151 lines
4.8 KiB
Python
151 lines
4.8 KiB
Python
"""
|
||
联网搜索公共工具 - 无需 API Key，免费使用 DuckDuckGo
|
||
Web Search Public Utility - Free, no API Key, using DuckDuckGo
|
||
"""
|
||
|
||
from typing import List, Dict, Any, Optional
|
||
from dataclasses import dataclass
|
||
from datetime import datetime
|
||
|
||
|
||
@dataclass
|
||
class SearchResult:
|
||
"""搜索结果数据类"""
|
||
title: str
|
||
url: str
|
||
snippet: str
|
||
source: str = "DuckDuckGo"
|
||
timestamp: datetime = None
|
||
|
||
def __post_init__(self):
|
||
if self.timestamp is None:
|
||
self.timestamp = datetime.now()
|
||
|
||
|
||
class WebSearchTool:
|
||
"""联网搜索公共工具类"""
|
||
|
||
def __init__(self, max_results: int = 5):
|
||
self.max_results = max_results
|
||
|
||
def search(self, query: str, max_results: Optional[int] = None) -> List[SearchResult]:
|
||
"""
|
||
使用 DuckDuckGo 搜索
|
||
|
||
Args:
|
||
query: 搜索关键词
|
||
max_results: 返回结果数量，默认使用初始化时的设置
|
||
|
||
Returns:
|
||
搜索结果列表
|
||
"""
|
||
try:
|
||
from duckduckgo_search import DDGS
|
||
|
||
num_results = max_results or self.max_results
|
||
|
||
with DDGS() as ddgs:
|
||
results = ddgs.text(query, max_results=num_results)
|
||
|
||
search_results = []
|
||
for r in results:
|
||
search_results.append(SearchResult(
|
||
title=r.get("title", ""),
|
||
url=r.get("href", ""),
|
||
snippet=r.get("body", ""),
|
||
source="DuckDuckGo"
|
||
))
|
||
|
||
return search_results
|
||
|
||
except ImportError:
|
||
# 如果 duckduckgo-search 未安装，返回模拟数据
|
||
return self._search_mock(query, max_results)
|
||
except Exception as e:
|
||
print(f"搜索出错：{e}")
|
||
# 出错时返回模拟数据
|
||
return self._search_mock(query, max_results)
|
||
|
||
def _search_mock(self, query: str, max_results: Optional[int] = None) -> List[SearchResult]:
|
||
"""模拟搜索结果（兜底方案）"""
|
||
mock_results = [
|
||
SearchResult(
|
||
title=f"{query} - 搜索结果 1",
|
||
url="https://example.com/result1",
|
||
snippet=f"这是关于 {query} 的模拟搜索结果，包含相关信息摘要...",
|
||
),
|
||
SearchResult(
|
||
title=f"{query} - 搜索结果 2",
|
||
url="https://example.com/result2",
|
||
snippet=f"更多关于 {query} 的内容，涵盖多个方面和细节...",
|
||
),
|
||
SearchResult(
|
||
title=f"{query} - 搜索结果 3",
|
||
url="https://example.com/result3",
|
||
snippet=f"深入分析 {query} 的各个维度，提供全面的视角...",
|
||
),
|
||
]
|
||
|
||
num = max_results or self.max_results
|
||
return mock_results[:num]
|
||
|
||
def format_search_results(self, results: List[SearchResult]) -> str:
|
||
"""
|
||
格式化搜索结果（带引用溯源）
|
||
|
||
Args:
|
||
results: 搜索结果列表
|
||
|
||
Returns:
|
||
格式化后的 Markdown 文本
|
||
"""
|
||
if not results:
|
||
return "未找到相关搜索结果"
|
||
|
||
lines = []
|
||
lines.append("## 🔍 联网搜索结果\n")
|
||
|
||
for idx, result in enumerate(results, 1):
|
||
lines.append(f"### [{idx}] {result.title}")
|
||
lines.append(f"- 🔗 来源：[{result.url}]({result.url})")
|
||
lines.append(f"- 📝 摘要：{result.snippet}")
|
||
lines.append(f"- 📅 时间：{result.timestamp.strftime('%Y-%m-%d %H:%M:%S')}")
|
||
lines.append("")
|
||
|
||
# 添加引用溯源说明
|
||
lines.append("---")
|
||
lines.append("💡 **引用溯源说明**：")
|
||
lines.append("- 以上搜索结果均标注了来源链接")
|
||
lines.append("- 使用方括号数字标识引用（如 [1]、[2]）")
|
||
lines.append("- 可通过链接追溯原始信息")
|
||
|
||
return "\n".join(lines)
|
||
|
||
|
||
# 单例实例
|
||
_web_search_tool = None
|
||
|
||
|
||
def get_web_search_tool() -> WebSearchTool:
|
||
"""获取联网搜索工具单例"""
|
||
global _web_search_tool
|
||
if _web_search_tool is None:
|
||
_web_search_tool = WebSearchTool()
|
||
return _web_search_tool
|
||
|
||
|
||
def web_search(query: str, max_results: int = 5) -> str:
|
||
"""
|
||
便捷函数：联网搜索并返回格式化结果
|
||
|
||
Args:
|
||
query: 搜索关键词
|
||
max_results: 返回结果数量
|
||
|
||
Returns:
|
||
格式化后的搜索结果文本
|
||
"""
|
||
tool = get_web_search_tool()
|
||
results = tool.search(query, max_results)
|
||
return tool.format_search_results(results)
|