# DoNew
[](https://badge.fury.io/py/donew)
[](https://pypi.org/project/donew/)
[](https://pypi.org/project/donew/)
A powerful Python package designed for AI agents to perform web processing, document navigation, and autonomous task execution. DoNew provides a high-level, agentic interface that makes it easy for AI systems to interact with web content and documents.
## Quick Install
```bash
pip install donew
donew-install-browsers # Install required browsers
```
## Why DoNew?
DoNew is built with AI agents in mind, providing intuitive interfaces for:
- Autonomous web navigation and interaction
- Document understanding and processing
- Task execution and decision making
- State management and context awareness
## Features
- Browser automation using Playwright
- Web page processing and interaction
- Vision-related tasks and image processing
- Easy-to-use API for web automation
- Async support for better performance
- AI-friendly interfaces for autonomous operation
## Roadmap
### Current Features
- **DO.Browse**: Agentic web navigation
- Autonomous webpage interaction
- Element detection and manipulation
- State awareness and context management
- Cookie and storage handling
- Visual debugging tools
### Coming Soon
- **DO.Read**: Agentic document navigation
- PDF processing and understanding
- Document structure analysis
- Content extraction and processing
- Cross-document reference handling
- **DO(...).New**: Agentic behavior execution
- Task planning and execution
- Decision making based on content
- Multi-step operation handling
- Context-aware actions
## Quick Start
```python
import asyncio
from donew import DO
async def main():
# Configure browser settings (optional)
DO.Config(headless=True) # Run in headless mode
# Start agentic web navigation
browser = await DO.Browse("https://example.com")
try:
# Analyze page content
content = await browser.text()
print("Page content:", content)
# Get all interactive elements with their context
elements = browser.elements()
# Smart element detection (finds relevant input fields by context)
input_fields = {
elem.element_label or elem.attributes.get("name", ""): id
for id, elem in elements.items()
if elem.element_type == "input"
and elem.attributes.get("type") in ["text", "email"]
}
# Autonomous form interaction
for label, element_id in input_fields.items():
await browser.type(element_id, f"test_{label}")
# State management
cookies = await browser.cookies()
print("Current browser state (cookies):", cookies)
# Context persistence
await browser.storage({
"localStorage": {"agent_context": "form_filling"},
"sessionStorage": {"task_state": "in_progress"}
})
# Visual debugging (helps AI understand page state)
await browser.toggle_annotation(True)
# Get current state for decision making
state = await browser._get_state_dict()
print("Current agent state:", state)
finally:
await browser.close()
if __name__ == "__main__":
asyncio.run(main())
```
### Example: AI Agent Task Execution
```python
from donew import DO
async def search_and_extract(query: str):
browser = await DO.Browse("https://example.com/search")
try:
# Find and interact with search form
elements = browser.elements()
search_input = next(
(id for id, elem in elements.items()
if elem.element_type == "input" and
("search" in elem.element_label.lower() if elem.element_label else False)),
None
)
if search_input:
# Execute search
await browser.type(search_input, query)
await browser.press("Enter")
# Wait for and analyze results
content = await browser.text()
# Extract structured data
return {
"query": query,
"results": content,
"page_state": await browser._get_state_dict()
}
finally:
await browser.close()
```
## Development Setup
1. Clone the repository
2. Create a virtual environment using `uv`:
```bash
uv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
```
3. Install development dependencies:
```bash
uv pip install -e ".[dev]"
```
4. Install Playwright browsers:
```bash
donew-install-browsers
```
## Testing
Run the test suite:
```bash
pytest tests/
```
For more detailed testing options, including using local or remote httpbin, see the [Testing Documentation](docs/testing.md).
## Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
Raw data
{
"_id": null,
"home_page": null,
"name": "donew",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "web automation, vision, browser, playwright, image processing",
"author": null,
"author_email": "Kenan Deniz <kenan@unrealists.com>",
"download_url": "https://files.pythonhosted.org/packages/be/60/663615e3f08d18974743e0b8750ef817ad678613083c15450d3b35a7bde3/donew-0.1.5.tar.gz",
"platform": null,
"description": "# DoNew\n\n[](https://badge.fury.io/py/donew)\n[](https://pypi.org/project/donew/)\n[](https://pypi.org/project/donew/)\n\nA powerful Python package designed for AI agents to perform web processing, document navigation, and autonomous task execution. DoNew provides a high-level, agentic interface that makes it easy for AI systems to interact with web content and documents.\n\n## Quick Install\n\n```bash\npip install donew\ndonew-install-browsers # Install required browsers\n```\n\n## Why DoNew?\n\nDoNew is built with AI agents in mind, providing intuitive interfaces for:\n- Autonomous web navigation and interaction\n- Document understanding and processing\n- Task execution and decision making\n- State management and context awareness\n\n## Features\n\n- Browser automation using Playwright\n- Web page processing and interaction\n- Vision-related tasks and image processing\n- Easy-to-use API for web automation\n- Async support for better performance\n- AI-friendly interfaces for autonomous operation\n\n## Roadmap\n\n### Current Features\n- **DO.Browse**: Agentic web navigation\n - Autonomous webpage interaction\n - Element detection and manipulation\n - State awareness and context management\n - Cookie and storage handling\n - Visual debugging tools\n\n### Coming Soon\n- **DO.Read**: Agentic document navigation\n - PDF processing and understanding\n - Document structure analysis\n - Content extraction and processing\n - Cross-document reference handling\n\n- **DO(...).New**: Agentic behavior execution\n - Task planning and execution\n - Decision making based on content\n - Multi-step operation handling\n - Context-aware actions\n\n## Quick Start\n\n```python\nimport asyncio\nfrom donew import DO\n\nasync def main():\n # Configure browser settings (optional)\n DO.Config(headless=True) # Run in headless mode\n \n # Start agentic web navigation\n browser = await DO.Browse(\"https://example.com\")\n \n try:\n # Analyze page content\n content = await browser.text()\n print(\"Page content:\", content)\n \n # Get all interactive elements with their context\n elements = browser.elements()\n \n # Smart element detection (finds relevant input fields by context)\n input_fields = {\n elem.element_label or elem.attributes.get(\"name\", \"\"): id\n for id, elem in elements.items()\n if elem.element_type == \"input\"\n and elem.attributes.get(\"type\") in [\"text\", \"email\"]\n }\n \n # Autonomous form interaction\n for label, element_id in input_fields.items():\n await browser.type(element_id, f\"test_{label}\")\n \n # State management\n cookies = await browser.cookies()\n print(\"Current browser state (cookies):\", cookies)\n \n # Context persistence\n await browser.storage({\n \"localStorage\": {\"agent_context\": \"form_filling\"},\n \"sessionStorage\": {\"task_state\": \"in_progress\"}\n })\n \n # Visual debugging (helps AI understand page state)\n await browser.toggle_annotation(True)\n \n # Get current state for decision making\n state = await browser._get_state_dict()\n print(\"Current agent state:\", state)\n \n finally:\n await browser.close()\n\nif __name__ == \"__main__\":\n asyncio.run(main())\n```\n\n### Example: AI Agent Task Execution\n\n```python\nfrom donew import DO\n\nasync def search_and_extract(query: str):\n browser = await DO.Browse(\"https://example.com/search\")\n try:\n # Find and interact with search form\n elements = browser.elements()\n search_input = next(\n (id for id, elem in elements.items() \n if elem.element_type == \"input\" and \n (\"search\" in elem.element_label.lower() if elem.element_label else False)),\n None\n )\n \n if search_input:\n # Execute search\n await browser.type(search_input, query)\n await browser.press(\"Enter\")\n \n # Wait for and analyze results\n content = await browser.text()\n \n # Extract structured data\n return {\n \"query\": query,\n \"results\": content,\n \"page_state\": await browser._get_state_dict()\n }\n finally:\n await browser.close()\n```\n\n## Development Setup\n\n1. Clone the repository\n2. Create a virtual environment using `uv`:\n```bash\nuv venv\nsource .venv/bin/activate # On Windows: .venv\\Scripts\\activate\n```\n3. Install development dependencies:\n```bash\nuv pip install -e \".[dev]\"\n```\n4. Install Playwright browsers:\n```bash\ndonew-install-browsers\n```\n\n## Testing\n\nRun the test suite:\n```bash\npytest tests/\n```\n\nFor more detailed testing options, including using local or remote httpbin, see the [Testing Documentation](docs/testing.md).\n\n## Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details. \n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A Python package for web processing and vision tasks with browser automation capabilities",
"version": "0.1.5",
"project_urls": null,
"split_keywords": [
"web automation",
" vision",
" browser",
" playwright",
" image processing"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "42d4f25450d2c5a9462e523d317352b150914669918ee5988505352a17d6d1a7",
"md5": "85de6271af5cef778f17e3a368aae592",
"sha256": "dc1721d8c6024d8f3b322a621b87302654834f99ca5414b22ca1a83d86d77b2b"
},
"downloads": -1,
"filename": "donew-0.1.5-py3-none-any.whl",
"has_sig": false,
"md5_digest": "85de6271af5cef778f17e3a368aae592",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 20988,
"upload_time": "2025-01-03T20:01:21",
"upload_time_iso_8601": "2025-01-03T20:01:21.671543Z",
"url": "https://files.pythonhosted.org/packages/42/d4/f25450d2c5a9462e523d317352b150914669918ee5988505352a17d6d1a7/donew-0.1.5-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "be60663615e3f08d18974743e0b8750ef817ad678613083c15450d3b35a7bde3",
"md5": "95f31e0595be6cb68072dc06d81f80ab",
"sha256": "fa244374501a406936894cbd27b318bbbdc3d89277860d673d0ed1ff8a1671bc"
},
"downloads": -1,
"filename": "donew-0.1.5.tar.gz",
"has_sig": false,
"md5_digest": "95f31e0595be6cb68072dc06d81f80ab",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 23356,
"upload_time": "2025-01-03T20:01:24",
"upload_time_iso_8601": "2025-01-03T20:01:24.235027Z",
"url": "https://files.pythonhosted.org/packages/be/60/663615e3f08d18974743e0b8750ef817ad678613083c15450d3b35a7bde3/donew-0.1.5.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-01-03 20:01:24",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "donew"
}
JSON