doesnt work properly

ShadowLibrary/Core.hs

@@ -33,7 +33,7 @@ import Data.Tree.NTree.TypeDefs
 import Data.Maybe
 import Control.Monad.Trans
 import Text.XML.HXT.XPath
--- import Text.XML.HXT.Curl
+import Text.XML.HXT.Curl
 import Text.XML.HXT.HTTP
 
 import Text.Regex.TDFA
@@ -64,8 +64,8 @@ downloadDocument = readFromDocument [withParseHTML yes,
                                      withEncodingErrors no,
                                      withPreserveComment yes,
                                      withStrictInput yes,
-                                     withHTTP []
+--                                     withHTTP []
---                                     withCurl [("curl--user-agent","AMU Digital Libraries Indexing Agent")]
+                                     withCurl [("curl--user-agent","AMU Digital Libraries Indexing Agent")]
                                     ]
 
 downloadDocumentWithEncoding enc = readFromDocument [withParseHTML yes,
@@ -73,13 +73,13 @@ downloadDocumentWithEncoding enc = readFromDocument [withParseHTML yes,
                                                      withEncodingErrors no,
                                                      withPreserveComment yes,
                                                      withInputEncoding enc,
-					             withHTTP []]		
+--                       		             withHTTP []]
---                                                     withCurl []]
+                                                     withCurl []]
 
 downloadXmlDocument = readFromDocument [withWarnings no,
                                         withEncodingErrors no,
-					withHTTP []]
+--					withHTTP []]
---                                        withCurl [] ]
+                                        withCurl [] ]
 
 
 data ShadowLibrary = ShadowLibrary { logoUrl :: Maybe String,

app/almanachmuszyny.hs

@@ -4,7 +4,7 @@ import ShadowLibrary.Core
 
 import Text.XML.HXT.Core
 import Text.XML.HXT.XPath
--- import Text.XML.HXT.Curl
+--import Text.XML.HXT.Curl
 import Data.List
 import Data.List.Utils (replace)
 

app/geojournals.hs

@@ -0,0 +1,60 @@
+
+{-# 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[@class='action' and text() = 'View Journal']"
+--                     >>> arr ((++"/issue/archive") . init)
+--                     >>> extractLinksWithText "//div/h4[contains(@class, 'Vol')]/a"
+
+extractRecords = extractLinksWithText "//a[@class='action' and text() = 'View Journal']"  -- pary adres-tytuł
+                 >>> second (arr $ replace "\r\n            " " ") -- czyścimy drugi element pary, czyli tytuł z niepotrzebnych białych znaków
+                 >>> first (arr ((++"/issue/archive") . init))  -- modyfikujemy pierwszy element pary, czyli adres URL
+                 >>> first (extractLinksWithText "//div/h4[contains(@class, 'Vol')]/a")
+           
+
+                --  >>> first (extractLinksWithText "//div[@class='tocTitle']/a")
+                --  >>> first (arr ((++"/pdf") . init)) 
+                -- >>> second (arr $ replace "2020")
+
+                 -- ostatecznie wyjdą trójki ((adres URL, tytuł artykułu), tytuł rocznika)
+
+toShadowItem :: ((String, String), String) -> ShadowItem
+toShadowItem ((url, articleTitle), yearlyTitle) =
+  (defaultShadowItem url title) {
+    originalDate = Just date,
+    itype = "periodical",
+    format = Just "pdf",
+    finalUrl = url
+    }
+  where title = "Geo Journal OOO" ++ yearlyTitle ++ " AAAAA" ++ (replace "\r\n" "" (replace "\r\n          " "" articleTitle))
+        date = "202020"
+
+
+-- getDate url =
+--   case url =~~ "/(19[0-9][0-9]|20[0-9][0-9])/" :: Maybe [[String]] of
+--     Just [[_, year]] -> year
+--     otherwise -> error $ "unexpected url: " ++ url
+
+    
+
+
+main = do
+    let start = "https://geojournals.pgi.gov.pl"
+    
+    let shadowLibrary = ShadowLibrary {logoUrl=Nothing,
+                                       lname="Polish Geological Journals",
+                                       abbrev="geojour",
+                                       lLevel=0,
+                                       webpage=start}
+    extractItemsStartingFromUrl shadowLibrary start (extractRecords >>> arr toShadowItem)

shadow-library.cabal

@@ -20,6 +20,7 @@ library
                      , HTTP
                      , hxt
                      , hxt-http
+                     , hxt-curl
                      , hxt-xpath
                      , MissingH
                      , monad-logger
@@ -34,18 +35,18 @@ library
                      , tz
   default-language:    Haskell2010
 
--- executable maly-modelarz-exe
+executable geojournals
---    hs-source-dirs:      app
+   hs-source-dirs:      app
---    main-is:             malymodelarz.hs
+   main-is:             geojournals.hs
---    ghc-options:         -threaded -rtsopts -with-rtsopts=-N
+   ghc-options:         -threaded -rtsopts -with-rtsopts=-N
---    build-depends:       base
+   build-depends:       base
---                       , hxt
+                      , hxt
---                       , hxt-curl
+                      , hxt-curl
---                       , hxt-xpath
+                      , hxt-xpath
---                       , MissingH
+                      , MissingH
---                       , regex-posix
+                      , regex-posix
---                       , shadow-library
+                      , shadow-library
---    default-language:    Haskell2010
+   default-language:    Haskell2010
 
 executable almanachmuszyny
    hs-source-dirs:      app
@@ -54,6 +55,7 @@ executable almanachmuszyny
    build-depends:       base
                       , hxt
                       , hxt-xpath
+                      , hxt-curl
                       , MissingH
                       , regex-posix
                       , shadow-library