duckduckgo-search

Performs web searches using DuckDuckGo to retrieve real-time information from the internet. Use when the user needs to search for current events, documentation, tutorials, or any information that requires web search capabilities.

1,864 stars

Best use case

duckduckgo-search is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Performs web searches using DuckDuckGo to retrieve real-time information from the internet. Use when the user needs to search for current events, documentation, tutorials, or any information that requires web search capabilities.

Teams using duckduckgo-search should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/duckduckgo-search/SKILL.md --create-dirs "https://raw.githubusercontent.com/LeoYeAI/openclaw-master-skills/main/skills/duckduckgo-search/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/duckduckgo-search/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How duckduckgo-search Compares

Feature / Agentduckduckgo-searchStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Performs web searches using DuckDuckGo to retrieve real-time information from the internet. Use when the user needs to search for current events, documentation, tutorials, or any information that requires web search capabilities.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# DuckDuckGo Web Search Skill

这个技能通过 DuckDuckGo 搜索引擎实现网络搜索功能,帮助获取实时信息。

## 功能特性

- 🔍 基于 DuckDuckGo 的隐私友好型搜索
- 📰 支持新闻搜索
- 🖼️ 支持图片搜索
- 📹 支持视频搜索
- 🌐 无需 API Key,免费使用
- 🔒 保护隐私,不追踪用户

## 安装

```bash
# 使用 uv 安装(推荐)
uv pip install duckduckgo-search

# 或使用 pip 安装
pip install duckduckgo-search
```

## 快速开始

### 命令行方式

```bash
# 基础文本搜索
python -c "
from duckduckgo_search import DDGS

with DDGS() as ddgs:
    results = list(ddgs.text('Python tutorial', max_results=5))
    for r in results:
        print(f\"标题: {r['title']}\")
        print(f\"链接: {r['href']}\")
        print(f\"摘要: {r['body']}\")
        print('---')
"
```

## 搜索类型

### 1. 文本搜索 (Text Search)

最常用的搜索方式,返回网页结果:

```bash
python -c "
from duckduckgo_search import DDGS

query = 'your search query'

with DDGS() as ddgs:
    results = list(ddgs.text(
        query,
        region='cn-zh',      # 地区设置:cn-zh(中国), us-en(美国), wt-wt(全球)
        safesearch='moderate', # 安全搜索:on, moderate, off
        timelimit='m',       # 时间范围:d(天), w(周), m(月), y(年), None(不限)
        max_results=10       # 最大结果数
    ))
    
    for i, r in enumerate(results, 1):
        print(f\"{i}. {r['title']}\")
        print(f\"   URL: {r['href']}\")
        print(f\"   摘要: {r['body'][:100]}...\")
        print()
"
```

### 2. 新闻搜索 (News Search)

搜索最新新闻:

```bash
python -c "
from duckduckgo_search import DDGS

with DDGS() as ddgs:
    results = list(ddgs.news(
        'AI technology',
        region='wt-wt',
        safesearch='moderate',
        timelimit='d',       # d=过去24小时, w=过去一周, m=过去一月
        max_results=10
    ))
    
    for r in results:
        print(f\"📰 {r['title']}\")
        print(f\"   来源: {r['source']}\")
        print(f\"   时间: {r['date']}\")
        print(f\"   链接: {r['url']}\")
        print()
"
```

### 3. 图片搜索 (Image Search)

搜索图片资源:

```bash
python -c "
from duckduckgo_search import DDGS

with DDGS() as ddgs:
    results = list(ddgs.images(
        'cute cats',
        region='wt-wt',
        safesearch='moderate',
        size='Medium',       # Small, Medium, Large, Wallpaper
        type_image='photo',  # photo, clipart, gif, transparent, line
        layout='Square',     # Square, Tall, Wide
        max_results=10
    ))
    
    for r in results:
        print(f\"🖼️ {r['title']}\")
        print(f\"   图片: {r['image']}\")
        print(f\"   缩略图: {r['thumbnail']}\")
        print(f\"   来源: {r['source']}\")
        print()
"
```

### 4. 视频搜索 (Video Search)

搜索视频内容:

```bash
python -c "
from duckduckgo_search import DDGS

with DDGS() as ddgs:
    results = list(ddgs.videos(
        'Python programming',
        region='wt-wt',
        safesearch='moderate',
        timelimit='w',       # d, w, m
        resolution='high',   # high, standard
        duration='medium',   # short, medium, long
        max_results=10
    ))
    
    for r in results:
        print(f\"📹 {r['title']}\")
        print(f\"   时长: {r.get('duration', 'N/A')}\")
        print(f\"   来源: {r['publisher']}\")
        print(f\"   链接: {r['content']}\")
        print()
"
```

### 5. 即时回答 (Instant Answers)

获取 DuckDuckGo 的即时回答:

```bash
python -c "
from duckduckgo_search import DDGS

with DDGS() as ddgs:
    results = ddgs.answers('what is python programming language')
    
    for r in results:
        print(f\"📚 {r['text']}\")
        print(f\"   来源: {r.get('url', 'DuckDuckGo')}\")
"
```

