org.apache.manifoldcf.agents.transformation.htmlextractor

Class JsoupProcessing

java.lang.Object

org.apache.manifoldcf.agents.transformation.htmlextractor.JsoupProcessing

public class JsoupProcessing
extends java.lang.Object

Constructor Summary

Constructors

Constructor and Description
JsoupProcessing()

Method Summary

Modifier and Type	Method and Description
static java.util.Hashtable<java.lang.String,java.lang.String>	extractTextAndMetadataHtmlDocument(java.io.InputStream streamDoc, java.lang.String whitelist, java.util.List<java.lang.String> blacklist, boolean stripHtml)

Methods inherited from class java.lang.Object

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

Constructor Detail

JsoupProcessing

public JsoupProcessing()

Method Detail

extractTextAndMetadataHtmlDocument

public static java.util.Hashtable<java.lang.String,java.lang.String> extractTextAndMetadataHtmlDocument(java.io.InputStream streamDoc,
                                                                                                        java.lang.String whitelist,
                                                                                                        java.util.List<java.lang.String> blacklist,
                                                                                                        boolean stripHtml)
                                                                                                 throws java.io.IOException

Throws:

java.io.IOException