# LiteAuto 🚀
[](https://badge.fury.io/py/liteauto)
[](https://opensource.org/licenses/MIT)
LiteAuto is a lightweight Python library that provides easy-to-use tools for web automation, content parsing, vision AI, and smart searching. It's designed to be simple yet powerful, making common automation tasks effortless.
## 📦 Installation
```bash
pip install liteauto
```
## ✨ Features
- 🔍 Smart Google search with multi-query support
- 📄 Fast content parsing from web pages and PDFs
- 🧠 Vision AI for content analysis
- 📧 Gmail automation
- 📚 arXiv paper analysis
- 🔄 Project to prompt conversion
- 🎯 Word-level text operations
## 🚀 Quick Start
### Web Search and Parsing
```python
from liteauto import google, parse
# Simple Google search
urls = google("python programming", max_urls=5)
# Parse web content
contents = parse(urls)
for content in contents:
print(f"URL: {content.url}")
print(f"Content: {content.content[:200]}...")
```
### Vision AI Features
```python
from liteauto import visionai, wlanswer, wlsplit
# Get AI-powered search results
results = visionai("machine learning fundamentals", k=3)
print(results)
# Split text into meaningful chunks
chunks = wlsplit(long_text)
# Get relevant answers from context
answer = wlanswer(context="long text...", query="specific question", k=1)
```
### Gmail Automation
```python
from liteauto import gmail, automail
# Send a simple email
gmail(body="Hello World!",
subject="Test Email",
to_email="recipient@example.com")
# Create an automated email responder
def auto_response(subject, body):
return f"Auto-reply to: {subject}"
automail(auto_response, sleep_time=2)
```
### arXiv Integration
```python
from liteauto import get_todays_arxiv_papers, research_paper_analysis
# Get today's arXiv papers
papers_df = get_todays_arxiv_papers()
# Analyze a research paper
paper_insights = research_paper_analysis("https://arxiv.org/pdf/2301.00001.pdf")
print(paper_insights.summary_insights)
```
### Project Analysis
```python
from liteauto import ProjectToPrompt, project_to_markdown
# Convert project to documentation
project = ProjectToPrompt("path/to/project")
docs = project.generate_markdown()
# Generate markdown from project
markdown = project_to_markdown("path/to/project")
```
## 📚 Main Components
```python
from liteauto import (
# Search and parsing
google, # Google search functionality
parse, # Web content parser
aparse, # Async web content parser
# Vision AI
visionai, # Advanced vision AI search
minivisionai, # Lightweight vision AI
deepvisionai, # Deep vision AI analysis
# Text operations
wlanswer, # Get answers from context
wlsplit, # Split text into chunks
wlsimchunks, # Get similar chunks
wltopk, # Get top-k similar items
# Email
gmail, # Gmail operations
automail, # Email automation
GmailAutomation,# Full Gmail automation class
# arXiv
get_todays_arxiv_papers, # Get recent arXiv papers
research_paper_analysis, # Analyze research papers
# Project tools
ProjectToPrompt, # Convert project to prompts
project_to_markdown # Convert project to markdown
)
```
## 🛠️ Advanced Usage
### Custom Search Configuration
```python
# Configure advanced search parameters
urls = google(
query="python tutorials",
max_urls=10,
animation=False,
allow_pdf_extraction=True,
allow_youtube_urls_extraction=True
)
```
### Vision AI with Custom Parameters
```python
results = visionai(
query="deep learning applications",
max_urls=15,
k=10,
model="llama3.2:1b-instruct-q4_K_M",
temperature=0.05,
genai_query_k=7,
query_k=15
)
```
### Automated Paper Analysis
```python
from liteauto import research_paper_analysis
paper = research_paper_analysis("paper_url.pdf")
print(f"Problem Statement: {paper.abs_insights.problem_statement}")
print(f"Key Approach: {paper.abs_insights.key_approach}")
print(f"Main Findings: {paper.summary_insights.main_results}")
```
## 🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
1. Fork the repository
2. Create your feature branch (`git checkout -b feature/AmazingFeature`)
3. Commit your changes (`git commit -m 'Add some AmazingFeature'`)
4. Push to the branch (`git push origin feature/AmazingFeature`)
5. Open a Pull Request
## 📝 License
This project is licensed under the MIT License - see the LICENSE file for details.
