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:
1 parent
e20478fcbd
commit
c077a7ae40
31 files changed
+1188
-3148
No files matched your search
@@ -18,7 +18,7 @@ from typing import Any, Optional
|
||||
|
||||
import httpx
|
||||
|
||||
from scripts.core.base import SearchEngine, SearchResult
|
||||
from scripts.core.base import BaseEngine, SearchResult
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -51,18 +51,18 @@ def _get_api_key() -> str:
|
||||
return env_from_file.get(ENV_KEY, "")
|
||||
|
||||
|
||||
class BaiduQianFanEngine(SearchEngine):
|
||||
class BaiduQianFanEngine(BaseEngine):
|
||||
"""百度千帆 AI 搜索 API 引擎."""
|
||||
|
||||
def __init__(self, config: Optional[dict] = None):
|
||||
super().__init__("Baidu Qianfan", config)
|
||||
name = "baidu_qianfan"
|
||||
|
||||
def __init__(self, config: Optional[dict] = None, timeout: float = 30.0):
|
||||
super().__init__(timeout=timeout)
|
||||
self.api_key = (config or {}).get("api_key", "") or _get_api_key()
|
||||
if not self.api_key:
|
||||
logger.warning(
|
||||
f"BAIDU_API_KEY not set! Set it in .env file or as environment variable."
|
||||
"BAIDU_API_KEY not set. Set it in .env or as environment variable."
|
||||
)
|
||||
|
||||
timeout = (config or {}).get("timeout", 30)
|
||||
self._client = httpx.AsyncClient(
|
||||
timeout=timeout,
|
||||
headers={
|
||||
@@ -76,17 +76,7 @@ class BaiduQianFanEngine(SearchEngine):
|
||||
async def search(
|
||||
self, query: str, max_results: int = 10, **kwargs
|
||||
) -> list[SearchResult]:
|
||||
"""Search via Baidu Qianfan AI Search API.
|
||||
|
||||
Args:
|
||||
query: Search keywords.
|
||||
max_results: Max results to return.
|
||||
**kwargs:
|
||||
site: Restrict search to a specific site (e.g. "mp.weixin.qq.com").
|
||||
recency: Time filter: "week", "month", "semiyear", "year" (default: "year").
|
||||
edition: "standard" (default) or "lite".
|
||||
safe_search: bool, default False.
|
||||
"""
|
||||
"""Search via Baidu Qianfan AI Search API."""
|
||||
if not self.api_key:
|
||||
return [
|
||||
SearchResult(
|
||||
@@ -100,19 +90,14 @@ class BaiduQianFanEngine(SearchEngine):
|
||||
)
|
||||
]
|
||||
|
||||
# Build resource_type_filter based on max_results
|
||||
top_k = min(max_results, 50)
|
||||
resource_type_filter = [
|
||||
{"type": "web", "top_k": top_k},
|
||||
]
|
||||
resource_type_filter = [{"type": "web", "top_k": top_k}]
|
||||
|
||||
# Build search_filter if site is specified
|
||||
search_filter = {}
|
||||
site = kwargs.get("site")
|
||||
if site:
|
||||
search_filter["match"] = {"site": [site]}
|
||||
search_filter: dict[str, Any] = {}
|
||||
if kwargs.get("site"):
|
||||
search_filter["match"] = {"site": [kwargs["site"]]}
|
||||
|
||||
request_body = {
|
||||
request_body: dict[str, Any] = {
|
||||
"messages": [{"content": query, "role": "user"}],
|
||||
"edition": kwargs.get("edition", "standard"),
|
||||
"search_source": "baidu_search_v2",
|
||||
@@ -134,38 +119,24 @@ class BaiduQianFanEngine(SearchEngine):
|
||||
logger.error(f"Baidu Qianfan API error: {data.get('message', '')}")
|
||||
return []
|
||||
|
||||
references = data.get("references", [])
|
||||
results = []
|
||||
for i, ref in enumerate(references[:max_results]):
|
||||
results.append(
|
||||
SearchResult(
|
||||
title=ref.get("title", ""),
|
||||
url=ref.get("url", ""),
|
||||
snippet=ref.get("snippet", ""),
|
||||
source=self.name,
|
||||
rank=i + 1,
|
||||
category="web",
|
||||
extra={
|
||||
k: ref[k]
|
||||
for k in ("site", "date", "type", "source")
|
||||
if k in ref
|
||||
},
|
||||
)
|
||||
)
|
||||
for i, ref in enumerate(data.get("references", [])[:max_results]):
|
||||
results.append(SearchResult(
|
||||
title=ref.get("title", ""),
|
||||
url=ref.get("url", ""),
|
||||
snippet=ref.get("snippet", ""),
|
||||
source=self.name,
|
||||
rank=i + 1,
|
||||
category="web",
|
||||
extra={k: ref[k] for k in ("site", "date", "type", "source") if k in ref},
|
||||
))
|
||||
return results
|
||||
|
||||
except httpx.HTTPStatusError as e:
|
||||
logger.error(f"Baidu Qianfan API HTTP error: {e.response.status_code}")
|
||||
if e.response.status_code == 401:
|
||||
logger.error("API Key 无效或未授权,请检查 BAIDU_API_KEY")
|
||||
elif e.response.status_code == 429:
|
||||
logger.error("API 配额不足")
|
||||
logger.error(f"Baidu Qianfan HTTP {e.response.status_code}: {e}")
|
||||
return []
|
||||
except httpx.RequestError as e:
|
||||
logger.error(f"Baidu Qianfan API request failed: {e}")
|
||||
return []
|
||||
except json.JSONDecodeError as e:
|
||||
logger.error(f"Baidu Qianfan API response parse failed: {e}")
|
||||
logger.error(f"Baidu Qianfan request failed: {e}")
|
||||
return []
|
||||
|
||||
async def close(self):
|
||||
|
||||
Reference in new issue
Block a user