{"id":49505211,"url":"https://github.com/zjzhao1002/arxivflow","last_synced_at":"2026-05-01T15:01:24.426Z","repository":{"id":353338827,"uuid":"1218948485","full_name":"zjzhao1002/arXivFlow","owner":"zjzhao1002","description":"A Python-based automation tool that streamlines research paper tracking by fetching data from arXiv, downloading PDFs, performing local AI-driven keyword extraction, and synchronizing everything to Google Sheets.","archived":false,"fork":false,"pushed_at":"2026-05-01T03:57:50.000Z","size":27,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-01T04:20:11.516Z","etag":null,"topics":["artificial-intelligence","arxiv-api","automation","google-sheets-api"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/zjzhao1002.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-04-23T11:28:38.000Z","updated_at":"2026-05-01T03:49:44.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/zjzhao1002/arXivFlow","commit_stats":null,"previous_names":["zjzhao1002/arxiv-data-automation","zjzhao1002/arxivflow"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/zjzhao1002/arXivFlow","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zjzhao1002%2FarXivFlow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zjzhao1002%2FarXivFlow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zjzhao1002%2FarXivFlow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zjzhao1002%2FarXivFlow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zjzhao1002","download_url":"https://codeload.github.com/zjzhao1002/arXivFlow/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zjzhao1002%2FarXivFlow/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32501403,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-30T13:12:12.517Z","status":"online","status_checked_at":"2026-05-01T02:00:05.856Z","response_time":64,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["artificial-intelligence","arxiv-api","automation","google-sheets-api"],"created_at":"2026-05-01T15:01:22.250Z","updated_at":"2026-05-01T15:01:24.152Z","avatar_url":"https://github.com/zjzhao1002.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# arXivFlow 🚀\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Python 3.13+](https://img.shields.io/badge/python-3.13+-blue.svg)](https://www.python.org/downloads/)\n[![Static Badge](https://img.shields.io/badge/pypi-0.1.1-blue)](https://pypi.org/project/arxivflow/)\n[![Ollama](https://img.shields.io/badge/Ollama-Llama3.2-orange.svg)](https://ollama.ai/)\n[![arXiv](https://img.shields.io/badge/arXiv-API-red.svg)](https://arxiv.org/help/api/index)\n\n**arXivFlow** is a powerful Python-based automation tool designed to streamline the research paper discovery and tracking process. It autonomously fetches metadata from arXiv, performs local AI-driven analysis using **Ollama (Llama 3.2)**, and synchronizes the results with **Google Sheets** and local databases.\n\n---\n\n## ✨ Features\n\n- **Automated Retrieval**: Fetch the latest papers from specific arXiv categories (e.g., `cs.AI`, `cs.LG`, `hep-ph`) within any date range.\n- **Local AI Analysis**: Uses **Ollama (Llama 3.2)** to extract keywords and contact information (emails/affiliations) directly from PDF text. No cloud API costs or data privacy concerns.\n- **Intelligent PDF Handling**: Automatically downloads PDFs and extracts text for deep analysis. Supports custom storage paths.\n- **Multi-Format Export**: Save your research data to **CSV**, **JSON**, **Excel**, or **SQLite** for flexible offline analysis.\n- **Google Sheets Sync**: Seamlessly push compiled research data to a shared Google Sheet for team collaboration.\n- **Type-Safe \u0026 Modular**: Clean, documented Python code with full type hinting and a class-based architecture.\n\n---\n\n## 🛠️ Prerequisites\n\n1. **Python 3.13+**: Ensure you have a modern Python environment.\n2. **Ollama**: Install [Ollama](https://ollama.ai/) and download the required model:\n   ```bash\n   ollama pull llama3.2\n   ```\n3. **Google Cloud Credentials**:\n   - Enable the **Google Sheets** and **Google Drive** APIs.\n   - Create a **Service Account** and download the JSON key as `credentials.json`.\n   - Ensure the service account has 'Editor' permissions on the sheet.\n\n---\n\n## 🚀 Installation\n\n### From PyPI (Recommended)\n```bash\npip install arxivflow\n```\n\n### From Source (For Development)\n\n1. **Clone the repository**:\n   ```bash\n   git clone https://github.com/zjzhao/arXivFlow.git\n   cd arXivFlow\n   ```\n\n2. **Set up virtual environment**:\n   ```bash\n   python -m venv .\n   source bin/activate  # On Windows: Scripts\\activate\n   ```\n\n3. **Install dependencies**:\n   ```bash\n   pip install -e .\n   ```\n\n---\n\n## 📖 Usage\n\n### Quick Start\n\n```python\nfrom arxivflow import arXivFlow\nimport datetime\n\n# 1. Initialize the flow\nflow = arXivFlow(\n    categories=[\"cs.AI\", \"cs.CV\"], \n    ollama_model=\"llama3.2\",\n    max_results=20,\n    start_date=datetime.datetime.now() - datetime.timedelta(days=7)\n)\n\n# 2. Fetch data \u0026 Extract info (Keywords/Contacts)\ndf = flow.get_arxiv_data(download_pdfs=True)\n\n# 3. Save to your preferred formats\nflow.save_to_csv(\"my_research.csv\")\nflow.save_to_sqlite(\"research.db\")\n\n# 4. Sync with Google Sheets\nflow.save_to_google_sheet(\n    sheet_id=\"YOUR_SHEET_ID\", \n    credentials_file=\"credentials.json\"\n)\n```\n\n---\n\n## 🏗️ Architecture\n\nThe project follows a modular structure for easy extension:\n\n- `src/arxivflow/arxivflow.py`: The main orchestrator class (`arXivFlow`).\n- `src/arxivflow/ollama_functions.py`: Local LLM interface using the Ollama API.\n\n---\n\n## 📜 License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## 🤝 Contributing\n\nContributions are what make the open-source community such an amazing place to learn, inspire, and create. Any contributions you make are **greatly appreciated**.\n\n1. Fork the Project\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","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzjzhao1002%2Farxivflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzjzhao1002%2Farxivflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzjzhao1002%2Farxivflow/lists"}