https://github.com/deedy5/ddgs
DDGS | Dux Distributed Global Search. A metasearch library that aggregates results from diverse web search services
https://github.com/deedy5/ddgs
api ddgs mcp mcp-server metasearch python search websearch
Last synced: 15 days ago
JSON representation
DDGS | Dux Distributed Global Search. A metasearch library that aggregates results from diverse web search services
- Host: GitHub
- URL: https://github.com/deedy5/ddgs
- Owner: deedy5
- License: mit
- Created: 2021-04-25T18:46:43.000Z (almost 5 years ago)
- Default Branch: main
- Last Pushed: 2026-02-14T07:35:48.000Z (2 months ago)
- Last Synced: 2026-02-14T15:44:50.120Z (2 months ago)
- Topics: api, ddgs, mcp, mcp-server, metasearch, python, search, websearch
- Language: Python
- Homepage:
- Size: 763 KB
- Stars: 2,177
- Watchers: 19
- Forks: 220
- Open Issues: 14
-
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- License: LICENSE.md
Awesome Lists containing this project
- awesome-mcp - deedy5/ddgs - DDGS is a metasearch library that aggregates results from multiple web search services and integrates with the Model Context Protocol (MCP) for AI-assisted search capabilities. (MCP Frameworks and libraries / Python)
README
 [](https://github.com/deedy5/ddgs/releases) [](https://pypi.org/project/ddgs)
# DDGS | Dux Distributed Global Search
A metasearch library that aggregates results from diverse web search services.
## Table of Contents
* [Install](#install)
* [CLI version](#cli-version)
* [API Server (with MCP Integration)](#api-server-with-mcp-integration)
* [Engines](#engines)
* [DDGS class](#ddgs-class)
* [1. text()](#1-text)
* [2. images()](#2-images)
* [3. videos()](#3-videos)
* [4. news()](#4-news)
* [5. books()](#5-books)
* [6. extract()](#6-extract)
* [Disclaimer](#disclaimer)
___
## Install
```python
pip install -U ddgs # Base install
pip install -U ddgs[mcp] # With MCP server (stdio)
pip install -U ddgs[api] # With MCP + API server (SSE + FastAPI)
```
## CLI version
```python3
ddgs --help
```
[Go To TOP](#TOP)
___
## API Server (with MCP Integration)
- **Install**
```bash
pip install -U ddgs[mcp] # MCP server (stdio)
pip install -U ddgs[api] # MCP + API server (SSE + FastAPI)
```
- **CLI**
```bash
ddgs mcp # Start MCP server (stdio transport, for local MCP clients)
ddgs mcp -pr socks5h://127.0.0.1:9150 # with proxy
ddgs api # Start MCP + API server (SSE transport + FastAPI)
ddgs api -d # Start in detached mode
ddgs api -s # Stop detached server
ddgs api --host 127.0.0.1 --port 9000 -pr socks5h://127.0.0.1:9150 # Custom host / port / proxy
```
- **Docker compose**
```bash
git clone https://github.com/deedy5/ddgs && cd ddgs
docker-compose up --build
```
- **Bash script**
```bash
git clone https://github.com/deedy5/ddgs && cd ddgs
chmod +x start_api.sh
./start_api.sh
```
#### Available Endpoints
- MCP Endpoints (for AI assistants):
- **stdio** — `ddgs mcp`
- **sse** — `ddgs api`(`http://localhost:8000/sse`)
- API Docs: `http://localhost:8000/docs`
- Health Check: `http://localhost:8000/health`
#### Available MCP Tools
- `search_text` - Web text searches
- `search_images` - Image searches
- `search_news` - News searches
- `search_videos` - Video searches
- `search_books` - Book searches
- `extract_content` - Extract content from a URL
#### Typical configuration
- **stdio** (for local MCP clients):
```json
{
"mcpServers": {
"ddgs": {
"command": "ddgs",
"args": ["mcp"]
}
}
}
```
- **SSE** (for HTTP-based MCP clients):
```json
{
"mcpServers": {
"ddgs": {
"url": "http://localhost:8000/sse"
}
}
}
```
[Go To TOP](#TOP)
___
## Engines
| DDGS function | Available backends |
| --------------|:-------------------|
| text() | `bing`, `brave`, `duckduckgo`, `google`, `grokipedia`, `mojeek`, `yandex`, `yahoo`, `wikipedia`|
| images() | `duckduckgo` |
| videos() | `duckduckgo` |
| news() | `bing`, `duckduckgo`, `yahoo` |
| books() | `annasarchive` |
[Go To TOP](#TOP)
## DDGS class
DDGS class is lazy-loaded.
