我正在尝试从网页中读取源代码。我的 java 代码是
import java.net.*;
import java.io.*;
import java.util.*;
import javax.swing.JOptionPane;
class Testing{
public static void Connect() throws Exception{
URL url = new URL("http://excite.com/education");
URLConnection spoof = url.openConnection();
spoof.setRequestProperty( "User-Agent", "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0; H010818)" );
BufferedReader in = new BufferedReader(new InputStreamReader(spoof.getInputStream()));
String strLine = "";
while ((strLine = in.readLine()) != null){
System.out.println(strLine);
}
System.out.println("End of page.");
}
public static void main(String[] args){
try{
Connect();
}catch(Exception e){
}
}
当我编译并运行此代码时，它给出了以下输出：
任何人请帮忙。 提前谢谢。I�%&/m�{J�J��t� $ؐ@ iG#( * eVe]f@ 흼 { { ; N' ？\fdl J ɞ！ ？~|？"~ $}> 4 7N + UƳm N ？J tZfM G j R ！ 9 ？>JgE Ge[ ⳏ W ？ 8|8ho 0׳ |փ：-- | L Uο m zt n3 l\ w O^f G[ CGJ�P��_�..?������x�Z�$ E> 느 u E~ {媘 f e1۷ QZ， f e 3Jٻb ^ 4 ۴> y ; n[ �,t�?����~�n�S�u#SL��n�^��������EC��q�/�y���FE�tpm������e&��oB���z9eY��������P��IK?����̦����w�N��;�;J?����;�/��5���M���rZ��q��]��C�dᖣ��F�nd���}���A5���M�5�.�:��/�_D�?�3����'�c�Z7��}��(OI),ۏi����{�<�w�������DZ?e����'q���eY]=���kj���߬������qhrRn���l�o-��.���k��_���oD8��GA�P�r��|$��ȈPv~Y�:�[q?�sH�� <��C��ˬ�^N�[ v(��S��l�c�C����3���E5&5�VӪL�T��۔���oQrĈ��/���#[f�5�5"� [ t vm \ .0 nh aڌWYM^T |\， 퓜 L u B ̌ C r ' % { ( (; fV ] g，> C c2 p 4 }H P ( %j" } & ： Oh\5I l 氪 {/] LB l 2 I" = Y |> ֏n } ~ [ ' O：/( Wz 3 lo .5 k & H[ji b WWy} 5 ֝Q |f ] KjH5 }yNm g ʷ ǣ> 'o 泏
它对我有用。
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();
}
试着这样读：
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();
}
并根据网页设置编码 - 请注意以下行：
BufferedReader in = new BufferedReader(new InputStreamReader(
urlConn.getInputStream(), "UTF-8"));
首先，您必须使用 GZIPInputStream 解压缩内容。然后将未压缩的流放入输入流并使用缓冲阅读器读取它
使用 Apache HTTP Client 4.1.1
Maven dependency
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
<version>4.1.1</version>
</dependency>
用于解析 gzip 内容的示例代码。
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();
}
}
}