forked from filipg/twilight-library
Compare commits
1 Commits
Author | SHA1 | Date | |
---|---|---|---|
8883a924b4 |
@ -33,7 +33,7 @@ import Data.Tree.NTree.TypeDefs
|
|||||||
import Data.Maybe
|
import Data.Maybe
|
||||||
import Control.Monad.Trans
|
import Control.Monad.Trans
|
||||||
import Text.XML.HXT.XPath
|
import Text.XML.HXT.XPath
|
||||||
import Text.XML.HXT.Curl
|
-- import Text.XML.HXT.Curl
|
||||||
import Text.XML.HXT.HTTP
|
import Text.XML.HXT.HTTP
|
||||||
|
|
||||||
import Text.Regex.TDFA
|
import Text.Regex.TDFA
|
||||||
@ -64,8 +64,8 @@ downloadDocument = readFromDocument [withParseHTML yes,
|
|||||||
withEncodingErrors no,
|
withEncodingErrors no,
|
||||||
withPreserveComment yes,
|
withPreserveComment yes,
|
||||||
withStrictInput yes,
|
withStrictInput yes,
|
||||||
-- withHTTP []
|
withHTTP []
|
||||||
withCurl [("curl--user-agent","AMU Digital Libraries Indexing Agent")]
|
-- withCurl [("curl--user-agent","AMU Digital Libraries Indexing Agent")]
|
||||||
]
|
]
|
||||||
|
|
||||||
downloadDocumentWithEncoding enc = readFromDocument [withParseHTML yes,
|
downloadDocumentWithEncoding enc = readFromDocument [withParseHTML yes,
|
||||||
@ -73,13 +73,13 @@ downloadDocumentWithEncoding enc = readFromDocument [withParseHTML yes,
|
|||||||
withEncodingErrors no,
|
withEncodingErrors no,
|
||||||
withPreserveComment yes,
|
withPreserveComment yes,
|
||||||
withInputEncoding enc,
|
withInputEncoding enc,
|
||||||
-- withHTTP []]
|
withHTTP []]
|
||||||
withCurl []]
|
-- withCurl []]
|
||||||
|
|
||||||
downloadXmlDocument = readFromDocument [withWarnings no,
|
downloadXmlDocument = readFromDocument [withWarnings no,
|
||||||
withEncodingErrors no,
|
withEncodingErrors no,
|
||||||
-- withHTTP []]
|
withHTTP []]
|
||||||
withCurl [] ]
|
-- withCurl [] ]
|
||||||
|
|
||||||
|
|
||||||
data ShadowLibrary = ShadowLibrary { logoUrl :: Maybe String,
|
data ShadowLibrary = ShadowLibrary { logoUrl :: Maybe String,
|
||||||
|
@ -11,11 +11,14 @@ import Data.List.Utils (replace)
|
|||||||
import Text.Regex.Posix
|
import Text.Regex.Posix
|
||||||
import Text.Printf
|
import Text.Printf
|
||||||
|
|
||||||
extractRecords = extractLinksWithText "//a[@class='roczniki']"
|
|
||||||
>>> second (arr $ replace "\r\n " "")
|
|
||||||
>>> first (arr ((++"tr") . init))
|
|
||||||
>>> first (extractLinksWithText "//li/a[contains(@href,'.pdf')]")
|
|
||||||
|
|
||||||
|
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
|
||||||
|
-- ostatecznie wyjdą trójki ((adres URL, tytuł artykułu), tytuł rocznika)
|
||||||
|
|
||||||
|
-- ... a tutaj te trójki przerabiamy do docelowej struktury ShadowItem
|
||||||
toShadowItem :: ((String, String), String) -> ShadowItem
|
toShadowItem :: ((String, String), String) -> ShadowItem
|
||||||
toShadowItem ((url, articleTitle), yearlyTitle) =
|
toShadowItem ((url, articleTitle), yearlyTitle) =
|
||||||
(defaultShadowItem url title) {
|
(defaultShadowItem url title) {
|
||||||
@ -28,7 +31,7 @@ toShadowItem ((url, articleTitle), yearlyTitle) =
|
|||||||
date = getDate url
|
