Java crawls the web data to get all the link instances Shared in the web page
- 2020-04-01 02:43:28
- OfStack
rendering
< img border = 0 id = theimg onclick = window. The open this. (SRC) SRC = "/ / files.jb51.net/file_images/article/201312/20131231092541.jpg? 2013113192629 ">
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) {
//Constructor stub automatically generated by TODO
this.htmlUrl = htmlUrl;
}
public ArrayList<String> getHrefList() throws IOException {
parser();
return hrefList;
}
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);
}
}
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;
}
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));
}
}