fetch_and_extract
Extract main content, metadata, and optional comments from web pages by providing a URL. Returns structured JSON data with text, title, author, and date information.
Instructions
Fetches a URL and extracts the main content, metadata, and comments. Returns a JSON object with the extracted data.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| include_comments | No | Whether to include comment sections at the bottom of articles. | |
| include_tables | No | Extract text from HTML <table> elements. | |
| url | Yes | The URL of the web page to process. |
Input Schema (JSON Schema)
{
"properties": {
"include_comments": {
"default": false,
"description": "Whether to include comment sections at the bottom of articles.",
"title": "Include Comments",
"type": "boolean"
},
"include_tables": {
"default": false,
"description": "Extract text from HTML <table> elements.",
"title": "Include Tables",
"type": "boolean"
},
"url": {
"description": "The URL of the web page to process.",
"title": "Url",
"type": "string"
}
},
"required": [
"url"
],
"type": "object"
}