Initial commit
This commit is contained in:
@@ -0,0 +1,32 @@
|
||||
"""新闻抓取模块 (M1)。
|
||||
|
||||
公共 API:
|
||||
- load_crawler_config: 加载 sources.yaml
|
||||
- crawl_all: 一键抓取所有启用的源
|
||||
- crawl_source: 抓取单个源(供测试/调试)
|
||||
- CrawlerConfig / SourceConfig / CrawlResult: 数据模型
|
||||
"""
|
||||
|
||||
from .config import load_crawler_config
|
||||
from .engine import crawl_all, crawl_source, extract_article_links
|
||||
from .models import (
|
||||
ArticleLink,
|
||||
CrawlerConfig,
|
||||
CrawlerSettings,
|
||||
CrawlResult,
|
||||
CrawlStage,
|
||||
SourceConfig,
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"ArticleLink",
|
||||
"CrawlResult",
|
||||
"CrawlStage",
|
||||
"CrawlerConfig",
|
||||
"CrawlerSettings",
|
||||
"SourceConfig",
|
||||
"crawl_all",
|
||||
"crawl_source",
|
||||
"extract_article_links",
|
||||
"load_crawler_config",
|
||||
]
|
||||
Reference in New Issue
Block a user