```python3
class DDGS:
"""Dux Distributed Global Search. A metasearch library that aggregates results from diverse web search services.
Args:
proxy (str, optional): proxy for the HTTP client, supports http/https/socks5 protocols.
example: "http://user:pass@example.com:3128". Defaults to None.
timeout (int, optional): Timeout value for the HTTP client. Defaults to 5.
verify: (bool | str): True to verify, False to skip, or a str path to a PEM file. Defaults to True.
"""
```
Here is an example of initializing the DDGS class.
```python3
from ddgs import DDGS
results = DDGS().text("python programming", max_results=5)
print(results)
```
[Go To TOP](#TOP)
## 1. text()
```python
def text(
query: str,
region: str = "us-en",
safesearch: str = "moderate",
timelimit: str | None = None,
max_results: int | None = 10,
page: int = 1,
backend: str = "auto",
) -> list[dict[str, str]]:
"""DDGS text metasearch.
Args:
query: text search query.
region: us-en, uk-en, ru-ru, etc. Defaults to us-en.
safesearch: on, moderate, off. Defaults to "moderate".
timelimit: d, w, m, y. Defaults to None.
max_results: maximum number of results. Defaults to 10.
page: page of results. Defaults to 1.
backend: A single or comma-delimited backends. Defaults to "auto".
Returns:
List of dictionaries with search results.
"""
```
***Example***
```python
results = DDGS().text('live free or die', region='us-en', safesearch='off', timelimit='y', page=1, backend="auto")
# Searching for pdf files
results = DDGS().text('russia filetype:pdf', region='us-en', safesearch='off', timelimit='y', page=1, backend="auto")
print(results)
[
{
"title": "News, sport, celebrities and gossip | The Sun",
"href": "https://www.thesun.co.uk/",
"body": "Get the latest news, exclusives, sport, celebrities, showbiz, politics, business and lifestyle from The Sun",
}, ...
]
```
[Go To TOP](#TOP)
## 2. images()
```python
def images(
query: str,
region: str = "us-en",
safesearch: str = "moderate",
timelimit: str | None = None,
max_results: int | None = 10,
page: int = 1,
backend: str = "auto",
size: str | None = None,
color: str | None = None,
type_image: str | None = None,
layout: str | None = None,
license_image: str | None = None,
) -> list[dict[str, str]]:
"""DDGS images metasearch.
Args:
query: images search query.
region: us-en, uk-en, ru-ru, etc. Defaults to us-en.
safesearch: on, moderate, off. Defaults to "moderate".
timelimit: d, w, m, y. Defaults to None.
max_results: maximum number of results. Defaults to 10.
page: page of results. Defaults to 1.
backend: A single or comma-delimited backends. Defaults to "auto".
size: Small, Medium, Large, Wallpaper. Defaults to None.
color: color, Monochrome, Red, Orange, Yellow, Green, Blue,
Purple, Pink, Brown, Black, Gray, Teal, White. Defaults to None.
type_image: photo, clipart, gif, transparent, line.
Defaults to None.
layout: Square, Tall, Wide. Defaults to None.
license_image: any (All Creative Commons), Public (PublicDomain),
Share (Free to Share and Use), ShareCommercially (Free to Share and Use Commercially),
Modify (Free to Modify, Share, and Use), ModifyCommercially (Free to Modify, Share, and
Use Commercially). Defaults to None.
Returns:
List of dictionaries with images search results.
"""
```
***Example***
```python
results = DDGS().images(
query="butterfly",
region="us-en",
safesearch="off",
timelimit="m",
page=1,
backend="auto",
size=None,
color="Monochrome",
type_image=None,
layout=None,
license_image=None,
)
print(images)
[
{
"title": "File:The Sun by the Atmospheric Imaging Assembly of NASA's Solar ...",
"image": "https://upload.wikimedia.org/wikipedia/commons/b/b4/The_Sun_by_the_Atmospheric_Imaging_Assembly_of_NASA's_Solar_Dynamics_Observatory_-_20100819.jpg",
"thumbnail": "https://tse4.mm.bing.net/th?id=OIP.lNgpqGl16U0ft3rS8TdFcgEsEe&pid=Api",
"url": "https://en.wikipedia.org/wiki/File:The_Sun_by_the_Atmospheric_Imaging_Assembly_of_NASA's_Solar_Dynamics_Observatory_-_20100819.jpg",
"height": 3860,
"width": 4044,
"source": "Bing",
}, ...
]
```
[Go To TOP](#TOP)
## 3. videos()
```python
def videos(
query: str,
region: str = "us-en",
safesearch: str = "moderate",
timelimit: str | None = None,
max_results: int | None = 10,
page: int = 1,
backend: str = "auto",
resolution: str | None = None,
duration: str | None = None,
license_videos: str | None = None,
) -> list[dict[str, str]]:
"""DDGS videos metasearch.
Args:
query: videos search query.
region: us-en, uk-en, ru-ru, etc. Defaults to us-en.
safesearch: on, moderate, off. Defaults to "moderate".
timelimit: d, w, m. Defaults to None.
max_results: maximum number of results. Defaults to 10.
page: page of results. Defaults to 1.
backend: A single or comma-delimited backends. Defaults to "auto".
resolution: high, standart. Defaults to None.
duration: short, medium, long. Defaults to None.
license_videos: creativeCommon, youtube. Defaults to None.
Returns:
List of dictionaries with videos search results.
"""
```
***Example***
```python
results = DDGS().videos(
query="cars",
region="us-en",
safesearch="off",
timelimit="w",
page=1,
backend="auto",
resolution="high",
duration="medium",
)
print(results)
[
{
"content": "https://www.youtube.com/watch?v=6901-C73P3g",
"description": "Watch the Best Scenes of popular Tamil Serial #Meena that airs on Sun TV. Watch all Sun TV serials immediately after the TV telecast on Sun NXT app. *Free for Indian Users only Download here: Android - http://bit.ly/SunNxtAdroid iOS: India - http://bit.ly/sunNXT Watch on the web - https://www.sunnxt.com/ Two close friends, Chidambaram ...",
"duration": "8:22",
"embed_html": '',
"embed_url": "https://www.youtube.com/embed/6901-C73P3g?autoplay=1",
"image_token": "6c070b5f0e24e5972e360d02ddeb69856202f97718ea6c5d5710e4e472310fa3",
"images": {
"large": "https://tse4.mm.bing.net/th?id=OVF.JWBFKm1u%2fHd%2bz2e1GitsQw&pid=Api",
"medium": "https://tse4.mm.bing.net/th?id=OVF.JWBFKm1u%2fHd%2bz2e1GitsQw&pid=Api",
"motion": "",
"small": "https://tse4.mm.bing.net/th?id=OVF.JWBFKm1u%2fHd%2bz2e1GitsQw&pid=Api",
},
"provider": "Bing",
"published": "2024-07-03T05:30:03.0000000",
"publisher": "YouTube",
"statistics": {"viewCount": 29059},
"title": "Meena - Best Scenes | 02 July 2024 | Tamil Serial | Sun TV",
"uploader": "Sun TV",
}, ...
]
```
[Go To TOP](#TOP)
## 4. news()
```python
def news(
query: str,
region: str = "us-en",
safesearch: str = "moderate",
timelimit: str | None = None,
max_results: int | None = 10,
page: int = 1,
backend: str = "auto",
) -> list[dict[str, str]]:
"""DDGS news metasearch.
