小说分割器,按章节划分为html

客官°小女子只卖身不卖艺 2023-10-03 14:05 6阅读 0赞

package tmp03;
    
    /*
     * 用来将只放在一个文件中的小说切隔成
     * 一个章节的html页面，其中每个页面还包括上一页，下一页，目录 的超链接
     * 同时还生成一个目录文件contents.html
     *====================
     *注意源码的编码是：utf-8
     *文件读取的来源文件的编码也需是utf-8
     *===================
     *这里的神墓的切隔的原理是：
     *根据第一个章节的标题都包含："章 "
     *
     */
    
    import java.io.BufferedReader;
    import java.io.BufferedWriter;
    import java.io.File;
    import java.io.FileInputStream;
    import java.io.FileWriter;
    import java.io.InputStreamReader;
    import java.io.PrintWriter;
    import java.util.ArrayList;
    import java.util.Scanner;
    import java.util.regex.Matcher;
    import java.util.regex.Pattern;
    import utils.FileUtils;
    
    
    public class GeneraeHtml {
    
    
        private ArrayList<String> fileNames;
    
        public GeneraeHtml() {
            fileNames = new ArrayList<String>();
        }
    
        public void generateHtmlByFile(File file) throws Exception {
            generate(file);
            generateContent();
    
        }
    
        //Create all chapters's html file
        private void generate(File file) throws Exception {
            boolean isFirstTitle = true;
            InputStreamReader isr = new InputStreamReader(
                new FileInputStream(file), "GBK");
            BufferedReader read = new BufferedReader(isr);
    //        BufferedReader source = new BufferedReader(new FileReader(file.getAbsolutePath()));
            Scanner sca = new Scanner(read);
            String currentContent = "";
            String currentLineStr = "";
            String currentPageFileName = "";
            String nextPageFileName = "";
            int currentPageIndex = -1;
    
            sca.useDelimiter("/n");
            while (sca.hasNextLine()) {
                currentLineStr = sca.nextLine();
                //正则表达式：我的小说章节名是以 ###开头，###结尾 ，所以用第二个更好
                Pattern p = Pattern.compile("(第\\S*)[章节卷集部篇回](\\s)(\\S*)[^#]");
    //				Pattern p = Pattern.compile("(###)(.*)(###)");
                Matcher matcher = p.matcher(currentLineStr);
                if (matcher.find()) {
                    currentLineStr = matcher.group();
                    System.out.println("matcher.group() = " + matcher.group());
                    if (!isFirstTitle) {
                        System.out.println("Current output title:" + currentPageFileName);
                        nextPageFileName = (currentPageIndex + 1) + currentLineStr.trim() + ".html";
                        nextPageFileName= FileUtils.filterSpecialCharts(nextPageFileName, "");
                        fileNames.add(nextPageFileName);
    //                    System.out.println("currentContent = " + currentContent);
                        writeContent(currentContent, currentPageFileName, currentPageIndex);
    
                        currentPageFileName = nextPageFileName;
                        currentContent = "";
                    } else {
                        currentPageFileName = (currentPageIndex + 1) + currentLineStr.trim() + ".html";
                        currentPageFileName = FileUtils.filterSpecialCharts(currentPageFileName, "");
                        fileNames.add(currentPageFileName);
                        isFirstTitle = false;
                    }
                    currentPageIndex++;
                }
                currentContent += currentLineStr + "</br>";
            }
            sca.close();
        }
    
        //It will write the current chapter into a html file
        private void writeContent(String bodyContent, String currentFileName, int currentPageIndex)
            throws Exception {
            int previousPageIndex = 0;
            int nextPageIndex = currentPageIndex + 1;
            if (currentPageIndex != 0) {
                previousPageIndex = currentPageIndex - 1;
            }
            String pageContent = "<html>\n<head>\n"
                + "<meta http-equiv='content-type' content='text/html;charset=utf-8'>\n"
                + "</head>\n<body bgcolor='#e6f3ff'>\n"
                + bodyContent
                + "</br>"
                + "<table align='center'>"
                + "<tr>"
                + "<td><a href='./" + fileNames.get(previousPageIndex) + "'>上一页</a></td>"
                + "<td><a href='./contents.html'>目录</a></td>"
                + "<td><a href='./" + fileNames.get(nextPageIndex) + "'>下一页</a></td>"
                + "</tr>"
                + "</table>"
                + "</body>/n</html>";
            String filePath = outDirPath + FileUtils.filterSpecialCharts(currentFileName, "");
            PrintWriter out = new PrintWriter(new BufferedWriter(new FileWriter(filePath)));
            out.print(pageContent);
            out.flush();
            out.close();
        }
    
