Compare commits

..

1 Commits

Author SHA1 Message Date
107793cbf1 Change to Curl 2019-03-17 21:52:13 +01:00
3 changed files with 14 additions and 15 deletions

View File

@ -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,

View File

@ -4,21 +4,18 @@ import ShadowLibrary.Core
import Text.XML.HXT.Core import Text.XML.HXT.Core
import Text.XML.HXT.XPath import Text.XML.HXT.XPath
-- import Text.XML.HXT.Curl --import Text.XML.HXT.Curl
import Data.List import Data.List
import Data.List.Utils (replace) 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) {

View File

@ -20,6 +20,7 @@ library
, HTTP , HTTP
, hxt , hxt
, hxt-http , hxt-http
, hxt-curl
, hxt-xpath , hxt-xpath
, MissingH , MissingH
, monad-logger , monad-logger
@ -54,6 +55,7 @@ executable almanachmuszyny
build-depends: base build-depends: base
, hxt , hxt
, hxt-xpath , hxt-xpath
, hxt-curl
, MissingH , MissingH
, regex-posix , regex-posix
, shadow-library , shadow-library