1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
|
# coding: utf-8
# -------------------------------------------------------------------------
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See License.txt in the project root for
# license information.
# --------------------------------------------------------------------------
"""
FILE: sample_analyze_result_pdf_async.py
DESCRIPTION:
This sample demonstrates how to convert an analog PDF into a PDF with embedded text.
This sample uses Read model to demonstrate.
See pricing: https://azure.microsoft.com/pricing/details/ai-document-intelligence/.
USAGE:
python sample_analyze_result_pdf_async.py
Set the environment variables with your own values before running the sample:
1) DOCUMENTINTELLIGENCE_ENDPOINT - the endpoint to your Document Intelligence resource.
2) DOCUMENTINTELLIGENCE_API_KEY - your Document Intelligence API key.
"""
import asyncio
import os
async def analyze_result_pdf():
path_to_sample_documents = os.path.abspath(
os.path.join(
os.path.abspath(__file__),
"..",
"..",
"sample_forms/layout/layout-pageobject.pdf",
)
)
from azure.core.credentials import AzureKeyCredential
from azure.ai.documentintelligence.aio import DocumentIntelligenceClient
from azure.ai.documentintelligence.models import AnalyzeOutputOption, AnalyzeResult
endpoint = os.environ["DOCUMENTINTELLIGENCE_ENDPOINT"]
key = os.environ["DOCUMENTINTELLIGENCE_API_KEY"]
document_intelligence_client = DocumentIntelligenceClient(endpoint=endpoint, credential=AzureKeyCredential(key))
async with document_intelligence_client:
with open(path_to_sample_documents, "rb") as f:
poller = await document_intelligence_client.begin_analyze_document(
"prebuilt-read",
body=f,
output=[AnalyzeOutputOption.PDF],
)
result: AnalyzeResult = await poller.result()
operation_id = poller.details["operation_id"]
response = await document_intelligence_client.get_analyze_result_pdf(
model_id=result.model_id, result_id=operation_id
)
with open("async_analyze_result.pdf", "wb") as file:
async for chunk in response:
file.write(chunk)
async def main():
await analyze_result_pdf()
if __name__ == "__main__":
from azure.core.exceptions import HttpResponseError
from dotenv import find_dotenv, load_dotenv
try:
load_dotenv(find_dotenv())
asyncio.run(main())
except HttpResponseError as error:
# Examples of how to check an HttpResponseError
# Check by error code:
if error.error is not None:
if error.error.code == "InvalidImage":
print(f"Received an invalid image error: {error.error}")
if error.error.code == "InvalidRequest":
print(f"Received an invalid request error: {error.error}")
# Raise the error again after printing it
raise
# If the inner error is None and then it is possible to check the message to get more information:
if "Invalid request".casefold() in error.message.casefold():
print(f"Uh-oh! Seems there was an invalid request: {error}")
# Raise the error again
raise
|