        //Create a html file contain chapter's reference.
        private void generateContent() throws Exception {
            String pageContent = "<html>\n<head>\n"
                + "<meta http-equiv='content-type' content='text/html;charset=utf-8'>\n"
                + "</head>\n<body bgcolor='#e6f3ff'>\n"
                + "<table align='center' width='80%' border=1>"
                + "<tr align='center'>";
    
    
            for (int i = 0; i < fileNames.size(); i++) {
                String item = fileNames.get(i);
                pageContent +=
                    "<td width=33% color='green'><a href='./" + item + "'>" + item + "</a></td>";
                if ((i + 1) % 3 == 0) {
                    pageContent += "</tr>\n<tr align='center'>";
                }
            }
            pageContent += "</table>\n</body>\n</html>";
            String fileName = outDirPath + "contents.html";
            System.out.println("pageContent = " + pageContent);
            PrintWriter out = new PrintWriter(new BufferedWriter(new FileWriter(
                fileName)));
            out.print(pageContent);
            out.flush();
            out.close();
    
        }
    
        public static final String filePath = "D:/06tmp/7175.txt";
        public static final String outDirPath = "D:/06tmp/神墓/";
    
        public static void main(String[] args) {
            GeneraeHtml generaeHtml = new GeneraeHtml();
            try {
                File file = new File(filePath);
                generaeHtml.generateHtmlByFile(file);
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
    
    }

package tmp03;
    
    /*
     * 用来将只放在一个文件中的小说切隔成
     * 一个章节的html页面，其中每个页面还包括上一页，下一页，目录 的超链接
     * 同时还生成一个目录文件contents.html
     *====================
     *注意源码的编码是：utf-8
     *文件读取的来源文件的编码也需是utf-8
     *===================
     *这里的神墓的切隔的原理是：
     *根据第一个章节的标题都包含："章 "
     *
     */
    
    import java.io.BufferedReader;
    import java.io.BufferedWriter;
    import java.io.File;
    import java.io.FileInputStream;
    import java.io.FileWriter;
    import java.io.InputStreamReader;
    import java.io.PrintWriter;
    import java.util.ArrayList;
    import java.util.Scanner;
    import utils.FileUtils;
    
    
    public class GeneraeHtml1 {
    
    
        private ArrayList<String> fileNames;
    
        public GeneraeHtml1() {
            fileNames = new ArrayList<String>();
        }
    
        public void generateHtmlByFile(File file) throws Exception {
            generate(file);
            generateContent();
    
        }
    
        //Create all chapters's html file
        private void generate(File file) throws Exception {
            boolean isFirstTitle = true;
            InputStreamReader isr = new InputStreamReader(
                new FileInputStream(file), "GBK");
            BufferedReader read = new BufferedReader(isr);
    //        BufferedReader source = new BufferedReader(new FileReader(file.getAbsolutePath()));
            Scanner sca = new Scanner(read);
            String currentContent = "";
            String currentLineStr = "";
            String currentPageFileName = "";
            String nextPageFileName = "";
            int currentPageIndex = -1;
    
            sca.useDelimiter("/n");
            while (sca.hasNextLine()) {
    //            currentLineStr = sca.next();
    //            System.out.println("currentLineStr = " + currentLineStr);
    //            System.out.println("currentLineStr 1= " + (currentLineStr = sca.nextLine()));
                currentLineStr = sca.nextLine();
    //            System.out.println("currentPageIndex = " + (currentLineStr.indexOf("章") != -1));
                if (currentLineStr.indexOf("章") != -1) {
                    if (!isFirstTitle) {
                        System.out.println("Current output title:" + currentPageFileName);
                        nextPageFileName = (currentPageIndex + 1) + currentLineStr.trim() + ".html";
                        nextPageFileName= FileUtils.filterSpecialCharts(nextPageFileName, "");
                        fileNames.add(nextPageFileName);
    //                    System.out.println("currentContent = " + currentContent);
                        writeContent(currentContent, currentPageFileName, currentPageIndex);
    
