{"id":26201664,"url":"https://github.com/furyolo/mistralocr","last_synced_at":"2025-08-15T22:33:31.910Z","repository":{"id":281869029,"uuid":"946699158","full_name":"furyolo/mistralOCR","owner":"furyolo","description":"该仓库是一个基于Mistral API的文档识别工具，支持处理PDF和图片文件（如JPG、JPEG、PNG）。它提供图形用户界面和命令行界面，能够自动保存处理结果为Markdown格式，并支持配置文件管理和批量处理文件","archived":false,"fork":false,"pushed_at":"2025-03-13T04:24:16.000Z","size":18,"stargazers_count":74,"open_issues_count":3,"forks_count":15,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-15T05:56:24.968Z","etag":null,"topics":["batch-processing","command-line","document-recognition","gui","markdown","mistral-api","ocr","python"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/furyolo.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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}},"created_at":"2025-03-11T14:41:48.000Z","updated_at":"2025-04-15T04:36:31.000Z","dependencies_parsed_at":"2025-03-11T15:49:54.882Z","dependency_job_id":"543376c6-5681-4f00-ae09-46fb768c12b5","html_url":"https://github.com/furyolo/mistralOCR","commit_stats":null,"previous_names":["furyolo/mistralocr"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/furyolo%2FmistralOCR","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/furyolo%2FmistralOCR/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/furyolo%2FmistralOCR/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/furyolo%2FmistralOCR/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/furyolo","download_url":"https://codeload.github.com/furyolo/mistralOCR/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249016320,"owners_count":21198832,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["batch-processing","command-line","document-recognition","gui","markdown","mistral-api","ocr","python"],"created_at":"2025-03-12T03:23:09.923Z","updated_at":"2025-04-15T05:56:33.333Z","avatar_url":"https://github.com/furyolo.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Mistral OCR 文档识别工具\n\n基于 Mistral API 的文档识别工具，支持处理 PDF 和图片文件。\n\n## 功能特点\n\n- 支持处理 PDF 文件和图片文件（JPG、JPEG、PNG）\n- 提供图形用户界面和命令行界面\n- 自动保存处理结果为 Markdown 格式\n- 支持配置文件管理\n- 支持批量处理文件\n\n## 安装\n\n1. 克隆项目代码：\n\n```bash\ngit clone https://github.com/yourusername/mistralOCR.git\ncd mistralOCR\n```\n\n2. 安装依赖：\n\n```bash\npip install -r requirements.txt\n```\n\n3. 安装tkinter（如果尚未安装）：\n\n在Mac上，您可以使用以下命令安装tkinter：\n\n```bash\nbrew install python-tk\n```\n\n## 使用方法\n\n### 图形界面\n\n运行以下命令启动图形界面：\n\n```bash\npython -m src.main --gui\n```\n\n### 命令行界面\n\n使用命令行处理文件：\n\n```bash\npython -m src.main --file \u003c文件路径\u003e --api-key \u003cAPI密钥\u003e\n```\n\n### Windows下运行\n\n在Windows系统中，您可以直接双击运行 `run.bat` 文件来启动程序。\n\n```bash\n# 直接双击 run.bat 文件\n```\n\n## 项目结构\n\n```\nmistralOCR/\n├── src/                # 源代码目录\n│   ├── __init__.py    # 包初始化文件\n│   ├── main.py        # 主程序入口\n│   ├── ocr.py         # OCR核心功能\n│   ├── gui.py         # 图形界面\n│   └── config.py      # 配置管理\n├── tests/             # 测试目录\n├── docs/              # 文档目录\n├── results_pdf/       # PDF处理结果\n├── results_image/     # 图片处理结果\n├── README.md          # 项目说明\n├── requirements.txt   # 依赖列表\n└── config.json        # 配置文件\n```\n\n## 配置文件\n\n配置文件 `config.json` 用于存储常用设置：\n\n```json\n{\n    \"api_key\": \"your-api-key\"\n}\n```\n\n请注意，您可以在以下网址获取Mistral API Key: [https://console.mistral.ai/](https://console.mistral.ai/)\n\n## 开发说明\n\n### 环境要求\n\n- Python 3.7+\n- 依赖包见 requirements.txt\n\n### 开发设置\n\n1. 创建虚拟环境：\n\n```bash\npython -m venv venv\nsource venv/bin/activate  # Linux/Mac\nvenv\\Scripts\\activate     # Windows\n```\n\n2. 安装开发依赖：\n\n```bash\npip install -r requirements-dev.txt\n```\n\n### 运行测试\n\n```bash\npython -m pytest tests/\n```\n\n## 许可证\n\nMIT License\n\n## 贡献指南\n\n1. Fork 项目\n2. 创建特性分支\n3. 提交更改\n4. 推送到分支\n5. 创建 Pull Request\n\n## 问题反馈\n\n如果您在使用过程中遇到任何问题，请在 GitHub Issues 页面提交问题。 ","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffuryolo%2Fmistralocr","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffuryolo%2Fmistralocr","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffuryolo%2Fmistralocr/lists"}