This commit is contained in:
Vojtaz 2021-04-05 22:45:06 +02:00
parent 8883a924b4
commit 73e4a732ec
4 changed files with 74 additions and 5 deletions

View File

@ -13,9 +13,9 @@ import Text.Printf
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
-- >>> 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
@ -43,4 +43,4 @@ main = do
abbrev="AlmMusz",
lLevel=0,
webpage=start}
extractItemsStartingFromUrl shadowLibrary start (extractRecords >>> arr toShadowItem)
extractItemsStartingFromUrl shadowLibrary start (extractRecords)-- >>> arr toShadowItem)

37
app/robot.hs Normal file
View File

@ -0,0 +1,37 @@
{-# LANGUAGE Arrows, NoMonomorphismRestriction #-}
import ShadowLibrary.Core
import Text.XML.HXT.Core
import Text.XML.HXT.XPath
import Data.List
import Data.List.Utils (replace)
import Text.Regex.Posix
import Text.Printf
extractRecords = extractLinksWithText "//a"
>>> first (extractLinksWithText "//a[contains(@href,'.pdf')]")
toShadowItem :: ((String, String), String) -> ShadowItem
toShadowItem ((url, articleTitle), yearlyTitle) =
(defaultShadowItem url title) {
originalDate = extractMonthAndYear title,
itype = "periodical",
format = Just "pdf",
finalUrl = url
}
where title = "Kosmos " ++ yearlyTitle ++ (replace ".pdf" "" articleTitle)
extractMonthAndYear :: String -> Maybe String
extractMonthAndYear n =
case n =~~ ("(1[6789]|20)[0-9][0-9]" :: String) of
Just year -> Just year
otherwise -> Nothing
main = do
let start = "http://kosmos.icm.edu.pl/PDF/"
let shadowLibrary = ShadowLibrary {logoUrl=Nothing,
lname="kosmos.icm.edu",
abbrev="Kos",
lLevel=0,
webpage=start}
extractItemsStartingFromUrl shadowLibrary start (extractRecords >>> arr toShadowItem)

View File

@ -59,7 +59,20 @@ executable almanachmuszyny
, shadow-library
default-language: Haskell2010
executable robot
hs-source-dirs: app
main-is: robot.hs
ghc-options: -threaded -rtsopts -with-rtsopts=-N
build-depends: base
, hxt
, 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/s426229/twilight-library.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