使用Jsoup开发简易网页爬虫程序

Java基础

mavan：

<dependency>
  <groupId>org.jsoup</groupId>
  <artifactId>jsoup</artifactId>
  <version>1.8.1</version>
</dependency>

URL url = new URL("https://www.zybuluo.com/ruoli/note/483730");
Document document=HTTPCommonUtil.getHttpsDocument(url, 5000);
String content=document.select("div#editor-reader-full").toString();

HTTPCommonUtil.java

package tools;
import java.net.MalformedURLException;
import java.net.URL;
import java.security.SecureRandom;
import java.security.cert.CertificateException;
import java.security.cert.X509Certificate;
import java.util.Map;
import javax.net.ssl.HostnameVerifier;
import javax.net.ssl.HttpsURLConnection;
import javax.net.ssl.SSLContext;
import javax.net.ssl.SSLSession;
import javax.net.ssl.X509TrustManager;
import org.jsoup.Connection;
import org.jsoup.helper.HttpConnection;
import org.jsoup.nodes.Document;
public class HTTPCommonUtil {
    public static void trustEveryone() {
        try {
            HttpsURLConnection.setDefaultHostnameVerifier(new HostnameVerifier() {
                public boolean verify(String hostname, SSLSession session) {
                    return true;
                }
            });
            SSLContext context = SSLContext.getInstance("TLS");
            context.init(null, new X509TrustManager[] { new X509TrustManager() {
                public void checkClientTrusted(X509Certificate[] chain, String authType) throws CertificateException {
                }
                public void checkServerTrusted(X509Certificate[] chain, String authType) throws CertificateException {
                }
                public X509Certificate[] getAcceptedIssuers() {
                    return new X509Certificate[0];
                }
            } }, new SecureRandom());
            HttpsURLConnection.setDefaultSSLSocketFactory(context.getSocketFactory());
        } catch (Exception e) {
            // e.printStackTrace();
        }
    }
    public static Object getHttpHeaders(URL url, int timeout) {
        try {
            trustEveryone();
            Connection conn = HttpConnection.connect(url);
            conn.timeout(timeout);
            conn.header("Accept-Encoding", "gzip,deflate,sdch");
            conn.header("Connection", "close");
            conn.get();
            Map<String, String> result = conn.response().headers();
            result.put("title", conn.response().parse().title());
            return result;
        } catch (Exception e) {
            //e.printStackTrace();
        }
        return null;
    }
    public static Document getHttpsDocument(URL url, int timeout){
        try {
            trustEveryone();
            Connection conn = HttpConnection.connect(url);
            conn.timeout(timeout);
            conn.header("Accept-Encoding", "gzip,deflate,sdch");
            conn.header("Connection", "close");
            Document document=conn.get();
            return document;
        } catch (Exception e) {
            e.printStackTrace();
        }
        return null;
    }
    public static void main(String[] args) {
        try {
            URL url = new URL("https://www.zybuluo.com/ruoli/note/483730");
            Document document=HTTPCommonUtil.getHttpsDocument(url, 5000);
            String title = document.title();
            System.out.println(document.toString());
        } catch (MalformedURLException e) {
            e.printStackTrace();
        }
    }
}