Text.Pandoc.Readers.HTML

Conversion of HTML to Pandoc document.

Documentation

readHtml

Arguments

:: ParserState

Parser state

-> String

String to parse (assumes '\n' line endings)

-> Pandoc

Convert HTML-formatted string to Pandoc document.

rawHtmlInline :: GenParser Char ParserState Inline

rawHtmlBlock :: GenParser Char ParserState Block

anyHtmlBlockTag :: GenParser Char ParserState [Char]

anyHtmlInlineTag :: GenParser Char ParserState [Char]

anyHtmlTag :: GenParser Char ParserState [Char]

Parse any HTML tag (opening or self-closing) and return text of tag

anyHtmlEndTag :: GenParser Char ParserState [Char]

htmlEndTag :: [Char] -> GenParser Char ParserState [Char]

Parse an end tag of type tag

extractTagType :: String -> String

Extract type from a tag: e.g. br from <br>

htmlBlockElement :: GenParser Char ParserState [Char]

htmlComment :: GenParser Char st [Char]

Parses an HTML comment.

unsanitaryURI :: String -> Bool

Returns True if the specified URI is potentially a security risk.