## ✨ Contributors
<a href="https://github.com/yourusername/liteauto/graphs/contributors">
<img src="https://contrib.rocks/image?repo=yourusername/liteauto" />
</a>
## 🌟 Star History
[](https://star-history.com/#yourusername/liteauto&Date)
Raw data
{
"_id": null,
"home_page": "https://github.com/santhosh/",
"name": "liteauto",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.10",
"maintainer_email": null,
"keywords": null,
"author": "Kammari Santhosh",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/c6/e8/529de60e2e5e616565cf0a8de11523e70fd1084fbae5ade859c8688d3ac2/liteauto-0.0.81.tar.gz",
"platform": null,
"description": "# LiteAuto \ud83d\ude80\n\n[](https://badge.fury.io/py/liteauto)\n[](https://opensource.org/licenses/MIT)\n\nLiteAuto is a lightweight Python library that provides easy-to-use tools for web automation, content parsing, vision AI, and smart searching. It's designed to be simple yet powerful, making common automation tasks effortless.\n\n## \ud83d\udce6 Installation\n\n```bash\npip install liteauto\n```\n\n## \u2728 Features\n\n- \ud83d\udd0d Smart Google search with multi-query support\n- \ud83d\udcc4 Fast content parsing from web pages and PDFs\n- \ud83e\udde0 Vision AI for content analysis\n- \ud83d\udce7 Gmail automation\n- \ud83d\udcda arXiv paper analysis\n- \ud83d\udd04 Project to prompt conversion\n- \ud83c\udfaf Word-level text operations\n\n## \ud83d\ude80 Quick Start\n\n### Web Search and Parsing\n\n```python\nfrom liteauto import google, parse\n\n# Simple Google search\nurls = google(\"python programming\", max_urls=5)\n\n# Parse web content\ncontents = parse(urls)\nfor content in contents:\n print(f\"URL: {content.url}\")\n print(f\"Content: {content.content[:200]}...\")\n```\n\n### Vision AI Features\n\n```python\nfrom liteauto import visionai, wlanswer, wlsplit\n\n# Get AI-powered search results\nresults = visionai(\"machine learning fundamentals\", k=3)\nprint(results)\n\n# Split text into meaningful chunks\nchunks = wlsplit(long_text)\n\n# Get relevant answers from context\nanswer = wlanswer(context=\"long text...\", query=\"specific question\", k=1)\n```\n\n### Gmail Automation\n\n```python\nfrom liteauto import gmail, automail\n\n# Send a simple email\ngmail(body=\"Hello World!\", \n subject=\"Test Email\", \n to_email=\"recipient@example.com\")\n\n# Create an automated email responder\ndef auto_response(subject, body):\n return f\"Auto-reply to: {subject}\"\n\nautomail(auto_response, sleep_time=2)\n```\n\n### arXiv Integration\n\n```python\nfrom liteauto import get_todays_arxiv_papers, research_paper_analysis\n\n# Get today's arXiv papers\npapers_df = get_todays_arxiv_papers()\n\n# Analyze a research paper\npaper_insights = research_paper_analysis(\"https://arxiv.org/pdf/2301.00001.pdf\")\nprint(paper_insights.summary_insights)\n```\n\n### Project Analysis\n\n```python\nfrom liteauto import ProjectToPrompt, project_to_markdown\n\n# Convert project to documentation\nproject = ProjectToPrompt(\"path/to/project\")\ndocs = project.generate_markdown()\n\n# Generate markdown from project\nmarkdown = project_to_markdown(\"path/to/project\")\n```\n\n## \ud83d\udcda Main Components\n\n```python\nfrom liteauto import (\n # Search and parsing\n google, # Google search functionality\n parse, # Web content parser\n aparse, # Async web content parser\n \n # Vision AI\n visionai, # Advanced vision AI search\n minivisionai, # Lightweight vision AI\n deepvisionai, # Deep vision AI analysis\n \n # Text operations\n wlanswer, # Get answers from context\n wlsplit, # Split text into chunks\n wlsimchunks, # Get similar chunks\n wltopk, # Get top-k similar