23 lines
445 B
Python
23 lines
445 B
Python
"""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",
|
|
]
|