fetch-url
Retrieve and parse web page content from a specified URL, allowing control over text length extraction, main content focus, and inclusion of links, images, or specific tag exclusions.
Instructions
Fetch the content of a URL and return it as text, with options to control extraction
Input Schema
Name | Required | Description | Default |
---|---|---|---|
excludeTags | No | Tags to exclude from extraction (default: script, style, etc.) | |
extractMainContent | No | Whether to attempt to extract main content (default: true) | |
includeImages | No | Whether to include image alt text (default: true) | |
includeLinks | No | Whether to include link text (default: true) | |
maxLength | No | Maximum length of content to return (default: 10000) | |
url | Yes | The URL to fetch |