information-composer 0.4.0

A comprehensive toolkit for collecting, composing, and filtering information from various web resources with AI-powered markdown processing

Information Composer

A comprehensive toolkit for collecting, composing, and filtering information from various web resources with AI-powered markdown processing.

Features

Core Modules

• PDF Validation: Validate PDF file formats and integrity
• Markdown Processing: Advanced markdown processing with LLM filtering
• DOI Management: Download and manage academic papers by DOI
• PubMed Integration: Query and process PubMed data with CLI tool

AI-Powered Features

• LLM Filtering: Support for DashScope, Ollama, and OpenAI
• PubMed Analyzer: AI-powered literature analysis using Pydantic AI
• Markdown Filter: Intelligent content extraction and filtering

Migration Note: This project uses Pydantic AI for type-safe LLM integration. See Migration Guide for details.

Web Scraping & Data Collection

• Crossref Integration: Query Crossref API for bibliographic data
• Google Scholar Integration: Crawl and process Google Scholar citations
• RSS Feed Processing: Parse and manage scientific RSS feeds
• RiceDataCN Parser: Extract gene data from RiceDataCN database

Developer Tools

• Code Quality: Ruff linter and formatter (primary tool)
• Testing: Pytest with 51%+ coverage (570 tests passed)
• Multi-format Support: PDF, Markdown, JSON, XML, TXT

Installation

Prerequisites

• Python 3.12 or 3.13 (Python 3.12 is the minimum required version)
• Virtual environment (recommended)

Setup

1. Clone the repository:

git clone https://github.com/yourusername/information-composer.git
cd information-composer

2. Create and activate virtual environment:

# Linux/macOS
python -m venv .venv
source .venv/bin/activate

# Windows
python -m venv .venv
.venv\Scripts\activate

3. Install dependencies:

pip install -e .

Quick Start

Activate Environment

# Linux/macOS
source activate.sh

# Windows
activate.bat

Available CLI Commands

Command	Description
pdf-validator	Validate PDF files
md-llm-filter	Filter markdown with LLM
pubmed-cli	Search and fetch PubMed data
google-scholar-crawler	Crawl Google Scholar citations
rss-fetcher	Fetch and process RSS feeds
crossref-cli	Query Crossref API

Examples

# Validate PDF files
pdf-validator document.pdf

# Validate directory of PDFs
pdf-validator -d /path/to/directory -r

# Filter markdown with LLM
md-llm-filter -i input.md -o output.md

# Search PubMed
pubmed-cli search "cancer research" -e [e-mail]

# Get details for specific PMIDs
pubmed-cli details 12345678 23456789 -e [e-mail]

# Crawl Google Scholar
google-scholar-crawler -q "machine learning" -n 20

# Fetch RSS feeds
rss-fetcher -u "https://example.com/feed.xml" -o output.json

# Query Crossref
crossref-cli query --doi "10.1038/nature12373"

Python API Usage

PubMed Integration

from information_composer.pubmed import query_pmid, fetch_pubmed_details_batch_sync

# Search for articles
pmids = query_pmid("cancer immunotherapy", "[e-mail]", 50)

# Fetch detailed information
details = fetch_pubmed_details_batch_sync(pmids, "[e-mail]")

Crossref Integration

from information_composer import CrossrefClient, query_crossref

# Query Crossref API
client = CrossrefClient()
results = client.query_works(query="machine learning", limit=10)

# Or use the convenience function
works = query_crossref("machine learning")

DOI Downloader

from information_composer import DOIDownloader

# Download paper by DOI
downloader = DOIDownloader()
result = downloader.download_doi("10.1038/nature12373")

Markdown Processing

from information_composer import jsonify, markdownify

# Convert markdown to JSON
json_data = jsonify(markdown_content)

# Convert JSON to markdown
markdown_content = markdownify(json_data)

PDF Validation

from information_composer import PDFValidator

# Validate PDF
validator = PDFValidator(verbose=True)
is_valid, error = validator.validate_single_pdf("document.pdf")

Google Scholar Crawling

from information_composer.sites.google_scholar import SearchConfig, google_scholar_search

# Search Google Scholar
config = SearchConfig(query="deep learning", num_results=20)
results = google_scholar_search(config)

Development

Code Quality

This project uses Ruff as the primary code quality tool:

# Run all checks
python scripts/check_code.py

# Auto-fix issues
python scripts/check_code.py --fix

# With tests
python scripts/check_code.py --with-tests

# Verbose output
python scripts/check_code.py --verbose

Testing

# Run tests
pytest tests/ -v

# Run tests with coverage
python scripts/check_code.py --with-tests

Project Structure

information-composer/
├── src/information_composer/
│   ├── core/              # Core functionality (DOI downloader)
│   ├── crossref/          # Crossref API integration
│   ├── llm_filter/        # LLM-based markdown filtering
│   ├── markdown/          # Markdown processing utilities
│   ├── pdf/               # PDF validation
│   ├── pubmed/            # PubMed integration
│   ├── rss/               # RSS feed processing
│   └── sites/             # Web scraping (Google Scholar, RiceDataCN)
├── examples/              # Usage examples
├── scripts/               # Utility scripts
├── docs/                  # Documentation
└── tests/                 # Test files

Documentation

• 📚 Complete Documentation - Full project documentation
• 🚀 Quick Start - Get started in 5 minutes
• ⚙️ Configuration - Configuration options
• 📖 Feature Guides - Detailed feature documentation
  • PDF Validation
  • Markdown Processing
  • PubMed Integration
  • Crossref Integration
  • Google Scholar
  • RSS Processing
  • DOI Download
  • LLM Filtering
• 🔧 Development - Development and contributing guide

Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Run code quality checks: python scripts/check_code.py --fix
5. Run tests: python scripts/check_code.py --with-tests
6. Submit a pull request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Support

For questions and support, please open an issue on GitHub.