Package com.cloudburo.grab.webcontent

Class Grabber

java.lang.Object

com.cloudburo.grab.webcontent.Grabber

public class Grabber
extends java.lang.Object

Constructor Summary

Constructors

Constructor	Description
Grabber()

Method Summary

Modifier and Type	Method	Description
GrabberRecord	extractArticle(java.lang.String inurl, boolean textOnly)
java.lang.String	extractCanloa(java.lang.String inurl)
java.lang.String	extractDefault(java.lang.String inurl)
java.lang.String	extractLargestContent(java.lang.String inurl)

Methods inherited from class java.lang.Object

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

Constructor Detail

Grabber

public Grabber()

Method Detail

extractArticle

public GrabberRecord extractArticle(java.lang.String inurl,
                                    boolean textOnly)
                             throws java.io.IOException,
                                    BoilerpipeProcessingException,
                                    org.xml.sax.SAXException

Throws:

java.io.IOException

BoilerpipeProcessingException

org.xml.sax.SAXException

extractDefault

public java.lang.String extractDefault(java.lang.String inurl)
                                throws java.io.IOException,
                                       BoilerpipeProcessingException,
                                       org.xml.sax.SAXException

Throws:

java.io.IOException

BoilerpipeProcessingException

org.xml.sax.SAXException

extractCanloa

public java.lang.String extractCanloa(java.lang.String inurl)
                               throws java.io.IOException,
                                      BoilerpipeProcessingException,
                                      org.xml.sax.SAXException

Throws:

java.io.IOException

BoilerpipeProcessingException

org.xml.sax.SAXException

extractLargestContent

public java.lang.String extractLargestContent(java.lang.String inurl)
                                       throws java.io.IOException,
                                              BoilerpipeProcessingException,
                                              org.xml.sax.SAXException

Throws:

java.io.IOException

BoilerpipeProcessingException

org.xml.sax.SAXException