-
public class RegexHyperlinkExtractor
-
-
Field Summary
Fields Modifier and Type Field Description private final WebPagepageprivate final FeaturedDocumentdocumentprivate final StringrestrictCssprivate final StringurlPattern
-
Constructor Summary
Constructors Constructor Description RegexHyperlinkExtractor(PulsarSession session, WebPage page, String restrictCss, String urlPattern)RegexHyperlinkExtractor(WebPage page, FeaturedDocument document, String restrictCss, String urlPattern)
-
Method Summary
Modifier and Type Method Description final WebPagegetPage()final FeaturedDocumentgetDocument()final StringgetRestrictCss()final StringgetUrlPattern()final Collection<Hyperlink>extract()final Collection<Hyperlink>extractTo(Collection<Hyperlink> fetchUrls)-
-
Constructor Detail
-
RegexHyperlinkExtractor
RegexHyperlinkExtractor(PulsarSession session, WebPage page, String restrictCss, String urlPattern)
-
-
Method Detail
-
getPage
final WebPage getPage()
-
getDocument
final FeaturedDocument getDocument()
-
getRestrictCss
final String getRestrictCss()
-
getUrlPattern
final String getUrlPattern()
-
extract
final Collection<Hyperlink> extract()
-
extractTo
final Collection<Hyperlink> extractTo(Collection<Hyperlink> fetchUrls)
-
-
-
-