refactor: restructure project with CLI tool, multi-engine support, and skill-builder compliant SKILL.md

- Replace setup.py with pyproject.toml (uv-compatible)
- Add CLI entry point (web-search) with 9 subcommands
- Add multi-engine architecture (14 web + 7 special sources)
- Add WeChat/CLS/WallStreetCN/ArXiv/Twitter search engines
- Remove old src/ and examples/ directories
- Remove redundant requirements.txt and setup.py
- Update README.md and SKILL.md with full documentation
- SKILL.md now compliant with skill-builder standards (frontmatter, triggers, structure)
This commit is contained in:
vex1023 committed 2026-05-14 16:31:54 +08:00
1 parent 80ac14491e
commit 87935b59ce
29 files changed
+2364 -354

No files matched your search

+1
View File
@@ -0,0 +1 @@
"""Search engine implementations."""
+80
View File
@@ -0,0 +1,80 @@
"""
Parsing-based search engines (e.g. DuckDuckGo HTML scraper).
"""
from __future__ import annotations
import logging
from typing import Optional
import httpx
from bs4 import BeautifulSoup
from scripts.core.base import SearchEngine, SearchResult
logger = logging.getLogger(__name__)
class DuckDuckGoEngine(SearchEngine):
"""DuckDuckGo HTML search engine (no API key required)."""
SEARCH_URL = "https://html.duckduckgo.com/html/"
def __init__(self, config: Optional[dict] = None):
super().__init__("DuckDuckGo", config)
timeout = (config or {}).get("timeout", 15)
self._client = httpx.AsyncClient(
timeout=timeout,
headers={
"User-Agent": (config or {}).get(
"user_agent",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
"AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/120.0.0.0 Safari/537.36",
),
},
follow_redirects=True,
)
def build_url(self, query: str, **kwargs) -> str:
"""Build DuckDuckGo search URL."""
from urllib.parse import quote_plus
return f"https://duckduckgo.com/?q={quote_plus(query)}"
async def search(
self, query: str, max_results: int = 10, **kwargs
) -> list[SearchResult]:
"""Search DuckDuckGo and parse HTML results."""
params = {"q": query}
try:
response = await self._client.post(self.SEARCH_URL, data=params)
response.raise_for_status()
return self._parse_results(response.text, max_results)
except httpx.HTTPError as e:
logger.error(f"DuckDuckGo search failed: {e}")
return []
def _parse_results(self, html: str, max_results: int) -> list[SearchResult]:
"""Parse DuckDuckGo HTML search results."""
soup = BeautifulSoup(html, "lxml")
results = []
for i, result in enumerate(soup.select(".result")[:max_results]):
title_el = result.select_one(".result__title a")
snippet_el = result.select_one(".result__snippet")
if title_el:
results.append(
SearchResult(
title=title_el.get_text(strip=True),
url=title_el.get("href", ""),
snippet=snippet_el.get_text(strip=True)
if snippet_el else "",
source=self.name,
rank=i + 1,
category="web",
)
)
return results
async def close(self):
await self._client.aclose()
+60
View File
@@ -0,0 +1,60 @@
"""
Generic URL-based search engine.
Builds search URLs from templates defined in engines.json
and returns them as URL results.
"""
from __future__ import annotations
import logging
from typing import Any, Optional
from urllib.parse import quote_plus
from scripts.core.base import SearchEngine, SearchResult
logger = logging.getLogger(__name__)
class UrlSearchEngine(SearchEngine):
"""
Generic search engine that builds URLs from templates.
Reads URL templates from config (engines.json) and returns
the constructed search URL as a SearchResult.
"""
def __init__(self, name: str, engine_def: dict[str, Any]):
super().__init__(name, engine_def.get("config", {}))
self.url_template = engine_def.get("url", "")
self.region = engine_def.get("region", "global")
def build_url(self, query: str, **kwargs) -> str:
"""Build search URL by replacing {keyword} with encoded query."""
if not self.url_template:
return ""
encoded = quote_plus(query)
return self.url_template.replace("{keyword}", encoded)
async def search(
self, query: str, max_results: int = 10, **kwargs
) -> list[SearchResult]:
"""Return the search URL as a single result."""
url = self.build_url(query, **kwargs)
if not url:
return []
return [
SearchResult(
title=f"{self.name}: {query}",
url=url,
snippet=f"Search {self.name} for '{query}'",
source=self.name,
rank=1,
category="web",
extra={"url": url, "region": self.region},
)
]
async def close(self):
pass