date = getDate url
|
||||||
|
|
||||||
getDate url =
|
getDate url =
|
||||||
case url =~~ "/(20[0-9][0-9])/" :: Maybe [[String]] of
|
case url =~~ "/(19[0-9][0-9]|20[0-9][0-9])/" :: Maybe [[String]] of
|
||||||
Just [[_, year]] -> year
|
Just [[_, year]] -> year
|
||||||
otherwise -> error $ "unexpected url: " ++ url
|
otherwise -> error $ "unexpected url: " ++ url
|
||||||
|
|
||||||
|
@ -1,37 +0,0 @@
|
|||||||
{-# LANGUAGE Arrows, NoMonomorphismRestriction #-}
|
|
||||||
import ShadowLibrary.Core
|
|
||||||
|
|
||||||
import Text.XML.HXT.Core
|
|
||||||
import Text.XML.HXT.XPath
|
|
||||||
-- import Text.XML.HXT.Curl
|
|
||||||
import Data.List
|
|
||||||
import Data.List.Utils (replace)
|
|
||||||
|
|
||||||
import Text.Regex.Posix
|
|
||||||
import Text.Printf
|
|
||||||
|
|
||||||
extractRecords = extractLinksWithText "//td/a[contains(@href,'.pdf')]"
|
|
||||||
|
|
||||||
toShadowItem :: (String, String) -> ShadowItem
|
|
||||||
toShadowItem (url, monthlytitle) =
|
|
||||||
(defaultShadowItem url title) {
|
|
||||||
originalDate = Just date,
|
|
||||||
itype = "periodical",
|
|
||||||
format = Just "pdf",
|
|
||||||
finalUrl = url
|
|
||||||
}
|
|
||||||
where title = "IP" ++ date ++ " " ++ (replace "\r" "" (replace "\n" "" (replace "\t" "" monthlytitle)))
|
|
||||||
date = getDate $ replace "%20" " " url
|
|
||||||
|
|
||||||
getDate :: String -> String
|
|
||||||
getDate url = date where
|
|
||||||
date = url Text.Regex.Posix.=~ "(202[0-2]|20[0-1][0-9])" :: String
|
|
||||||
|
|
||||||
main = do
|
|
||||||
let start = "https://www.pip.gov.pl/pl/inspektor-pracy/66546,archiwum-inspektora-pracy-.html"
|
|
||||||
let shadowLibrary = ShadowLibrary {logoUrl=Nothing,
|
|
||||||
lname="Inspektor Pracy",
|
|
||||||
abbrev="InspPrac",
|
|
||||||
lLevel=0,
|
|
||||||
webpage=start}
|
|
||||||
extractItemsStartingFromUrl shadowLibrary start (extractRecords >>> arr toShadowItem)
|
|
@ -20,7 +20,6 @@ library
|
|||||||
, HTTP
|
, HTTP
|
||||||
, hxt
|
, hxt
|
||||||
, hxt-http
|
, hxt-http
|
||||||
, hxt-curl
|
|
||||||
, hxt-xpath
|
, hxt-xpath
|
||||||
, MissingH
|
, MissingH
|
||||||
, monad-logger
|
, monad-logger
|
||||||
@ -52,19 +51,6 @@ executable almanachmuszyny
|
|||||||
hs-source-dirs: app
|
hs-source-dirs: app
|
||||||
main-is: almanachmuszyny.hs
|
main-is: almanachmuszyny.hs
|
||||||
ghc-options: -threaded -rtsopts -with-rtsopts=-N
|
ghc-options: -threaded -rtsopts -with-rtsopts=-N
|
||||||
build-depends: base
|
|
||||||
, hxt
|
|
||||||
, hxt-xpath
|
|
||||||
, hxt-curl
|
|
||||||
, MissingH
|
|
||||||
, regex-posix
|
|
||||||
, shadow-library
|
|
||||||
default-language: Haskell2010
|
|
||||||
|
|
||||||
executable inspektoratpracy
|
|
||||||
hs-source-dirs: app
|
|
||||||
main-is: inspektoratpracy.hs
|
|
||||||
ghc-options: -threaded -rtsopts -with-rtsopts=-N
|
|
||||||
build-depends: base
|
build-depends: base
|
||||||
, hxt
|
, hxt
|
||||||
, hxt-xpath
|
, hxt-xpath
|
||||||
|
@ -1,19 +0,0 @@
|
|||||||
# 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
|
|
Loading…
Reference in New Issue
Block a user