Skip to main content
The document extraction function can recognize stamp information in documents, including stamp type, color, position, and other detailed information. Stamp information is significant for document authenticity verification and compliance checking.

​
Stamp Structure

Stamp information is located in result.files[].data.stamps[], with each stamp containing the following attributes:
  • page: Page number where the stamp is located (starting from 0)
  • text: Text content in the stamp
  • type: Stamp type (such as “Invoice Special Seal”, “Financial Special Seal”, etc.)
  • color: Stamp color (such as “Red”, “Blue”, etc.)
  • shape: Stamp shape (such as “Round Seal”, “Square Seal”, etc.)

​
Stamp Data Structure

{
  "page": 0,                    // Page number
  "text": "National Unified Invoice Supervision Seal",  // Stamp text
  "type": "Other",               // Stamp type
  "color": "Red"               // Stamp color
}

​
Example Code

import requests
import json

def extract_stamps(workspace_id, batch_number, app_id, secret_code):
    """Extract stamp information from documents"""
    
    host = "https://docflow.textin.ai"
    url = "/api/app-api/sip/platform/v2/file/fetch"
    
    resp = requests.get(
        f"{host}{url}",
        params={
            "workspace_id": workspace_id, 
            "batch_number": batch_number
        },
        headers={
            "x-ti-app-id": app_id, 
            "x-ti-secret-code": secret_code
        },
        timeout=60,
    )
    
    if resp.status_code != 200:
        print(f"Request failed: {resp.status_code}")
        return None
    
    data = resp.json()
    
    for file in data.get("result", {}).get("files", []):
        print(f"File name: {file.get('name')}")
        
        # Extract stamp information
        stamps = file.get("data", {}).get("stamps", [])
        
        if stamps:
            print(f"\n=== Stamp Information ===")
            print(f"Number of stamps: {len(stamps)}")
            
            for i, stamp in enumerate(stamps):
                page = stamp.get("page", 0)
                text = stamp.get("text", "")
                stamp_type = stamp.get("type", "")
                color = stamp.get("color", "")
                
                print(f"\nStamp {i+1}:")
                print(f"  Page: Page {page+1}")
                print(f"  Text: {text}")
                print(f"  Type: {stamp_type}")
                print(f"  Color: {color}")
        else:
            print("No stamp information found")
    
    return data

# Usage example
if __name__ == "__main__":
    workspace_id = "<your-workspace-id>"
    batch_number = "<your-batch-number>"
    app_id = "<your-app-id>"
    secret_code = "<your-secret-code>"
    
    result = extract_stamps(workspace_id, batch_number, app_id, secret_code)

​
Return Data Example

{
  "code": 200,
  "result": {
    "files": [
      {
        "id": "202412190001",
        "name": "invoice.pdf",
        "recognition_status": 1,
        "data": {
          "stamps": [
            {
              "page": 0,
              "text": "National Unified Invoice Supervision Seal",
              "type": "Other",
              "color": "Red"
            },
            {
              "page": 0,
              "text": "Shanghai XX Technology Co., Ltd. Invoice Special Seal",
              "type": "Invoice Special Seal",
              "color": "Red"
            },
            {
              "page": 0,
              "text": "December 19, 2024",
              "type": "Date Seal",
              "color": "Blue"
            }
          ]
        }
      }
    ]
  }
}