{ "id": "doc-parser", "name": "文档解析器", "icon": "", "shortDesc": "支持 50+ 格式的文档解析与结构化提取", "fullDesc": "文档解析器是 Agent 的文档理解基础设施。无论是扫描版 PDF、手写笔记照片还是复杂排版的 Word 文档,都能准确提取文本、表格、图片和元数据,输出结构化的 Markdown 或 JSON。\n\n支持格式:\n- 办公文档:Word、Excel、PowerPoint、WPS\n- 版式文档:PDF(含扫描版 OCR)、EPUB、MOBI\n- 图片文档:JPG、PNG、TIFF、WebP(OCR 识别)\n- 标记语言:Markdown、HTML、XML、LaTeX\n- 代码文档:Jupyter Notebook、Swagger/OpenAPI", "category": "data", "tags": [ "文档解析", "OCR", "PDF处理", "表格提取", "格式转换" ], "version": "2.1.3", "latestVersion": "2.1.3", "updatedAt": "2025-02-14", "maintainer": { "name": "DesireCore Official", "verified": true }, "downloads": 38920, "rating": 4.7, "ratingCount": 1567, "installStatus": "not_installed", "riskLevel": "low", "requires": { "tools": [ "ocr_engine", "pdf_renderer", "table_extractor", "layout_analyzer" ], "connections": [] }, "compatibleAgents": [ "writing-coach", "data-analyst", "translator", "code-reviewer" ], "changelog": "v2.1.3: 新增手写公式识别,支持 LaTeX 自动转换" }