forked from filipg/twilight-library
v1
This commit is contained in:
Mikołaj Pokrywka
parent
66720e3317
commit
f79ab1fe01
7
README.md
Normal file
7
README.md
Normal file
@ -0,0 +1,7 @@
|
||||
# Build and run project
|
||||
|
||||
`stack install`
|
||||
|
||||
`stack build`
|
||||
|
||||
`stack exec kulturaparyska`
|
||||
@ -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,
|
||||
|
||||
@ -20,6 +20,7 @@ extractRecords = extractLinksWithText "//a[@class='roczniki']" -- pary adres-ty
|
||||
|
||||
-- ... a tutaj te trójki przerabiamy do docelowej struktury ShadowItem
|
||||
toShadowItem :: ((String, String), String) -> ShadowItem
|
||||
|
||||
toShadowItem ((url, articleTitle), yearlyTitle) =
|
||||
(defaultShadowItem url title) {
|
||||
originalDate = Just date,
|
||||
|
||||
@ -12,10 +12,10 @@ import Text.Regex.Posix
|
||||
import Text.Printf
|
||||
|
||||
|
||||
extractRecords = extractLinksWithText "//a[@class='roczniki']" -- pary adres-tytuł
|
||||
extractRecords = extractLinksWithText "//a[@class='year-anchor ']" -- 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
|
||||
-- >>> first (arr ((++"f") . init)) -- modyfikujemy pierwszy element pary, czyli adres URL
|
||||
>>> 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)
|
||||
|
||||
-- ... a tutaj te trójki przerabiamy do docelowej struktury ShadowItem
|
||||
@ -27,8 +27,8 @@ toShadowItem ((url, articleTitle), yearlyTitle) =
|
||||
format = Just "pdf",
|
||||
finalUrl = url
|
||||
}
|
||||
where title = "Almanach Muszyny " ++ yearlyTitle ++ " " ++ (replace "\r\n" "" (replace "\r\n " "" articleTitle))
|
||||
date = getDate url
|
||||
where title = "Kultura Paryska " ++ yearlyTitle ++ " " ++ (replace "\r\n" "" (replace "\r\n " "" articleTitle))
|
||||
date = yearlyTitle
|
||||
|
||||
getDate url =
|
||||
case url =~~ "/(19[0-9][0-9]|20[0-9][0-9])/" :: Maybe [[String]] of
|
||||
@ -37,10 +37,11 @@ getDate url =
|
||||
|
||||
|
||||
main = do
|
||||
let start = "http://www.almanachmuszyny.pl/"
|
||||
let start = "https://kulturaparyska.com/pl/publication/4/year/1946"
|
||||
let shadowLibrary = ShadowLibrary {logoUrl=Nothing,
|
||||
lname="Almanach Muszyny",
|
||||
abbrev="AlmMusz",
|
||||
lname="Kultura Paryska",
|
||||
abbrev="kultParys",
|
||||
lLevel=0,
|
||||
webpage=start}
|
||||
putStrLn "Program started"
|
||||
extractItemsStartingFromUrl shadowLibrary start (extractRecords >>> arr toShadowItem)
|
||||
|
||||
@ -2,11 +2,11 @@ name: shadow-library
|
||||
version: 0.1.0.0
|
||||
synopsis: Initial project template from stack
|
||||
description: Please see README.md
|
||||
homepage: http://github.com/name/project
|
||||
homepage: https://git.wmi.amu.edu.pl/s444463/twilight-library
|
||||
license: Proprietary
|
||||
license-file: LICENSE
|
||||
author: Your name here
|
||||
maintainer: your.address@example.com
|
||||
author: Mikołaj Pokrywka
|
||||
maintainer: -
|
||||
-- copyright:
|
||||
category: Web
|
||||
build-type: Simple
|
||||
@ -19,6 +19,7 @@ library
|
||||
build-depends: base >= 4.7 && < 5
|
||||
, HTTP
|
||||
, hxt
|
||||
, hxt-curl
|
||||
, hxt-http
|
||||
, hxt-xpath
|
||||
, MissingH
|
||||
@ -59,7 +60,20 @@ executable almanachmuszyny
|
||||
, shadow-library
|
||||
default-language: Haskell2010
|
||||
|
||||
executable kulturaparyska
|
||||
hs-source-dirs: app
|
||||
main-is: kulturaparyska.hs
|
||||
ghc-options: -threaded -rtsopts -with-rtsopts=-N
|
||||
build-depends: base
|
||||
, hxt
|
||||
, hxt-curl
|
||||
, hxt-xpath
|
||||
, 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/s444463/twilight-library
|
||||
|
||||
Loading…
Reference in New Issue
Block a user