java爬虫中的字符串截取问题

Question

刚开始接触爬虫，已先将网页爬虫至tizi.txt，要从中获取作者和其发表的内容，一开始用的缓存，代码如下：
import java.io.*;

public class SpiderTest01 {

public static void main(String[] args) throws IOException {
    FileReader fr = null;
    FileWriter fw = null;

    try {
        fr = new FileReader("d:/tiezi.txt");
        fw = new FileWriter("d:/replace.txt");
        BufferedReader bufr = new BufferedReader(fr);
        BufferedWriter bufw = new BufferedWriter(fw);

        String line = null;
        String name = null;
        String text = null;
        String userNameBegin = "=utf-8\" target=\"_blank\">";
        String userNameEnd = "</a>";
        String userTextBegin = "class=\"d_post_content j_d_post_content  clearfix\">";
        String userTextEnd = "</div><br>";
        while ((line = bufr.readLine()) != null) {
            String userstr = null;
            String textstr = null;
            if (line.contains(userNameBegin) & line.contains(userNameEnd)) {
                // 若一行中包含开头和结尾
                name = line.substring(line.indexOf(userNameBegin) + 24,
                        line.indexOf(userNameEnd));
            } else if (line.contains(userNameBegin)
                    & (line.contains(userNameEnd) == false)) {
                userstr = line.substring(line.indexOf(userNameBegin));
            } else if (line.contains(userNameEnd)
                    & (line.contains(userNameBegin) == false)) {
                name = userstr
                        + line.substring(0, line.indexOf(userNameEnd));
            } 
            if(name!=null){
            bufw.write(name + '#');
            bufw.flush();
            }
            // 文本匹配
            if (line.contains(userTextBegin) & line.contains(userTextEnd)) {
                // 若一行中包含开头和结尾
                text = line.substring(line.indexOf(userTextBegin) + 36,
                        line.indexOf(userTextEnd));
            } else if (line.contains(userTextBegin)
                    & (line.contains(userTextEnd) == false)) {
                textstr = line.substring(line.indexOf(userTextBegin));
            } else if (line.contains(userTextEnd)
                    & (line.contains(userTextBegin) == false)) {
                text = userstr
                        + line.substring(0, line.indexOf(userTextEnd));
            }
            if(text!=null){
            bufw.write(text);
            bufw.flush();
    } else {
                continue;
            }
        }
        bufr.close();
        bufw.close();
    } catch (IOException e) {
        throw new RuntimeException("读写失败");
    }

}

}

在replace文件中发现并不是想要获取的内容，在想，是不是因为readline方法的局限问题，因为标识符有可能出现在一行的结尾和下一行的开始处，故采用数组方式获取，代码如下：
import java.io.*;
public class SpiderTestDemo02 {

public static void main(String[] args) throws IOException{

    FileWriter fw =null;
    FileReader fr =null;
    String name = null;
    String text = null;
    //定义作者开头及结尾标识，以及正文开始和结尾标识
    String userNameBegin = "=utf-8\" target=\"_blank\">";
    String userNameEnd = "</a>";
    String userTextBegin = "class=\"d_post_content j_d_post_content  clearfix\">";
    String userTextEnd = "</div><br>";

    try
    {
        //指定读写路径
        fw = new FileWriter("d:/tizi.txt");
        fr = new FileReader("d:/replace.txt");
        char[] ch = new char[1024];

        int len = 0;

        while((len=fr.read())!=-1)//读取原文件内容至数组
        {
            String line = new String(ch,0,len);

            if (line.contains(userNameBegin))
            {
                if(line.contains(userNameEnd))
                {
                    // 若一行中包含开头和结尾
                    name = line.substring(line.indexOf(userNameBegin) + 24,
                            line.indexOf(userNameEnd));
                    fw.write(name+"#");
                    fw.flush();
                }

            }
            if (line.contains(userTextBegin))
            {
                if(line.contains(userTextEnd))
                {
                    // 若一行中包含开头和结尾
                    text = line.substring(line.indexOf(userTextBegin) + 36,
                            line.indexOf(userTextEnd));
                    fw.write(text);
                    fw.write("\r\n");
                    fw.flush();
                }

            }
            if(line.contains(userNameBegin)==false&line.contains(userTextBegin)==false)
            {
                continue;
            }
        }
        fr.close();
        fw.close();

    }catch(IOException e){
        System.out.print(e);
    }

}

}

结果这次运行的结果是replace文件中无任何数据，求大婶指点

Answer 1

有没有大婶给解释下代码哪里出了问题呢，没有币了，不胜感谢