refactor: cleanup dead code, fix model confusion, streamline CLI

- Remove 3 dead modules: academic/, wechat/, social/ (merged into engines/)
- Remove 4 stale news scripts (tech_news.py, wallstreetcn.py, cls.py, rss.py)
- scripts/core/base.py: canonical SearchResult + BaseEngine (was in engines/base.py)
- scripts/engines/base.py: re-exports from core.base for compatibility
- scripts/engines/news_engine.py: Bing News + RSS unified (was in scripts/news/rss.py)
- scripts/engines/academic_engine.py: ArXiv + CrossRef unified (was in scripts/academic/arxiv.py)
- scripts/cli.py: complete rewrite — 10 commands (search/web/news/academic/wechat/social/rss/baidu/health/sources)
- scripts/unified_search.py: clean async Python API (was a stub)
- ws.py: lightweight launcher
- README.md + SKILL.md: updated to reflect actual 15+ engines
- All EngineResult → SearchResult
- All engines return list[SearchResult]
This commit is contained in:
openbot-coder committed 2026-05-30 16:25:41 +08:00
1 parent e20478fcbd
commit c077a7ae40
31 files changed
+1188 -3148

No files matched your search

+4 -4
View File
@@ -9,7 +9,7 @@ from urllib.parse import quote_plus
import httpx
from bs4 import BeautifulSoup
from scripts.engines.base import BaseEngine, EngineResult
from scripts.core.base import BaseEngine, SearchResult
logger = logging.getLogger(__name__)
@@ -27,7 +27,7 @@ class SogouScraper(BaseEngine):
name = "sogou"
async def search(self, query: str, max_results: int = 10,
**kwargs) -> list[EngineResult]:
**kwargs) -> list[SearchResult]:
t0 = time.time()
url = f"https://www.sogou.com/web?query={quote_plus(query)}"
@@ -43,7 +43,7 @@ class SogouScraper(BaseEngine):
logger.warning(f"[sogou] failed: {e}")
return []
def _parse(self, html: str, max_results: int) -> list[EngineResult]:
def _parse(self, html: str, max_results: int) -> list[SearchResult]:
soup = BeautifulSoup(html, "html.parser")
results = []
@@ -57,7 +57,7 @@ class SogouScraper(BaseEngine):
snippet = snippet_el.get_text(strip=True) if snippet_el else ""
if title and href and not href.startswith("/"):
results.append(EngineResult(
results.append(SearchResult(
title=title, url=href, snippet=snippet, source="sogou",
))
if len(results) >= max_results: