0

package.json

@@ -26,9 +26,12 @@
     "@koa/multer": "^3.0.2",
     "@koa/router": "^13.1.0",
     "axios": "^1.9.0",
+    "cheerio": "^1.1.2",
     "child_process": "^1.0.2",
     "cos-nodejs-sdk-v5": "^2.16.0-beta.3",
     "gm": "^1.25.1",
+    "jsdom": "^27.0.0",
+    "jszip": "^3.10.1",
     "koa": "^2.13.4",
     "koa-bodyparser": "^4.4.1",
     "koa-router": "^13.0.1",
@@ -40,7 +43,8 @@
     "mysql2": "^3.14.1",
     "pdfkit": "^0.17.1",
     "request-promise": "^4.2.6",
-    "tencentcloud-sdk-nodejs-ocr": "^4.1.70"
+    "tencentcloud-sdk-nodejs-ocr": "^4.1.70",
+    "uuid": "^13.0.0"
   },
   "devDependencies": {
     "cross-env": "^7.0.3"

src/web_crawler/crawler_yinsha.js

@@ -0,0 +1,538 @@
+import fs from 'fs';
+import axios from 'axios';
+import * as cheerio from 'cheerio';
+import path from 'path';
+import { setTimeout } from 'timers/promises';
+
+/**
+ * 格式化章节内容
+ * @param {string} content - 原始文本内容
+ * @returns {string} - 格式化后的HTML内容
+ */
+async function formatChapterContent(content) {
+    // 将章节标题替换为<h2>
+    content = content.replace(/Chapter \d+/g, match => `<h2>${match}</h2>`);
+    
+    // 将正文段落用<p>包裹
+    content = content.replace(/\n\n/g, '</p><p>');
+    content = `<p>${content}</p>`;
+    
+    return content;
+}
+
+/**
+ * 处理文本文件，为章节标题添加h2标签，为段落添加p标签
+ * @param {string} filePath - 文本文件路径
+ * @param {string} outputPath - 输出文件路径
+ * @returns {Promise<void>}
+ */
+async function formatTextFile(filePath, outputPath) {
+    try {
+        // 读取文本文件
+        const content = await fs.promises.readFile(filePath, 'utf-8');
+        console.log(`已读取文件: ${filePath}`);
+        
+        // 分割成章节
+        const chapters = content.split(/Chapter \d+/).filter(Boolean);
+        console.log(`检测到 ${chapters.length} 个章节内容块`);
+        
+        let formattedContent = '';
+        let chapterIndex = 1;
+        
+        // 处理每个章节
+        for (const chapter of chapters) {
+            // 添加章节标题
+            formattedContent += `<h2>Chapter ${chapterIndex}</h2>\n`;
+            
+            // 处理章节内容，将段落用<p>标签包裹
+            const paragraphs = chapter.trim().split(/\n\s*\n/);
+            for (const paragraph of paragraphs) {
+                if (paragraph.trim()) {
+                    formattedContent += `<p>${paragraph.trim()}</p>\n`;
+                }
+            }
+            
+            chapterIndex++;
+        }
+        
+        // 写入输出文件
+        await fs.promises.writeFile(outputPath, formattedContent);
+        console.log(`格式化完成! 结果已保存到: ${outputPath}`);
+        console.log(`共处理了 ${chapters.length} 个章节`);
+        
+    } catch (error) {
+        console.error('处理文本文件时出错:', error);
+    }
+}
+
+async function mergeChapterFiles(sourceDir, outputFile) {
+    try {
+        const SEPARATOR = '\n******************\n';
+        const { readdir, readFile, writeFile } = fs.promises;
+
+        // 获取所有HTML文件并按章节顺序排序
+        const files = (await readdir(sourceDir))
+            .filter(file => file.endsWith('.html'))
+            .sort((a, b) => parseInt(a.split('_')[0]) - parseInt(b.split('_')[0]));
+
+        if (files.length === 0) {
+            console.error('未找到任何章节文件');
+            return;
+        }
+
+        let mergedContent = '';
+        
+        // 处理每个章节文件
+        for (const file of files) {
+            const filePath = path.join(sourceDir, file);
+            const html = await readFile(filePath, 'utf-8');
+            
+            // 提取章节标题
+            const titleMatch = file.match(/_([^\.]+)\.html$/);
+            const title = titleMatch ? titleMatch[1] : file;
+            
+            // 提取正文内容
+            const contentMatch = html.match(/<div id="showReading"[^>]*>([\s\S]*?)<\/div>/);
+            if (!contentMatch) continue;
+            
+            let content = contentMatch[1]
+                .replace(/<sent[^>]*>/g, '')
+                .replace(/<\/sent>/g, '')
+                .replace(/<br>/g, '\n')
