Replace encoded symbols with latin letters and filter away titleless ShadowItems

ShadowLibrary/Core.hs

@@ -298,7 +298,15 @@ extractItems shadowLibrary start extractor = do
 --  insertIntoDatabase shadowLibrary items
   putStrLn (show items)
 
+getTitle :: ShadowItem -> String  
+getTitle (ShadowItem _ title _ _ _ _ _ _ _) = title
+
+isEmpty :: String -> Bool
+isEmpty str = length str == 0
+
+removeTitleless :: [ShadowItem] -> [ShadowItem]
+removeTitleless = filter (\si -> not .isEmpty . getTitle $ si) 
+
 extractItemsStartingFromUrl shadowLibrary start extractor = do
   items <- runX $ (arr (const start) >>> setTraceLevel 1 >>> extractor)
---  insertIntoDatabase shadowLibrary items
+  mapM_ (putStrLn . show) (removeTitleless items)
-  mapM_ (putStrLn . show) items

app/podkarpacki.hs

@@ -15,6 +15,16 @@ import Text.Printf
 extractRecords = extractLinksWithText "//a[contains(@href, '.pdf')]"  -- pary adres-tytuł
                  >>> second (arr $ replace "\n\t\t\t\t\t\t\t\t\t\t\t" "") -- czyścimy drugi element pary, czyli tytuł z niepotrzebnych białych znaków
                  >>> second (arr $ replace "\n\t\t\t\t\t\t\t\t\t\t" "")   -- czyścimy drugi element pary, czyli tytuł z niepotrzebnych białych znaków   
+                 >>> second (arr $ replace "\324" "n")
+                 >>> second (arr $ replace "\281" "e")
+                 >>> second (arr $ replace "\380" "z")
+                 >>> second (arr $ replace "\322" "l")
+                 >>> second (arr $ replace "\243" "o")
+                 >>> second (arr $ replace "\347" "s")
+                 >>> second (arr $ replace "\263" "c")
+                 >>> second (arr $ replace "\346" "S")
+                 
+
 
 -- ... a tutaj te trójki przerabiamy do docelowej struktury ShadowItem
 toShadowItem :: (String, String) -> ShadowItem