Haskell Language Parsing HTML with taggy-lens and lens Filtering elements from the tree
Example
Find div with id="article" and strip out all the inner script tags.
#!/usr/bin/env stack
-- stack --resolver lts-7.1 --install-ghc runghc --package text --package lens --package taggy-lens --package string-class --package classy-prelude
{-# LANGUAGE NoImplicitPrelude #-}
{-# LANGUAGE OverloadedStrings #-}
import ClassyPrelude
import Control.Lens hiding (children, element)
import Data.String.Class (toText, fromText, toString)
import Data.Text (Text)
import Text.Taggy.Lens
import qualified Text.Taggy.Lens as Taggy
import qualified Text.Taggy.Renderer as Renderer
somehtmlSmall :: Text
somehtmlSmall =
"<!doctype html><html><body>\
\<div id=\"article\"><div>first</div><div>second</div><script>this should be removed</script><div>third</div></div>\
\</body></html>"
renderWithoutScriptTag :: Text
renderWithoutScriptTag =
let mArticle :: Maybe Taggy.Element
mArticle =
(fromText somehtmlSmall) ^? html .
allAttributed (ix "id" . only "article")
mArticleFiltered =
fmap
(transform
(children %~
filter (\n -> n ^? element . name /= Just "script")))
mArticle
in maybe "" (toText . Renderer.render) mArticleFiltered
main :: IO ()
main = print renderWithoutScriptTag
-- outputs:
-- "<div id=\"article\"><div>first</div><div>second</div><div>third</div></div>"
Contribution based upon @duplode's SO answer