+                .replace(/<[^>]+>/g, '')
+                .replace(/\(adsbygoogle\s*=\s*window\.adsbygoogle\s*\|\|\s*\[\]\).push\(\{\}\);/g, '')
+                .replace(/\n{3,}/g, '\n\n');
+            
+            // 添加到合并内容
+            mergedContent += `${title}\n\n${content.trim()}${SEPARATOR}`;
+            console.log(`已处理: ${file}`);
+        }
+
+        // 格式化合并后的内容
+        const formattedContent = await formatChapterContent(mergedContent);
+        
+        // 写入合并文件
+        await writeFile(outputFile, formattedContent);
+        console.log(`\n合并完成! 结果已保存到: ${outputFile}`);
+        console.log(`共合并了 ${files.length} 个章节`);
+
+    } catch (error) {
+        console.error('合并章节时出错:', error);
+    }
+}
+
+/**
+ * 爬取单个章节内容
+ * @param {string} baseUrl - 网站基础URL
+ * @param {string} chapterUrl - 章节URL
+ * @param {object} headers - 请求头
+ * @param {boolean} debug - 是否开启调试模式
+ * @returns {Promise<string|null>} - 章节内容或null
+ */
+async function fetchChapterContent(baseUrl, chapterUrl, headers, debug = false) {
+    try {
+        // 如果URL不是以http开头，则添加baseUrl
+        const fullUrl = chapterUrl.startsWith('http') ? chapterUrl : `${baseUrl}${chapterUrl}`;
+        
+        if (debug) {
+            console.log(`爬取章节内容: ${fullUrl}`);
+        }
+        
+        const response = await axios.get(fullUrl, { headers });
+        
+        if (response.status !== 200) {
+            console.error(`获取章节内容失败，状态码: ${response.status}`);
+            return null;
+        }
+        
+        const $ = cheerio.load(response.data);
+        
+        // 尝试多种选择器来获取章节内容
+        const contentSelectors = [
+            '.chapter-content',
+            '.article-content',
+            '.content',
+            '#content',
+            '.text-content',
+            '.chapter-text',
+            '.novel-content'
+        ];
+        
+        let content = null;
+        
+        for (const selector of contentSelectors) {
+            const element = $(selector);
+            if (element.length > 0) {
+                content = element.html();
+                if (debug) {
+                    console.log(`使用选择器 ${selector} 成功获取章节内容`);
+                }
+                break;
+            }
+        }
+        
+        // 如果上面的选择器都没找到内容，尝试查找包含大量文本的元素
+        if (!content) {
+            let maxTextLength = 0;
+            let maxTextElement = null;
+            
+            $('div, article, section, p').each((_, element) => {
+                const text = $(element).text().trim();
+                if (text.length > maxTextLength && text.length > 500) {
+                    maxTextLength = text.length;
+                    maxTextElement = element;
+                }
+            });
+            
+            if (maxTextElement) {
+                content = $(maxTextElement).html();
+                if (debug) {
+                    console.log(`使用最长文本元素获取章节内容，长度: ${maxTextLength}`);
+                }
+            }
+        }
+        
+        return content;
+    } catch (error) {
+        console.error(`爬取章节内容出错: ${error.message}`);
+        return null;
+    }
+}
+
+/**
+ * 爬取小说章节目录
+ * @param {string} title - 小说标题
+ * @param {boolean} debug - 是否开启调试模式
+ * @param {string} outputDir - 输出目录
+ * @param {boolean} fetchContent - 是否爬取章节内容
+ * @returns {Promise<Array|Object>} - 章节目录数组或错误对象
+ */
+async function runScript(title, debug = false, outputDir = 'src/web_crawler', fetchContent = false){
+    const url = `https://novelhi.com/s/index/`+title;
+    console.log(`正在爬取网址: ${url}`);
+
+    try {
+        // 设置请求头，模拟浏览器行为
+        const headers = {
+            'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36',
+            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
+            'Accept-Language': 'en-US,en;q=0.5',
+            'Connection': 'keep-alive',
+            'Upgrade-Insecure-Requests': '1',
+            'Cache-Control': 'max-age=0'
+        };
+
