印章结构
印章信息位于result.files[].data.stamps[] 中，每个印章包含以下属性：
page: 印章所在页码（从0开始）text: 印章中的文字内容type: 印章类型（如”发票专用章”、“财务专用章”等）color: 印章颜色（如”红色”、“蓝色”等）shape: 印章形状（如”圆章”、“方章”等）
印章数据结构
{
"page": 0, // 页码
"text": "全国统一发票监制章", // 印章文字
"type": "其他", // 印章类型
"color": "红色" // 印章颜色
}
示例代码
import requests
import json
def extract_stamps(workspace_id, batch_number, app_id, secret_code):
"""提取文档中的印章信息"""
host = "https://docflow.textin.com"
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"请求失败: {resp.status_code}")
return None
data = resp.json()
for file in data.get("result", {}).get("files", []):
print(f"文件名: {file.get('name')}")
# 提取印章信息
stamps = file.get("data", {}).get("stamps", [])
if stamps:
print(f"\n=== 印章信息 ===")
print(f"印章数量: {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"\n印章 {i+1}:")
print(f" 页码: 第{page+1}页")
print(f" 文字: {text}")
print(f" 类型: {stamp_type}")
print(f" 颜色: {color}")
else:
print("未找到印章信息")
return data
# 使用示例
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)
返回数据示例
{
"code": 200,
"result": {
"files": [
{
"id": "202412190001",
"name": "invoice.pdf",
"recognition_status": 1,
"data": {
"stamps": [
{
"page": 0,
"text": "全国统一发票监制章",
"type": "其他",
"color": "红色"
},
{
"page": 0,
"text": "上海某某科技有限公司发票专用章",
"type": "发票专用章",
"color": "红色"
},
{
"page": 0,
"text": "2024年12月19日",
"type": "日期章",
"color": "蓝色"
}
]
}
}
]
}
}