자바 웹 페이지 데 이 터 를 캡 처 하여 웹 페이지 의 모든 링크 인 스 턴 스 공 유 를 가 져 옵 니 다.
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
public class HtmlParser {
/**
*
*/
String htmlUrl;
/**
*
*/
ArrayList<String> hrefList = new ArrayList();
/**
*
*/
String charSet;
public HtmlParser(String htmlUrl) {
// TODO
this.htmlUrl = htmlUrl;
}
/**
*
*
* @throws IOException
*/
public ArrayList<String> getHrefList() throws IOException {
parser();
return hrefList;
}
/**
*
*
* @return
* @throws IOException
*/
private void parser() throws IOException {
URL url = new URL(htmlUrl);
HttpURLConnection connection = (HttpURLConnection) url.openConnection();
connection.setDoOutput(true);
String contenttype = connection.getContentType();
charSet = getCharset(contenttype);
InputStreamReader isr = new InputStreamReader(
connection.getInputStream(), charSet);
BufferedReader br = new BufferedReader(isr);
String str = null, rs = null;
while ((str = br.readLine()) != null) {
rs = getHref(str);
if (rs != null)
hrefList.add(rs);
}
}
/**
*
*
* @param str
*/
private String getCharset(String str) {
Pattern pattern = Pattern.compile("charset=.*");
Matcher matcher = pattern.matcher(str);
if (matcher.find())
return matcher.group(0).split("charset=")[1];
return null;
}
/**
*
*
* @return
*/
private String getHref(String str) {
Pattern pattern = Pattern.compile("<a href=.*</a>");
Matcher matcher = pattern.matcher(str);
if (matcher.find())
return matcher.group(0);
return null;
}
public static void main(String[] arg) throws IOException {
HtmlParser a = new HtmlParser("http://news.163.com/");
ArrayList<String> hrefList = a.getHrefList();
for (int i = 0; i < hrefList.size(); i++)
System.out.println(hrefList.get(i));
}
}