items\n \n # Email\n gmail, # Gmail operations\n automail, # Email automation\n GmailAutomation,# Full Gmail automation class\n \n # arXiv\n get_todays_arxiv_papers, # Get recent arXiv papers\n research_paper_analysis, # Analyze research papers\n \n # Project tools\n ProjectToPrompt, # Convert project to prompts\n project_to_markdown # Convert project to markdown\n)\n```\n\n## \ud83d\udee0\ufe0f Advanced Usage\n\n### Custom Search Configuration\n\n```python\n# Configure advanced search parameters\nurls = google(\n query=\"python tutorials\",\n max_urls=10,\n animation=False,\n allow_pdf_extraction=True,\n allow_youtube_urls_extraction=True\n)\n```\n\n### Vision AI with Custom Parameters\n\n```python\nresults = visionai(\n query=\"deep learning applications\",\n max_urls=15,\n k=10,\n model=\"llama3.2:1b-instruct-q4_K_M\",\n temperature=0.05,\n genai_query_k=7,\n query_k=15\n)\n```\n\n### Automated Paper Analysis\n\n```python\nfrom liteauto import research_paper_analysis\n\npaper = research_paper_analysis(\"paper_url.pdf\")\nprint(f\"Problem Statement: {paper.abs_insights.problem_statement}\")\nprint(f\"Key Approach: {paper.abs_insights.key_approach}\")\nprint(f\"Main Findings: {paper.summary_insights.main_results}\")\n```\n\n## \ud83e\udd1d Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\n1. Fork the repository\n2. Create your feature branch (`git checkout -b feature/AmazingFeature`)\n3. Commit your changes (`git commit -m 'Add some AmazingFeature'`)\n4. Push to the branch (`git push origin feature/AmazingFeature`)\n5. Open a Pull Request\n\n## \ud83d\udcdd License\n\nThis project is licensed under the MIT License - see the LICENSE file for details.\n\n## \u2728 Contributors\n\n<a href=\"https://github.com/yourusername/liteauto/graphs/contributors\">\n <img src=\"https://contrib.rocks/image?repo=yourusername/liteauto\" />\n</a>\n\n## \ud83c\udf1f Star History\n\n[](https://star-history.com/#yourusername/liteauto&Date)",
"bugtrack_url": null,
"license": "MIT",
"summary": "free google results",
"version": "0.0.81",
"project_urls": {
"Homepage": "https://github.com/santhosh/",
"Repository": "https://github.com/santhosh/"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "88c52f4557954899d15285a6152647cbdeffa9caa2c53066561d9e64cba35535",
"md5": "19cf9f6eb68246ac0200aa64c788191d",
"sha256": "ceed1b04af4c53bc8c1f1c9d462023ebc47f9b0afe018bbb84f35ed301808c30"
},
"downloads": -1,
"filename": "liteauto-0.0.81-py3-none-any.whl",
"has_sig": false,
"md5_digest": "19cf9f6eb68246ac0200aa64c788191d",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.10",
"size": 85902,
"upload_time": "2025-02-01T14:34:15",
"upload_time_iso_8601": "2025-02-01T14:34:15.059793Z",
"url": "https://files.pythonhosted.org/packages/88/c5/2f4557954899d15285a6152647cbdeffa9caa2c53066561d9e64cba35535/liteauto-0.0.81-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "c6e8529de60e2e5e616565cf0a8de11523e70fd1084fbae5ade859c8688d3ac2",
"md5": "dc25826c83508d82c01f0e81fcaf83e2",
"sha256": "63cd89f5b39823e9a47edd97e54d8c102a985f799648f39b5d463c934bef619f"
},
"downloads": -1,
"filename": "liteauto-0.0.81.tar.gz",
"has_sig": false,
"md5_digest": "dc25826c83508d82c01f0e81fcaf83e2",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.10",
"size": 67810,
"upload_time": "2025-02-01T14:34:18",
"upload_time_iso_8601": "2025-02-01T14:34:18.026575Z",
"url": "https://files.pythonhosted.org/packages/c6/e8/529de60e2e5e616565cf0a8de11523e70fd1084fbae5ade859c8688d3ac2/liteauto-0.0.81.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-02-01 14:34:18",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "liteauto"
}
JSON