for in publication 1 to 11

README.md

@@ -0,0 +1,7 @@
+# Build and run project
+
+`stack install`
+
+`stack build`
+
+`stack exec kulturaparyska`

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

@@ -20,6 +20,7 @@ extractRecords = extractLinksWithText "//a[@class='roczniki']"  -- pary adres-ty
 
 -- ... a tutaj te trójki przerabiamy do docelowej struktury ShadowItem
 toShadowItem :: ((String, String), String) -> ShadowItem
+
 toShadowItem ((url, articleTitle), yearlyTitle) =
   (defaultShadowItem url title) {
     originalDate = Just date,

app/kulturaparyska.hs

@@ -0,0 +1,96 @@
+
+{-# 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[@class='year-anchor ']"  -- pary adres-tytuł
+                 >>> second (arr $ replace "\r\n            " " ") -- czyścimy drugi element pary, czyli tytuł z niepotrzebnych białych znaków
+                --  >>> first (arr ((++"f") . init))  -- modyfikujemy pierwszy element pary, czyli adres URL
+                 >>> first (extractLinksWithText "//a[@class='pdf-exist'][contains(@href,'.pdf')]") -- pobieramy stronę z adresu URL i wyciągamy linki z tej strony pasujące do wyrażenia XPathowego
+                 -- ostatecznie wyjdą trójki ((adres URL, tytuł artykułu), tytuł rocznika)
+
+-- extractRecords2 = extractLinksWithText "//a[@class='year-anchor']"  -- pary adres-tytuł
+--                  >>> second (arr $ replace "\r\n            " " ") -- czyścimy drugi element pary, czyli tytuł z niepotrzebnych białych znaków
+--                 --  >>> first (arr ((++"f") . init))  -- modyfikujemy pierwszy element pary, czyli adres URL
+--                  >>> first (extractLinksWithText "//a[ends-with(@href,'.pdf')]") -- pobieramy stronę z adresu URL i wyciągamy linki z tej strony pasujące do wyrażenia XPathowego
+--                  -- ostatecznie wyjdą trójki ((adres URL, tytuł artykułu), tytuł rocznika)
+
+-- ... a tutaj te trójki przerabiamy do docelowej struktury ShadowItem
+toShadowItem :: ((String, String), String) -> ShadowItem
+toShadowItem ((url, articleTitle), yearlyTitle) =
+  (defaultShadowItem url title) {
+    originalDate = Just date,
+    itype = "periodical",
+    format = Just "pdf",
+    finalUrl = url
+    }
+  where title = "Kultura Paryska " ++ yearlyTitle ++ " " ++ (replace "\r\n" "" (replace "\r\n          " "" articleTitle))
+        date = yearlyTitle
+
+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://kulturaparyska.com/pl/publication/4/year/1946"
+    let shadowLibrary = ShadowLibrary {logoUrl=Nothing,
+                                       lname="Kultura Paryska",
+                                       abbrev="kultParys",
+                                       lLevel=0,
+                                       webpage=start}
+    putStrLn "Program started"
+    extractItemsStartingFromUrl shadowLibrary start (extractRecords >>> arr toShadowItem)
+    
+    -- First time using haskell and for loop in haskell is hard
+    
+    putStrLn "New link"
+    let start2 = "https://kulturaparyska.com/pl/publication/1/year/1946"
+    extractItemsStartingFromUrl shadowLibrary start2 (extractRecords >>> arr toShadowItem)
+
+    putStrLn "New link"
+    let start2 = "https://kulturaparyska.com/pl/publication/2/year/1946"
+    extractItemsStartingFromUrl shadowLibrary start2 (extractRecords >>> arr toShadowItem)
+
+    putStrLn "New link"
+    let start2 = "https://kulturaparyska.com/pl/publication/3/year/1946"
+    extractItemsStartingFromUrl shadowLibrary start2 (extractRecords >>> arr toShadowItem)
+
+    putStrLn "New link"
+    let start2 = "https://kulturaparyska.com/pl/publication/5/year/1946"
+    extractItemsStartingFromUrl shadowLibrary start2 (extractRecords >>> arr toShadowItem)
+
+    putStrLn "New link"
+    let start2 = "https://kulturaparyska.com/pl/publication/6/year/1946"
+    extractItemsStartingFromUrl shadowLibrary start2 (extractRecords >>> arr toShadowItem)
+
+    putStrLn "New link"
+    let start2 = "https://kulturaparyska.com/pl/publication/7/year/1946"
+    extractItemsStartingFromUrl shadowLibrary start2 (extractRecords >>> arr toShadowItem)
+
+    putStrLn "New link"
+    let start2 = "https://kulturaparyska.com/pl/publication/8/year/1946"
+    extractItemsStartingFromUrl shadowLibrary start2 (extractRecords >>> arr toShadowItem)
+
+    putStrLn "New link"
+    let start2 = "https://kulturaparyska.com/pl/publication/9/year/1946"
+    extractItemsStartingFromUrl shadowLibrary start2 (extractRecords >>> arr toShadowItem)
+
+    putStrLn "New link"
+    let start2 = "https://kulturaparyska.com/pl/publication/10/year/1946"
+    extractItemsStartingFromUrl shadowLibrary start2 (extractRecords >>> arr toShadowItem)
+
+    putStrLn "New link"
+    let start2 = "https://kulturaparyska.com/pl/publication/11/year/1946"
+    extractItemsStartingFromUrl shadowLibrary start2 (extractRecords >>> arr toShadowItem)

