twilight-library/app/teatrLalek.hs

{-# LANGUAGE Arrows, NoMonomorphismRestriction #-}
import ShadowLibrary.Core

import Text.XML.HXT.Core
import Text.XML.HXT.XPath
-- import Text.XML.HXT.Curl
import Data.List
import Data.List.Utils (replace)

import Text.Regex.Posix
import Text.Printf


extractRecords = extractLinks "//a[contains(@href, '.pdf')]"


toShadowItem :: String -> ShadowItem
toShadowItem url =
  (defaultShadowItem url title) {
    originalDate = Just date,
    itype = "periodical",
    format = Just "pdf",
    finalUrl = url
    }
  where
    date = last $ getAllTextMatches $ url =~ "(19[0-9][0-9]|20[0-9][0-9])" :: String
    titleToProcess = last $ getAllTextMatches $ url =~ "/[a-zA-Z ]+[-_]" :: String
    title = titleToProcess =~ "[a-zA-Z ]+" :: String


main = do
    let start = "http://polunima.pl/teatr-lalek/"
    let shadowLibrary = ShadowLibrary {logoUrl=Nothing,
                                       lname="Teatr Lalek",
                                       abbrev="Teatr",
                                       lLevel=0,
                                       webpage=start}
    extractItemsStartingFromUrl shadowLibrary start (extractRecords >>> arr toShadowItem)