From 430c17097cba8c970c2826be0e622b6cb7bb6818 Mon Sep 17 00:00:00 2001
From: Daniel Schadt <kingdread@gmx.de>
Date: Sat, 2 Dec 2023 11:52:18 +0100
Subject: head commit

---
 src/MiniScalp.hs | 56 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)
 create mode 100644 src/MiniScalp.hs

(limited to 'src/MiniScalp.hs')

diff --git a/src/MiniScalp.hs b/src/MiniScalp.hs
new file mode 100644
index 0000000..f0e3e11
--- /dev/null
+++ b/src/MiniScalp.hs
@@ -0,0 +1,56 @@
+-- |
+-- Module      : MiniScalp
+-- Description : Wrapper around zenacy-html for web scraping
+-- Copyright   : (c) Daniel Schadt, 2023
+-- License     : MIT
+-- Maintainer  : sample@email.com
+-- Stability   : experimental
+-- Portability : POSIX
+--
+-- MiniScalp is a wrapper around [@zenacy-html@](https://hackage.haskell.org/package/zenacy-html) to do web scraping.
+--
+-- As @zenacy-html@ implements HTML parsing according to the WHATWG standard, this should produce results equivalent to
+-- what your browser produces.
+--
+-- = DOM navigation
+--
+-- The interface of MiniScalp is similar to that of [@scalpel@](https://hackage.haskell.org/package/scalpel) in the
+-- sense that you are provided with a monadic interface to the DOM. The bread and butter function is
+-- 'MiniScalp.Query.chroot', which allows you to focus on a specific subpart of the DOM by using
+-- 'MiniScalp.Types.Predicate' functions.
+--
+-- A number of helpful predicates are defined in "MiniScalp.Predicates".
+--
+-- = Example
+--
+-- > import Control.Monad
+-- > import Data.Maybe
+-- > import Data.Text
+-- > import MiniScalp.Predicates
+-- > import MiniScalp.Query
+-- > import MiniScalp.Sources
+-- > import MiniScalp.Types
+-- >
+-- > data MensaLine = MensaLine Text [Text] deriving (Show)
+-- >
+-- > mensaScraper :: Scraper [MensaLine]
+-- > mensaScraper = chroots (tag "tr" @& hasClass "mensatype_rows") $ do
+-- >   name <- chroot ("td" @: [hasClass "mensatype"]) text'
+-- >   meals <- chroots ("td" @: [hasClass "menu-title"]) text'
+-- >   return $ MensaLine name meals
+-- >
+-- > main :: IO ()
+-- > main = do
+-- >   scraped <- fromJust <$> scrapeFile "mensa.html" mensaScraper
+-- >   forM_ scraped $ \(MensaLine name meals) -> do
+-- >     putStrLn $ unpack name
+-- >     forM_ meals $ \meal -> putStrLn ("  " ++ unpack meal)
+-- >     putStrLn ""
+--
+-- = Modules
+--
+-- * "MiniScalp.Types": Basic definitions of the needed types.
+-- * "MiniScalp.Query": Data extraction routines.
+-- * "MiniScalp.Predicates": Predicates to select the wanted nodes.
+-- * "MiniScalp.Sources": Various data sources.
+module MiniScalp () where
-- 
cgit v1.2.3