+        const response = await axios.get(url, { headers });
+        console.log(`请求状态码: ${response.status}`);
+        
+        // 如果开启调试模式，保存HTML内容
+        if (debug) {
+            const debugFilePath = path.join(outputDir, 'debug_page.html');
+            fs.writeFileSync(debugFilePath, response.data);
+            console.log(`已保存HTML内容到 ${debugFilePath} 文件`);
+        }
+        
+        const $ = cheerio.load(response.data);
+        
+        // 提取章节目录
+        const chapters = [];
+        
+        // 如果开启调试模式，打印页面结构信息
+        if (debug) {
+            console.log('页面标题:', $('title').text());
+            console.log('页面主要容器数量:');
+            console.log('- div 元素数量:', $('div').length);
+            console.log('- ul 元素数量:', $('ul').length);
+            console.log('- li 元素数量:', $('li').length);
+            console.log('- a 元素数量:', $('a').length);
+        }
+        
+        // 尝试多种选择器
+        const selectors = [
+            '.chapter-list li',
+            '.book-catalog-list a',
+            '.catalog-list li',
+            '.chapter-item',
+            '.chapter a',
+            'ul.chapters li',
+            '.book-chapters a',
+            '.novel-chapters a',
+            'span:contains("Chapter")'
+        ];
+        
+        for (const selector of selectors) {
+            console.log(`尝试选择器: ${selector}`);
+            const elements = $(selector);
+            console.log(`找到 ${elements.length} 个元素`);
+            
+            if (elements.length > 0) {
+                elements.each((index, element) => {
+                    let chapterTitle, chapterUrl;
+                    
+                    if (selector === 'span:contains("Chapter")') {
+                        chapterTitle = $(element).text().trim();
+                        // 对于这个网站，我们可能需要构造章节URL
+                        chapterUrl = `/s/${title}/${chapterTitle.replace('Chapter ', '')}`;
+                    } else if (selector.includes('a')) {
+                        chapterTitle = $(element).text().trim();
+                        chapterUrl = $(element).attr('href');
+                    } else {
+                        chapterTitle = $(element).find('a').text().trim();
+                        chapterUrl = $(element).find('a').attr('href');
+                    }
+                    
+                    if (chapterTitle) {
+                        chapters.push({
+                            title: chapterTitle,
+                            url: chapterUrl || '#',
+                            index: index + 1
+                        });
+                    }
+                });
+                
+                if (chapters.length > 0) {
+                    console.log(`使用选择器 ${selector} 成功找到章节`);
+                    break;
+                }
+            }
+        }
+        
+        // 如果上面的选择器都没有找到章节，尝试更通用的方法
+        if (chapters.length === 0) {
+            console.log('尝试查找所有可能的章节链接...');
+            
+            // 查找所有包含"chapter"或"第"字样的链接或文本
+            $('*').each((index, element) => {
+                const text = $(element).text().trim();
+                
+                if (text && (text.includes('Chapter') || text.includes('第') || text.includes('章'))) {
+                    // 检查是否是单独的章节标题（不包含其他章节）
+                    if (text.match(/^Chapter \d+$/) || text.match(/^第[一二三四五六七八九十百千万]+章/) || text.match(/^\d+\.\s+.+$/)) {
+                        chapters.push({
+                            title: text,
+                            url: '#',  // 如果没有URL，使用占位符
+                            index: index + 1
+                        });
+                    }
+                }
+            });
+        }
+        
+        console.log(`共找到 ${chapters.length} 个章节`);
+        
+        // 将结果保存到文件中
+        const outputFilePath = path.join(outputDir, `${title}_chapters.json`);
+        fs.writeFileSync(outputFilePath, JSON.stringify(chapters, null, 2));
