twilight-library/app/inspektoratpracy.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 = extractLinksWithText "//td/a[contains(@href,'.pdf')]"

toShadowItem :: (String, String) -> ShadowItem
toShadowItem (url, monthlytitle) =
  (defaultShadowItem url title) {
    originalDate = Just date,
    itype = "periodical",
    format = Just "pdf",
    finalUrl = url
    }
    where title = (replace "\r" "" (replace "\n" "" (replace "\t" "" monthlytitle)))
          date = getDate $ replace "%20" " " url

getDate :: String -> String
getDate url = date where
  date = url Text.Regex.Posix.=~ "(202[0-2]|20[0-1][0-9])" :: String

main = do
    let start = "https://www.pip.gov.pl/pl/inspektor-pracy/66546,archiwum-inspektora-pracy-.html"
    let shadowLibrary = ShadowLibrary {logoUrl=Nothing,
                                       lname="Inspektor Pracy",
                                       abbrev="InspPrac",
                                       lLevel=0,
                                       webpage=start}
    extractItemsStartingFromUrl shadowLibrary start (extractRecords >>> arr toShadowItem)