shadow-library.cabal

@@ -2,11 +2,11 @@ name:                shadow-library
 version:             0.1.0.0
 synopsis:            Initial project template from stack
 description:         Please see README.md
-homepage:            http://github.com/name/project
+homepage:            https://git.wmi.amu.edu.pl/s444463/twilight-library
 license:             Proprietary
 license-file:        LICENSE
-author:              Your name here
+author:              Mikołaj Pokrywka
-maintainer:          your.address@example.com
+maintainer:          -
 -- copyright:
 category:            Web
 build-type:          Simple
@@ -19,6 +19,7 @@ library
   build-depends:       base >= 4.7 && < 5
                      , HTTP
                      , hxt
+                     , hxt-curl
                      , hxt-http
                      , hxt-xpath
                      , MissingH
@@ -59,7 +60,20 @@ executable almanachmuszyny
                       , shadow-library
    default-language:    Haskell2010
 
+executable kulturaparyska
+   hs-source-dirs:      app
+   main-is:             kulturaparyska.hs
+   ghc-options:         -threaded -rtsopts -with-rtsopts=-N
+   build-depends:       base
+                      , hxt
+                      , hxt-curl
+                      , hxt-xpath
+                      , MissingH
+                      , regex-posix
+                      , shadow-library
+   default-language:    Haskell2010
+
 
 source-repository head
   type:     git
-  location: https://github.com/name/project
+  location: https://git.wmi.amu.edu.pl/s444463/twilight-library

stack.yaml.lock

@@ -0,0 +1,19 @@
+# This file was autogenerated by Stack.
+# You should not edit this file by hand.
+# For more information, please see the documentation at:
+#   https://docs.haskellstack.org/en/stable/lock_files
+
+packages:
+- completed:
+    hackage: hxt-xpath-9.1.2.2@sha256:9cd590ae93a04573db8f90fa4094625ebd97dded45da7667c577ce6b38a42900,1999
+    pantry-tree:
+      size: 2225
+      sha256: aee2f75974e868ff429b8ff349a29667536c60397098f5dfedc968d1951511bb
+  original:
+    hackage: hxt-xpath-9.1.2.2
+snapshots:
+- completed:
+    size: 507596
+    url: https://raw.githubusercontent.com/commercialhaskell/stackage-snapshots/master/lts/11/9.yaml
+    sha256: 42f472dbf06482da1b3319241f3e3b3593a45bd7d4f537d2789f21386b9b2ad3
+  original: lts-11.9