# doc2ppt

**Repository Path**: zhou-jiming/doc2ppt

## Basic Information

- **Project Name**: doc2ppt
- **Description**: 根据docx文档，利用api调用人工智能，提炼成演讲稿
- **Primary Language**: Python
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-10-23
- **Last Updated**: 2025-10-23

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

1. # Word Document to PPT Intelligent Generation Tool - User Manual

   ## Tool Overview

   The Word Document to PPT Intelligent Generation Tool is a Python-based  automated utility that intelligently converts Word document content into PowerPoint presentations. The tool supports two modes:

   - **AI Intelligent Refinement Mode**: Uses DeepSeek API for smart content analysis and refinement
   - **Basic Extraction Mode**: Uses built-in algorithms to extract key content

   ## Features

   ### 🚀 Core Functions

   - **Intelligent Structure Analysis**: Automatically identifies chapter structure in Word documents
   - **Content Refinement**: Condenses lengthy documents into PPT-friendly key points
   - **Automatic Layout**: Generates professional and aesthetically pleasing PPT layouts
   - **AI Enhancement**: Optimizes content expression using large language models

   ### 📊 Output Content

   - Cover page
   - Table of contents page
   - Chapter title pages
   - Content slides
   - Key points summary page
   - Closing page

   ## System Requirements

   ### Hardware & Software

   - Windows/MacOS/Linux
   - Python 3.7 or higher
   - Microsoft PowerPoint (for viewing generated PPT files)

   ### Python Dependencies

   bash

   ```
   pip install python-docx python-pptx requests
   ```

   

   ## Installation

   ### Method 1: Direct Execution

   1. Ensure Python 3.7+ is installed
   2. Install required dependencies
   3. Download the `apidoc2ppt.py` file
   4. Run the program

   ### Method 2: Run from Source Code

   bash

   ```
   git clone <repository-url>
   cd project-directory
   pip install -r requirements.txt
   python apidoc2ppt.py
   ```

   

   ## Configuration

   ### API Key Configuration (Optional)

   To use AI intelligent refinement features, configure DeepSeek API key:

   **Method 1: Direct Code Modification**

   python

   ```
   # Uncomment and add your API key in main() function
   DEEPSEEK_API_KEY = "sk-your-actual-api-key-here"
   ```

   

   **Method 2: Environment Variables**

   python

   ```
   import os
   DEEPSEEK_API_KEY = os.getenv('DEEPSEEK_API_KEY')
   ```

   

   ### Obtaining API Key

   1. Visit [DeepSeek Official Website](https://www.deepseek.com)
   2. Register an account and obtain API key
   3. Ensure sufficient account balance

   ## Usage Instructions

   ### Basic Usage Process

   1. **Start the Program**

      bash

   ```
   python apidoc2ppt.py
   ```

   

   1. **Input Document Path**
      - Program will prompt for Word document path
      - Drag and drop document into command line window
      - Or manually enter full path
   2. **Wait for Processing**
      - Program automatically analyzes document structure
      - Processes content based on configured mode
      - Generates PPT file
   3. **View Results**
      - Program automatically opens generated PPT file
      - Output file saved in same directory as original Word document

   ### Command Line Parameters (Optional Modifications)

   Adjustable default parameters in code:

   python

   ```
   # Default document path (used if no input provided)
   docx_path = r"e:\temp\img2ppt\doc_folder\06-第1章.docx"
   
   # Output file naming convention
   output_ppt_path = f"{base_name}_{'AI_Refined' if converter.use_api else 'Basic'}.pptx"
   ```

   

   ## Document Format Requirements

   ### Supported Formats

   - Word documents in `.docx` format
   - Does not support legacy `.doc` format

   ### Recommended Document Structure

   For optimal conversion results, ensure Word documents have clear structure:

   **Recommended Format:**

   text

   ```
   Chapter 1 Chapter Title
      1.1 Section Title
      Content text...
      1.2 Section Title
      Content text...
   Chapter 2 Chapter Title
      2.1 Section Title
      Content text...
   ```

   

