Example of a Java regular expression matching all urls and link text on a web page
- 2020-04-01 03:06:52
- OfStack
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.net.*;
import java.io.*;
import java.util.regex.*;
public class Urls
{
private String startUrl; //Start collecting urls
String urlContent;
String ContentArea;
private String strAreaBegin ,strAreaEnd ; //The collection area begins and ends the collection string
private String stringInUrl,stringNotInUrl;
String strContent;//Acquire the collection content
String[] allUrls; //All urls collected
private String regex; //Acquisition rules
UrlAndTitle urlAndTitle=new UrlAndTitle(); //Store url and title & NBSP;
public static void main(String[] args)
{
Urls myurl=new Urls("<body","/body>");
myurl.getStartUrl("http://www.zuzwn.com/");
myurl.getUrlContent();
myurl.getContentArea();
myurl.getStartUrl("http://www.zuzwn.com/");
myurl.getStringNotInUrl("google");
myurl.Urls();
//System.out.println("startUrl:"+myurl.startUrl);
//System.out.println("urlcontent:"+myurl.urlContent);
//System.out.println("ContentArea:"+myurl.ContentArea);
}
//Initializes the constructors strAreaBegin and strAreaEnd
public Urls (String strAreaBegin,String strAreaEnd)
{
this.strAreaBegin=strAreaBegin;
this.strAreaEnd=strAreaEnd;
}
//
public void Urls()
{
int i=0;
//String regex ="<a href="?'?http://[a-zA-Z0-9]+/.[a-zA-Z0-9]+/.[a-zA-Z]+/?[/.?[/S|/s]]+[a>]$";
String regex ="<a.*?/a>";
//String regex ="http://.*?>";
Pattern pt=Pattern.compile(regex);
Matcher mt=pt.matcher(ContentArea);
while(mt.find())
{
System.out.println(mt.group());
i++;
//Get the title
Matcher title=Pattern.compile(">.*?</a>").matcher(mt.group());
while(title.find())
{
System.out.println(" The title :"+title.group().replaceAll(">|</a>",""));
}
//Access to the website
Matcher myurl=Pattern.compile("href=.*?>").matcher(mt.group());
while(myurl.find())
{
System.out.println(" The url :"+myurl.group().replaceAll("href=|>",""));
}
System.out.println();
}
System.out.println(" A total of "+i+" Individual consistent results ");
}
// To obtain Start collecting urls
public void getStartUrl(String startUrl)
{
this.startUrl=startUrl;
}
//Get the content of the url;
public void getUrlContent()
{
StringBuffer is=new StringBuffer();
try
{
URL myUrl=new URL(startUrl);
BufferedReader br= new BufferedReader(
new InputStreamReader(myUrl.openStream()));
String s;
while((s=br.readLine())!=null)
{
is.append(s);
}
urlContent=is.toString();
}
catch(Exception e)
{
System.out.println(" The url file could not be output ");
e.printStackTrace();
}
}
//Get the matching area section where the url is located
public void getContentArea()
{
int pos1=0,pos2=0;
pos1= urlContent.indexOf(strAreaBegin)+strAreaBegin.length();
pos2=urlContent.indexOf(strAreaEnd,pos1);
ContentArea=urlContent.substring(pos1,pos2);
}
//The following two functions get the keywords that should and should not be included in the url
//This is just a preliminary experiment. Later, there should be more than one keyword protected and not included.
public void getStringInUrl(String stringInUrl)
{
this.stringInUrl=stringInUrl;
}
public void getStringNotInUrl(String stringNotInUrl)
{
this.stringNotInUrl=stringNotInUrl;
}
// To obtain Acquisition rules
//Get the url
public void getUrl()
{
}
public String getRegex()
{
return regex;
}
class UrlAndTitle
{
String myURL;
String title;
}
}