s478873/twilight-library
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

add pdf names

Browse Source
This commit is contained in:
Adrian Świderski 2022-05-10 00:20:35 +02:00
parent d28c055f3b
commit 3ab57f0f58
1 changed files with 12 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
app/best_robot.hs
View File

@ -13,16 +13,17 @@ import Text.Printf
extractRecords = extractLinksWithText "//a[@class='title']" -- pary adres-tytuł
>>> second (arr $ replace "\n\t\t\t\t\t" "")-- czyścimy drugi element pary, czyli tytuł z niepotrzebnych białych znaków
>>> first (extractLinksWithText "//a[@class='obj_galley_link 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)
extractRecords = extractLinksWithText "//a[@class='title']"
>>> second (arr $ replace "\n\t\t\t\t\t" "")
>>> first (extractLinksWithText "//div[@class='title']"
>>> first (extractLinksWithText"//a[@class='obj_galley_link pdf']"))
-- >>> first (extractLinksWithText"//ul[@class='value galleys_links']//a[@class='obj_galley_link pdf']"))
-- ... a tutaj te trójki przerabiamy do docelowej struktury ShadowItem
toShadowItem :: ((String, String), String) -> ShadowItem
toShadowItem ((url, articleTitle), yearlyTitle) =
toShadowItem :: (((String, String), String),String)-> ShadowItem
-- toShadowItem :: ((String, String),String) -> ShadowItem
-- toShadowItem ((url, articleTitle), yearlyTitle) =
toShadowItem (((url, articleTitle),pdfTitle), yearlyTitle)=
(defaultShadowItem url title) {
originalDate = Just date,
itype = "periodical",
@ -30,9 +31,8 @@ toShadowItem ((url, articleTitle), yearlyTitle) =
finalUrl = url
}
where title = replace "\n\t\t\t" "" yearlyTitle ++ " " ++ (replace "\n\n\t" "" (replace "\n\n\t\t\n\t" " " articleTitle))
where title = replace "\n\t\t\t" " " yearlyTitle ++ (replace "\t\n\t" "" (replace "\n\n\t" " " articleTitle)) ++ (replace "\n\t\t \n\t\t\t" " " (replace "\n\t\t\t\t\t \n\t" "" (replace "\n\t\t\t\t\t\t\t \n\t\t\t\t\t" " " (replace "\n\t\t\t\t " ""pdfTitle))))
date = getDate yearlyTitle
getDate yearlyTitle =
case yearlyTitle =~~ "(19[0-9][0-9]|20[0-9][0-9])" :: Maybe [[String]] of
Just [[_, year]] -> year
@ -45,7 +45,7 @@ main = do
let start3 = "https://etyka.uw.edu.pl/index.php/etyka/issue/archive/3"
let shadowLibrary = ShadowLibrary {logoUrl=Nothing,
lname="Tom",
abbrev="AlmMusz",
abbrev="Etyka",
lLevel=0,
webpage=start}
extractItemsStartingFromUrl shadowLibrary start (extractRecords >>> arr toShadowItem)