s440054/twilight-library
1
0
Fork 0
forked from filipg/twilight-library
Code Issues Pull Requests Releases Wiki Activity

clean output

Browse Source
This commit is contained in:
Norbert Litkowski 2021-04-07 23:28:39 +02:00
parent 0d45d42336
commit 1d077001b8
1 changed files with 12 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
app/ZborBielawa.hs
View File

@ -8,7 +8,6 @@ import Text.XML.HXT.XPath
import Data.List
import Data.List.Utils (replace)
-- import Text.Regex.Posix
import Text.Printf
import Control.Lens.Regex.Text
@ -31,14 +30,18 @@ extractNestedLinksWithText xpathCondition = proc url -> do
extractRecords = proc startUrl -> do
-- (catUrl, catText) <- extractLinksWithText "(//aside[@class='widget widget_maxmegamenu']//a[@class='mega-menu-link'])[2]" -< startUrl -- pary adres-tytuł podstrony
(catUrl, catText) <- extractLinksWithText "//aside[@class='widget widget_maxmegamenu']//a[@class='mega-menu-link']" -< startUrl -- pary adres-tytuł podstrony
(collUrl, collText) <- (extractLinksWithText "(//aside[@class='widget widget_maxmegamenu']//a[@class='mega-menu-link'])[1]") -< catUrl -- pobieramy podstronę kategorii i kolejne podstrony z menu
-- (collUrl, collText) <- (extractLinksWithText "//aside[@class='widget widget_maxmegamenu']//a[@class='mega-menu-link']") -< catUrl -- pobieramy podstronę kategorii i kolejne podstrony z menu
(relUrl, relText) <- (extractNestedLinksWithText "(//big[a[contains(@href,'.pdf')]])[1]") -< collUrl -- pobieramy stronę z wydaniami z danej kolekcji i linki do PDFów
-- (relUrl, relText) <- (extractNestedLinksWithText "//big[a[contains(@href,'.pdf')]]") -< collUrl -- pobieramy stronę z wydaniami z danej kolekcji i linki do PDFów
(collUrl, collText) <- (extractLinksWithText "//aside[@class='widget widget_maxmegamenu']//a[@class='mega-menu-link']") -< catUrl -- pobieramy podstronę kategorii i kolejne podstrony z menu
(relUrl, relText) <- (extractNestedLinksWithText "//big[a[contains(@href,'.pdf')]]") -< collUrl -- pobieramy stronę z wydaniami z danej kolekcji i linki do PDFów
returnA -< (relUrl, relText, collText, catText) -- ostatecznie wyjdą krotki (adres URL PDFa wydania, tytuł wydania, tytuł zbioru, tytuł kategorii)
cleanReleaseTitle :: String -> String
cleanReleaseTitle = proc text -> do
endCleaned <- replace " |\160" "" -< text
nbspCleaned <- replace "\160" " " -< endCleaned
res <- replace "\8211 " "" -< nbspCleaned
returnA -< res
-- ... a tutaj te krotki przerabiamy do docelowej struktury ShadowItem
toShadowItem :: (String, String, String, String) -> ShadowItem
toShadowItem (url, releaseTitle, collectionTitle, categoryTitle) =
@ -48,7 +51,7 @@ toShadowItem (url, releaseTitle, collectionTitle, categoryTitle) =
format = Just "pdf",
finalUrl = url
}
where title = categoryTitle ++ (" " ++ collectionTitle)
where title = categoryTitle ++ (" " ++ arr cleanReleaseTitle releaseTitle)
date = getDate $ T.pack $ releaseTitle