Initial commit

This commit is contained in:
2026-07-18 15:51:01 +08:00
commit f2c80c5a9c
799 changed files with 133475 additions and 0 deletions
+22
View File
@@ -0,0 +1,22 @@
"""中文新闻正文提取模块 (M2)。
公共 API:
- extract_article: 从 HTML 提取 Article
- Article: 统一文章模型
- ExtractError: 提取失败异常
"""
from .models import Article, ExtractError
from .parser import (
MIN_CONTENT_LENGTH,
SOURCE_NAME_MAP,
extract_article,
)
__all__ = [
"MIN_CONTENT_LENGTH",
"SOURCE_NAME_MAP",
"Article",
"ExtractError",
"extract_article",
]