refactor: 将核心代码迁移到 scripts 目录
- 创建 scripts/ 目录作为核心代码根目录 - 移动 core/, readers/, utils/ 到 scripts/ 下 - 移动 config.py, lyxy_document_reader.py 到 scripts/ - 移动 encoding_detection.py 到 scripts/utils/ - 更新 pyproject.toml 中的入口点路径和 pytest 配置 - 更新所有内部导入语句为 scripts.* 模块 - 更新 README.md 目录结构说明 - 更新 openspec/config.yaml 添加目录结构说明 - 删除无用的 main.py 此变更使项目结构更清晰,便于区分核心代码与测试、文档等支撑文件。
This commit is contained in:
25
scripts/readers/html/html2text.py
Normal file
25
scripts/readers/html/html2text.py
Normal file
@@ -0,0 +1,25 @@
|
||||
"""使用 html2text 解析 HTML(兜底方案)"""
|
||||
|
||||
from typing import Optional, Tuple
|
||||
|
||||
|
||||
def parse(html_content: str) -> Tuple[Optional[str], Optional[str]]:
|
||||
"""使用 html2text 解析 HTML(兜底方案)"""
|
||||
try:
|
||||
import html2text
|
||||
except ImportError:
|
||||
return None, "html2text 库未安装"
|
||||
|
||||
try:
|
||||
converter = html2text.HTML2Text()
|
||||
converter.ignore_emphasis = False
|
||||
converter.ignore_links = False
|
||||
converter.ignore_images = True
|
||||
converter.body_width = 0
|
||||
converter.skip_internal_links = True
|
||||
markdown_content = converter.handle(html_content)
|
||||
if not markdown_content.strip():
|
||||
return None, "解析内容为空"
|
||||
return markdown_content, None
|
||||
except Exception as e:
|
||||
return None, f"html2text 解析失败: {str(e)}"
|
||||
Reference in New Issue
Block a user