java - 从java中的网页读取源代码

Answer 1

It works for me.

private static String getWebPabeSource(String sURL) throws IOException {
        URL url = new URL(sURL);
        URLConnection urlCon = url.openConnection();
        BufferedReader in = null;

        if (urlCon.getHeaderField("Content-Encoding") != null
                && urlCon.getHeaderField("Content-Encoding").equals("gzip")) {
            in = new BufferedReader(new InputStreamReader(new GZIPInputStream(
                    urlCon.getInputStream())));
        } else {
            in = new BufferedReader(new InputStreamReader(
                    urlCon.getInputStream()));
        }

        String inputLine;
        StringBuilder sb = new StringBuilder();

        while ((inputLine = in.readLine()) != null)
            sb.append(inputLine);
        in.close();

        return sb.toString();
}

Answer 2

Try reading it this way:

private static String getUrlSource(String url) throws IOException {
        URL url = new URL(url);
        URLConnection urlConn = url.openConnection();
        BufferedReader in = new BufferedReader(new InputStreamReader(
                urlConn.getInputStream(), "UTF-8"));
        String inputLine;
        StringBuilder a = new StringBuilder();
        while ((inputLine = in.readLine()) != null)
            a.append(inputLine);
        in.close();

        return a.toString();
    }

and set your encoding according to the web page - notice this line:

BufferedReader in = new BufferedReader(new InputStreamReader(
                urlConn.getInputStream(), "UTF-8"));

Answer 3

First you have to uncompress the content using GZIPInputStream. Then put the uncompressed stream to Input Stream and read it using BufferedReader

Use Apache HTTP Client 4.1.1

Maven dependency

<dependency>
    <groupId>org.apache.httpcomponents</groupId>
    <artifactId>httpclient</artifactId>
    <version>4.1.1</version>
</dependency>   

Sample Code to parse gzip content.

package com.gzip.simple;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.util.zip.GZIPInputStream;

import org.apache.http.Header;
import org.apache.http.HttpResponse;
import org.apache.http.client.ClientProtocolException;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.DefaultHttpClient;

public class GZIPFetcher {
    public static void main(String[] args) {
        try {

            DefaultHttpClient httpClient = new DefaultHttpClient();
            HttpGet getRequest = new HttpGet("http://excite.com/education");
            getRequest.addHeader("accept", "application/json");

            HttpResponse response = httpClient.execute(getRequest);

            if (response.getStatusLine().getStatusCode() != 200) {
                throw new RuntimeException("Failed : HTTP error code : "
                        + response.getStatusLine().getStatusCode());
            }

            InputStream instream = response.getEntity().getContent();

            // Check whether the content-encoding is gzip or not.
            Header contentEncoding = response
                    .getFirstHeader("Content-Encoding");

            if (contentEncoding != null
                    && contentEncoding.getValue().equalsIgnoreCase("gzip")) {
                instream = new GZIPInputStream(instream);
            }

            BufferedReader in = new BufferedReader(new InputStreamReader(
                    instream));

            String content;
            System.out.println("Output from Server .... \n");
            while ((content = in.readLine()) != null)
                System.out.println(content);

            httpClient.getConnectionManager().shutdown();

        } catch (ClientProtocolException e) {

            e.printStackTrace();

        } catch (IOException e) {

            e.printStackTrace();
        }

    }
}