|
|
@@ -1,769 +0,0 @@
|
|
1
|
|
-import fs from 'fs';
|
|
2
|
|
-import axios from 'axios';
|
|
3
|
|
-import * as cheerio from 'cheerio';
|
|
4
|
|
-import path from 'path';
|
|
5
|
|
-import { setTimeout } from 'timers/promises';
|
|
6
|
|
-import { fileURLToPath } from 'url';
|
|
7
|
|
-import JSZip from 'jszip';
|
|
8
|
|
-import { v4 as uuidv4 } from 'uuid';
|
|
9
|
|
-import { JSDOM } from 'jsdom';
|
|
10
|
|
-
|
|
11
|
|
-const __filename = fileURLToPath(import.meta.url);
|
|
12
|
|
-const __dirname = path.dirname(__filename);
|
|
13
|
|
-
|
|
14
|
|
-/**
|
|
15
|
|
- * 格式化章节内容
|
|
16
|
|
- * @param {string} content - 原始文本内容
|
|
17
|
|
- * @returns {string} - 格式化后的HTML内容
|
|
18
|
|
- */
|
|
19
|
|
-async function formatChapterContent(content) {
|
|
20
|
|
- // 将章节标题替换为<h2>
|
|
21
|
|
- content = content.replace(/Chapter \d+/g, match => `<h2>${match}</h2>`);
|
|
22
|
|
-
|
|
23
|
|
- // 将正文段落用<p>包裹
|
|
24
|
|
- content = content.replace(/\n\n/g, '</p><p>');
|
|
25
|
|
- content = `<p>${content}</p>`;
|
|
26
|
|
-
|
|
27
|
|
- return content;
|
|
28
|
|
-}
|
|
29
|
|
-
|
|
30
|
|
-/**
|
|
31
|
|
- * 处理文本文件，为章节标题添加h2标签，为段落添加p标签
|
|
32
|
|
- * @param {string} filePath - 文本文件路径
|
|
33
|
|
- * @param {string} outputPath - 输出文件路径
|
|
34
|
|
- * @returns {Promise<void>}
|
|
35
|
|
- */
|
|
36
|
|
-async function formatTextFile(filePath, outputPath) {
|
|
37
|
|
- try {
|
|
38
|
|
- // 读取文本文件
|
|
39
|
|
- const content = await fs.promises.readFile(filePath, 'utf-8');
|
|
40
|
|
- console.log(`已读取文件: ${filePath}`);
|
|
41
|
|
-
|
|
42
|
|
- // 分割成章节
|
|
43
|
|
- const chapters = content.split(/Chapter \d+/).filter(Boolean);
|
|
44
|
|
- console.log(`检测到 ${chapters.length} 个章节内容块`);
|
|
45
|
|
-
|
|
46
|
|
- let formattedContent = '';
|
|
47
|
|
- let chapterIndex = 1;
|
|
48
|
|
-
|
|
49
|
|
- // 处理每个章节
|
|
50
|
|
- for (const chapter of chapters) {
|
|
51
|
|
- // 添加章节标题
|
|
52
|
|
- formattedContent += `<h2>Chapter ${chapterIndex}</h2>\n`;
|
|
53
|
|
-
|
|
54
|
|
- // 处理章节内容，将段落用<p>标签包裹
|
|
55
|
|
- const paragraphs = chapter.trim().split(/\n\s*\n/);
|
|
56
|
|
- for (const paragraph of paragraphs) {
|
|
57
|
|
- if (paragraph.trim()) {
|
|
58
|
|
- formattedContent += `<p>${paragraph.trim()}</p>\n`;
|
|
59
|
|
- }
|
|
60
|
|
- }
|
|
61
|
|
-
|
|
62
|
|
- chapterIndex++;
|
|
63
|
|
- }
|
|
64
|
|
-
|
|
65
|
|
- // 写入输出文件
|
|
66
|
|
- await fs.promises.writeFile(outputPath, formattedContent);
|
|
67
|
|
- console.log(`格式化完成! 结果已保存到: ${outputPath}`);
|
|
68
|
|
- console.log(`共处理了 ${chapters.length} 个章节`);
|
|
69
|
|
-
|
|
70
|
|
- } catch (error) {
|
|
71
|
|
- console.error('处理文本文件时出错:', error);
|
|
72
|
|
- }
|
|
73
|
|
-}
|
|
74
|
|
-
|
|
75
|
|
-async function mergeChapterFiles(sourceDir, outputFile) {
|
|
76
|
|
- try {
|
|
77
|
|
- const SEPARATOR = '\n******************\n';
|
|
78
|
|
- const { readdir, readFile, writeFile } = fs.promises;
|
|
79
|
|
-
|
|
80
|
|
- // 获取所有HTML文件并按章节顺序排序
|
|
81
|
|
- const files = (await readdir(sourceDir))
|
|
82
|
|
- .filter(file => file.endsWith('.html'))
|
|
83
|
|
- .sort((a, b) => parseInt(a.split('_')[0]) - parseInt(b.split('_')[0]));
|
|
84
|
|
-
|
|
85
|
|
- if (files.length === 0) {
|
|
86
|
|
- console.error('未找到任何章节文件');
|
|
87
|
|
- return;
|
|
88
|
|
- }
|
|
89
|
|
-
|
|
90
|
|
- let mergedContent = '';
|
|
91
|
|
-
|
|
92
|
|
- // 处理每个章节文件
|
|
93
|
|
- for (const file of files) {
|
|
94
|
|
- const filePath = path.join(sourceDir, file);
|
|
95
|
|
- const html = await readFile(filePath, 'utf-8');
|
|
96
|
|
-
|
|
97
|
|
- // 提取章节标题
|
|
98
|
|
- const titleMatch = file.match(/_([^\.]+)\.html$/);
|
|
99
|
|
- const title = titleMatch ? titleMatch[1] : file;
|
|
100
|
|
-
|
|
101
|
|
- // 提取正文内容
|
|
102
|
|
- const contentMatch = html.match(/<div id="showReading"[^>]*>([\s\S]*?)<\/div>/);
|
|
103
|
|
- if (!contentMatch) continue;
|
|
104
|
|
-
|
|
105
|
|
- let content = contentMatch[1]
|
|
106
|
|
- .replace(/<sent[^>]*>/g, '')
|
|
107
|
|
- .replace(/<\/sent>/g, '')
|
|
108
|
|
- .replace(/<br>/g, '\n')
|
|
109
|
|
- .replace(/<[^>]+>/g, '')
|
|
110
|
|
- .replace(/\(adsbygoogle\s*=\s*window\.adsbygoogle\s*\|\|\s*\[\]\).push\(\{\}\);/g, '')
|
|
111
|
|
- .replace(/\n{3,}/g, '\n\n');
|
|
112
|
|
-
|
|
113
|
|
- // 添加到合并内容
|
|
114
|
|
- mergedContent += `${title}\n\n${content.trim()}${SEPARATOR}`;
|
|
115
|
|
- console.log(`已处理: ${file}`);
|
|
116
|
|
- }
|
|
117
|
|
-
|
|
118
|
|
- // 格式化合并后的内容
|
|
119
|
|
- const formattedContent = mergedContent;
|
|
120
|
|
-
|
|
121
|
|
- // 写入合并文件
|
|
122
|
|
- await writeFile(outputFile, formattedContent);
|
|
123
|
|
- console.log(`\n合并完成! 结果已保存到: ${outputFile}`);
|
|
124
|
|
- console.log(`共合并了 ${files.length} 个章节`);
|
|
125
|
|
-
|
|
126
|
|
- } catch (error) {
|
|
127
|
|
- console.error('合并章节时出错:', error);
|
|
128
|
|
- }
|
|
129
|
|
-}
|
|
130
|
|
-
|
|
131
|
|
-/**
|
|
132
|
|
- * 爬取单个章节内容
|
|
133
|
|
- * @param {string} baseUrl - 网站基础URL
|
|
134
|
|
- * @param {string} chapterUrl - 章节URL
|
|
135
|
|
- * @param {object} headers - 请求头
|
|
136
|
|
- * @param {boolean} debug - 是否开启调试模式
|
|
137
|
|
- * @returns {Promise<string|null>} - 章节内容或null
|
|
138
|
|
- */
|
|
139
|
|
-async function fetchChapterContent(baseUrl, chapterUrl, headers, debug = false) {
|
|
140
|
|
- try {
|
|
141
|
|
- // 如果URL不是以http开头，则添加baseUrl
|
|
142
|
|
- const fullUrl = chapterUrl.startsWith('http') ? chapterUrl : `${baseUrl}${chapterUrl}`;
|
|
143
|
|
-
|
|
144
|
|
- if (debug) {
|
|
145
|
|
- console.log(`爬取章节内容: ${fullUrl}`);
|
|
146
|
|
- }
|
|
147
|
|
-
|
|
148
|
|
- const response = await axios.get(fullUrl, { headers });
|
|
149
|
|
-
|
|
150
|
|
- if (response.status !== 200) {
|
|
151
|
|
- console.error(`获取章节内容失败，状态码: ${response.status}`);
|
|
152
|
|
- return null;
|
|
153
|
|
- }
|
|
154
|
|
-
|
|
155
|
|
- const $ = cheerio.load(response.data);
|
|
156
|
|
-
|
|
157
|
|
- // 尝试多种选择器来获取章节内容
|
|
158
|
|
- const contentSelectors = [
|
|
159
|
|
- '.chapter-content',
|
|
160
|
|
- '.article-content',
|
|
161
|
|
- '.content',
|
|
162
|
|
- '#content',
|
|
163
|
|
- '.text-content',
|
|
164
|
|
- '.chapter-text',
|
|
165
|
|
- '.novel-content'
|
|
166
|
|
- ];
|
|
167
|
|
-
|
|
168
|
|
- let content = null;
|
|
169
|
|
-
|
|
170
|
|
- for (const selector of contentSelectors) {
|
|
171
|
|
- const element = $(selector);
|
|
172
|
|
- if (element.length > 0) {
|
|
173
|
|
- content = element.html();
|
|
174
|
|
- if (debug) {
|
|
175
|
|
- console.log(`使用选择器 ${selector} 成功获取章节内容`);
|
|
176
|
|
- }
|
|
177
|
|
- break;
|
|
178
|
|
- }
|
|
179
|
|
- }
|
|
180
|
|
-
|
|
181
|
|
- // 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
|
|
182
|
|
- if (!content) {
|
|
183
|
|
- let maxTextLength = 0;
|
|
184
|
|
- let maxTextElement = null;
|
|
185
|
|
-
|
|
186
|
|
- $('div, article, section, p').each((_, element) => {
|
|
187
|
|
- const text = $(element).text().trim();
|
|
188
|
|
- if (text.length > maxTextLength && text.length > 500) {
|
|
189
|
|
- maxTextLength = text.length;
|
|
190
|
|
- maxTextElement = element;
|
|
191
|
|
- }
|
|
192
|
|
- });
|
|
193
|
|
-
|
|
194
|
|
- if (maxTextElement) {
|
|
195
|
|
- content = $(maxTextElement).html();
|
|
196
|
|
- if (debug) {
|
|
197
|
|
- console.log(`使用最长文本元素获取章节内容，长度: ${maxTextLength}`);
|
|
198
|
|
- }
|
|
199
|
|
- }
|
|
200
|
|
- }
|
|
201
|
|
-
|
|
202
|
|
- return content;
|
|
203
|
|
- } catch (error) {
|
|
204
|
|
- console.error(`爬取章节内容出错: ${error.message}`);
|
|
205
|
|
- return null;
|
|
206
|
|
- }
|
|
207
|
|
-}
|
|
208
|
|
-
|
|
209
|
|
-/**
|
|
210
|
|
- * 爬取小说章节目录
|
|
211
|
|
- * @param {string} title - 小说标题
|
|
212
|
|
- * @param {boolean} debug - 是否开启调试模式
|
|
213
|
|
- * @param {string} outputDir - 输出目录
|
|
214
|
|
- * @param {boolean} fetchContent - 是否爬取章节内容
|
|
215
|
|
- * @returns {Promise<Array|Object>} - 章节目录数组或错误对象
|
|
216
|
|
- */
|
|
217
|
|
-async function runScript(title, debug = false, outputDir = 'src/web_crawler', fetchContent = false){
|
|
218
|
|
- const url = `https://novelhi.com/s/index/`+title;
|
|
219
|
|
- console.log(`正在爬取网址: ${url}`);
|
|
220
|
|
-
|
|
221
|
|
- try {
|
|
222
|
|
- // 设置请求头，模拟浏览器行为
|
|
223
|
|
- const headers = {
|
|
224
|
|
- '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',
|
|
225
|
|
- 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
|
|
226
|
|
- 'Accept-Language': 'en-US,en;q=0.5',
|
|
227
|
|
- 'Connection': 'keep-alive',
|
|
228
|
|
- 'Upgrade-Insecure-Requests': '1',
|
|
229
|
|
- 'Cache-Control': 'max-age=0'
|
|
230
|
|
- };
|
|
231
|
|
-
|
|
232
|
|
- const response = await axios.get(url, { headers });
|
|
233
|
|
- console.log(`请求状态码: ${response.status}`);
|
|
234
|
|
-
|
|
235
|
|
- // 如果开启调试模式，保存HTML内容
|
|
236
|
|
- if (debug) {
|
|
237
|
|
- const debugFilePath = path.join(outputDir, 'debug_page.html');
|
|
238
|
|
- fs.writeFileSync(debugFilePath, response.data);
|
|
239
|
|
- console.log(`已保存HTML内容到 ${debugFilePath} 文件`);
|
|
240
|
|
- }
|
|
241
|
|
-
|
|
242
|
|
- const $ = cheerio.load(response.data);
|
|
243
|
|
-
|
|
244
|
|
- // 提取章节目录
|
|
245
|
|
- const chapters = [];
|
|
246
|
|
-
|
|
247
|
|
- // 如果开启调试模式，打印页面结构信息
|
|
248
|
|
- if (debug) {
|
|
249
|
|
- console.log('页面标题:', $('title').text());
|
|
250
|
|
- console.log('页面主要容器数量:');
|
|
251
|
|
- console.log('- div 元素数量:', $('div').length);
|
|
252
|
|
- console.log('- ul 元素数量:', $('ul').length);
|
|
253
|
|
- console.log('- li 元素数量:', $('li').length);
|
|
254
|
|
- console.log('- a 元素数量:', $('a').length);
|
|
255
|
|
- }
|
|
256
|
|
-
|
|
257
|
|
- // 尝试多种选择器
|
|
258
|
|
- const selectors = [
|
|
259
|
|
- '.chapter-list li',
|
|
260
|
|
- '.book-catalog-list a',
|
|
261
|
|
- '.catalog-list li',
|
|
262
|
|
- '.chapter-item',
|
|
263
|
|
- '.chapter a',
|
|
264
|
|
- 'ul.chapters li',
|
|
265
|
|
- '.book-chapters a',
|
|
266
|
|
- '.novel-chapters a',
|
|
267
|
|
- 'span:contains("Chapter")'
|
|
268
|
|
- ];
|
|
269
|
|
-
|
|
270
|
|
- for (const selector of selectors) {
|
|
271
|
|
- console.log(`尝试选择器: ${selector}`);
|
|
272
|
|
- const elements = $(selector);
|
|
273
|
|
- console.log(`找到 ${elements.length} 个元素`);
|
|
274
|
|
-
|
|
275
|
|
- if (elements.length > 0) {
|
|
276
|
|
- elements.each((index, element) => {
|
|
277
|
|
- let chapterTitle, chapterUrl;
|
|
278
|
|
-
|
|
279
|
|
- if (selector === 'span:contains("Chapter")') {
|
|
280
|
|
- chapterTitle = $(element).text().trim();
|
|
281
|
|
- // 对于这个网站，我们可能需要构造章节URL
|
|
282
|
|
- chapterUrl = `/s/${title}/${chapterTitle.replace('Chapter ', '')}`;
|
|
283
|
|
- } else if (selector.includes('a')) {
|
|
284
|
|
- chapterTitle = $(element).text().trim();
|
|
285
|
|
- chapterUrl = $(element).attr('href');
|
|
286
|
|
- } else {
|
|
287
|
|
- chapterTitle = $(element).find('a').text().trim();
|
|
288
|
|
- chapterUrl = $(element).find('a').attr('href');
|
|
289
|
|
- }
|
|
290
|
|
-
|
|
291
|
|
- if (chapterTitle) {
|
|
292
|
|
- chapters.push({
|
|
293
|
|
- title: chapterTitle,
|
|
294
|
|
- url: chapterUrl || '#',
|
|
295
|
|
- index: index + 1
|
|
296
|
|
- });
|
|
297
|
|
- }
|
|
298
|
|
- });
|
|
299
|
|
-
|
|
300
|
|
- if (chapters.length > 0) {
|
|
301
|
|
- console.log(`使用选择器 ${selector} 成功找到章节`);
|
|
302
|
|
- break;
|
|
303
|
|
- }
|
|
304
|
|
- }
|
|
305
|
|
- }
|
|
306
|
|
-
|
|
307
|
|
- // 如果上面的选择器都没有找到章节，尝试更通用的方法
|
|
308
|
|
- if (chapters.length === 0) {
|
|
309
|
|
- console.log('尝试查找所有可能的章节链接...');
|
|
310
|
|
-
|
|
311
|
|
- // 查找所有包含"chapter"或"第"字样的链接或文本
|
|
312
|
|
- $('*').each((index, element) => {
|
|
313
|
|
- const text = $(element).text().trim();
|
|
314
|
|
-
|
|
315
|
|
- if (text && (text.includes('Chapter') || text.includes('第') || text.includes('章'))) {
|
|
316
|
|
- // 检查是否是单独的章节标题（不包含其他章节）
|
|
317
|
|
- if (text.match(/^Chapter \d+$/) || text.match(/^第[一二三四五六七八九十百千万]+章/) || text.match(/^\d+\.\s+.+$/)) {
|
|
318
|
|
- chapters.push({
|
|
319
|
|
- title: text,
|
|
320
|
|
- url: '#', // 如果没有URL，使用占位符
|
|
321
|
|
- index: index + 1
|
|
322
|
|
- });
|
|
323
|
|
- }
|
|
324
|
|
- }
|
|
325
|
|
- });
|
|
326
|
|
- }
|
|
327
|
|
-
|
|
328
|
|
- console.log(`共找到 ${chapters.length} 个章节`);
|
|
329
|
|
-
|
|
330
|
|
- // 将结果保存到文件中
|
|
331
|
|
- const outputFilePath = path.join(outputDir, `${title}_chapters.json`);
|
|
332
|
|
- fs.writeFileSync(outputFilePath, JSON.stringify(chapters, null, 2));
|
|
333
|
|
- console.log(`已将章节目录保存到 ${outputFilePath} 文件`);
|
|
334
|
|
-
|
|
335
|
|
- // 打印前10个章节和后10个章节
|
|
336
|
|
- if (debug || chapters.length <= 20) {
|
|
337
|
|
- console.log("章节目录:");
|
|
338
|
|
- console.log(JSON.stringify(chapters, null, 2));
|
|
339
|
|
- } else {
|
|
340
|
|
- console.log("前10个章节:");
|
|
341
|
|
- console.log(JSON.stringify(chapters.slice(0, 10), null, 2));
|
|
342
|
|
-
|
|
343
|
|
- console.log("...");
|
|
344
|
|
-
|
|
345
|
|
- console.log("后10个章节:");
|
|
346
|
|
- console.log(JSON.stringify(chapters.slice(-10), null, 2));
|
|
347
|
|
- }
|
|
348
|
|
-
|
|
349
|
|
- // 如果需要爬取章节内容
|
|
350
|
|
- if (fetchContent && chapters.length > 0) {
|
|
351
|
|
- console.log(`开始爬取章节内容...`);
|
|
352
|
|
-
|
|
353
|
|
- // 创建章节内容目录
|
|
354
|
|
- const contentDir = path.join(outputDir, `${title}_contents`);
|
|
355
|
|
- if (!fs.existsSync(contentDir)) {
|
|
356
|
|
- fs.mkdirSync(contentDir, { recursive: true });
|
|
357
|
|
- }
|
|
358
|
|
-
|
|
359
|
|
- // 创建一个包含所有章节内容的对象
|
|
360
|
|
- const contentsObj = {};
|
|
361
|
|
-
|
|
362
|
|
- // 设置基础URL
|
|
363
|
|
- const baseUrl = 'https://novelhi.com';
|
|
364
|
|
-
|
|
365
|
|
- // 爬取所有章节
|
|
366
|
|
- const chaptersToFetch = chapters;
|
|
367
|
|
- console.log(`将爬取 ${chaptersToFetch.length}/${chapters.length} 个章节的内容`);
|
|
368
|
|
-
|
|
369
|
|
- // 爬取章节内容
|
|
370
|
|
- for (let i = 0; i < chaptersToFetch.length; i++) {
|
|
371
|
|
- const chapter = chaptersToFetch[i];
|
|
372
|
|
-
|
|
373
|
|
- // 每爬取10个章节，暂停一下，避免请求过于频繁
|
|
374
|
|
- if (i > 0 && i % 10 === 0) {
|
|
375
|
|
- console.log(`已爬取 ${i}/${chaptersToFetch.length} 章节，暂停 2 秒...`);
|
|
376
|
|
- await setTimeout(2000);
|
|
377
|
|
- }
|
|
378
|
|
-
|
|
379
|
|
- // 爬取章节内容
|
|
380
|
|
- const content = await fetchChapterContent(baseUrl, chapter.url, headers, debug);
|
|
381
|
|
-
|
|
382
|
|
- if (content) {
|
|
383
|
|
- // 更新章节对象，添加内容
|
|
384
|
|
- chapters[i].content = content;
|
|
385
|
|
- contentsObj[chapter.title] = content;
|
|
386
|
|
-
|
|
387
|
|
- // 将章节内容保存到单独的文件
|
|
388
|
|
- const chapterFileName = `${String(chapter.index).padStart(4, '0')}_${chapter.title.replace(/[\\/:*?"<>|]/g, '_')}.html`;
|
|
389
|
|
- const chapterFilePath = path.join(contentDir, chapterFileName);
|
|
390
|
|
-
|
|
391
|
|
- // 创建一个完整的HTML文件
|
|
392
|
|
- const htmlContent = `<!DOCTYPE html>
|
|
393
|
|
-<html>
|
|
394
|
|
-<head>
|
|
395
|
|
- <meta charset="UTF-8">
|
|
396
|
|
- <title>${chapter.title}</title>
|
|
397
|
|
- <style>
|
|
398
|
|
- body {
|
|
399
|
|
- font-family: Arial, sans-serif;
|
|
400
|
|
- line-height: 1.6;
|
|
401
|
|
- margin: 0 auto;
|
|
402
|
|
- max-width: 800px;
|
|
403
|
|
- padding: 20px;
|
|
404
|
|
- }
|
|
405
|
|
- h1 {
|
|
406
|
|
- text-align: center;
|
|
407
|
|
- margin-bottom: 30px;
|
|
408
|
|
- }
|
|
409
|
|
- p {
|
|
410
|
|
- text-indent: 2em;
|
|
411
|
|
- margin-bottom: 1em;
|
|
412
|
|
- }
|
|
413
|
|
- </style>
|
|
414
|
|
-</head>
|
|
415
|
|
-<body>
|
|
416
|
|
- <h1>${chapter.title}</h1>
|
|
417
|
|
- ${content}
|
|
418
|
|
-</body>
|
|
419
|
|
-</html>`;
|
|
420
|
|
-
|
|
421
|
|
- fs.writeFileSync(chapterFilePath, htmlContent);
|
|
422
|
|
-
|
|
423
|
|
- if (debug) {
|
|
424
|
|
- console.log(`已保存章节 ${chapter.title} 到 ${chapterFilePath}`);
|
|
425
|
|
- } else if (i % 10 === 0 || i === chapters.length - 1) {
|
|
426
|
|
- console.log(`已保存 ${i + 1}/${chapters.length} 章节`);
|
|
427
|
|
- }
|
|
428
|
|
- } else {
|
|
429
|
|
- console.error(`获取章节 ${chapter.title} 内容失败`);
|
|
430
|
|
- }
|
|
431
|
|
- }
|
|
432
|
|
-
|
|
433
|
|
- // 保存所有章节内容到一个文件
|
|
434
|
|
- const allContentsPath = path.join(outputDir, `${title}_all_contents.json`);
|
|
435
|
|
- fs.writeFileSync(allContentsPath, JSON.stringify(contentsObj, null, 2));
|
|
436
|
|
- console.log(`已将所有章节内容保存到 ${allContentsPath} 文件`);
|
|
437
|
|
-
|
|
438
|
|
- // 更新章节目录文件，包含内容
|
|
439
|
|
- const chaptersWithContentPath = path.join(outputDir, `${title}_chapters_with_content.json`);
|
|
440
|
|
- fs.writeFileSync(chaptersWithContentPath, JSON.stringify(chapters, null, 2));
|
|
441
|
|
- console.log(`已将包含内容的章节目录保存到 ${chaptersWithContentPath} 文件`);
|
|
442
|
|
- }
|
|
443
|
|
-
|
|
444
|
|
- return chapters;
|
|
445
|
|
- } catch (err) {
|
|
446
|
|
- console.error("爬取过程中出错:", err.message);
|
|
447
|
|
- return { errcode: 101, errStr: err.message };
|
|
448
|
|
- } finally {
|
|
449
|
|
- console.log("完成");
|
|
450
|
|
- }
|
|
451
|
|
-}
|
|
452
|
|
-
|
|
453
|
|
-/**
|
|
454
|
|
- * 生成 EPUB 电子书
|
|
455
|
|
- * @param {string} contentFilePath - HTML 格式的正文文件路径
|
|
456
|
|
- * @param {string} coverImagePath - 封面图片路径
|
|
457
|
|
- * @param {string} outputPath - 输出 EPUB 文件路径
|
|
458
|
|
- * @param {string} bookTitle - 电子书标题
|
|
459
|
|
- * @param {string} author - 作者名称
|
|
460
|
|
- * @returns {Promise<void>}
|
|
461
|
|
- */
|
|
462
|
|
-async function generateEpub(contentFilePath, coverImagePath, outputPath, bookTitle, author) {
|
|
463
|
|
- try {
|
|
464
|
|
- // 读取 HTML 内容
|
|
465
|
|
- const htmlContent = fs.readFileSync(contentFilePath, 'utf-8');
|
|
466
|
|
- const dom = new JSDOM(htmlContent);
|
|
467
|
|
- const document = dom.window.document;
|
|
468
|
|
-
|
|
469
|
|
- // 提取章节 (h2 标签)
|
|
470
|
|
- const chapterElements = document.querySelectorAll('h2');
|
|
471
|
|
- const chapters = [];
|
|
472
|
|
-
|
|
473
|
|
- // 处理每个章节
|
|
474
|
|
- chapterElements.forEach((chapterElement, index) => {
|
|
475
|
|
- const title = chapterElement.textContent.trim();
|
|
476
|
|
- let content = '';
|
|
477
|
|
-
|
|
478
|
|
- // 收集当前章节的所有段落，直到下一个 h2 或文档结束
|
|
479
|
|
- let currentElement = chapterElement.nextElementSibling;
|
|
480
|
|
- while (currentElement && currentElement.tagName.toLowerCase() !== 'h2') {
|
|
481
|
|
- if (currentElement.tagName.toLowerCase() === 'p') {
|
|
482
|
|
- // 每个 p 标签作为独立段落，用 <p> 标签包裹并添加样式类
|
|
483
|
|
- content += `<p>${currentElement.innerHTML}</p>\n`;
|
|
484
|
|
- }
|
|
485
|
|
- currentElement = currentElement.nextElementSibling;
|
|
486
|
|
- }
|
|
487
|
|
-
|
|
488
|
|
- chapters.push({ title, content });
|
|
489
|
|
- });
|
|
490
|
|
-
|
|
491
|
|
- // 读取封面图片
|
|
492
|
|
- const coverImage = fs.readFileSync(coverImagePath);
|
|
493
|
|
-
|
|
494
|
|
- // 创建 EPUB 容器
|
|
495
|
|
- const zip = new JSZip();
|
|
496
|
|
-
|
|
497
|
|
- // 添加 mimetype 文件（必须是第一个文件，且不压缩）
|
|
498
|
|
- zip.file('mimetype', 'application/epub+zip', { compression: 'STORE' });
|
|
499
|
|
-
|
|
500
|
|
- // 创建 META-INF 目录
|
|
501
|
|
- const metaInf = zip.folder('META-INF');
|
|
502
|
|
- metaInf.file('container.xml', `<?xml version="1.0"?>
|
|
503
|
|
-<container version="1.0" xmlns="urn:oasis:names:tc:opendocument:xmlns:container">
|
|
504
|
|
- <rootfiles>
|
|
505
|
|
- <rootfile full-path="OEBPS/content.opf" media-type="application/oebps-package+xml"/>
|
|
506
|
|
- </rootfiles>
|
|
507
|
|
-</container>`);
|
|
508
|
|
-
|
|
509
|
|
- // 创建 OEBPS 目录
|
|
510
|
|
- const oebps = zip.folder('OEBPS');
|
|
511
|
|
-
|
|
512
|
|
- // 添加封面图片
|
|
513
|
|
- oebps.file('Images/cover.jpg', coverImage);
|
|
514
|
|
-
|
|
515
|
|
- // 生成封面页 XHTML
|
|
516
|
|
- const coverXhtml = `<?xml version="1.0" encoding="UTF-8"?>
|
|
517
|
|
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
|
|
518
|
|
-<html xmlns="http://www.w3.org/1999/xhtml">
|
|
519
|
|
-<head>
|
|
520
|
|
- <title>封面</title>
|
|
521
|
|
- <meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>
|
|
522
|
|
- <meta name="calibre:cover" content="true"/>
|
|
523
|
|
- <link rel="stylesheet" type="text/css" href="../Styles/stylesheet.css"/>
|
|
524
|
|
- <style type="text/css">
|
|
525
|
|
- body {
|
|
526
|
|
- margin: 0;
|
|
527
|
|
- padding: 0;
|
|
528
|
|
- text-align: center;
|
|
529
|
|
- }
|
|
530
|
|
- img {
|
|
531
|
|
- max-width: 100%;
|
|
532
|
|
- height: auto;
|
|
533
|
|
- margin: 0;
|
|
534
|
|
- padding: 0;
|
|
535
|
|
- }
|
|
536
|
|
- </style>
|
|
537
|
|
-</head>
|
|
538
|
|
-<body>
|
|
539
|
|
- <div class="cover-container">
|
|
540
|
|
- <img src="../Images/cover.jpg" alt="封面"/>
|
|
541
|
|
- </div>
|
|
542
|
|
-</body>
|
|
543
|
|
-</html>`;
|
|
544
|
|
-
|
|
545
|
|
- const textFolder = oebps.folder('Text');
|
|
546
|
|
- textFolder.file('cover.xhtml', coverXhtml);
|
|
547
|
|
-
|
|
548
|
|
- // 生成章节 HTML 文件
|
|
549
|
|
- const spineItems = [
|
|
550
|
|
- { idref: 'cover', linear: 'no' }
|
|
551
|
|
- ];
|
|
552
|
|
- const manifestItems = [
|
|
553
|
|
- { id: 'cover', href: 'Text/cover.xhtml', mediaType: 'application/xhtml+xml', properties: 'cover-image' },
|
|
554
|
|
- { id: 'cover-image', href: 'Images/cover.jpg', mediaType: 'image/jpeg' },
|
|
555
|
|
- { id: 'ncx', href: 'toc.ncx', mediaType: 'application/x-dtbncx+xml' }
|
|
556
|
|
- ];
|
|
557
|
|
-
|
|
558
|
|
- chapters.forEach((chapter, index) => {
|
|
559
|
|
- const { title, content } = chapter;
|
|
560
|
|
- const chapterId = `chapter_${index}`;
|
|
561
|
|
- const chapterFileName = `${chapterId}.xhtml`;
|
|
562
|
|
-
|
|
563
|
|
- const chapterHtml = `<?xml version="1.0" encoding="UTF-8"?>
|
|
564
|
|
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
|
|
565
|
|
-<html xmlns="http://www.w3.org/1999/xhtml">
|
|
566
|
|
-<head>
|
|
567
|
|
- <title>${title}</title>
|
|
568
|
|
- <meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>
|
|
569
|
|
- <link rel="stylesheet" type="text/css" href="../Styles/stylesheet.css"/>
|
|
570
|
|
-</head>
|
|
571
|
|
-<body>
|
|
572
|
|
- <h2 class="chapter-title">${title}</h2>
|
|
573
|
|
- <div class="chapter-content">
|
|
574
|
|
- ${content}
|
|
575
|
|
- </div>
|
|
576
|
|
-</body>
|
|
577
|
|
-</html>`;
|
|
578
|
|
-
|
|
579
|
|
- textFolder.file(chapterFileName, chapterHtml);
|
|
580
|
|
- manifestItems.push({ id: chapterId, href: `Text/${chapterFileName}`, mediaType: 'application/xhtml+xml' });
|
|
581
|
|
- spineItems.push({ idref: chapterId });
|
|
582
|
|
- });
|
|
583
|
|
-
|
|
584
|
|
- // 生成目录文件
|
|
585
|
|
- const tocHtml = `<?xml version="1.0" encoding="UTF-8"?>
|
|
586
|
|
-<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
|
|
587
|
|
-<html xmlns="http://www.w3.org/1999/xhtml">
|
|
588
|
|
-<head>
|
|
589
|
|
- <title>目录</title>
|
|
590
|
|
- <meta http-equiv="Content-Type" content="text/html; charset=utf-8"/>
|
|
591
|
|
- <link rel="stylesheet" type="text/css" href="../Styles/stylesheet.css"/>
|
|
592
|
|
-</head>
|
|
593
|
|
-<body>
|
|
594
|
|
- <h2 class="toc-title">目录</h2>
|
|
595
|
|
- <ol class="toc-list">
|
|
596
|
|
- ${chapters.map((chapter, index) => {
|
|
597
|
|
- return `<li class="toc-item"><a href="chapter_${index}.xhtml">${chapter.title}</a></li>`;
|
|
598
|
|
- }).join('\n')}
|
|
599
|
|
- </ol>
|
|
600
|
|
-</body>
|
|
601
|
|
-</html>`;
|
|
602
|
|
-
|
|
603
|
|
- textFolder.file('toc.xhtml', tocHtml);
|
|
604
|
|
- manifestItems.push({ id: 'toc', href: 'Text/toc.xhtml', mediaType: 'application/xhtml+xml' });
|
|
605
|
|
-
|
|
606
|
|
- // 添加 CSS 文件
|
|
607
|
|
- const cssFolder = oebps.folder('Styles');
|
|
608
|
|
- const csspath=path.join(__dirname, 'epub_styles.css');
|
|
609
|
|
- console.log("🚀 ~ generateEpub ~ csspath:", csspath)
|
|
610
|
|
-
|
|
611
|
|
- const cssContent = fs.readFileSync(csspath, 'utf-8');
|
|
612
|
|
- cssFolder.file('stylesheet.css', cssContent);
|
|
613
|
|
- manifestItems.push({ id: 'stylesheet', href: 'Styles/stylesheet.css', mediaType: 'text/css' });
|
|
614
|
|
-
|
|
615
|
|
- // 生成唯一标识符
|
|
616
|
|
- const bookUUID = uuidv4();
|
|
617
|
|
-
|
|
618
|
|
- // 生成 toc.ncx 文件
|
|
619
|
|
- const tocNcx = `<?xml version='1.0' encoding='utf-8'?>
|
|
620
|
|
-<ncx xmlns="http://www.daisy.org/z3986/2005/ncx/" version="2005-1" xml:lang="zh-CN">
|
|
621
|
|
- <head>
|
|
622
|
|
- <meta content="${bookUUID}" name="dtb:uid"/>
|
|
623
|
|
- <meta content="2" name="dtb:depth"/>
|
|
624
|
|
- <meta content="0" name="dtb:totalPageCount"/>
|
|
625
|
|
- <meta content="0" name="dtb:maxPageNumber"/>
|
|
626
|
|
- </head>
|
|
627
|
|
- <docTitle>
|
|
628
|
|
- <text>${bookTitle}</text>
|
|
629
|
|
- </docTitle>
|
|
630
|
|
- <navMap>
|
|
631
|
|
- <navPoint id="navpoint-0" playOrder="0">
|
|
632
|
|
- <navLabel>
|
|
633
|
|
- <text>封面</text>
|
|
634
|
|
- </navLabel>
|
|
635
|
|
- <content src="Text/cover.xhtml"/>
|
|
636
|
|
- </navPoint>
|
|
637
|
|
- <navPoint id="navpoint-1" playOrder="1">
|
|
638
|
|
- <navLabel>
|
|
639
|
|
- <text>目录</text>
|
|
640
|
|
- </navLabel>
|
|
641
|
|
- <content src="Text/toc.xhtml"/>
|
|
642
|
|
- </navPoint>
|
|
643
|
|
- ${chapters.map((chapter, index) => {
|
|
644
|
|
- return `<navPoint id="navpoint-${index + 2}" playOrder="${index + 2}">
|
|
645
|
|
- <navLabel>
|
|
646
|
|
- <text>${chapter.title}</text>
|
|
647
|
|
- </navLabel>
|
|
648
|
|
- <content src="Text/chapter_${index}.xhtml"/>
|
|
649
|
|
- </navPoint>`;
|
|
650
|
|
- }).join('\n')}
|
|
651
|
|
- </navMap>
|
|
652
|
|
-</ncx>`;
|
|
653
|
|
-
|
|
654
|
|
- oebps.file('toc.ncx', tocNcx);
|
|
655
|
|
-
|
|
656
|
|
- // 生成 content.opf 文件
|
|
657
|
|
- const contentOpf = `<?xml version="1.0" encoding="UTF-8"?>
|
|
658
|
|
-<package xmlns="http://www.idpf.org/2007/opf" version="2.0" unique-identifier="uuid_id">
|
|
659
|
|
- <metadata xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:opf="http://www.idpf.org/2007/opf">
|
|
660
|
|
- <dc:identifier id="uuid_id">urn:uuid:${bookUUID}</dc:identifier>
|
|
661
|
|
- <dc:title>${bookTitle}</dc:title>
|
|
662
|
|
- <dc:creator>${author}</dc:creator>
|
|
663
|
|
- <dc:language>zh-CN</dc:language>
|
|
664
|
|
- <dc:date>${new Date().toISOString().split('T')[0]}</dc:date>
|
|
665
|
|
- <meta name="cover" content="cover-image"/>
|
|
666
|
|
- </metadata>
|
|
667
|
|
- <manifest>
|
|
668
|
|
- ${manifestItems.map(item => `<item id="${item.id}" href="${item.href}" media-type="${item.mediaType}"/>`).join('\n')}