+        console.log(`已将章节目录保存到 ${outputFilePath} 文件`);
+        
+        // 打印前10个章节和后10个章节
+        if (debug || chapters.length <= 20) {
+            console.log("章节目录:");
+            console.log(JSON.stringify(chapters, null, 2));
+        } else {
+            console.log("前10个章节:");
+            console.log(JSON.stringify(chapters.slice(0, 10), null, 2));
+            
+            console.log("...");
+            
+            console.log("后10个章节:");
+            console.log(JSON.stringify(chapters.slice(-10), null, 2));
+        }
+        
+        // 如果需要爬取章节内容
+        if (fetchContent && chapters.length > 0) {
+            console.log(`开始爬取章节内容...`);
+            
+            // 创建章节内容目录
+            const contentDir = path.join(outputDir, `${title}_contents`);
+            if (!fs.existsSync(contentDir)) {
+                fs.mkdirSync(contentDir, { recursive: true });
+            }
+            
+            // 创建一个包含所有章节内容的对象
+            const contentsObj = {};
+            
+            // 设置基础URL
+            const baseUrl = 'https://novelhi.com';
+            
+            // 爬取所有章节
+            const chaptersToFetch = chapters;
+            console.log(`将爬取 ${chaptersToFetch.length}/${chapters.length} 个章节的内容`);
+            
+            // 爬取章节内容
+            for (let i = 0; i < chaptersToFetch.length; i++) {
+                const chapter = chaptersToFetch[i];
+                
+                // 每爬取10个章节，暂停一下，避免请求过于频繁
+                if (i > 0 && i % 10 === 0) {
+                    console.log(`已爬取 ${i}/${chaptersToFetch.length} 章节，暂停 2 秒...`);
+                    await setTimeout(2000);
+                }
+                
+                // 爬取章节内容
+                const content = await fetchChapterContent(baseUrl, chapter.url, headers, debug);
+                
+                if (content) {
+                    // 更新章节对象，添加内容
+                    chapters[i].content = content;
+                    contentsObj[chapter.title] = content;
+                    
+                    // 将章节内容保存到单独的文件
+                    const chapterFileName = `${String(chapter.index).padStart(4, '0')}_${chapter.title.replace(/[\\/:*?"<>|]/g, '_')}.html`;
+                    const chapterFilePath = path.join(contentDir, chapterFileName);
+                    
+                    // 创建一个完整的HTML文件
+                    const htmlContent = `<!DOCTYPE html>
+<html>
+<head>
+    <meta charset="UTF-8">
+    <title>${chapter.title}</title>
+    <style>
+        body {
+            font-family: Arial, sans-serif;
+            line-height: 1.6;
+            margin: 0 auto;
+            max-width: 800px;
+            padding: 20px;
+        }
+        h1 {
+            text-align: center;
+            margin-bottom: 30px;
+        }
+        p {
+            text-indent: 2em;
+            margin-bottom: 1em;
+        }
+    </style>
+</head>
+<body>
+    <h1>${chapter.title}</h1>
+    ${content}
+</body>
+</html>`;
+                    
+                    fs.writeFileSync(chapterFilePath, htmlContent);
+                    
+                    if (debug) {
+                        console.log(`已保存章节 ${chapter.title} 到 ${chapterFilePath}`);
+                    } else if (i % 10 === 0 || i === chapters.length - 1) {
+                        console.log(`已保存 ${i + 1}/${chapters.length} 章节`);
+                    }
+                } else {
+                    console.error(`获取章节 ${chapter.title} 内容失败`);
+                }
+            }
+            
+            // 保存所有章节内容到一个文件
+            const allContentsPath = path.join(outputDir, `${title}_all_contents.json`);
+            fs.writeFileSync(allContentsPath, JSON.stringify(contentsObj, null, 2));
+            console.log(`已将所有章节内容保存到 ${allContentsPath} 文件`);
+            
+            // 更新章节目录文件，包含内容
+            const chaptersWithContentPath = path.join(outputDir, `${title}_chapters_with_content.json`);
