{-# 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 "//a[contains(@href,'.pdf')]"

toShadowItem :: (String, String) -> ShadowItem
toShadowItem (url, nr) =
  (defaultShadowItem url title) {
    originalDate = Just date,
    itype = "periodical",
    format = Just "pdf",
    finalUrl = url
    }
  where title = "Wszechświat " ++ "Rok " ++ getDate url ++ " " ++ getNr nr
        date = getDate url

getDate url =
  case url =~~ "/pdf_(19[0-9][0-9]|20[0-9][0-9]|18[0-9][0-9]|19[0-9][0-9]_19[0-9][0-9])/" :: Maybe [[String]] of
    Just [[_, year]] -> year
    otherwise -> error $ "unexpected url: " ++ url

getNr nr =
  case nr =~~ "(Nr [0-9][0-9]|Nr [0-9][0-9]-[0-9][0-9])" :: Maybe [[String]] of
    Just [[_, nr]] -> nr
    otherwise -> error $ "unexpected url: " ++ nr

main = do
    let start = "https://www.ptpk.org/archiwum.html"
    let shadowLibrary = ShadowLibrary {logoUrl=Nothing,
                                       lname="Czasopismo Wszechświat",
                                       abbrev="Wszechświat",
                                       lLevel=0,
                                       webpage=start}
    extractItemsStartingFromUrl shadowLibrary start (extractRecords >>> arr toShadowItem)