                        currentPageFileName = nextPageFileName;
                        currentContent = "";
                    } else {
                        currentPageFileName = (currentPageIndex + 1) + currentLineStr.trim() + ".html";
                        currentPageFileName = FileUtils.filterSpecialCharts(currentPageFileName, "");
                        fileNames.add(currentPageFileName);
                        isFirstTitle = false;
                    }
                    currentPageIndex++;
    
                }
                currentContent += currentLineStr + "</br>";
            }
            sca.close();
        }
    
        //It will write the current chapter into a html file
        private void writeContent(String bodyContent, String currentFileName, int currentPageIndex)
            throws Exception {
            int previousPageIndex = 0;
            int nextPageIndex = currentPageIndex + 1;
            if (currentPageIndex != 0) {
                previousPageIndex = currentPageIndex - 1;
            }
            String pageContent = "<html>/n<head>/n"
                + "<meta http-equiv='content-type' content='text/html;charset=utf-8'>/n"
                + "</head>/n<body bgcolor='#e6f3ff'>/n"
                + bodyContent
                + "</br>"
                + "<table align='center'>"
                + "<tr>"
                + "<td><a href='./" + fileNames.get(previousPageIndex) + "'>上一页</a></td>"
                + "<td><a href='./contents.html'>目录</a></td>"
                + "<td><a href='./" + fileNames.get(nextPageIndex) + "'>下一页</a></td>"
                + "</tr>"
                + "</table>"
                + "</body>/n</html>";
            String filePath = outDirPath + FileUtils.filterSpecialCharts(currentFileName, "");
            PrintWriter out = new PrintWriter(new BufferedWriter(new FileWriter(filePath)));
            out.print(pageContent);
            out.flush();
            out.close();
        }
    
        //Create a html file contain chapter's reference.
        private void generateContent() throws Exception {
            String pageContent = "<html>/n<head>/n"
                + "<meta http-equiv='content-type' content='text/html;charset=utf-8'>/n"
                + "</head>/n<body bgcolor='#e6f3ff'>/n"
                + "<table align='center' width='80%' border=1>"
                + "<tr align='center'>";
            for (int i = 0; i < fileNames.size(); i++) {
                String item = fileNames.get(i);
                pageContent +=
                    "<td width=33% color='green'><a href='./" + item + "'>" + item + "</a></td>";
                if ((i + 1) % 3 == 0) {
                    pageContent += "</tr>/n<tr align='center'>";
                }
            }
            pageContent += "</table>/n</body>/n</html>";
            String fileName = outDirPath + "contents.html";
    //        File file = new File(fileName);
    //        file.createNewFile();
            PrintWriter out = new PrintWriter(new BufferedWriter(new FileWriter(
                fileName)));
            out.print(pageContent);
            out.flush();
            out.close();
    
        }
    
        public static final String filePath = "D:/06tmp/7175.txt";
        public static final String outDirPath = "D:/06tmp/神墓/";
    
        public static void main(String[] args) {
            GeneraeHtml1 generaeHtml = new GeneraeHtml1();
            try {
                File file = new File(filePath);
                generaeHtml.generateHtmlByFile(file);
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
    
    }

不咋好用

package tmp03;
    
    /*
     * 用来将只放在一个文件中的小说切隔成
     * 一个章节的html页面，其中每个页面还包括上一页，下一页，目录 的超链接
     * 同时还生成一个目录文件contents.html
     *====================
     *注意源码的编码是：utf-8
     *文件读取的来源文件的编码也需是utf-8
     *===================
     *这里的神墓的切隔的原理是：
     *根据第一个章节的标题都包含："章 "
     *
     */
    
    import java.io.BufferedWriter;
    import java.io.File;
    import java.io.FileWriter;
    import java.io.PrintWriter;
    import java.util.ArrayList;
    import java.util.Scanner;
    
    
    public class GeneraeHtml {
    
    
        private ArrayList<String> fileNames;
    
        public GeneraeHtml() {
            fileNames = new ArrayList<String>();
        }
    
        public void generateHtmlByFile(File file) throws Exception {
            generate(file);
            generateContent();
    