+            fs.writeFileSync(chaptersWithContentPath, JSON.stringify(chapters, null, 2));
+            console.log(`已将包含内容的章节目录保存到 ${chaptersWithContentPath} 文件`);
+        }
+        
+        return chapters;
+    } catch (err) {
+        console.error("爬取过程中出错:", err.message);
+        return { errcode: 101, errStr: err.message };
+    } finally {
+        console.log("完成");
+    }
+}
+
+/**
+ * 显示使用帮助
+ */
+function showHelp() {
+    console.log(`
+爬虫程序使用说明:
+----------------
+用法: node crawler_yinsha.js [小说标题] [选项]
+
+参数:
+  小说标题            要爬取的小说标题，默认为 "Hidden-Assassin"
+
+选项:
+  --debug            开启调试模式，保存HTML内容并打印详细信息
+  --output=<目录>     指定输出目录，默认为 src/web_crawler
+  --content          爬取章节内容（默认只爬取目录）
+
+  --help             显示此帮助信息
+
+示例:
+  node crawler_yinsha.js "My-Novel-Title"
+  node crawler_yinsha.js "Another-Novel" --debug
+  node crawler_yinsha.js "Some-Book" --output=./output
+  node crawler_yinsha.js "Hidden-Assassin" --content
+  node crawler_yinsha.js "Hidden-Assassin" --content
+`);
+}
+
+/**
+ * 命令行入口
+ */
+let order=3;
+if (order==1) {
+    // 从命令行参数获取小说标题
+    const args = process.argv.slice(2);
+    
+    // 显示帮助信息
+    if (args.includes("--help") || args.includes("-h")) {
+        showHelp();
+        process.exit(0);
+    }
+    
+    // 获取参数
+    const title = args.filter(arg => !arg.startsWith("-"))[0] || "Hidden-Assassin";
+    const debug = args.includes("--debug");
+    const outputDir = args.find(arg => arg.startsWith("--output="))?.split("=")[1] || "src/web_crawler";
+    const fetchContent = args.includes("--content");
+    
+
+    
+    console.log(`开始爬取小说: ${title}`);
+    console.log(`调试模式: ${debug ? "开启" : "关闭"}`);
+    console.log(`输出目录: ${outputDir}`);
+    console.log(`爬取章节内容: ${fetchContent ? "是" : "否"}`);
+    
+    // 确保输出目录存在
+    if (!fs.existsSync(outputDir)) {
+        fs.mkdirSync(outputDir, { recursive: true });
+    }
+    
+    runScript(title, debug, outputDir, fetchContent)
+        .then(result => {
+            if (result && result.errcode) {
+                console.error(`爬取失败: ${result.errStr}`);
+                process.exit(1);
+            } else {
+                console.log("爬取任务完成！");
+            }
+        })
+        .catch(err => {
+            console.error("程序执行出错:", err);
+            process.exit(1);
+        });
+}
+else if (order==2) {
+    let __dirname="/Users/chengjie/Documents/git/miaoguo_system_server/src/web_crawler";
+    let sourceDir = path.join(__dirname, 'Hidden-Assassin_contents');
+    let outputFile = path.join(__dirname, 'Hidden-Assassin_merged.txt');
+
+    mergeChapterFiles(sourceDir, outputFile)
+    .then(() => console.log('合并操作完成'))
+    .catch(err => console.error('合并操作失败:', err));
+}
+else if (order==3) {
+    let __dirname="/Users/chengjie/Documents/git/miaoguo_system_server/src/web_crawler";
+    let sourceDir = path.join(__dirname, 'Hidden-Assassin.txt');
+    let outputFile = path.join(__dirname, 'Hidden-Assassin.html');
+
+    await formatTextFile(sourceDir, outputFile);
+}
+
+// 导出函数，以便其他模块使用
+export default runScript;

src/web_crawler/epub_generator.js

@@ -0,0 +1,249 @@
+import fs from 'fs';
+import path from 'path';
+import JSZip from 'jszip';
+import { v4 as uuidv4 } from 'uuid';
+import { JSDOM } from 'jsdom';
+import { fileURLToPath } from 'url';
+
+// 获取当前文件的目录路径
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = path.dirname(__filename);
+
+/**
+ * 生成 EPUB 电子书
+ * @param {string} contentFilePath - HTML 格式的正文文件路径
+ * @param {string} coverImagePath - 封面图片路径
+ * @param {string} outputPath - 输出 EPUB 文件路径
+ * @param {string} bookTitle - 电子书标题
+ * @param {string} author - 作者名称
+ * @returns {Promise<void>}
+ */
+async function generateEpub(contentFilePath, coverImagePath, outputPath, bookTitle, author) {
+    try {
+        // 读取 HTML 内容
+        const htmlContent = fs.readFileSync(contentFilePath, 'utf-8');
+        const dom = new JSDOM(htmlContent);
+        const document = dom.window.document;
