Text.HTML.Parser

This is a performance-oriented HTML tokenizer aim at web-crawling applications. It follows the HTML5 parsing specification quite closely, so it behaves reasonable well on ill-formed documents from the open Web.

Parsing

parseTokens :: Text -> [Token]

Parse a lazy list of tokens from strict Text.

parseTokensLazy :: Text -> [Token]

Parse a lazy list of tokens from lazy Text.

token :: Parser Token

Parse a single Token.

Types

data Token

An HTML token

Constructors

TagOpen !TagName [Attr]

An opening tag. Attribute ordering is arbitrary.

TagSelfClose !TagName [Attr]

A self-closing tag.

TagClose !TagName

A closing tag.

ContentText !Text

The content between tags.

ContentChar !Char

A single character of content

Comment !Builder

Contents of a comment.

Doctype !Text

Doctype

Instances

Eq Token

Methods

(==) :: Token -> Token -> Bool

(/=) :: Token -> Token -> Bool

Ord Token

Methods

compare :: Token -> Token -> Ordering

(<) :: Token -> Token -> Bool

(<=) :: Token -> Token -> Bool

(>) :: Token -> Token -> Bool

(>=) :: Token -> Token -> Bool

max :: Token -> Token -> Token

min :: Token -> Token -> Token

Show Token

Methods

showsPrec :: Int -> Token -> ShowS

show :: Token -> String

showList :: [Token] -> ShowS

Generic Token

Associated Types

type Rep Token :: * -> *

Methods

from :: Token -> Rep Token x

to :: Rep Token x -> Token

NFData Token

Methods

rnf :: Token -> ()

type Rep Token

type Rep Token = D1 (MetaData "Token" "Text.HTML.Parser" "html-parse-0.2.0.1-KZMZhy2Hro2IdmADVCJ5oU" False) ((:+:) ((:+:) (C1 (MetaCons "TagOpen" PrefixI False) ((:*:) (S1 (MetaSel (Nothing Symbol) NoSourceUnpackedness SourceStrict DecidedStrict) (Rec0 TagName)) (S1 (MetaSel (Nothing Symbol) NoSourceUnpackedness NoSourceStrictness DecidedLazy) (Rec0 [Attr])))) ((:+:) (C1 (MetaCons "TagSelfClose" PrefixI False) ((:*:) (S1 (MetaSel (Nothing Symbol) NoSourceUnpackedness SourceStrict DecidedStrict) (Rec0 TagName)) (S1 (MetaSel (Nothing Symbol) NoSourceUnpackedness NoSourceStrictness DecidedLazy) (Rec0 [Attr])))) (C1 (MetaCons "TagClose" PrefixI False) (S1 (MetaSel (Nothing Symbol) NoSourceUnpackedness SourceStrict DecidedStrict) (Rec0 TagName))))) ((:+:) ((:+:) (C1 (MetaCons "ContentText" PrefixI False) (S1 (MetaSel (Nothing Symbol) NoSourceUnpackedness SourceStrict DecidedStrict) (Rec0 Text))) (C1 (MetaCons "ContentChar" PrefixI False) (S1 (MetaSel (Nothing Symbol) NoSourceUnpackedness SourceStrict DecidedStrict) (Rec0 Char)))) ((:+:) (C1 (MetaCons "Comment" PrefixI False) (S1 (MetaSel (Nothing Symbol) NoSourceUnpackedness SourceStrict DecidedStrict) (Rec0 Builder))) (C1 (MetaCons "Doctype" PrefixI False) (S1 (MetaSel (Nothing Symbol) NoSourceUnpackedness SourceStrict DecidedStrict) (Rec0 Text))))))

type TagName = Text

A tag name (e.g. body)

type AttrName = Text

An attribute name (e.g. href)

type AttrValue = Text

The value of an attribute

data Attr

An attribute of a tag

Constructors

Attr !AttrName !AttrValue

Instances

Eq Attr

Methods

(==) :: Attr -> Attr -> Bool

(/=) :: Attr -> Attr -> Bool

Ord Attr

Methods

compare :: Attr -> Attr -> Ordering

(<) :: Attr -> Attr -> Bool

(<=) :: Attr -> Attr -> Bool

(>) :: Attr -> Attr -> Bool

(>=) :: Attr -> Attr -> Bool

max :: Attr -> Attr -> Attr

min :: Attr -> Attr -> Attr

Show Attr

Methods

showsPrec :: Int -> Attr -> ShowS

show :: Attr -> String

showList :: [Attr] -> ShowS

Rendering, text canonicalization

renderTokens :: [Token] -> Text

See renderToken.

renderToken :: Token -> Text

(Somewhat) canonical string representation of Token.

renderAttrs :: [Attr] -> Text

See renderAttr.

renderAttr :: Attr -> Text

Does not escape quotation in attribute values!

canonicalizeTokens :: [Token] -> [Token]

Meld neighoring ContentChar and ContentText constructors together and drops empty text elements.