\r \r

Invoice Extractor\r

\r Extract invoice information from images (PNG, JPG) and PDF files, then export to Excel format.\r \r

Capabilities\r

\r

• Multi-format support: PNG, JPG, JPEG, BMP, TIFF, PDF\r
• High accuracy: Uses Baidu OCR API specialized for invoice recognition\r
• Complete fields: Extracts all invoice fields including buyer/seller info, amounts, items\r
• Excel export: Formatted Excel output with summary and detail sheets\r
• Flexible input: Single file, multiple files, or entire directory processing\r
• Batch processing: Process hundreds of invoices in one command\r
• Preview mode: List files before processing\r \r

Prerequisites\r

\r

1. Baidu Cloud OCR API credentials (free tier: 50,000 requests/day)\r
2. Python environment with required packages\r \r

Quick Start\r

\r

1. Setup Baidu OCR\r

\r Get API credentials from https://cloud.baidu.com/product/ocr:\r

1. Register/login to Baidu Cloud\r
2. Create an application\r
3. Get API Key and Secret Key\r \r

2. Configure\r

\r Create config.txt in the project root:\r

BAIDU_API_KEY=your_api_key_here\r
BAIDU_SECRET_KEY=your_secret_key_here\r
```\r
\r
Or run the setup wizard:\r
```bash\r
python main_baidu.py --setup\r
```\r
\r
### 3. Run\r
\r
**Process a single file:**\r
```bash\r
python main_baidu.py -f invoice.pdf\r
```\r
\r
**Process multiple files:**\r
```bash\r
python main_baidu.py -f invoice1.pdf -f invoice2.png\r
```\r
\r
**Process entire directory:**\r
```bash\r
python main_baidu.py -i ./fp\r
```\r
\r
**Mixed mode (directory + extra files):**\r
```bash\r
python main_baidu.py -i ./fp -f extra_invoice.pdf\r
```\r
\r
Output will be saved to `output/` directory as Excel file.\r
\r
## Workflow\r
\r
```\r
Task Progress:\r
- [ ] Check prerequisites (Baidu API credentials)\r
- [ ] Choose input method (single file / multiple files / directory)\r
- [ ] Scan and collect invoice files\r
- [ ] Preview files (optional with --list)\r
- [ ] Process each file with Baidu OCR\r
- [ ] Parse invoice fields\r
- [ ] Export to Excel\r
- [ ] Verify output\r
```\r
\r
## Input Methods\r
\r
### Single File\r
Process one specific invoice file:\r
```bash\r
python main_baidu.py -f invoice.pdf\r
python main_baidu.py -f "path/to/invoice.png"\r
```\r
\r
### Multiple Files\r
Process several specific files:\r
```bash\r
python main_baidu.py -f file1.pdf -f file2.png -f file3.jpg\r
```\r
\r
### Entire Directory\r
Process all invoice files in a directory (recursive):\r
```bash\r
python main_baidu.py -i ./my_invoices\r
python main_baidu.py -i "/path/to/invoice/folder"\r
```\r
\r
### Mixed Mode\r
Combine directory and individual files:\r
```bash\r
python main_baidu.py -i ./fp -f ./extra/invoice.pdf\r
```\r
\r
### Preview Mode\r
List files without processing:\r
```bash\r
python main_baidu.py -i ./fp --list\r
```\r
\r
## Extracted Fields\r
\r
### Basic Information\r
- Invoice code (发票代码)\r
- Invoice number (发票号码)\r
- Invoice date (开票日期)\r
- Invoice type (发票类型)\r
\r
### Buyer Information\r
- Name (购买方名称)\r
- Tax number (纳税人识别号)\r
- Address and phone (地址电话)\r
- Bank account (开户行及账号)\r
\r
### Seller Information\r
- Name (销售方名称)\r
- Tax number (纳税人识别号)\r
- Address and phone (地址电话)\r
- Bank account (开户行及账号)\r
\r
### Amounts\r
- Total amount (合计金额)\r
- Total tax (合计税额)\r
- Amount with tax (价税合计)\r
\r
### Items\r
- Product name (货物名称)\r
- Specification (规格型号)\r
- Unit (单位)\r
- Quantity (数量)\r
- Unit price (单价)\r
- Amount (金额)\r
- Tax rate (税率)\r
- Tax amount (税额)\r
\r
## Command Line Options\r
\r
```bash\r
python main_baidu.py [options]\r
\r
Input Options:\r
  -f FILE, --file FILE     Specify invoice file (can be used multiple times)\r