### 6. 建议搜索 (Suggestions)

获取搜索建议:

```bash
python -c "
from duckduckgo_search import DDGS

with DDGS() as ddgs:
    suggestions = list(ddgs.suggestions('python'))
    
    print('🔍 搜索建议:')
    for s in suggestions:
        print(f\"   - {s['phrase']}\")
"
```

### 7. 地图搜索 (Maps Search)

搜索地点信息:

```bash
python -c "
from duckduckgo_search import DDGS

with DDGS() as ddgs:
    results = list(ddgs.maps(
        'coffee shop',
        place='Beijing, China',
        max_results=10
    ))
    
    for r in results:
        print(f\"📍 {r['title']}\")
        print(f\"   地址: {r['address']}\")
        print(f\"   电话: {r.get('phone', 'N/A')}\")
        print(f\"   坐标: {r['latitude']}, {r['longitude']}\")
        print()
"
```

## 实用脚本

### 通用搜索函数

创建一个可复用的搜索脚本:

```bash
python -c "
from duckduckgo_search import DDGS
import json

def web_search(query, search_type='text', max_results=5, region='wt-wt', timelimit=None):
    '''
    执行 DuckDuckGo 搜索
    
    参数:
        query: 搜索关键词
        search_type: 搜索类型 (text, news, images, videos)
        max_results: 最大结果数
        region: 地区 (cn-zh, us-en, wt-wt)
        timelimit: 时间限制 (d, w, m, y)
    '''
    with DDGS() as ddgs:
        if search_type == 'text':
            results = list(ddgs.text(query, region=region, timelimit=timelimit, max_results=max_results))
        elif search_type == 'news':
            results = list(ddgs.news(query, region=region, timelimit=timelimit, max_results=max_results))
        elif search_type == 'images':
            results = list(ddgs.images(query, region=region, max_results=max_results))
        elif search_type == 'videos':
            results = list(ddgs.videos(query, region=region, timelimit=timelimit, max_results=max_results))
        else:
            results = []
    
    return results

# 使用示例
query = 'Python 3.12 new features'
results = web_search(query, search_type='text', max_results=5)

print(f'🔍 搜索: {query}')
print(f'📊 找到 {len(results)} 个结果')
print()

for i, r in enumerate(results, 1):
    print(f\"{i}. {r['title']}\")
    print(f\"   {r['href']}\")
    print(f\"   {r['body'][:150]}...\")
    print()
"
```

### 搜索并保存结果

```bash
python -c "
from duckduckgo_search import DDGS
import json
from datetime import datetime

query = 'latest tech news'
output_file = f'search_results_{datetime.now().strftime(\"%Y%m%d_%H%M%S\")}.json'

with DDGS() as ddgs:
    results = list(ddgs.text(query, max_results=10))

# 保存到 JSON 文件
with open(output_file, 'w', encoding='utf-8') as f:
    json.dump({
        'query': query,
        'timestamp': datetime.now().isoformat(),
        'results': results
    }, f, ensure_ascii=False, indent=2)

print(f'✅ 搜索结果已保存到: {output_file}')
print(f'📊 共 {len(results)} 条结果')
"
```

### 多关键词批量搜索

```bash
python -c "
from duckduckgo_search import DDGS
import time

queries = [
    'Python best practices 2024',
    'React vs Vue 2024',
    'AI development tools'
]

all_results = {}

with DDGS() as ddgs:
    for query in queries:
        print(f'🔍 搜索: {query}')
        results = list(ddgs.text(query, max_results=3))
        all_results[query] = results
        print(f'   找到 {len(results)} 个结果')
        time.sleep(1)  # 避免请求过快

print()
print('=' * 50)
print('📊 搜索汇总')
print('=' * 50)

for query, results in all_results.items():
    print(f'\n🔎 {query}:')
    for i, r in enumerate(results, 1):
        print(f\"   {i}. {r['title'][:60]}...\")
"
```

## 参数说明

### 地区代码 (region)

| 代码 | 地区 |
|------|------|
| `cn-zh` | 中国 |
| `us-en` | 美国 |
| `uk-en` | 英国 |
| `jp-jp` | 日本 |
| `kr-kr` | 韩国 |
| `wt-wt` | 全球 (无地区限制) |

### 时间限制 (timelimit)

| 值 | 含义 |
|----|------|
| `d` | 过去 24 小时 |
| `w` | 过去一周 |
| `m` | 过去一月 |
| `y` | 过去一年 |
| `None` | 不限制 |

### 安全搜索 (safesearch)

| 值 | 含义 |
|----|------|
| `on` | 严格过滤 |
| `moderate` | 适度过滤 (默认) |
| `off` | 关闭过滤 |

## 错误处理

```bash
python -c "
from duckduckgo_search import DDGS
from duckduckgo_search.exceptions import DuckDuckGoSearchException

try:
    with DDGS() as ddgs:
        results = list(ddgs.text('test query', max_results=5))
        print(f'✅ 搜索成功,找到 {len(results)} 个结果')
except DuckDuckGoSearchException as e:
    print(f'❌ 搜索出错: {e}')
except Exception as e:
    print(f'❌ 未知错误: {e}')
"
```

## 使用代理

如果需要使用代理:

```bash
python -c "
from duckduckgo_search import DDGS

# 设置代理
proxy = 'http://127.0.0.1:7890'  # 替换为你的代理地址

with DDGS(proxy=proxy) as ddgs:
    results = list(ddgs.text('test query', max_results=5))
    print(f'通过代理搜索成功,找到 {len(results)} 个结果')
"
```

## 常见问题

**安装失败?**
```bash
# 确保 pip 是最新版本
pip install --upgrade pip
pip install duckduckgo-search

# 或使用 uv
uv pip install duckduckgo-search
```

**搜索无结果?**
```bash
# 检查网络连接
# 尝试使用代理
# 减少搜索关键词复杂度
# 检查地区设置是否正确
```

**请求被限制?**
```bash
# 在多次搜索之间添加延迟
import time
time.sleep(1)  # 等待 1 秒

# 减少单次请求的结果数量
max_results=5  # 而不是 50
```

## 与其他工具集成

### 结合 browser-use 获取详细内容

```bash
# 1. 先用 DuckDuckGo 搜索
python -c "
from duckduckgo_search import DDGS

with DDGS() as ddgs:
    results = list(ddgs.text('Python async tutorial', max_results=1))
    if results:
        url = results[0]['href']
        print(f'URL: {url}')
"

# 2. 用 browser-use 打开并获取详细内容
browser-use open <url_from_search>
browser-use state
```

## 注意事项

⚠️ **使用建议**:

1. **遵守使用频率限制**:避免短时间内大量请求
2. **合理设置结果数量**:不要一次请求过多结果
3. **添加适当延迟**:批量搜索时在请求之间添加 `time.sleep()`
4. **处理异常情况**:始终添加错误处理代码
5. **尊重版权**:搜索结果仅供参考,注意内容版权

Related Skills

web-search-plus

1864
from LeoYeAI/openclaw-master-skills

Unified search skill with Intelligent Auto-Routing. Uses multi-signal analysis to automatically select between Serper (Google), Tavily (Research), Exa (Neural), Perplexity (AI Answers), You.com (RAG/Real-time), and SearXNG (Privacy/Self-hosted) with confidence scoring.

ux-researcher-designer

1864
from LeoYeAI/openclaw-master-skills

UX research and design toolkit for Senior UX Designer/Researcher including data-driven persona generation, journey mapping, usability testing frameworks, and research synthesis. Use for user research, persona creation, journey mapping, and design validation.

research-summarizer

1864
from LeoYeAI/openclaw-master-skills

Structured research summarization agent skill for non-dev users. Handles academic papers, web articles, reports, and documentation. Extracts key findings, generates comparative analyses, and produces properly formatted citations. Use when: user wants to summarize a research paper, compare multiple sources, extract citations from documents, or create structured research briefs. Plugin for Claude Code, Codex, Gemini CLI, and OpenClaw.

tavily-search

1864
from LeoYeAI/openclaw-master-skills

Web search via Tavily API (alternative to Brave). Use when the user asks to search the web / look up sources / find links and Brave web_search is unavailable or undesired. Returns a small set of relevant results (title, url, snippet) and can optionally include short answer summaries.

multi-search-engine

1864
from LeoYeAI/openclaw-master-skills

Multi search engine integration with 17 engines (8 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and WolframAlpha knowledge queries. No API keys required.

google-search

1864
from LeoYeAI/openclaw-master-skills

Search the web using Google Custom Search Engine (PSE). Use this when you need live information, documentation, or to research topics and the built-in web_search is unavailable.

file-search

1864
from LeoYeAI/openclaw-master-skills

Fast file-name and content search using `fd` and `rg` (ripgrep).

exa-web-search-free

1864
from LeoYeAI/openclaw-master-skills

Free AI search via Exa MCP. Web search for news/info, code search for docs/examples from GitHub/StackOverflow, company research for business intel. No API key needed.

eBay Product Research - eBay 选品工具

1864
from LeoYeAI/openclaw-master-skills

## Description

eastmoney_financial_search

1864
from LeoYeAI/openclaw-master-skills

本skill基于东方财富妙想搜索能力,基于金融场景进行信源智能筛选,用于获取涉及时效性信息或特定事件信息的任务,包括新闻、公告、研报、政策、交易规则、具体事件、各种影响分析、以及需要检索外部数据的非常识信息等。避免AI在搜索金融场景信息时,参考到非权威、及过时的信息。

desearch-web-search

1864
from LeoYeAI/openclaw-master-skills

Search the web and get real-time SERP-style results with titles, URLs, and snippets. Use this for general web queries when you need current links and information from across the internet.

deep-research-pro

1864
from LeoYeAI/openclaw-master-skills

Multi-source deep research agent. Searches the web, synthesizes findings, and delivers cited reports. No API keys required.