+        
+        // 提取章节 (h2 标签)
+        const chapterElements = document.querySelectorAll('h2');
+        const chapters = [];
+        
+        // 处理每个章节
+        chapterElements.forEach((chapterElement, index) => {
+            const title = chapterElement.textContent.trim();
+            let content = '';
+            
+            // 收集当前章节的所有段落，直到下一个 h2 或文档结束
+            let currentElement = chapterElement.nextElementSibling;
+            while (currentElement && currentElement.tagName.toLowerCase() !== 'h2') {
+                if (currentElement.tagName.toLowerCase() === 'p') {
+                    // 每个 p 标签作为独立段落，用 <p> 标签包裹并添加样式类
+                    content += `<p class="calibre2">${currentElement.innerHTML}</p>\n`;
+                }
+                currentElement = currentElement.nextElementSibling;
+            }
+            
+            chapters.push({ title, content });
+        });
+
+        // 读取封面图片
+        const coverImage = fs.readFileSync(coverImagePath);
+
+        // 创建 EPUB 容器
+        const zip = new JSZip();
+
+        // 添加 mimetype 文件（必须是第一个文件，且不压缩）
+        zip.file('mimetype', 'application/epub+zip', { compression: 'STORE' });
+
+        // 创建 META-INF 目录
+        const metaInf = zip.folder('META-INF');
+        metaInf.file('container.xml', `<?xml version="1.0"?>
+<container version="1.0" xmlns="urn:oasis:names:tc:opendocument:xmlns:container">
+    <rootfiles>
+        <rootfile full-path="OEBPS/content.opf" media-type="application/oebps-package+xml"/>
+    </rootfiles>
+</container>`);
+
+        // 创建 OEBPS 目录
+        const oebps = zip.folder('OEBPS');
+
+        // 添加封面图片
+        oebps.file('Images/cover.jpg', coverImage);
+
+        // 生成封面页 XHTML
+        const coverXhtml = `<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml">
+<head>
+    <title>封面</title>
+    <meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>
+    <style type="text/css">
+        body {
+            margin: 0;
+            padding: 0;
+            text-align: center;
+        }
+        img {
+            max-width: 100%;
+            height: auto;
+            margin: 0;
+            padding: 0;
+        }
+    </style>
+</head>
+<body>
+    <div>
+        <img src="../Images/cover.jpg" alt="封面"/>
+    </div>
+</body>
+</html>`;
+
+        const textFolder = oebps.folder('Text');
+        textFolder.file('cover.xhtml', coverXhtml);
+
+        // 生成章节 HTML 文件
+        const spineItems = [];
+        const manifestItems = [
+            { id: 'cover', href: 'Text/cover.xhtml', mediaType: 'application/xhtml+xml' },
+            { id: 'cover-image', href: 'Images/cover.jpg', mediaType: 'image/jpeg' },
+            { id: 'ncx', href: 'toc.ncx', mediaType: 'application/x-dtbncx+xml' }
+        ];
+
+        chapters.forEach((chapter, index) => {
+            const { title, content } = chapter;
+            const chapterId = `chapter_${index}`;
+            const chapterFileName = `${chapterId}.xhtml`;
+
+            const chapterHtml = `<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml">
+<head>
+    <title>${title}</title>
+    <meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>
+</head>
+<body>
+    <h1>${title}</h1>
+    <div>
+        ${content}
+    </div>
+</body>
+</html>`;
+
+            textFolder.file(chapterFileName, chapterHtml);
+            manifestItems.push({ id: chapterId, href: `Text/${chapterFileName}`, mediaType: 'application/xhtml+xml' });
+            spineItems.push({ idref: chapterId });
+        });
+
+        // 生成目录文件
+        const tocHtml = `<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml">
+<head>
+    <title>目录</title>
+    <meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>
+</head>
+<body>
+    <h1>目录</h1>
+    <ol>
+        ${chapters.map((chapter, index) => {
+            return `<li><a href="chapter_${index}.xhtml">${chapter.title}</a></li>`;
+        }).join('\n')}
+    </ol>
+</body>
