テーブル構造
テーブル情報はresult.files[].data.items[][] に格納されており、二次元配列構造を使用しています：
items[][]：テーブルデータ。外側の配列は行を表し、内側の配列は行内のセルを表します
テーブルデータ構造
{
"items": [
[
{"key": "Goods/Services Name", "value": "*Electronic Computer*Microcomputer Host"},
{"key": "Specification/Model", "value": "DMS-SC68"},
{"key": "Unit", "value": "Set"},
{"key": "Quantity", "value": "1"},
{"key": "Unit Price", "value": "5000.00"},
{"key": "Amount", "value": "5000.00"}
],
[
{"key": "Goods/Services Name", "value": "*Software*System Software"},
{"key": "Specification/Model", "value": "V1.0"},
{"key": "Unit", "value": "Set"},
{"key": "Quantity", "value": "2"},
{"key": "Unit Price", "value": "1000.00"},
{"key": "Amount", "value": "2000.00"}
]
],
}
サンプルコード
import requests
import json
import pandas as pd
def extract_tables(workspace_id, batch_number, app_id, secret_code):
"""Extract table 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 table information
items = file.get("data", {}).get("items", [])
if items:
print(f"\n=== Table Information ===")
print(f"Number of data rows: {len(items)}")
# Display table data
for i, row in enumerate(items):
print(f"\nRow {i+1}:")
for cell in row:
key = cell.get("key", "")
value = cell.get("value", "")
print(f" {key}: {value}")
else:
print("No table 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_tables(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": {
"items": [
[
{
"key": "Goods/Services Name",
"value": "*Electronic Computer*Microcomputer Host",
"position": [
{
"page": 0,
"vertices": [100, 400, 300, 400, 300, 430, 100, 430]
}
]
},
{
"key": "Specification/Model",
"value": "DMS-SC68",
"position": [
{
"page": 0,
"vertices": [310, 400, 400, 400, 400, 430, 310, 430]
}
]
},
{
"key": "Unit",
"value": "Set",
"position": [
{
"page": 0,
"vertices": [410, 400, 450, 400, 450, 430, 410, 430]
}
]
},
{
"key": "Quantity",
"value": "1",
"position": [
{
"page": 0,
"vertices": [460, 400, 500, 400, 500, 430, 460, 430]
}
]
},
{
"key": "Unit Price",
"value": "5000.00",
"position": [
{
"page": 0,
"vertices": [510, 400, 600, 400, 600, 430, 510, 430]
}
]
},
{
"key": "Amount",
"value": "5000.00",
"position": [
{
"page": 0,
"vertices": [610, 400, 700, 400, 700, 430, 610, 430]
}
]
}
],
[
{
"key": "Goods/Services Name",
"value": "*Software*System Software",
"position": [
{
"page": 0,
"vertices": [100, 440, 300, 440, 300, 470, 100, 470]
}
]
},
{
"key": "Specification/Model",
"value": "V1.0",
"position": [
{
"page": 0,
"vertices": [310, 440, 400, 440, 400, 470, 310, 470]
}
]
},
{
"key": "Unit",
"value": "Set",
"position": [
{
"page": 0,
"vertices": [410, 440, 450, 440, 450, 470, 410, 470]
}
]
},
{
"key": "Quantity",
"value": "2",
"position": [
{
"page": 0,
"vertices": [460, 440, 500, 440, 500, 470, 460, 470]
}
]
},
{
"key": "Unit Price",
"value": "1000.00",
"position": [
{
"page": 0,
"vertices": [510, 440, 600, 440, 600, 470, 510, 470]
}
]
},
{
"key": "Amount",
"value": "2000.00",
"position": [
{
"page": 0,
"vertices": [610, 440, 700, 440, 700, 470, 610, 470]
}
]
}
]
]
}
}
]
}
}