Compare commits
6 Commits
Author | SHA1 | Date | |
---|---|---|---|
|
8d86f78924 | ||
|
5272c99c3a | ||
|
3e9ad1fa0b | ||
|
a7bf508ff4 | ||
3b8318d752 | |||
107793cbf1 |
@ -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,
|
||||
|
63
app/ptd.hs
Normal file
63
app/ptd.hs
Normal file
@ -0,0 +1,63 @@
|
||||
|
||||
{-# 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
|
||||
|
||||
extractNestedLinksWithText xpathCondition = (downloadDocument &&& this)
|
||||
>>> first (getXPathTrees xpathCondition
|
||||
>>> ((getXPathTrees "//a" >>> getAttrValue "href")
|
||||
&&& (listA (deep isText >>> getText)
|
||||
>>> arr (intercalate " "))))
|
||||
>>> arr rotateSecTh
|
||||
>>> first expandURIFixed
|
||||
|
||||
extractRecords = extractLinksWithText "//div[@class='entry-content']/p/a[contains(@href, 'id')]"
|
||||
>>> first (arr $ replace "http:" "https:")
|
||||
>>> first (extractNestedLinksWithText "//div[@class='entry-content']/p[strong[a]] | //div[@class='entry-content']/p[a]")
|
||||
|
||||
toShadowItem :: ((String, String), String) -> ShadowItem
|
||||
toShadowItem ((url, articleTitle), magazineTitle) =
|
||||
(defaultShadowItem url title) {
|
||||
originalDate = date,
|
||||
itype = "periodical",
|
||||
format = Just "pdf",
|
||||
finalUrl = url
|
||||
}
|
||||
where title = magazineTitle ++ " - " ++ (replace " \8211 pdf" "" articleTitle)
|
||||
date = getYear url
|
||||
|
||||
getYear :: String -> Maybe String
|
||||
getYear url =
|
||||
case url =~~ "/(rocznik[0-9][0-9])/" :: Maybe [[String]] of
|
||||
Just [[_, raw_year]] -> Just (catalogueMapper (replace "rocznik" "" raw_year))
|
||||
otherwise -> case url =~~ "/(19[0-9][0-9]|20[0-9][0-9])/" :: Maybe [[String]] of
|
||||
Just [[_, year]] -> (Just year)
|
||||
otherwise -> Nothing
|
||||
|
||||
-- Rozwiązanie także zadziała
|
||||
-- catalogueMapper :: String -> String
|
||||
-- catalogueMapper number = show((read number :: Integer) + 1952)
|
||||
|
||||
catalogueMapper :: String -> String
|
||||
catalogueMapper number
|
||||
| number == "67" = "2019"
|
||||
| number == "66" = "2018"
|
||||
| number == "65" = "2017"
|
||||
| number == "64" = "2016"
|
||||
|
||||
main = do
|
||||
let baseUrl = "https://www.ptd.pl/?page_id=7"
|
||||
let shadowLibrary = ShadowLibrary {logoUrl=Nothing,
|
||||
lname="Polskie Towarzystwo Dendrologiczne",
|
||||
abbrev="ptd",
|
||||
lLevel=0,
|
||||
webpage=baseUrl}
|
||||
extractItemsStartingFromUrl shadowLibrary baseUrl (extractRecords >>> arr toShadowItem)
|
19
readme.md
Normal file
19
readme.md
Normal file
@ -0,0 +1,19 @@
|
||||
# PTD - Polskie Towarzystwo Dendrologiczne
|
||||
|
||||
## Wywołanie programu
|
||||
```bash
|
||||
stack build
|
||||
stack exec ptd
|
||||
```
|
||||
|
||||
## Przykładowa krotka wynikowa:
|
||||
Tytuł w postaci Wydawnictwo - Tytuł
|
||||
```
|
||||
ShadowItem {url = Just "http://www.ptd.pl/ptd/wp-content/download/wydawnictwaPTD/rocznik67/12_R_67_Digitalizacja.pdf", title = "Pe\322ne teksty Rocznik\243w PTD, pocz\261wszy od zeszytu 57; \nwersja online \8211 ISSN 2300-8326 - DOMINIK TOMASZEWSKI \nDigitalizacja zbior\243w zielnikowych \8211 krok w dobr\261 stron\281\8211 \nDigitisation of herbarium collections \8211 a step in the right direction \8211 \160pdf", itype = "periodical", originalDate = Just "2019", creator = Nothing, format = Just "pdf", lang = Just "pol", finalUrl = "http://www.ptd.pl/ptd/wp-content/download/wydawnictwaPTD/rocznik67/12_R_67_Digitalizacja.pdf", description = Nothing}
|
||||
```
|
||||
W przypadku braku roku zwrócone zostanie ```Nothing```
|
||||
|
||||
## Dodatkowe paczki zainstalowane na potrzebę uruchomienia programu:
|
||||
```bash
|
||||
apt-get install libcurl4-gnutls-dev
|
||||
```
|
@ -20,6 +20,7 @@ library
|
||||
, HTTP
|
||||
, hxt
|
||||
, hxt-http
|
||||
, hxt-curl
|
||||
, hxt-xpath
|
||||
, MissingH
|
||||
, monad-logger
|
||||
@ -54,12 +55,26 @@ executable almanachmuszyny
|
||||
build-depends: base
|
||||
, hxt
|
||||
, hxt-xpath
|
||||
, hxt-curl
|
||||
, MissingH
|
||||
, regex-posix
|
||||
, shadow-library
|
||||
default-language: Haskell2010
|
||||
|
||||
|
||||
executable ptd
|
||||
hs-source-dirs: app
|
||||
main-is: ptd.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
|
||||
|
Loading…
Reference in New Issue
Block a user