| java.lang.Object bplatt.spider.Arachnid
Arachnid | abstract public class Arachnid (Code) | | |
getBaseUrl | public URL getBaseUrl()(Code) | | Return base URL (starting point for Web traversal)
|
getContent | public byte[] getContent(URL url)(Code) | | Get contents of a URL
|
getDelay | public int getDelay()(Code) | | Returns delay (N second pause after processing EACH web page)
int |
handleBadIO | abstract protected void handleBadIO(URL url, URL parent)(Code) | | (Abstract) Handle an I/O Exception (server problem)
|
handleBadLink | abstract protected void handleBadLink(URL url, URL parent, PageInfo p)(Code) | | (Abstract) Handle bad URL
|
handleExternalLink | abstract protected void handleExternalLink(URL url, URL parent)(Code) | | (Abstract) Handle an external (outside of Web site) link
|
handleLink | abstract protected void handleLink(PageInfo p)(Code) | | (Abstract) Handle a link; a Web page in the site
|
handleNonHTMLlink | abstract protected void handleNonHTMLlink(URL url, URL parent, PageInfo p)(Code) | | (Abstract) Handle a non-HTML link
|
setDelay | public void setDelay(int delay)(Code) | | Sets delay (N second pause after processing EACH web page)
Parameters: delay - The delay to set |
traverse | public void traverse()(Code) | | Traverse Web site
|
|
|