Add files

This commit is contained in:
domzal 2022-04-17 21:15:49 +02:00
parent 8883a924b4
commit 07a854f8e2
3 changed files with 65 additions and 7 deletions

View File

@ -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 [("curl--user-agent","AMU Digital Libraries Indexing Agent")]]
downloadXmlDocument = readFromDocument [withWarnings no,
withEncodingErrors no,
withHTTP []]
-- withCurl [] ]
-- withHTTP,
withCurl [("curl--user-agent","AMU Digital Libraries Indexing Agent")]]
data ShadowLibrary = ShadowLibrary { logoUrl :: Maybe String,

View File

@ -0,0 +1,45 @@
{-# 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 "//h3[@class='media-heading']/a"
>>> first (arr (++"/issue/archive"))
>>> first (extractLinksWithText "//*[@class='media-heading']/a"
>>> first (extractLinksWithText "//*[@class='media-heading']/a"
>>> first (extractLinks "//div[@class='download']/a")))
toShadowItem :: (((String, String), String), String) -> ShadowItem
toShadowItem (((url, articleTitle), yearlyTitle), journalTitle) =
(defaultShadowItem url title) {
originalDate = Just date,
itype = "periodical",
format = Just "pdf",
finalUrl = url
}
where title = replace "\n" "" (replace "\t" "" (journalTitle ++ " " ++ yearlyTitle ++ " " ++ articleTitle))
date = getDate yearlyTitle
getDate yearlyTitle =
case yearlyTitle =~~ "(19[0-9][0-9]|20[0-9][0-9])" :: Maybe [[String]] of
Just [[_, year]] -> year
otherwise -> error $ "unexpected text: " ++ yearlyTitle
main = do
let start = "https://pressto.amu.edu.pl"
let shadowLibrary = ShadowLibrary {logoUrl=Nothing,
lname="Otwarte Czasopisma Naukowe UAM",
abbrev="OtwCzasNaukUAM",
lLevel=0,
webpage=start}
extractItemsStartingFromUrl shadowLibrary start (extractRecords >>> arr toShadowItem)

View File

@ -19,6 +19,7 @@ library
build-depends: base >= 4.7 && < 5
, HTTP
, hxt
, hxt-curl
, hxt-http
, hxt-xpath
, MissingH
@ -59,6 +60,18 @@ executable almanachmuszyny
, shadow-library
default-language: Haskell2010
executable otwarteczasopismauam
hs-source-dirs: app
main-is: otwarteczasopismauam.hs
ghc-options: -threaded -rtsopts -with-rtsopts=-N
build-depends: base
, hxt
, hxt-xpath
, hxt-curl
, MissingH
, regex-posix
, shadow-library
default-language: Haskell2010
source-repository head
type: git