public abstract class Crawler extends Object
Modifier and Type | Field and Description |
---|---|
protected FileFilter |
directoryFilter
A directory filter.
|
protected org.apache.commons.io.filefilter.IOFileFilter |
fileFilter
A file filter.
|
protected ArrayList<Target> |
ignoreList |
Constructor and Description |
---|
Crawler() |
Crawler(org.apache.commons.io.filefilter.IOFileFilter fileFilter) |
Modifier and Type | Method and Description |
---|---|
void |
addAllIgnoreItems(ArrayList<Target> ignoreList) |
List<Target> |
crawl(URL url) |
List<Target> |
crawl(URL url,
boolean getDirectories) |
abstract List<Target> |
crawl(URL url,
boolean getDirectories,
org.apache.commons.io.filefilter.IOFileFilter fileFilter) |
List<Target> |
crawl(URL url,
org.apache.commons.io.filefilter.IOFileFilter fileFilter) |
List<Target> |
crawl(URL url,
String[] extensions,
boolean getDirectories,
String nameToken) |
void |
setFileFilter(org.apache.commons.io.filefilter.IOFileFilter fileFilter) |
void |
setFileFilter(List<String> fileFilters) |
protected org.apache.commons.io.filefilter.IOFileFilter fileFilter
protected FileFilter directoryFilter
public Crawler()
public Crawler(org.apache.commons.io.filefilter.IOFileFilter fileFilter)
public void setFileFilter(org.apache.commons.io.filefilter.IOFileFilter fileFilter)
public List<Target> crawl(URL url) throws IOException
IOException
public List<Target> crawl(URL url, org.apache.commons.io.filefilter.IOFileFilter fileFilter) throws IOException
IOException
public List<Target> crawl(URL url, boolean getDirectories) throws IOException
IOException
public List<Target> crawl(URL url, String[] extensions, boolean getDirectories, String nameToken) throws IOException
IOException
public abstract List<Target> crawl(URL url, boolean getDirectories, org.apache.commons.io.filefilter.IOFileFilter fileFilter) throws IOException
IOException
Copyright © 2023 Jet Propulsion Laboratory, California Institute of Technology. All rights reserved.