问题是---------bufferreader不管如何转化字符集读取,内容显示均为乱码;后来,使用htmlparse解析html的开源代码,发现在读取网页时没有问题 ==== trace code 发现 乱码有可能是压缩网页造成
比如是-----gzip格式的网页;所以采用以下代码读取网页是没有问题
public static void GetFromHtml() throws IOException{
//int ret=0;
String contentEncoding;
HttpURLConnection url=null;
//String htmladdr="http://www.zhcw.com/data-js/nowdata50.js";
String htmladdr="http://www.itpub.net/753054.html";
StringBuffer buffer=new StringBuffer("");
try {
URL url1 = new URL(htmladdr);
url = (HttpURLConnection)url1.openConnection ();
url.setRequestProperty("User-Agent", "mozlla/5.0");
url.setRequestProperty("Accept-Encoding", "gzip, deflate");
url.connect();
contentEncoding=url.getContentEncoding();
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
return ;
}
if(url!=null){
InputStream stream;
if ((null != contentEncoding)
&& (-1 != contentEncoding.indexOf ("gzip"))
{
stream = new GZIPInputStream (
url.getInputStream ());
}
else if ((null != contentEncoding)
&& (-1 != contentEncoding.indexOf ("deflate"))
{
stream = new InflaterInputStream (
url.getInputStream ());
}
else
{
stream = url.getInputStream ();
}
//InputStream stream= url.getInputStream();
BufferedReader reader =
new BufferedReader(new InputStreamReader(stream));
String temp;
while (null != (temp = reader.readLine())) {
//temp=new String(reader.readLine().getBytes("gbk");
System.out.println(temp);
// break;
}
reader.close();
}
}