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
All Methods Instance Methods Concrete Methods Modifier and Type Method Description GrabberRecordextractArticle(java.lang.String inurl, boolean textOnly)java.lang.StringextractCanloa(java.lang.String inurl)java.lang.StringextractDefault(java.lang.String inurl)java.lang.StringextractLargestContent(java.lang.String inurl)
-
-
-
Method Detail
-
extractArticle
public GrabberRecord extractArticle(java.lang.String inurl, boolean textOnly) throws java.io.IOException, BoilerpipeProcessingException, org.xml.sax.SAXException
- Throws:
java.io.IOExceptionBoilerpipeProcessingExceptionorg.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.IOExceptionBoilerpipeProcessingExceptionorg.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.IOExceptionBoilerpipeProcessingExceptionorg.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.IOExceptionBoilerpipeProcessingExceptionorg.xml.sax.SAXException
-
-