手書き情報の構造
手書き情報はresult.files[].data.handwritings[] に格納されており、各手書き項目には以下の属性が含まれます：
page：手書きコンテンツが位置するページ番号（0 から開始）text：認識された手書きテキスト内容position[]：文書内における手書きコンテンツの位置座標情報
手書き情報のデータ構造
{
"page": 0, // ページ番号
"text": "3月1日", // 手書きテキスト内容
"position": [
{
"page": 0, // ページ番号
"vertices": [ // 四隅の座標 [x1,y1,x2,y2,x3,y3,x4,y4]
100, 200, // 左上
200, 200, // 右上
200, 250, // 右下
100, 250 // 左下
]
}
]
}
位置座標の構造
{
"page": 0, // ページ番号（0 から開始）
"vertices": [ // 四隅の座標 [x1,y1,x2,y2,x3,y3,x4,y4]
100, 200, // 左上
200, 200, // 右上
200, 250, // 右下
100, 250 // 左下
]
}
サンプルコード
import requests
import json
def extract_handwritings(workspace_id, batch_number, app_id, secret_code):
"""Extract handwriting 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 handwriting information
handwritings = file.get("data", {}).get("handwritings", [])
if handwritings:
print(f"\n=== 手書き情報 ===")
print(f"Number of handwriting items: {len(handwritings)}")
for i, handwriting in enumerate(handwritings):
page = handwriting.get("page", 0)
text = handwriting.get("text", "")
positions = handwriting.get("position", [])
print(f"\nHandwriting item {i+1}:")
print(f" Page: Page {page+1}")
print(f" Content: {text}")
# Display position information
for j, pos in enumerate(positions):
pos_page = pos.get("page", 0)
vertices = pos.get("vertices", [])
print(f" Position {j+1} (Page {pos_page+1}): {vertices}")
else:
print("No handwriting 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_handwritings(workspace_id, batch_number, app_id, secret_code)
返却データ例
{
"code": 200,
"result": {
"files": [
{
"id": "202412190001",
"name": "contract.pdf",
"recognition_status": 1,
"data": {
"handwritings": [
{
"page": 0,
"text": "John Smith",
"position": [
{
"page": 0,
"vertices": [100, 500, 150, 500, 150, 520, 100, 520]
}
]
},
{
"page": 0,
"text": "December 19, 2024",
"position": [
{
"page": 0,
"vertices": [200, 500, 300, 500, 300, 520, 200, 520]
}
]
},
{
"page": 0,
"text": "Agree to this clause",
"position": [
{
"page": 0,
"vertices": [100, 600, 200, 600, 200, 620, 100, 620]
}
]
},
{
"page": 1,
"text": "Jane Doe",
"position": [
{
"page": 1,
"vertices": [100, 300, 150, 300, 150, 320, 100, 320]
}
]
}
]
}
}
]
}
}