  -i DIR, --input DIR      Input directory (default: fp)\r
\r
Output Options:\r
  -o DIR, --output DIR     Output directory (default: output)\r
  -n NAME, --name NAME     Output filename prefix (default: 发票信息)\r
\r
Authentication Options:\r
  --api-key KEY            Baidu API Key\r
  --secret-key KEY         Baidu Secret Key\r
\r
Other Options:\r
  --setup                  Run configuration wizard\r
  --list                   List files to be processed without processing\r
  -h, --help              Show help\r
```\r
\r
## Usage Examples\r
\r
### Example 1: Single File\r
```bash\r
python main_baidu.py -f "invoice.pdf"\r
```\r
\r
### Example 2: Multiple Files\r
```bash\r
python main_baidu.py -f "1.pdf" -f "2.png" -f "3.jpg"\r
```\r
\r
### Example 3: Entire Directory\r
```bash\r
python main_baidu.py -i "./2024_invoices"\r
```\r
\r
### Example 4: Preview Before Processing\r
```bash\r
python main_baidu.py -i ./fp --list\r
# Then process:\r
python main_baidu.py -i ./fp\r
```\r
\r
### Example 5: Mixed Input\r
```bash\r
python main_baidu.py -i ./fp -f ./urgent/invoice.pdf -o ./output -n "March_2024"\r
```\r
\r
### Example 6: Custom Output\r
```bash\r
python main_baidu.py -i ./fp -o ./reports -n "Q1_Invoice_Summary"\r
```\r
\r
## Project Structure\r
\r
```\r
.\r
├── fp/                      # Place invoice files here\r
├── output/                  # Excel output directory\r
├── src/\r
│   ├── main_baidu.py       # Main entry point\r
│   ├── baidu_ocr_extractor.py  # Baidu OCR wrapper\r
│   ├── invoice_model.py    # Data models\r
│   ├── excel_exporter.py   # Excel export\r
│   └── config.py           # Configuration\r
├── scripts/                 # Utility scripts\r
│   ├── batch_process.py    # Batch processing helper\r
│   └── verify_export.py    # Verify Excel export\r
├── config.txt              # API credentials\r
├── requirements.txt        # Dependencies\r
├── SKILL.md                # This file\r
├── setup.md                # Detailed setup guide\r
└── examples.md             # Usage examples\r
```\r
\r
## Utility Scripts\r
\r
### Batch Processing Helper\r
```bash\r
python scripts/batch_process.py /path/to/invoices\r
```\r
\r
### Verify Export\r
```bash\r
python scripts/verify_export.py output/invoice_info.xlsx\r
```\r
\r
## Error Handling\r
\r
Common issues and solutions:\r
\r
**"Baidu OCR authentication failed"**\r
- Check API Key and Secret Key in config.txt\r
- Verify credentials are correct in Baidu Cloud console\r
\r
**"No invoice files found"**\r
- Ensure files are in the specified directory\r
- Check file formats (supported: png, jpg, jpeg, bmp, tiff, pdf)\r
- Use `--list` to see what files are detected\r
\r
**"Image format error"**\r
- PDF files are automatically converted to images\r
- Ensure PDF is not corrupted or password-protected\r
\r
**"File not found"**\r
- Check file path is correct\r
- Use quotes for paths with spaces: `"path/to/file name.pdf"`\r
\r
## Advanced Usage\r
\r
### Environment Variables\r
Set credentials via environment:\r
```bash\r
export BAIDU_API_KEY="your_key"\r
export BAIDU_SECRET_KEY="your_secret"\r
```\r
\r
### Batch Processing Script\r
Create a script for monthly processing:\r
```bash\r
#!/bin/bash\r
MONTH=$(date +%Y%m)\r
python main_baidu.py \\r
  -i "/invoices/$MONTH" \\r
  -o "/reports/$MONTH" \\r
  -n "Invoice_Report_$MONTH"\r
```\r
\r
## Additional Resources\r
\r
- For detailed setup instructions, see [setup.md](setup.md)\r
- For more examples, see [examples.md](examples.md)\r
- For API documentation, visit https://cloud.baidu.com/doc/OCR/index.html\r