+</html>`;
+
+        textFolder.file('toc.xhtml', tocHtml);
+        manifestItems.push({ id: 'toc', href: 'Text/toc.xhtml', mediaType: 'application/xhtml+xml' });
+
+        // 添加 CSS 文件
+        const cssFolder = oebps.folder('Styles');
+        const cssContent = fs.readFileSync(path.join(__dirname, 'epub_styles.css'), 'utf-8');
+        cssFolder.file('stylesheet.css', cssContent);
+        manifestItems.push({ id: 'stylesheet', href: 'Styles/stylesheet.css', mediaType: 'text/css' });
+
+        // 生成唯一标识符
+        const bookUUID = uuidv4();
+        
+        // 生成 toc.ncx 文件
+        const tocNcx = `<?xml version='1.0' encoding='utf-8'?>
+<ncx xmlns="http://www.daisy.org/z3986/2005/ncx/" version="2005-1" xml:lang="zh-CN">
+  <head>
+    <meta content="${bookUUID}" name="dtb:uid"/>
+    <meta content="2" name="dtb:depth"/>
+    <meta content="0" name="dtb:totalPageCount"/>
+    <meta content="0" name="dtb:maxPageNumber"/>
+  </head>
+  <docTitle>
+    <text>${bookTitle}</text>
+  </docTitle>
+  <navMap>
+    <navPoint id="navpoint-0" playOrder="0">
+      <navLabel>
+        <text>封面</text>
+      </navLabel>
+      <content src="Text/cover.xhtml"/>
+    </navPoint>
+    <navPoint id="navpoint-1" playOrder="1">
+      <navLabel>
+        <text>目录</text>
+      </navLabel>
+      <content src="Text/toc.xhtml"/>
+    </navPoint>
+    ${chapters.map((chapter, index) => {
+        return `<navPoint id="navpoint-${index + 2}" playOrder="${index + 2}">
+      <navLabel>
+        <text>${chapter.title}</text>
+      </navLabel>
+      <content src="Text/chapter_${index}.xhtml"/>
+    </navPoint>`;
+    }).join('\n')}
+  </navMap>
+</ncx>`;
+
+        oebps.file('toc.ncx', tocNcx);
+
+        // 生成 content.opf 文件
+        const contentOpf = `<?xml version="1.0" encoding="UTF-8"?>
+<package xmlns="http://www.idpf.org/2007/opf" version="2.0" unique-identifier="uuid_id">
+    <metadata xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:opf="http://www.idpf.org/2007/opf">
+        <dc:identifier id="uuid_id">urn:uuid:${bookUUID}</dc:identifier>
+        <dc:title>${bookTitle}</dc:title>
+        <dc:creator>${author}</dc:creator>
+        <dc:language>zh-CN</dc:language>
+        <dc:date>${new Date().toISOString().split('T')[0]}</dc:date>
+        <meta name="cover" content="cover-image"/>
+    </metadata>
+    <manifest>
+        ${manifestItems.map(item => `<item id="${item.id}" href="${item.href}" media-type="${item.mediaType}"/>`).join('\n')}
+    </manifest>
+    <spine toc="ncx">
+        <itemref idref="cover"/>
+        <itemref idref="toc"/>
+        ${spineItems.map(item => `<itemref idref="${item.idref}"/>`).join('\n')}
+    </spine>
+    <guide>
+        <reference type="cover" title="封面" href="Text/cover.xhtml"/>
+    </guide>
+</package>`;
+
+        oebps.file('content.opf', contentOpf);
+
+        // 生成 EPUB 文件
+        const epubContent = await zip.generateAsync({ 
+            type: 'nodebuffer', 
+            compression: 'DEFLATE',
+            mimeType: 'application/epub+zip'
+        });
+        fs.writeFileSync(outputPath, epubContent);
+
+        console.log(`EPUB 电子书已生成: ${outputPath}`);
+    } catch (error) {
+        console.error('生成 EPUB 电子书时出错:', error);
+    }
+}
+
+// 示例用法
+generateEpub(__dirname+'/Hidden-Assassin.html', __dirname+'/cover.jpeg', 'Hidden-Assassin.epub', 'Hidden-Assassin', 'Angry Banana');
+
+export { generateEpub };

src/web_crawler/epub_styles.css

@@ -0,0 +1,32 @@
+.calibre {
+    display: block;
+    font-size: 1em;
+    padding-left: 0;
+    padding-right: 0;
+    margin: 0 5pt
+}
+
+.calibre1 {
+    display: block;
+    font-size: 1.5em;
+    font-weight: bold;
+    line-height: 1.2;
+    margin: 0.83em 0
+}
+
+.calibre2 {
+    display: block;
+    font-size: 1em;
+    font-weight: normal;
+    line-height: 1.5;
+    margin: 1em 0
+}
+
+.calibre3 {
+    display: block
+}
+
+@page {
+    margin-bottom: 5pt;
+    margin-top: 5pt
+}