maxAgeHours": {
            "type": "number",
            "index": 5,
            "label": "Max Cache Age (hours)",
            "tooltip": "Use Exa's cached copy when it is newer than this many hours. <code>0</code> forces a fresh crawl, <code>-1</code> serves cache only. Maximum 720."
          },
          "subpages": {
            "type": "number",
            "index": 6,
            "label": "Subpages",
            "tooltip": "Also crawl up to this many linked subpages of each URL, between 0 and 100."
          },
          "subpageTarget": {
            "type": "text",
            "index": 7,
            "label": "Subpage Target",
            "tooltip": "Comma separated terms that steer which subpages are picked, e.g. <code>pricing, about</code>. Only applies when Subpages is set."
          },
          "outputType": {
            "type": "select",
            "index": 8,
            "label": "Output Type",
            "defaultValue": "array",
            "tooltip": "Choose whether you want to receive the result set as one complete list, or first item only or one item at a time or stream the items to a file.",
            "options": [
              {
                "label": "First Item Only",
                "value": "first"
              },
              {
                "label": "All items at once",
                "value": "array"
              },
              {
                "label": "One item at a time",
                "value": "object"
              },
              {
                "label": "Store to CSV file",
                "value": "file"
              }
            ]
          }
        }
      }
    }
  ],
  "outPorts": [
    {
      "name": "out",
      "source": {
        "url": "/component/appmixer/ai/exa/FindExtractedPages?outPort=out&ignoreAuth=true",
        "data": {
          "properties": {
            "generateOutputPortOptions": true
          },
          "messages": {
            "in/outputType": "inputs/in/outputType",
            "in/urls": "dummy"
          }
        }
      }
    },
    {
      "name": "notFound",
      "schema": {
        "type": "object",
        "properties": {
          "urls": {
            "type": "array",
            "title": "URLs",
            "items": {
              "type": "string"
            },
            "example": [
              "https://exa.ai/about"
            ]
          }
        }
      }
    }
  ],
  "icon": "(data URI omitted)"
}
```
