5507b1d986
- kb-link-parser: Multi-platform URL parser (Bilibili, YouTube, Zhihu) - kb-bilibili-metadata: Bilibili video/article/up主 metadata extractor - kb-zhihu-metadata: Zhihu question/answer/user metadata extractor - kb-bilibili-content: Bilibili video download and content extraction - kb-ocr-processor: OCR text extraction from video frames - kb-deep-analyzer: AI-powered deep content analysis - kb-workflow: Workflow orchestration (inbox, archive, subscriptions, report) Also add: - ARCHITECTURE_FLOWCHART.md: System architecture diagrams - DETAILED_DESIGN.md: Complete design documentation
18 lines
533 B
Python
18 lines
533 B
Python
from markdownify import MarkdownConverter as _MarkdownConverter
|
|
|
|
class MarkdownConverter:
|
|
"""HTML 转 Markdown 转换器,保留完整格式"""
|
|
|
|
def __init__(self):
|
|
self.converter = _MarkdownConverter(
|
|
heading_style="ATX",
|
|
bullets="*,-",
|
|
code_blocks=True,
|
|
tables=True,
|
|
strip=["script", "style", "nav", "footer", "aside"]
|
|
)
|
|
|
|
def convert(self, html: str) -> str:
|
|
"""转换 HTML 为 Markdown"""
|
|
return self.converter.convert(html)
|