de.l3s.icrawl.util

Class WebPageUtils

java.lang.Object

de.l3s.icrawl.util.WebPageUtils

public final class WebPageUtils
extends Object

Method Summary

Modifier and Type	Method and Description
static org.jsoup.nodes.Element	containingElement(org.jsoup.nodes.Node n)
static String	extractTextFromJavascript(org.jsoup.nodes.Document dom)
static org.jsoup.nodes.Element	findParagraphParent(org.jsoup.nodes.Element startElement)
static org.jsoup.nodes.Element	findParagraphParent(org.jsoup.nodes.Element startNode, int minParagraphTokens)
static org.jsoup.nodes.Element	findParagraphParent(org.jsoup.nodes.Node node, int minParagraphTokens)
static boolean	hasHtmlContent(String content)
static org.jsoup.nodes.Document	parseHtml(InputStream is, String url)
static org.jsoup.nodes.Document	parseHtml(String content, String url)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Method Detail

findParagraphParent

public static org.jsoup.nodes.Element findParagraphParent(org.jsoup.nodes.Element startNode,
                                                          int minParagraphTokens)

containingElement

public static org.jsoup.nodes.Element containingElement(org.jsoup.nodes.Node n)

findParagraphParent

public static org.jsoup.nodes.Element findParagraphParent(org.jsoup.nodes.Element startElement)

findParagraphParent

public static org.jsoup.nodes.Element findParagraphParent(org.jsoup.nodes.Node node,
                                                          int minParagraphTokens)

extractTextFromJavascript

public static String extractTextFromJavascript(org.jsoup.nodes.Document dom)

parseHtml

public static org.jsoup.nodes.Document parseHtml(InputStream is,
                                                 String url)

parseHtml

public static org.jsoup.nodes.Document parseHtml(String content,
                                                 String url)

hasHtmlContent

public static boolean hasHtmlContent(String content)