Safe Haskell	Safe
Language	Haskell2010

Text.HTML.Parser

Contents

Parsing
Types

Description

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.

Synopsis

Parsing

parseTokens :: Text -> [Token] Source #

Parse a lazy list of tokens from strict Text.

parseTokensLazy :: Text -> [Token] Source #

Parse a lazy list of tokens from lazy Text.

token :: Parser Token Source #

Parse a single Token.

Types

data Token Source #

An HTML token

Constructors

TagOpen !TagName [Attr]	An opening tag. Attribute ordering is arbitrary.
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 Source #
Methods (==) :: Token -> Token -> Bool # (/=) :: Token -> Token -> Bool #
Ord Token Source #
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 Source #
Methods showsPrec :: Int -> Token -> ShowS # show :: Token -> String # showList :: [Token] -> ShowS #
Generic Token Source #
Associated Types type Rep Token :: * -> * # Methods from :: Token -> Rep Token x # to :: Rep Token x -> Token #
NFData Token Source #
Methods rnf :: Token -> () #
type Rep Token Source #
type Rep Token = D1 (MetaData "Token" "Text.HTML.Parser" "html-parse-0.2.0.0-DiIjrjh4a5EFyTZ2FZKV4V" 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 "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 Source #

A tag name (e.g. body)

type AttrName = Text Source #

An attribute name (e.g. href)

type AttrValue = Text Source #

The value of an attribute

data Attr Source #

An attribute of a tag

Constructors

Attr !AttrName !AttrValue

Instances

Eq Attr Source #
Methods (==) :: Attr -> Attr -> Bool # (/=) :: Attr -> Attr -> Bool #
Ord Attr Source #
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 Source #
Methods showsPrec :: Int -> Attr -> ShowS # show :: Attr -> String # showList :: [Attr] -> ShowS #