Internet Tools
Tools for searching and accessing data on the Internet:
internet_searchfetch_contentfetch_linksfetch_filefetch_wikipedia
Documents
internet_search
Search the Internet or a specific site for a search term.
Parameters
search_term
The search term used to search the Internet or a specific site for relevant links.
site
Search only a specific site which should be a domain name or '-' which will search the Internet. A good default is - which will search the whole Internet.
output_path
Optional parameter specifying a fully qualified file or folder name where the output is saved: if a filename is provided and it already exists, an error is returned; if a folder is provided, a new file with a .json extension is auto-generated and saved in that folder; an empty string or '-' displays the output directly, with '-' being the recommended default for direct display
fetch_content
Fetch the readable text content from a URL.
Parameters
url
The URL to fetch text content from.
fetcher
The fetcher to use for extracting content from a URL, with Primary being a good default.
output_path
Optional parameter specifying a fully qualified file or folder name where the output is saved: if a filename is provided and it already exists, an error is returned; if a folder is provided, a new file with a .json extension is auto-generated and saved in that folder; an empty string or '-' displays the output directly, with '-' being the recommended default for direct display
fetch_links
Fetch the links within the HTML content of a URL.
Parameters
url
The URL to fetch links from.
fetcher
The fetcher to use for extracting links from a URL, with Primary being a good default.
output_path
Optional parameter specifying a fully qualified file or folder name where the output is saved: if a filename is provided and it already exists, an error is returned; if a folder is provided, a new file with a .json extension is auto-generated and saved in that folder; an empty string or '-' displays the output directly, with '-' being the recommended default for direct display
fetch_file
Fetch a file from the URL which must end in a filename with a supported extension.
Parameters
url
The URL to fetch the file from.
output_path
The fully qualified output filename or folder name where to save the file.
fetch_wikipedia
Fetch the text content from a Wikipedia URL. A Wikipedia URL is a URL that contains wikipedia.org in the host portion of the URL.
Parameters
url
The Wikipedia URL to fetch text content from.
output_path
Optional parameter specifying a fully qualified file or folder name where the output is saved: if a filename is provided and it already exists, an error is returned; if a folder is provided, a new file with a .json extension is auto-generated and saved in that folder; an empty string or '-' displays the output directly, with '-' being the recommended default for direct display