add project chelmek

This commit is contained in:
Maciej Ścigacz 2022-04-16 21:07:17 +02:00
parent 8883a924b4
commit a96e26c4ef
3 changed files with 71 additions and 10 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 []]
downloadXmlDocument = readFromDocument [withWarnings no,
withEncodingErrors no,
withHTTP []]
-- withCurl [] ]
-- withHTTP []]
withCurl [] ]
data ShadowLibrary = ShadowLibrary { logoUrl :: Maybe String,

47
app/chelmek.hs Normal file
View File

@ -0,0 +1,47 @@
{-# 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 "//div[@class='span4']//a[contains(@href,'o-nas')]" -- pary adres-tytuł
>>> first (extractLinksWithText "//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)
toShadowItem :: ((String, String), String) -> ShadowItem
toShadowItem ((url, articleTitle), yearlyTitle) =
(defaultShadowItem url title) {
originalDate = Just date,
itype = "periodical",
format = Just "pdf",
finalUrl = url
}
where title = "yearlyTitle: " ++ replace "\"" "'" (replace "\t\t\t\t\t" "" (replace "\n" "" yearlyTitle)) ++ " articleTitle: " ++ 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 -> "unexpected yearlyTitle" ++ yearlyTitle
main = do
let start = "http://moksir.chelmek.pl/o-nas/echo-chelmka"
let shadowLibrary = ShadowLibrary {logoUrl=Nothing,
lname="Chelmek",
abbrev="Chelmek",
lLevel=0,
webpage=start}
extractItemsStartingFromUrl shadowLibrary start (extractRecords >>> arr toShadowItem)

View File

@ -5,8 +5,8 @@ description: Please see README.md
homepage: http://github.com/name/project
license: Proprietary
license-file: LICENSE
author: Your name here
maintainer: your.address@example.com
author: Maciej Ścigacz
maintainer: macsci1@st.amu.edu.pl
-- copyright:
category: Web
build-type: Simple
@ -20,6 +20,7 @@ library
, HTTP
, hxt
, hxt-http
, hxt-curl
, hxt-xpath
, MissingH
, monad-logger
@ -54,12 +55,25 @@ executable almanachmuszyny
build-depends: base
, hxt
, hxt-xpath
, hxt-curl
, MissingH
, regex-posix
, shadow-library
default-language: Haskell2010
executable chelmek
hs-source-dirs: app
main-is: chelmek.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
location: https://github.com/name/project
location: https://git.wmi.amu.edu.pl/s444476/twilight-library