web-dev-qa-db-fra.com

Comment obtenir le code source d'une page Web à partir de Java

Je veux juste récupérer le code source de n'importe quelle page Web à partir de Java. J'ai trouvé beaucoup de solutions jusqu'à présent, mais je n'ai trouvé aucun code qui fonctionne pour tous les liens ci-dessous:

Le principal problème pour moi est que certains codes récupèrent le code source de la page Web, mais qu'il en manque. Par exemple, le code ci-dessous ne fonctionne pas pour le premier lien.

InputStream is = fURL.openStream(); //fURL can be one of the links above
BufferedReader buffer = null;
buffer = new BufferedReader(new InputStreamReader(is, "iso-8859-9"));

int byteRead;
while ((byteRead = buffer.read()) != -1) {
    builder.append((char) byteRead);
}
buffer.close();
System.out.println(builder.toString());
javawebweb-crawlerweb-content
10
brtb

Essayez le code suivant avec une propriété de demande ajoutée:

import Java.io.BufferedReader;
import Java.io.IOException;
import Java.io.InputStream;
import Java.io.InputStreamReader;
import Java.net.URL;
import Java.net.URLConnection;

public class SocketConnection
{
    public static String getURLSource(String url) throws IOException
    {
        URL urlObject = new URL(url);
        URLConnection urlConnection = urlObject.openConnection();
        urlConnection.setRequestProperty("User-Agent", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.95 Safari/537.11");

        return toString(urlConnection.getInputStream());
    }

    private static String toString(InputStream inputStream) throws IOException
    {
        try (BufferedReader bufferedReader = new BufferedReader(new InputStreamReader(inputStream, "UTF-8")))
        {
            String inputLine;
            StringBuilder stringBuilder = new StringBuilder();
            while ((inputLine = bufferedReader.readLine()) != null)
            {
                stringBuilder.append(inputLine);
            }

            return stringBuilder.toString();
        }
    }
}
25
narek.gevorgyan

Je suis sûr que vous avez trouvé une solution quelque part au cours des 2 dernières années, mais ce qui suit est une solution qui fonctionne pour votre site demandé

package javasandbox;

import Java.io.BufferedReader;
import Java.io.IOException;
import Java.io.InputStreamReader;
import Java.net.HttpURLConnection;
import Java.net.MalformedURLException;
import Java.net.URL;

/**
*
* @author Ryan.Oglesby
*/
public class JavaSandbox {

private static String sURL;

/**
 * @param args the command line arguments
 */
public static void main(String[] args) throws MalformedURLException, IOException {
    sURL = "http://www.cumhuriyet.com.tr/?hn=298710";
    System.out.println(sURL);
    URL url = new URL(sURL);
    HttpURLConnection httpCon = (HttpURLConnection) url.openConnection();
    //set http request headers
            httpCon.addRequestProperty("Host", "www.cumhuriyet.com.tr");
            httpCon.addRequestProperty("Connection", "keep-alive");
            httpCon.addRequestProperty("Cache-Control", "max-age=0");
            httpCon.addRequestProperty("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8");
            httpCon.addRequestProperty("User-Agent", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36");
            httpCon.addRequestProperty("Accept-Encoding", "gzip,deflate,sdch");
            httpCon.addRequestProperty("Accept-Language", "en-US,en;q=0.8");
            //httpCon.addRequestProperty("Cookie", "JSESSIONID=EC0F373FCC023CD3B8B9C1E2E2F7606C; lang=tr; __utma=169322547.1217782332.1386173665.1386173665.1386173665.1; __utmb=169322547.1.10.1386173665; __utmc=169322547; __utmz=169322547.1386173665.1.1.utmcsr=stackoverflow.com|utmccn=(referral)|utmcmd=referral|utmcct=/questions/8616781/how-to-get-a-web-pages-source-code-from-Java; __gads=ID=3ab4e50d8713e391:T=1386173664:S=ALNI_Mb8N_wW0xS_wRa68vhR0gTRl8MwFA; scrElm=body");
            HttpURLConnection.setFollowRedirects(false);
            httpCon.setInstanceFollowRedirects(false);
            httpCon.setDoOutput(true);
            httpCon.setUseCaches(true);

            httpCon.setRequestMethod("GET");

            BufferedReader in = new BufferedReader(new InputStreamReader(httpCon.getInputStream(), "UTF-8"));
            String inputLine;
            StringBuilder a = new StringBuilder();
            while ((inputLine = in.readLine()) != null)
                a.append(inputLine);
            in.close();

            System.out.println(a.toString());

            httpCon.disconnect();
}
}
3
Roglesby
URL yahoo = new URL("http://www.yahoo.com/");
BufferedReader in = new BufferedReader(
            new InputStreamReader(
            yahoo.openStream()));

String inputLine;

while ((inputLine = in.readLine()) != null)
    System.out.println(inputLine);

in.close();
1
subodh