> 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 Content

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

Extract the clean page content of one or more URLs. Accepts up to 20 URLs per call; URLs that could not be fetched are reported on the notFound port.

## Input ports

### Port `in`

| Field | Type | Description |
| --- | --- | --- |
| URLs (`urls`) | textarea | One or more URLs to extract, separated by commas or new lines. Maximum 20 URLs per call. |
| Extract Depth (`extractDepth`) | select | **Advanced** retrieves more data including tables and embedded content, at a higher credit cost and latency. |
| Format (`format`) | select | The format of the extracted content. |
| Query (`query`) | text | Optional. When set, the extracted content is reranked so the chunks most relevant to this query come first. |
| Include Images (`includeImages`) | toggle | Also return the URLs of images found on each page. |
| Include Favicon (`includeFavicon`) | toggle | Also return the favicon URL of each page. |
| 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/tavily/core/FindExtractedPages?outPort=out&ignoreAuth=true`.

### Port `notFound`

_No fields defined for this port._

## Full metadata (component.json)

```json
{
  "name": "appmixer.tavily.core.FindExtractedPages",
  "label": "Extract Content",
  "description": "Extract the clean page content of one or more URLs. Accepts up to 20 URLs per call; URLs that could not be fetched are reported on the notFound port.",
  "author": "Appmixer <info@appmixer.com>",
  "version": "1.0.0",
  "auth": {
    "service": "appmixer:tavily"
  },
  "quota": {
    "manager": "appmixer:tavily",
    "resources": "requests",
    "scope": {
      "userId": "{{userId}}"
    }
  },
  "inPorts": [
    {
      "name": "in",
      "schema": {
        "type": "object",
        "properties": {
          "urls": {
            "type": "string"
          },
          "extractDepth": {
            "type": "string"
          },
          "format": {
            "type": "string"
          },
          "query": {
            "type": "string"
          },
          "includeImages": {
            "type": "boolean"
          },
          "includeFavicon": {
            "type": "boolean"
          },
          "outputType": {
            "type": "string"
          }
        },
        "required": [
          "urls"
        ]
      },
      "inspector": {
        "inputs": {
          "urls": {
            "type": "textarea",
            "index": 1,
            "label": "URLs",
            "tooltip": "One or more URLs to extract, separated by commas or new lines. Maximum 20 URLs per call."
          },
          "extractDepth": {
            "type": "select",
            "index": 2,
            "label": "Extract Depth",
            "defaultValue": "basic",
            "tooltip": "<b>Advanced</b> retrieves more data including tables and embedded content, at a higher credit cost and latency.",
            "options": [
              {
                "label": "Basic",
                "value": "basic"
              },
              {
                "label": "Advanced",
                "value": "advanced"
              }
            ]
          },
          "format": {
            "type": "select",
            "index": 3,
            "label": "Format",
            "defaultValue": "markdown",
            "tooltip": "The format of the extracted content.",
            "options": [
              {
                "label": "Markdown",
                "value": "markdown"
              },
              {
                "label": "Plain text",
                "value": "text"
              }
            ]
          },
          "query": {
            "type": "text",
            "index": 4,
            "label": "Query",
            "tooltip": "Optional. When set, the extracted content is reranked so the chunks most relevant to this query come first."
          },
          "includeImages": {
            "type": "toggle",
            "index": 5,
            "label": "Include Images",
            "tooltip": "Also return the URLs of images found on each page."
          },
          "includeFavicon": {
            "type": "toggle",
            "index": 6,
            "label": "Include Favicon",
            "tooltip": "Also return the favicon URL of each page."
          },
          "outputType": {
            "type": "select",
            "label": "Output Type",
            "index": 7,
            "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/tavily/core/FindExtractedPages?outPort=out&ignoreAuth=true",
        "data": {
          "properties": {
            "generateOutputPortOptions": true
          },
          "messages": {
            "in/outputType": "inputs/in/outputType",
            "in/urls": "dummy"
          }
        }
      }
    },
    {
      "name": "notFound"
    }
  ],
  "icon": "(data URI omitted)"
}
```
