236 lines
8.2 KiB
Python
236 lines
8.2 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
|
||
import requests
|
||
import warnings
|
||
import re
|
||
|
||
|
||
@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]:
|
||
"""
|
||
使用多种方式搜索
|
||
|
||
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
|
||
"""
|
||
num_results = max_results or self.max_results
|
||
|
||
# 方式 1: 尝试用 ddgs 包
|
||
try:
|
||
from ddgs import DDGS
|
||
print(f"[WebSearch] 使用 ddgs 搜索: {query}")
|
||
with DDGS() as ddgs:
|
||
results = list(ddgs.text(query, max_results=num_results))
|
||
if 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"
|
||
))
|
||
print(f"[WebSearch] ddgs 返回 {len(search_results)} 条结果")
|
||
return search_results
|
||
except ImportError:
|
||
print("[WebSearch] ddgs 未安装，尝试 duckduckgo-search")
|
||
except Exception as e:
|
||
print(f"[WebSearch] ddgs 搜索失败: {e}")
|
||
|
||
# 方式 2: 尝试用旧的 duckduckgo-search 包
|
||
try:
|
||
from duckduckgo_search import DDGS
|
||
print(f"[WebSearch] 使用 duckduckgo-search 搜索: {query}")
|
||
with DDGS() as ddgs:
|
||
results = list(ddgs.text(query, max_results=num_results))
|
||
if 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"
|
||
))
|
||
print(f"[WebSearch] duckduckgo-search 返回 {len(search_results)} 条结果")
|
||
return search_results
|
||
except ImportError:
|
||
print("[WebSearch] duckduckgo-search 未安装")
|
||
except Exception as e:
|
||
print(f"[WebSearch] duckduckgo-search 搜索失败: {e}")
|
||
|
||
# 方式 3: 尝试用简单 HTTP 请求
|
||
try:
|
||
return self._search_http(query, num_results)
|
||
except Exception as e:
|
||
print(f"[WebSearch] HTTP 搜索也失败: {e}")
|
||
|
||
# 方式 4: 返回模拟数据作为最后兜底
|
||
return self._search_mock(query, num_results)
|
||
|
||
def _search_http(self, query: str, max_results: int) -> List[SearchResult]:
|
||
"""用简单 HTTP 请求搜索（备用方案）- 尝试多个国内源"""
|
||
print(f"[WebSearch] 尝试 HTTP 搜索")
|
||
|
||
# 方式 1: 尝试百度搜索（简单方式）
|
||
try:
|
||
return self._search_baidu(query, max_results)
|
||
except Exception as e:
|
||
print(f"[WebSearch] 百度搜索失败: {e}")
|
||
|
||
# 方式 2: 返回模拟数据
|
||
return self._search_mock(query, max_results)
|
||
|
||
def _search_baidu(self, query: str, max_results: int) -> List[SearchResult]:
|
||
"""尝试百度搜索"""
|
||
import requests
|
||
from urllib.parse import quote
|
||
|
||
url = f"https://www.baidu.com/s?wd={quote(query)}"
|
||
headers = {
|
||
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
|
||
}
|
||
|
||
try:
|
||
response = requests.get(url, headers=headers, timeout=10)
|
||
response.raise_for_status()
|
||
|
||
# 简单解析百度搜索结果（简化版）
|
||
results = []
|
||
# 这里只是示意，真实百度搜索需要更复杂的解析
|
||
results.append(SearchResult(
|
||
title=f"百度搜索: {query}",
|
||
url=url,
|
||
snippet="如需要真实搜索结果，请考虑使用百度搜索 API",
|
||
source="百度"
|
||
))
|
||
return results
|
||
except Exception as e:
|
||
print(f"[WebSearch] 百度搜索也失败: {e}")
|
||
raise
|
||
|
||
def _search_mock(self, query: str, max_results: Optional[int] = None) -> List[SearchResult]:
|
||
"""模拟搜索结果（兜底方案）"""
|
||
print(f"[WebSearch] 使用模拟搜索结果 (查询: {query})")
|
||
|
||
# 根据查询内容生成更有意义的模拟结果
|
||
mock_templates = [
|
||
{
|
||
"title": f"关于「{query}」的相关介绍",
|
||
"snippet": "这是模拟结果。如需真实搜索，请检查容器网络连接或配置代理。",
|
||
"url": "https://example.com/about"
|
||
},
|
||
{
|
||
"title": f"「{query}」 - 最新动态",
|
||
"snippet": "提示：在容器内运行时，需要确保能访问外网。",
|
||
"url": "https://example.com/latest"
|
||
},
|
||
{
|
||
"title": f"了解更多关于「{query}」的内容",
|
||
"snippet": "建议：检查 Docker 网络配置，或使用代理。",
|
||
"url": "https://example.com/more"
|
||
}
|
||
]
|
||
|
||
num = max_results or self.max_results
|
||
results = []
|
||
|
||
for i, template in enumerate(mock_templates[:num]):
|
||
results.append(SearchResult(
|
||
title=template["title"],
|
||
url=template["url"],
|
||
snippet=template["snippet"],
|
||
source="模拟数据"
|
||
))
|
||
|
||
return results
|
||
|
||
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)
|