分類指定アップロード

import requests
import os
from requests_toolbelt.multipart.encoder import MultipartEncoder

ti_app_id = "<your-app-id>"
ti_secret_code = "<your-secret-code>"
workspace_id = "<your-workspace-id>"
filepath = "/path/to/invoice.pdf"
category = "invoice"  # Specify file category

host = "https://docflow.textin.ai"
url = "/api/app-api/sip/platform/v2/file/upload"

mime_type = "application/pdf"
if filepath.lower().endswith((".jpg", ".jpeg", ".png")):
    mime_type = "image/jpeg"

payload = MultipartEncoder(fields={
    "file": (os.path.basename(filepath), open(filepath, "rb"), mime_type)
})

resp = requests.post(
    url=f"{host}{url}",
    params={
        "workspace_id": workspace_id,
        "category": category
    },
    data=payload.to_string(),
    headers={
        "Content-Type": payload.content_type,
        "x-ti-app-id": ti_app_id,
        "x-ti-secret-code": ti_secret_code,
    },
    timeout=60,
)

print(resp.status_code, resp.text)

import requests
import os
from requests_toolbelt.multipart.encoder import MultipartEncoder

ti_app_id = "<your-app-id>"
ti_secret_code = "<your-secret-code>"
workspace_id = "<your-workspace-id>"
category = "invoice"
batch_number = "INV-2024-001"

# Prepare multiple files
files = [
    "/path/to/invoice1.pdf",
    "/path/to/invoice2.pdf",
    "/path/to/invoice3.pdf"
]

# Build multipart data
fields = {}
for i, filepath in enumerate(files):
    mime_type = "application/pdf"
    if filepath.lower().endswith((".jpg", ".jpeg", ".png")):
        mime_type = "image/jpeg"

    fields[f"file"] = (os.path.basename(filepath), open(filepath, "rb"), mime_type)

payload = MultipartEncoder(fields=fields)

resp = requests.post(
    url="https://docflow.textin.ai/api/app-api/sip/platform/v2/file/upload",
    params={
        "workspace_id": workspace_id,
        "category": category,
        "batch_number": batch_number
    },
    data=payload.to_string(),
    headers={
        "Content-Type": payload.content_type,
        "x-ti-app-id": ti_app_id,
        "x-ti-secret-code": ti_secret_code,
    },
    timeout=60,
)

print(resp.status_code, resp.text)

import requests

resp = requests.get(
    "https://docflow.textin.ai/api/app-api/sip/platform/v2/file/fetch",
    params={
        "workspace_id": "<your-workspace-id>",
        "file_id": "<your-file_id>",
    },
    headers={"x-ti-app-id": "<your-app-id>", "x-ti-secret-code": "<your-secret-code>"},
    timeout=60,
)

data = resp.json()
for f in data.get("result", {}).get("files", []):
    print(f"File ID: {f['id']}")
    print(f"File name: {f.get('name')}")
    print(f"Specified category: {f.get('category')}")
    print(f"Processing status: {f.get('recognition_status')}")

import urllib.parse

# Chinese category name
chinese_category = "发票"
encoded_category = urllib.parse.quote(chinese_category)
print(f"Original category: {chinese_category}")
print(f"After encoding: {encoded_category}")
# Output: Original category: 发票
# Output: After encoding: %E5%8F%91%E7%A5%A8