example_usage

# MarkItDown 使用示例 本文档提供了在各种场景下使用 MarkItDown 的实际示例。 ## 基础示例 ### 1. 简单文件转换 python from markitdown import MarkItDown md = MarkItDown() # 转换 PDF result = md.convert("research_paper.pdf") print(result.text_content) # 转换 Word 文档 result = md.convert("manuscript.docx") print(result.text_content) # 转换 PowerPoint result = md.convert("presentation.pptx") print(result.text_content) ### 2. 保存到文件 python from markitdown import MarkItDown md = MarkItDown() result = md.convert("document.pdf") with open("output.md", "w", encoding="utf-8") as f: f.write(result.text_content) ### 3. 从流转换 python from markitdown import MarkItDown md = MarkItDown() with open("document.pdf", "rb") as f: result = md.convert_stream(f, file_extension=".pdf") print(result.text_content) ## 科学工作流 ### 转换研究论文 python from markitdown import MarkItDown from pathlib import Path md = MarkItDown() # 转换目录中的所有论文 papers_dir = Path("research_papers/") output_dir = Path("markdown_papers/") output_dir.mkdir(exist_ok=True) for paper in papers_dir.glob("*.pdf"): result = md.convert(str(paper)) # 使用原始文件名保存 output_file = output_dir / f"{paper.stem}.md" output_file.write_text(result.text_content) print(f"Converted: {paper.name}") ### 从 Excel 提取表格 python from markitdown import MarkItDown md = MarkItDown() # 将 Excel 转换为 Markdown 表格 result = md.convert("experimental_data.xlsx") # 结果包含 Markdown 格式的表格 print(result.text_content) # 保存以供进一步处理 with open("data_tables.md", "w") as f: f.write(result.text_content) ### 处理演示幻灯片 python from markitdown import MarkItDown from openai import OpenAI # 为图像添加 AI 描述 client = OpenAI() md = MarkItDown( llm_client=client, llm_model="anthropic/claude-sonnet-4.5", llm_prompt="Describe this scientific slide, focusing on data and key findings" ) result = md.convert("conference_talk.pptx") # 保存并附带元数据 output = f"""# Conference Talk {result.text_content} """ with open("talk_notes.md", "w") as f: f.write(output) ## AI 增强转换 ### 详细图像描述 python from markitdown import MarkItDown from openai import OpenAI # 初始化