Compare commits

...

3 Commits

Author SHA1 Message Date
2ff5b49ed1 direct download links 2022-05-25 14:54:54 +02:00
423e221f7d getDate fix 2022-05-13 13:32:05 +02:00
07a854f8e2 Add files 2022-04-17 21:15:49 +02:00
5 changed files with 142 additions and 7 deletions

50
.vscode/tasks.json vendored Normal file
View File

@ -0,0 +1,50 @@
{
// Automatically created by phoityne-vscode extension.
"version": "2.0.0",
"presentation": {
"reveal": "always",
"panel": "new"
},
"tasks": [
{
// F7
"group": {
"kind": "build",
"isDefault": true
},
"label": "haskell build",
"type": "shell",
//"command": "cabal configure && cabal build"
"command": "stack build"
},
{
// F6
"group": "build",
"type": "shell",
"label": "haskell clean & build",
//"command": "cabal clean && cabal configure && cabal build"
"command": "stack clean && stack build"
//"command": "stack clean ; stack build" // for powershell
},
{
// F8
"group": {
"kind": "test",
"isDefault": true
},
"type": "shell",
"label": "haskell test",
//"command": "cabal test"
"command": "stack test"
},
{
// F6
"isBackground": true,
"type": "shell",
"label": "haskell watch",
"command": "stack build --test --no-run-tests --file-watch"
}
]
}

View File

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

View File

@ -0,0 +1,50 @@
{-# 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.TDFA
-- import Text.Regex.TDFA.Text ()
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"
>>> extractLinks "//a[@class='download']")))
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
getDate :: String -> String
getDate yearlyTitle = date where
date = yearlyTitle Text.Regex.TDFA.=~ "(19[0-9][0-9]|20[0-9][0-9])" :: String
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 build-depends: base >= 4.7 && < 5
, HTTP , HTTP
, hxt , hxt
, hxt-curl
, hxt-http , hxt-http
, hxt-xpath , hxt-xpath
, MissingH , MissingH
@ -27,6 +28,7 @@ library
, network-uri , network-uri
, regex-pcre , regex-pcre
, regex-tdfa , regex-tdfa
, regex-tdfa-text
, resourcet , resourcet
, text , text
, time , time
@ -59,6 +61,20 @@ executable almanachmuszyny
, shadow-library , shadow-library
default-language: Haskell2010 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
, regex-tdfa
, regex-tdfa-text
, shadow-library
default-language: Haskell2010
source-repository head source-repository head
type: git type: git

19
stack.yaml.lock Normal file
View File

@ -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