フィールド構造
フィールド情報はresult.files[].data.fields[] に格納されており、各フィールドには以下の属性が含まれます：
key：フィールド名（「請求書番号」「請求書日付」など）value：フィールド値（認識されたテキスト内容）position[]：文書内におけるフィールドの位置座標情報。フィールドがページや行をまたぐ場合があるため、配列形式を採用しています
位置座標の構造
{
"page": 0, // フィールドが位置するページ番号
"vertices": [ // 四隅の座標 [x1,y1,x2,y2,x3,y3,x4,y4]
100, 200, // 左上
300, 200, // 右上
300, 250, // 右下
100, 250 // 左下
]
}
サンプルコード
import requests
import json
def extract_fields(workspace_id, batch_number, app_id, secret_code):
"""Extract field 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')}")
print(f"Recognition status: {file.get('recognition_status')}")
# Extract field information
fields = file.get("data", {}).get("fields", [])
if fields:
print("\n=== Field Information ===")
for field in fields:
key = field.get("key", "")
value = field.get("value", "")
positions = field.get("position", [])
print(f"Field: {key}")
print(f"Value: {value}")
# Display position information
for i, pos in enumerate(positions):
page = pos.get("page", 0)
vertices = pos.get("vertices", [])
print(f" Position {i+1} (Page {page+1}): {vertices}")
print("-" * 30)
else:
print("No field 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_fields(workspace_id, batch_number, app_id, secret_code)
返却データ例
{
"code": 200,
"result": {
"files": [
{
"id": "202412190001",
"name": "invoice.pdf",
"recognition_status": 1,
"data": {
"fields": [
{
"key": "Invoice Code",
"value": "3100231130",
"position": [
{
"page": 0,
"vertices": [100, 150, 200, 150, 200, 180, 100, 180]
}
]
},
{
"key": "Invoice Number",
"value": "12345678",
"position": [
{
"page": 0,
"vertices": [250, 150, 320, 150, 320, 180, 250, 180]
}
]
},
{
"key": "Invoice Date",
"value": "December 19, 2024",
"position": [
{
"page": 0,
"vertices": [400, 150, 500, 150, 500, 180, 400, 180]
}
]
},
{
"key": "Buyer Name",
"value": "Shanghai XX Technology Co., Ltd.",
"position": [
{
"page": 0,
"vertices": [100, 250, 400, 250, 400, 280, 100, 280]
}
]
},
{
"key": "Amount",
"value": "1000.00",
"position": [
{
"page": 0,
"vertices": [500, 350, 600, 350, 600, 380, 500, 380]
}
]
}
]
}
}
]
}
}