diff --git a/app/ZborBielawa.hs b/app/ZborBielawa.hs index b374db6..3916085 100644 --- a/app/ZborBielawa.hs +++ b/app/ZborBielawa.hs @@ -12,16 +12,6 @@ import Text.Regex.Posix import Text.Printf import Debug.Trace -extractNestedLinksWithText xpathCondition = (downloadDocument &&& this) - >>> first (getXPathTrees xpathCondition - >>> ( - (getXPathTrees "//a" >>> getAttrValue "href") - &&& (listA (deep isText >>> getText) - >>> arr (intercalate " ")) - )) - >>> arr rotateSecTh -- ((a, b), c) -> ((a, c), b) - >>> first expandURIFixed - getLinkAndText xpathCondition = proc doc -> do xpathTrees <- getXPathTrees xpathCondition -< doc @@ -30,20 +20,14 @@ getLinkAndText xpathCondition = proc doc -> do returnA -< traceShowId (href, txt) -extractNestedLinksWithText2 xpathCondition = proc url -> do +extractNestedLinksWithText xpathCondition = proc url -> do doc <- downloadDocument -< url (link, text) <- getLinkAndText xpathCondition -< doc uriFixed <- expandURIFixed -< (link, url) returnA -< (uriFixed, text) -extractRecords = extractLinksWithText "(//aside[@class='widget widget_maxmegamenu']//a[@class='mega-menu-link'])[1]" -- pary adres-tytuł podstrony - >>> first (extractLinksWithText "(//aside[@class='widget widget_maxmegamenu']//a[@class='mega-menu-link'])[1]") -- pobieramy podstronę i kolejne podstrony z menu - >>> first (first (extractNestedLinksWithText "//big/a[contains(@href,'.pdf')][img]")) -- pobieramy stronę z adresu URL i wyciągamy linki z tej strony pasujące do wyrażenia XPathowego - -- ostatecznie wyjdą krotki (((adres URL, tytuł nr-u), tytuł podstrony 2), tytuł podstrony 1) - - -extractRecords2 = proc x -> do +extractRecords = proc x -> do (a, b) <- extractLinksWithText "(//aside[@class='widget widget_maxmegamenu']//a[@class='mega-menu-link'])[1]" -< x -- pary adres-tytuł podstrony (a', b') <- (extractLinksWithText "(//aside[@class='widget widget_maxmegamenu']//a[@class='mega-menu-link'])[1]") -< a -- pobieramy podstronę i kolejne podstrony z menu a'' <- (extractNestedLinksWithText "//big/a[contains(@href,'.pdf')][img]") -< a' -- pobieramy stronę z adresu URL i wyciągamy linki z tej strony pasujące do wyrażenia XPathowego @@ -77,4 +61,4 @@ main = do abbrev="ZboBiel", lLevel=0, webpage=start} - extractItemsStartingFromUrl shadowLibrary start (extractRecords2 >>> arr toShadowItem) + extractItemsStartingFromUrl shadowLibrary start (extractRecords >>> arr toShadowItem)