        }
    
        //Create all chapters's html file
        private void generate(File file) throws Exception {
            boolean isFirstTitle = true;
            Scanner sca = new Scanner(file);
            String currentContent = "";
            String currentLineStr = "";
            String currentPageFileName = "";
            String nextPageFileName = "";
            int currentPageIndex = -1;
    
            sca.useDelimiter("/n");
    
            while (sca.hasNext()) {
                currentLineStr = sca.next();
    //            System.out.println("currentPageIndex = " + currentPageIndex);
                if (currentLineStr.indexOf("章 ") != -1) {
    
                    if (!isFirstTitle) {
                        System.out.println("Current output title:" + currentPageFileName);
                        nextPageFileName = (currentPageIndex + 1) + currentLineStr.trim() + ".html";
                        fileNames.add(nextPageFileName);
    
                        writeContent(currentContent, currentPageFileName, currentPageIndex);
    
                        currentPageFileName = nextPageFileName;
                        currentContent = "";
                    } else {
                        currentPageFileName = (currentPageIndex + 1) + currentLineStr.trim() + ".html";
                        fileNames.add(currentPageFileName);
                        isFirstTitle = false;
                    }
                    currentPageIndex++;
    
                }
                currentContent += currentLineStr + "</br>";
            }
            sca.close();
        }
    
        //It will write the current chapter into a html file
        private void writeContent(String bodyContent, String currentFileName, int currentPageIndex)
            throws Exception {
            int previousPageIndex = 0;
            int nextPageIndex = currentPageIndex + 1;
            if (currentPageIndex != 0) {
                previousPageIndex = currentPageIndex - 1;
            }
            String pageContent = "<html>/n<head>/n"
                + "<meta http-equiv='content-type' content='text/html;charset=utf-8'>/n"
                + "</head>/n<body bgcolor='#e6f3ff'>/n"
                + bodyContent
                + "</br>"
                + "<table align='center'>"
                + "<tr>"
                + "<td><a href='./" + fileNames.get(previousPageIndex) + "'>上一页</a></td>"
                + "<td><a href='./contents.html'>目录</a></td>"
                + "<td><a href='./" + fileNames.get(nextPageIndex) + "'>下一页</a></td>"
                + "</tr>"
                + "</table>"
                + "</body>/n</html>";
            String filePath = "神墓/" + currentFileName;
            PrintWriter out = new PrintWriter(new BufferedWriter(new FileWriter(filePath)));
            out.print(pageContent);
            out.flush();
            out.close();
        }
    
        //Create a html file contain chapter's reference.
        private void generateContent() throws Exception {
            String pageContent = "<html>/n<head>/n"
                + "<meta http-equiv='content-type' content='text/html;charset=utf-8'>/n"
                + "</head>/n<body bgcolor='#e6f3ff'>/n"
                + "<table align='center' width='80%' border=1>"
                + "<tr align='center'>";
            for (int i = 0; i < fileNames.size(); i++) {
                String item = fileNames.get(i);
                pageContent +=
                    "<td width=33% color='green'><a href='./" + item + "'>" + item + "</a></td>";
                if ((i + 1) % 3 == 0) {
                    pageContent += "</tr>/n<tr align='center'>";
                }
            }
            pageContent += "</table>/n</body>/n</html>";
            String fileName = "D:/06tmp/神墓/contents.html";
    //        File file = new File(fileName);
    //        file.createNewFile();
            PrintWriter out = new PrintWriter(new BufferedWriter(new FileWriter(
                fileName)));
            out.print(pageContent);
            out.flush();
            out.close();
    
        }
    
        public static void main(String[] args) {
            GeneraeHtml generaeHtml = new GeneraeHtml();
            try {
                File file = new File("D:/06tmp/7175.txt");
                generaeHtml.generateHtmlByFile(file);
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
    
    }