Add comments

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

@@ -4,18 +4,21 @@ 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)
 
 import Text.Regex.Posix
 import Text.Printf
 
-extractRecords = extractLinksWithText "//a[@class='roczniki']"
-                 >>> second (arr $ replace "\r\n              " "")
-                 >>> first (arr ((++"tr") . init))
-                 >>> first (extractLinksWithText "//li/a[contains(@href,'.pdf')]")
 
+extractRecords = extractLinksWithText "//a[@class='roczniki']"  -- pary adres-tytuł
+                 >>> second (arr $ replace "\r\n            " " ") -- czyścimy drugi element pary, czyli tytuł z niepotrzebnych białych znaków
+                 >>> first (arr ((++"tr") . init))  -- modyfikujemy pierwszy element pary, czyli adres URL
+                 >>> first (extractLinksWithText "//li/a[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)
+
+-- ... a tutaj te trójki przerabiamy do docelowej struktury ShadowItem
 toShadowItem :: ((String, String), String) -> ShadowItem
 toShadowItem ((url, articleTitle), yearlyTitle) =
   (defaultShadowItem url title) {

shadow-library.cabal

@@ -20,7 +20,6 @@ library
                      , HTTP
                      , hxt
                      , hxt-http
-                     , hxt-curl
                      , hxt-xpath
                      , MissingH
                      , monad-logger
@@ -55,7 +54,6 @@ executable almanachmuszyny
    build-depends:       base
                       , hxt
                       , hxt-xpath
-                      , hxt-curl
                       , MissingH
                       , regex-posix
                       , shadow-library