html-to-content

ai-research-agent / extractor/html-to-content/html-to-content

Functions

extractContentAndCite()

function extractContentAndCite(documentOrHTML, options): Object

Extracts the main content and citation information from a document or HTML string

Parameters

Parameter	Type	Description
documentOrHTML	string | object	The document or HTML string to extract content from
options	{ formatting: boolean; images: boolean; links: boolean; url: string; useExtractor2: boolean; }	Optional configuration options
options.formatting	boolean	default=true - Whether to preserve formatting in the extracted content
options.images	boolean	default=true - Whether to include images in the extracted content
options.links	boolean	default=true - Whether to include links in the extracted content
options.url	string	The URL of the original document, if available, for absolutify-ing URLs
options.useExtractor2	boolean	default=false - false uses Mozilla Readability, true uses Postlight Mercury. then use the alternate if the first returns less than 200 characters

Returns

Object

The extracted content and citation information

Author

ai-research-agent (2024)

Interfaces

ExtractedContent

Properties

author

author: string;

The author's name

author_cite

author_cite: string;

The full citation for the author

author_short

author_short: string;

A shortened version of the author's name

date

date: string;

The publication date

html

html: string;

The extracted main content in HTML format

source

source: string;

The source of the content

title

title: string;

The title of the content