htmlToMdast
Convert HTML to Mdast. If you simply want to convert from HTML to Markdown, we recommend using htmlToMarkdown.
Usage
import { htmlToMdast } from "webforai";
const mdast = htmlToMdast("<h1>Hello, world!</h1>");
=> { type: "root", children: [{ type: "heading", depth: 1, children: [{ type: "text", value: "Hello, world!" }] }] }
Returns
mdast.Nodes
The converted Mdast tree.
Parameters
htmlOrHast
type: string | Hast
The HTML string or HAST tree to convert.
const mdast = htmlToMdast("<h1>Hello, world!</h1>");
// => {
// type: "root",
// children: [{ type: "heading", depth: 1, children: [{ type: "text", value: "Hello, world!" }] }]
// }
options.extractors
type: ExtractorSelectors
An array of extractors to extract specific elements from the HTML. You can define your own functions in addition to the Extractor provided as a preset.
import { htmlToMdast, type Extractor, takumiExtractor } from "webforai"
const yourCustomExtractor: Extractor = (params) => {
const { hast, url } = params
// ... your logic ...
return hast
};
const html = "<h1>Hello, world!</h1>"
const mdast = htmlToMdast(html, {
extractors: [yourCustomExtractor, takumiExtractor]
});
options.linkAsText
type: boolean
Whether to convert links to plain text.
const mdast = htmlToMdast("<a href='/foo'>bar</a>", {
linkAsText: true,
});
options.tableAsText
type: boolean
Whether to convert tables to plain text.
options.hideImage
type: boolean
Whether to hide images.
options.lang
type: string
The language of the HTML.