Question

我写了一些代码

public static void main(String[] args) throws HttpException, IOException,
        JSONException {
    // TODO Auto-generated method stub
    try {
        URL murl = new URL(
                "http://www.baidu.com/link?url=NaethV_J2hSPVx_OdPlHk73964mU4LcwWkJmVUV4vIkuCXRf1y09ufRZVwkHJqSAa2mMSCoTLYVhGv2AyV_04_");
        HttpURLConnection conn = (HttpURLConnection) murl.openConnection();
        conn.setRequestProperty(
                "User-Agent",
                "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.111 Safari/537.36");
        conn.setConnectTimeout(10000);

        conn.connect();

        String strencoding = null;


        Map<String, List<String>> map = conn.getHeaderFields();
        Set<String> keys = map.keySet();
        Iterator<String> iterator = keys.iterator();


        String key = null;
        String tmp = null;
        while (iterator.hasNext()) {
            key = iterator.next();
            tmp = map.get(key).toString().toLowerCase();


            if (key != null && key.equals("Content-Type")) {
                System.out.println(tmp);
                int m = tmp.indexOf("charset=");
                if (m != -1) {
                    strencoding = tmp.substring(m + 8).replace("]", "");

                }
            }
        }
        strencoding = strencoding == null ? "UTF-8" : strencoding;

        conn.getResponseCode();
        // conn.connect();
        String href = conn.getURL().toString();
        System.out.println(href);
        href = href.replace("http://", "");
        try {
            href = href.split("/")[0];
        } catch (Exception eee) {

        }
        /*
         * ParseDomainName pdn = new ParseDomainName(href);
         * System.out.println("Your host IP is: " +
         * pdn.getMyIP().getHostAddress());
         * System.out.println("The Server IP is :" +
         * pdn.getServerIP().getHostAddress()); // InputStream inputstream =
         * conn.getInputStream();
         */

        BufferedReader reader = new BufferedReader(new InputStreamReader(
                conn.getInputStream(), strencoding));

        String lines;
        int i = 1;
        while ((lines = reader.readLine()) != null) {

            if (lines.toLowerCase().indexOf("charset") > 0) {
                System.out.println(lines);
                String strtmp = lines;
                int inttmp = strtmp.indexOf("charset");
                if (inttmp > -1) {
                    System.out.println(strtmp.length());
                    strencoding = strtmp
                            .substring(inttmp + 7, strtmp.length())
                            .replace("=", "").replace("/", "")
                            .replace("\"", "").replace("\'", "")
                            .replace(" ", "").replace("<", "")
                            .replace(">", "");
                    break;
                }
            }
            i++;
        }

        reader.mark(0);
        reader.reset();
        reader = new BufferedReader(new InputStreamReader(
                conn.getInputStream(), strencoding));

        while ((lines = reader.readLine()) != null) {
            System.out.println(i + "    " + lines);
            if (lines.toLowerCase().indexOf("icp") > 0) {
                // System.out.println(i + "    " + lines);
            }
            i++;
        }
        System.out.println(i + "---" + strencoding);
        reader.close();
        conn.disconnect();
    } catch (Exception e2) {
        e2.printStackTrace();

    }

}

最后一个while循环，在第一个循环中我检查页面charset并中断，然后我重置了读卡器，再次readLine，但是在seconed循环中，它从第一个循环结束的位置开始。

有时它会打印结果： enter image description here

有时不会在seconed循环中读取任何内容，如下所示： enter image description here

那么问题是什么？

Answer 1

你必须在第一个while循环之前调用reader.mark（）; reader.mark（）基本上保存了阅读器的当前位置，以便您在调用reader.reset（）时可以返回到该位置。

您也不想将0传递给reader.mark（）。请参阅以下参数的java规范：

readAheadLimit - 限制在保留标记的同时可以读取的字符数。尝试在读取字符达到此限制或更高时重置流可能会失败。大于输入缓冲区大小的限制值将导致分配一个大小不小于limit的新缓冲区。因此，应谨慎使用大值。

（换句话说，传入0将没用。你需要传入一个大于mark（）和reset（）之间读取的字符数的数字。

Answer 2

reader = new BufferedReader(new InputStreamReader(
        conn.getInputStream(), strencoding));

这一行导致您的代码创建一个新的阅读器，这将使读者从头开始。

Answer 3

最后，我发现问题出在conn.getInputStream()，它在第一次循环后已经被更改了，所以我做了一些修改，克隆了输入流，现在没问题了：

public static void main(String[] args) throws HttpException, IOException,
        JSONException {
    // TODO Auto-generated method stub
    try {
        URL murl = new URL(
                "http://www.baidu.com/link?url=NaethV_J2hSPVx_OdPlHk73964mU4LcwWkJmVUV4vIkuCXRf1y09ufRZVwkHJqSAa2mMSCoTLYVhGv2AyV_04_");
        HttpURLConnection conn = (HttpURLConnection) murl.openConnection();
        conn.setRequestProperty(
                "User-Agent",
                "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.111 Safari/537.36");
        conn.setConnectTimeout(10000);

        conn.connect();

        String strencoding = null;



        strencoding = strencoding == null ? "UTF-8" : strencoding;

        conn.getResponseCode();
        // conn.connect();
        String href = conn.getURL().toString();
        System.out.println(href);
        href = href.replace("http://", "");
        try {
            href = href.split("/")[0];
        } catch (Exception eee) {

        }


        InputStream inputStream=conn.getInputStream();
        ByteArrayOutputStream baos = new ByteArrayOutputStream();


        byte[] buffer = new byte[1024];
        int len;
        while ((len = inputStream.read(buffer)) > -1 ) {
            baos.write(buffer, 0, len);
        }
        baos.flush();


        InputStream copyInputStream1 = new ByteArrayInputStream(baos.toByteArray()); 
        InputStream copyInputStream2 = new ByteArrayInputStream(baos.toByteArray()); 

        BufferedReader reader = new BufferedReader(new InputStreamReader(
                copyInputStream1, strencoding));

        String lines;
        int i = 1;

        while ((lines = reader.readLine()) != null) {

            if (lines.toLowerCase().indexOf("charset") > 0) {
                System.out.println(lines);
                String strtmp = lines;
                int inttmp = strtmp.indexOf("charset");
                if (inttmp > -1) {
                    System.out.println(strtmp.length());
                    strencoding = strtmp
                            .substring(inttmp + 7, strtmp.length())
                            .replace("=", "").replace("/", "")
                            .replace("\"", "").replace("\'", "")
                            .replace(" ", "").replace("<", "")
                            .replace(">", "");
                    //break;
                }
            }
            i++;
        }


        reader = new BufferedReader(new InputStreamReader(
                copyInputStream2, strencoding));

        while ((lines = reader.readLine()) != null) {
            //System.out.println(i + "    " + lines);
            if (lines.toLowerCase().indexOf("icp") > 0) {
                 System.out.println(i + "    " + lines);
            }
            i++;
        }
        System.out.println(i + "---" + strencoding);
        reader.close();
        conn.disconnect();
    } catch (Exception e2) {
        e2.printStackTrace();

    }

}

如何重置BufferedReader？

3 个答案: