From 7717ad1f60b64a6091b3b6afb8255cc52eb917d4 Mon Sep 17 00:00:00 2001
From: oscarz <oscar@vip.qq.com>
Date: Sun, 30 Mar 2025 09:29:38 +0800
Subject: [PATCH] modify scripts

---
 aabook/src/dump_book.py    | 22 +++++++++++-
 aabook/src/text_to_epub.py | 71 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 92 insertions(+), 1 deletion(-)
 create mode 100644 aabook/src/text_to_epub.py

diff --git a/aabook/src/dump_book.py b/aabook/src/dump_book.py
index e26f65f..97f87c6 100644
--- a/aabook/src/dump_book.py
+++ b/aabook/src/dump_book.py
@@ -15,9 +15,29 @@ config.setup_logging()
 
 books_dir = f"{config.global_host_data_dir}/aabook/data"
 
+map_books = {
+    380     : "多情村妇",
+    2547    : "乡村乱情|奇思妙想",
+    2261    : "宋家湾那些事儿",
+    3152    : "渔港春夜",
+    3167    : "天狗",
+    3681    : "东北大炕",
+    5524    : "淫乱竹楼",
+    5389    : "杨家洼情事",
+    2783    : "风流岁月",
+    4827    : "蛮荒小村的风流韵事",
+    1114    : "熟透了的村妇",
+    4347    : "潭河峪的那些事儿",
+    3744    : "香火",
+    4984    : "山里人家",
+    
+}
+
 # 使用示例
 if __name__ == "__main__":
-    books = [4, 2600]
+    #books = [2689, 3727, 4698, 5446]
+    #books = [3167, 2985, 3098]
+    books = [2783]
     for book in books:
         data = db_tools.get_contents_by_book(book)
         if data:
diff --git a/aabook/src/text_to_epub.py b/aabook/src/text_to_epub.py
new file mode 100644
index 0000000..65709f6
--- /dev/null
+++ b/aabook/src/text_to_epub.py
@@ -0,0 +1,71 @@
+import re
+from ebooklib import epub
+import os
+import config
+
+config.setup_logging()
+
+books_dir = f"{config.global_host_data_dir}/aabook/data"
+
+
+def txt_to_epub(txt_path, epub_path):
+    # 读取 TXT 文件，使用 GB18030 编码
+    with open(txt_path, 'r', encoding='gb18030') as file:
+        content = file.read()
+
+    # 按章节分割内容
+    chapter_pattern = re.compile(r'第\d+章')
+    chapter_matches = list(chapter_pattern.finditer(content))
+    chapters = []
+    for i in range(len(chapter_matches)):
+        start = chapter_matches[i].start()
+        if i < len(chapter_matches) - 1:
+            end = chapter_matches[i + 1].start()
+        else:
+            end = len(content)
+        chapter_content = content[start:end]
+        chapter_title = chapter_pattern.search(chapter_content).group()
+        chapters.append((chapter_title, chapter_content))
+
+    # 创建 EPUB 书籍
+    book = epub.EpubBook()
+    book.set_title(os.path.basename(txt_path).replace('.txt', ''))
+    book.set_language('zh')
+
+    # 添加章节到 EPUB
+    epub_chapters = []
+    for title, content in chapters:
+        chapter = epub.EpubHtml(title=title, file_name=f'{title}.xhtml', lang='zh')
+        # 处理换行符，将换行符替换为 HTML 的 <br> 标签
+        content = content.replace(title, "", 1).strip()
+        content = content.replace('\r\n', '<br>')
+        content = content.replace('\n', '<br>')
+        chapter.content = f'<h1>{title}</h1><p>{content}</p>'
+        book.add_item(chapter)
+        epub_chapters.append(chapter)
+
+    # 定义书籍结构
+    book.toc = tuple(epub_chapters)
+    book.add_item(epub.EpubNcx())
+    book.add_item(epub.EpubNav())
+
+    # 定义样式
+    style = 'body { font-family: Times, serif; }'
+    nav_css = epub.EpubItem(uid="style_nav", file_name="style/nav.css", media_type="text/css", content=style)
+    book.add_item(nav_css)
+
+    # 设置书籍的页面布局
+    book.spine = ['nav'] + epub_chapters
+
+    # 保存 EPUB 文件
+    epub.write_epub(epub_path, book, {})
+
+
+# 使用示例
+txt_file1 = f"{books_dir}/我的青年岁月（加章节）.txt"
+txt_file2 = f"{books_dir}/废都（海外版）贾平凹-加章节.txt"
+epub_file1 = f"{books_dir}/我的青年岁月（加章节）.epub"
+epub_file2 = f"{books_dir}/废都（海外版）贾平凹-加章节.epub"
+
+txt_to_epub(txt_file1, epub_file1)
+txt_to_epub(txt_file2, epub_file2)