|
|
669
|
|
- </manifest>
|
|
670
|
|
- <spine toc="ncx">
|
|
671
|
|
- <itemref idref="cover"/>
|
|
672
|
|
- <itemref idref="toc"/>
|
|
673
|
|
- ${spineItems.map(item => `<itemref idref="${item.idref}"/>`).join('\n')}
|
|
674
|
|
- </spine>
|
|
675
|
|
- <guide>
|
|
676
|
|
- <reference type="cover" title="封面" href="Text/cover.xhtml"/>
|
|
677
|
|
- </guide>
|
|
678
|
|
-</package>`;
|
|
679
|
|
-
|
|
680
|
|
- oebps.file('content.opf', contentOpf);
|
|
681
|
|
-
|
|
682
|
|
- // 生成 EPUB 文件
|
|
683
|
|
- const epubContent = await zip.generateAsync({
|
|
684
|
|
- type: 'nodebuffer',
|
|
685
|
|
- compression: 'DEFLATE',
|
|
686
|
|
- mimeType: 'application/epub+zip'
|
|
687
|
|
- });
|
|
688
|
|
- fs.writeFileSync(outputPath, epubContent);
|
|
689
|
|
-
|
|
690
|
|
- console.log(`EPUB 电子书已生成: ${outputPath}`);
|
|
691
|
|
- } catch (error) {
|
|
692
|
|
- console.error('生成 EPUB 电子书时出错:', error);
|
|
693
|
|
- }
|
|
694
|
|
-}
|
|
695
|
|
-
|
|
696
|
|
-
|
|
697
|
|
-/**
|
|
698
|
|
- * 命令行入口
|
|
699
|
|
- */
|
|
700
|
|
-
|
|
701
|
|
-//const title = "Zhui-Xu";
|
|
702
|
|
-const title="Throne-of-Magical-Arcana";
|
|
703
|
|
-//const title = 'Release-that-Witch';
|
|
704
|
|
-//const title = 'Strange-Life-of-a-Cat';
|
|
705
|
|
-//const title = "Hidden-Assassin";
|
|
706
|
|
-//const author = "Angry Banana";
|
|
707
|
|
-const author = "Cuttlefish That Loves Diving";
|
|
708
|
|
-const coverName = "cover.jpg";
|
|
709
|
|
-
|
|
710
|
|
-// 从命令行参数获取小说标题
|
|
711
|
|
-
|
|
712
|
|
-const args = process.argv.slice(2);
|
|
713
|
|
-
|
|
714
|
|
-// 显示帮助信息
|
|
715
|
|
-if (args.includes("--help") || args.includes("-h")) {
|
|
716
|
|
- showHelp();
|
|
717
|
|
- process.exit(0);
|
|
718
|
|
-}
|
|
719
|
|
-
|
|
720
|
|
-// 获取参数
|
|
721
|
|
-const debug = args.includes("--debug");
|
|
722
|
|
-const outputDir = args.find(arg => arg.startsWith("--output="))?.split("=")[1] || title;
|
|
723
|
|
-const fetchContent = 1;
|
|
724
|
|
-
|
|
725
|
|
-console.log(`开始爬取小说: ${title}`);
|
|
726
|
|
-console.log(`调试模式: ${debug ? "开启" : "关闭"}`);
|
|
727
|
|
-console.log(`输出目录: ${outputDir}`);
|
|
728
|
|
-console.log(`爬取章节内容: ${fetchContent ? "是" : "否"}`);
|
|
729
|
|
-
|
|
730
|
|
-// 确保输出目录存在
|
|
731
|
|
-if (!fs.existsSync(outputDir)) {
|
|
732
|
|
- fs.mkdirSync(outputDir, { recursive: true });
|
|
733
|
|
-}
|
|
734
|
|
-
|
|
735
|
|
-if (1==1){
|
|
736
|
|
-await runScript(title, debug, outputDir, fetchContent)
|
|
737
|
|
- .then(result => {
|
|
738
|
|
- if (result && result.errcode) {
|
|
739
|
|
- console.error(`爬取失败: ${result.errStr}`);
|
|
740
|
|
- process.exit(1);
|
|
741
|
|
- } else {
|
|
742
|
|
-
|
|
743
|
|
- console.log("爬取任务完成！");
|
|
744
|
|
- }
|
|
745
|
|
- })
|
|
746
|
|
- .catch(err => {
|
|
747
|
|
- console.error("程序执行出错:", err);
|
|
748
|
|
- process.exit(1);
|
|
749
|
|
- });
|
|
750
|
|
-}
|
|
751
|
|
-
|
|
752
|
|
-let sourceDir = path.join(__dirname, title+'/'+title+'_contents');
|
|
753
|
|
-let outputFile = path.join(__dirname, title+'/'+title+'.txt');
|
|
754
|
|
-let outputFile2 = path.join(__dirname, title+'/'+title+'.html');
|
|
755
|
|
-let coverFile=path.join(__dirname, title+'/'+coverName);
|
|
756
|
|
-let epubFile=path.join(__dirname, title+'/'+title+'.epub');
|
|
757
|
|
-
|
|
758
|
|
-if (1==1){
|
|
759
|
|
- await mergeChapterFiles(sourceDir, outputFile)
|
|
760
|
|
- .then(() => console.log('合并操作完成'))
|
|
761
|
|
- .catch(err => console.error('合并操作失败:', err));
|
|
762
|
|
-
|
|
763
|
|
- await formatTextFile(outputFile, outputFile2);
|
|
764
|
|
-}
|
|
765
|
|
-
|
|
766
|
|
-await generateEpub(outputFile2, coverFile, epubFile, title, author);
|
|
767
|
|
-
|
|
768
|
|
-// 导出函数，以便其他模块使用
|
|
769
|
|
-export default runScript;
|
