java网络爬虫

import java.io.*;
import java.net.*;
import java.util.regex.*;
public class Calculator {
static String SendGet(String url) {

String result = “”;

BufferedReader in = null;
try {

URL realUrl = new URL(url);

URLConnection connection = realUrl.openConnection();

connection.connect();

in = new BufferedReader(new InputStreamReader(
connection.getInputStream(),”UTF-8”));

String line;
while ((line = in.readLine()) != null) {

result += line;

}
} catch (Exception e) {
System.out.println(“exception!” + e);
e.printStackTrace();
}

finally {
try {
if (in != null) {
in.close();
}
} catch (Exception e2) {
e2.printStackTrace();
}
}
return result;
}
static String RegexString(String targetStr, String patternStr) {

Pattern pattern = Pattern.compile(patternStr);

Matcher matcher = pattern.matcher(targetStr);

if (matcher.find()) {

return matcher.group(1);
}
return “Nothing”;
}
public static void main(String[] args) {

String url = “http://www.zhihu.com/explore/recommendations“;

String result = SendGet(url);

String imgSrc = RegexString(result, “question_link.+?>(.+?)<”);

System.out.println(imgSrc);
}
}

http://www.jb51.net/article/57197.htm