谭凯
7a93c52b42
- Refactor codebase into src/ (preprocessing, translation, assembly) - Add pipeline/ scripts for individual stages - Externalize configuration to config/config.yaml - Fix Cover Image preservation - Update documentation and manuals
179 lines
6.5 KiB
Python
179 lines
6.5 KiB
Python
"""
|
|
EPUB 清理器模块 (EpubCleaner)
|
|
|
|
负责在翻译前对 EPUB 进行标准化清洗，解决兼容性问题。
|
|
核心功能:
|
|
1. Flatten Structure: 将 div 转换为 p，简化结构
|
|
2. Fix TOC: 修复目录中的死链和缺失 UID
|
|
3. CSS Restoration: 找回丢失的样式表
|
|
"""
|
|
|
|
from bs4 import BeautifulSoup, Tag
|
|
from loguru import logger
|
|
from ebooklib import epub
|
|
import ebooklib
|
|
import zipfile
|
|
import uuid
|
|
from ebooklib.epub import Link
|
|
|
|
class EpubCleaner:
|
|
"""标准 EPUB 清理器"""
|
|
|
|
def clean_epub(self, input_path: str, output_path: str):
|
|
"""
|
|
清理 EPUB 文件并保存到新路径
|
|
"""
|
|
logger.info(f"开始清理: {input_path}")
|
|
|
|
# 1. 尝试打开 Zip 以读取原始内容 (Ebooklib 回退机制)
|
|
try:
|
|
input_zip = zipfile.ZipFile(input_path, 'r')
|
|
zip_files = set(input_zip.namelist())
|
|
except Exception as e:
|
|
logger.error(f"无法打开 Zip (样式回退功能将失效): {e}")
|
|
input_zip = None
|
|
zip_files = set()
|
|
|
|
# 2. 读取 EPUB
|
|
try:
|
|
book = epub.read_epub(input_path)
|
|
except Exception as e:
|
|
logger.error(f"Ebooklib 读取失败: {e}")
|
|
raise
|
|
|
|
# 3. 遍历并清理文档
|
|
count = 0
|
|
for item in book.get_items():
|
|
if item.get_type() == ebooklib.ITEM_DOCUMENT:
|
|
try:
|
|
file_name = item.get_name()
|
|
content = None
|
|
|
|
# 优先从 Zip 读取以保留 Head 信息 (CSS Links)
|
|
if input_zip and file_name in zip_files:
|
|
try:
|
|
content = input_zip.read(file_name).decode('utf-8')
|
|
except Exception:
|
|
pass
|
|
|
|
# 回退到 ebooklib
|
|
if content is None:
|
|
raw_content = item.get_content()
|
|
if raw_content:
|
|
content = raw_content.decode('utf-8')
|
|
|
|
if not content or not content.strip():
|
|
continue
|
|
|
|
# 执行清理
|
|
cleaned = self._clean_content(content, item)
|
|
|
|
# 安全检查
|
|
if not cleaned.strip():
|
|
logger.warning(f"警告: {file_name} 清理后为空，保留原始内容")
|
|
cleaned = content
|
|
|
|
item.set_content(cleaned.encode('utf-8'))
|
|
count += 1
|
|
|
|
except Exception as e:
|
|
logger.warning(f"清理文档失败 {item.get_name()}: {e}")
|
|
|
|
# 4. 修复 TOC (死链和 UID)
|
|
try:
|
|
book.toc = self._fix_and_clean_toc(book.toc, book)
|
|
except Exception as e:
|
|
logger.error(f"TOC 修复失败: {e}")
|
|
|
|
# 5. 保存
|
|
epub.write_epub(output_path, book)
|
|
logger.info(f"清理完成: {output_path} (处理了 {count} 个文档)")
|
|
|
|
def _clean_content(self, html_content: str, item=None) -> str:
|
|
"""
|
|
执行具体的 HTML 清理逻辑
|
|
"""
|
|
soup = BeautifulSoup(html_content, 'html.parser')
|
|
|
|
# 恢复 CSS 链接
|
|
if item:
|
|
self._restore_css_links(soup, item)
|
|
|
|
# div 转 p
|
|
stats = {'divs_to_p': 0}
|
|
inline_tags = {'span', 'em', 'strong', 'i', 'b', 'u', 'a', 'br', 'sub', 'sup'}
|
|
|
|
for div in list(soup.find_all('div')):
|
|
# 检查是否有块级子元素 (如果有，则保留 div 容器结构)
|
|
has_block = any(
|
|
isinstance(c, Tag) and c.name not in inline_tags
|
|
for c in div.children
|
|
)
|
|
|
|
if not has_block:
|
|
div.name = 'p'
|
|
stats['divs_to_p'] += 1
|
|
|
|
# 可以在这里添加更多清理逻辑 (如移除无用的空的 span 等)
|
|
|
|
return str(soup)
|
|
|
|
def _restore_css_links(self, soup, item):
|
|
"""从原始 HTML 中提取并恢复 CSS 链接到 item 对象"""
|
|
head = soup.find('head')
|
|
if head:
|
|
links = head.find_all('link', rel='stylesheet')
|
|
for link in links:
|
|
href = link.get('href')
|
|
if href:
|
|
existing_links = list(item.get_links())
|
|
exists = False
|
|
for l in existing_links:
|
|
l_href = getattr(l, 'href', None)
|
|
if l_href is None and isinstance(l, dict):
|
|
l_href = l.get('href')
|
|
if l_href == href:
|
|
exists = True
|
|
break
|
|
|
|
if not exists:
|
|
item.add_link(href=href, rel='stylesheet', type='text/css')
|
|
|
|
def _fix_and_clean_toc(self, toc, book):
|
|
"""修复 TOC：补全 UID 并移除指向不存在文件的死链"""
|
|
new_toc = []
|
|
|
|
for item in toc:
|
|
# Case 1: (Section, Children)
|
|
if isinstance(item, (tuple, list)):
|
|
section, children = item
|
|
cleaned_children = self._fix_and_clean_toc(children, book)
|
|
|
|
if isinstance(section, Link):
|
|
href = section.href.split('#')[0]
|
|
if book.get_item_with_href(href):
|
|
if section.uid is None:
|
|
section.uid = f'uuid-{uuid.uuid4()}'
|
|
new_toc.append((section, cleaned_children))
|
|
else:
|
|
logger.warning(f"移除无效 TOC 节点: {section.href}")
|
|
new_toc.extend(cleaned_children)
|
|
else:
|
|
new_toc.append((section, cleaned_children))
|
|
|
|
# Case 2: Link
|
|
elif isinstance(item, Link):
|
|
href = item.href.split('#')[0]
|
|
if book.get_item_with_href(href):
|
|
if item.uid is None:
|
|
item.uid = f'uuid-{uuid.uuid4()}'
|
|
new_toc.append(item)
|
|
else:
|
|
logger.warning(f"移除无效 TOC 节点: {item.href}")
|
|
|
|
# Case 3: Other
|
|
else:
|
|
new_toc.append(item)
|
|
|
|
return new_toc
|