diff --git a/ShadowLibrary/Core.hs b/ShadowLibrary/Core.hs index 678df33..84c7850 100644 --- a/ShadowLibrary/Core.hs +++ b/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 [] --- withCurl [("curl--user-agent","AMU Digital Libraries Indexing Agent")] +-- withHTTP [] + 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 []] --- withCurl []] +-- withHTTP []] + withCurl []] downloadXmlDocument = readFromDocument [withWarnings no, withEncodingErrors no, - withHTTP []] --- withCurl [] ] +-- withHTTP []] + withCurl [] ] data ShadowLibrary = ShadowLibrary { logoUrl :: Maybe String, diff --git a/app/almanachmuszyny.hs b/app/almanachmuszyny.hs index ebc4f5c..2569177 100644 --- a/app/almanachmuszyny.hs +++ b/app/almanachmuszyny.hs @@ -4,21 +4,18 @@ 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) { diff --git a/app/parafiasremm.hs b/app/parafiasremm.hs new file mode 100644 index 0000000..b9a73ed --- /dev/null +++ b/app/parafiasremm.hs @@ -0,0 +1,43 @@ + +{-# 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, 'index.php?download=gazetka')]" -- pary adres-tytuł + >>> second (arr $ replace "\r\n " " ") -- czyścimy drugi element pary, czyli tytuł z niepotrzebnych białych znaków + >>> first (arr $ replace "index.php?download=" "pliki/") -- modyfikujemy pierwszy element pary, czyli adres URL + +toShadowItem :: (String, String) -> ShadowItem +toShadowItem (url, articleTitle) = + (defaultShadowItem url title) { + originalDate = Just date, + itype = "periodical", + format = Just "pdf", + finalUrl = url + } + where title = "Parafia Srem " ++ articleTitle + date = getDate url + +getDate url = + case url =~~ "(20[0-1][0-9])" :: Maybe [[String]] of + Just [[_, year]] -> year + otherwise -> error $ "unexpected url: " ++ url + + +main = do + let start = "https://sremfara.pl/miesiecznik_30.html" + let shadowLibrary = ShadowLibrary {logoUrl=Nothing, + lname="Parafia Sremm", + abbrev="ParSre", + lLevel=0, + webpage=start} + extractItemsStartingFromUrl shadowLibrary start (extractRecords >>> arr toShadowItem) diff --git a/shadow-library.cabal b/shadow-library.cabal index cd77195..3e1bd4e 100644 --- a/shadow-library.cabal +++ b/shadow-library.cabal @@ -20,6 +20,7 @@ library , HTTP , hxt , hxt-http + , hxt-curl , hxt-xpath , MissingH , monad-logger @@ -54,6 +55,7 @@ executable almanachmuszyny build-depends: base , hxt , hxt-xpath + , hxt-curl , MissingH , regex-posix , shadow-library diff --git a/stack.yaml.lock b/stack.yaml.lock new file mode 100644 index 0000000..cc80ef3 --- /dev/null +++ b/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