   **Heading Styles:**

   - Use Word's "Heading 1", "Heading 2" styles
   - Or include clear identifiers like "Chapter X", "X.X"

   ## Output Quality

   ### PPT Structure

   1. **Cover Page**: Document title + generation mode identifier
   2. **Table of Contents**: Automatically generated chapter index
   3. **Chapter Pages**: Overview page for each chapter
   4. **Content Pages**: Key points for each section
   5. **Summary Page**: Consolidated key points from document
   6. **Closing Page**: Thank you + Q&A

   ### Visual Style

   - Professional business style
   - Consistent fonts and colors
   - Clear hierarchical structure
   - Appropriate text density

   ## Mode Comparison

   ### AI Intelligent Refinement Mode

   **Advantages:**

   - More precise and refined content
   - Clearer logical structure
   - More professional expression
   - Automatic overview and summary generation

   **Requirements:**

   - Valid DeepSeek API key
   - Internet connection
   - API call quota

   ### Basic Extraction Mode

   **Advantages:**

   - No API key required
   - Offline usage
   - Faster processing speed

   **Limitations:**

   - Simpler content extraction
   - Relies on original document structure
   - Basic overview and summary generation

   ## Troubleshooting

   ### Common Issues & Solutions

   **1. File Not Found Error**

   text

   ```
   Error: File 'xxx.docx' does not exist!
   ```

   

   - Check if file path is correct
   - Ensure file extension is `.docx`

   **2. Missing Dependencies**

   text

   ```
   ❌ Missing required libraries: ModuleNotFoundError
   ```

   

   - Run `pip install python-docx python-pptx requests`

   **3. API Call Failure**

   text

   ```
   ❌ API key invalid or expired
   ```

   

   - Verify API key correctness
   - Confirm sufficient account balance
   - Check internet connection

   **4. Inaccurate Content Recognition**

   - Ensure document uses standard heading styles
   - Check document structure clarity
   - Try AI mode for better results

   **5. Generated PPT Format Issues**

   - Ensure Microsoft PowerPoint is installed
   - Check file permissions
   - Try running as administrator

   ### Debugging Suggestions

   1. **Check Console Output**: Program displays detailed processing progress and error messages
   2. **Verify Document Structure**: Test with simple sample documents
   3. **Step-by-Step Testing**: Start with basic mode, then try AI mode
   4. **Review Generation Logs**: Program outputs analysis results and slide counts

   ## Advanced Usage

   ### Custom Modifications

   **Adjust Slide Layout**:

   python

   ```
   def _create_content_slide(self, prs, section, key_points):
       # Modify font size, color, layout, etc.
       p.font.size = Pt(18)  # Adjust font size
       p.font.color.rgb = RGBColor(0, 0, 0)  # Adjust font color
   ```

   

   **Add Company Logo**:

   python

   ```
   def _create_title_slide(self, prs, title):
       # Add logo to cover page
       logo_path = "company_logo.png"
       left = Inches(1)
       top = Inches(1)
       slide.shapes.add_picture(logo_path, left, top, width=Inches(1.5))
   ```

   

   ### Batch Processing

   Modify code for batch document processing:

   python

   ```
   def batch_convert(docx_folder):
       for file in os.listdir(docx_folder):
           if file.endswith('.docx'):
               docx_path = os.path.join(docx_folder, file)
               converter.convert(docx_path)
   ```

   

   ## Technical Support

   ### Getting Help

   When encountering issues, please provide:

   1. Complete error message from program execution
   2. Sample document used (if possible)
   3. Operating system and Python version
   4. Mode used (Basic/AI)

   ### Version Information

   - Current Version: v1.0
   - Last Updated: 2024
   - Compatibility: Python 3.7+

   ## Disclaimer

   1. This tool is an auxiliary utility; generated content requires manual review
   2. API usage must comply with relevant service terms
   3. Document content copyright belongs to original authors
   4. No guarantee for accuracy of generated content

   ------

   **Get Started**: Run `python apidoc2ppt.py` and follow the prompts!

   **Enjoy using the tool!** 🎉