从具有特定 id 的 div 中提取文本内容

Created: November-22, 2018

Taggy-lens 允许我们使用镜头来解析和检查 HTML 文档。

#!/usr/bin/env stack
-- stack --resolver lts-7.0 --install-ghc runghc --package text --package lens --package taggy-lens

{-# LANGUAGE OverloadedStrings #-}

import qualified Data.Text.Lazy as TL
import qualified Data.Text.IO as T
import Text.Taggy.Lens
import Control.Lens

someHtml::TL.Text
someHtml =
    "\
    \<!doctype html><html><body>\
    \<div>first div</div>\
    \<div id=\"thediv\">second div</div>\
    \<div id=\"not-thediv\">third div</div>"

main::IO ()
main = do
    T.putStrLn
        (someHtml ^. html . allAttributed (ix "id" . only "thediv") . contents)