Args:
query: news search query.
region: us-en, uk-en, ru-ru, etc. Defaults to us-en.
safesearch: on, moderate, off. Defaults to "moderate".
timelimit: d, w, m. Defaults to None.
max_results: maximum number of results. Defaults to 10.
page: page of results. Defaults to 1.
backend: A single or comma-delimited backends. Defaults to "auto".
Returns:
List of dictionaries with news search results.
"""
```
***Example***
```python
results = DDGS().news(query="sun", region="us-en", safesearch="off", timelimit="m", page=1, backend="auto")
print(results)
[
{
"date": "2024-07-03T16:25:22+00:00",
"title": "Murdoch's Sun Endorses Starmer's Labour Day Before UK Vote",
"body": "Rupert Murdoch's Sun newspaper endorsed Keir Starmer and his opposition Labour Party to win the UK general election, a dramatic move in the British media landscape that illustrates the country's shifting political sands.",
"url": "https://www.msn.com/en-us/money/other/murdoch-s-sun-endorses-starmer-s-labour-day-before-uk-vote/ar-BB1plQwl",
"image": "https://img-s-msn-com.akamaized.net/tenant/amp/entityid/BB1plZil.img?w=2000&h=1333&m=4&q=79",
"source": "Bloomberg on MSN.com",
}, ...
]
```
[Go To TOP](#TOP)
## 5. books()
```python
def books(
query: str,
max_results: int | None = 10,
page: int = 1,
backend: str = "auto",
) -> list[dict[str, str]]:
"""DDGS books metasearch.
Args:
query: news search query.
max_results: maximum number of results. Defaults to 10.
page: page of results. Defaults to 1.
backend: A single or comma-delimited backends. Defaults to "auto".
Returns:
List of dictionaries with news search results.
"""
```
***Example***
```python
results = DDGS().books(query="sea wolf jack london", page=1, backend="auto")
print(results)
[
{
'title': 'The Sea-Wolf',
'author': 'Jack London',
'publisher': 'DigiCat, 2022',
'info': 'English [en], .epub, 🚀/zlib, 0.5MB, 📗 Book (unknown)',
'url': 'https://annas-archive.li/md5/574f6556f1df6717de4044e36c7c2782',
'thumbnail': 'https://s3proxy.cdn-zlib.sk//covers299/collections/userbooks/da4954486be7c2b2b9f70b2aa5bcf01292de3ea510b5656f892821950ded9ada.jpg',
}, ...
]
```
[Go To TOP](#TOP)
## 6. extract()
Fetch a URL and extract its content in various formats.
```python
def extract(
url: str,
fmt: str = "text_markdown",
) -> dict[str, str | bytes]:
"""Fetch a URL and extract its content.
Args:
url: The URL to fetch and extract content from.
fmt: Output format:
"text_markdown" (HTML→Markdown, preserves links/headers/lists),
"text_plain" (HTML→plain text),
"text_rich" (HTML→rich text with headers/lists),
"text" (raw HTML),
"content" (raw bytes).
Returns:
Dictionary with 'url' and 'content' keys.
"""
```
***Examples***
```python
# Markdown (default) - preserves links, headers, lists
result = DDGS().extract("https://example.com")
print(result)
{"url": "https://example.com", "content": "# Example Domain\n\nThis domain is for use in..."}
# Plain text
result = DDGS().extract("https://example.com", fmt="text_plain")
# Rich text (headers/lists, no link URLs)
result = DDGS().extract("https://example.com", fmt="text_rich")
# Raw HTML
result = DDGS().extract("https://example.com", fmt="text")
# Raw bytes
result = DDGS().extract("https://example.com", fmt="content")
```
***CLI***
```bash
ddgs extract -u https://example.com
ddgs extract -u https://example.com -f text_plain
ddgs extract -u https://example.com -f content -o output.json
```
[Go To TOP](#TOP)
## Disclaimer
This library is for educational purposes only.