forked from GoogleCloudPlatform/python-docs-samples
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathquickstart_sample.py
More file actions
82 lines (66 loc) · 2.99 KB
/
Copy pathquickstart_sample.py
File metadata and controls
82 lines (66 loc) · 2.99 KB
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
# Copyright 2020 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
# flake8: noqa
# [START documentai_quickstart]
from google.api_core.client_options import ClientOptions
from google.cloud import documentai # type: ignore
# TODO(developer): Uncomment these variables before running the sample.
# project_id = "YOUR_PROJECT_ID"
# location = "YOUR_PROCESSOR_LOCATION" # Format is "us" or "eu"
# file_path = "/path/to/local/pdf"
# processor_display_name = "YOUR_PROCESSOR_DISPLAY_NAME" # Must be unique per project, e.g.: "My Processor"
def quickstart(
project_id: str,
location: str,
file_path: str,
processor_display_name: str = "My Processor",
):
# You must set the `api_endpoint`if you use a location other than "us".
opts = ClientOptions(api_endpoint=f"{location}-documentai.googleapis.com")
client = documentai.DocumentProcessorServiceClient(client_options=opts)
# The full resource name of the location, e.g.:
# `projects/{project_id}/locations/{location}`
parent = client.common_location_path(project_id, location)
# Create a Processor
processor = client.create_processor(
parent=parent,
processor=documentai.Processor(
type_="OCR_PROCESSOR", # Refer to https://cloud.google.com/document-ai/docs/create-processor for how to get available processor types
display_name=processor_display_name,
),
)
# Print the processor information
print(f"Processor Name: {processor.name}")
# Read the file into memory
with open(file_path, "rb") as image:
image_content = image.read()
# Load binary data
raw_document = documentai.RawDocument(
content=image_content,
mime_type="application/pdf", # Refer to https://cloud.google.com/document-ai/docs/file-types for supported file types
)
# Configure the process request
# `processor.name` is the full resource name of the processor, e.g.:
# `projects/{project_id}/locations/{location}/processors/{processor_id}`
request = documentai.ProcessRequest(name=processor.name, raw_document=raw_document)
result = client.process_document(request=request)
# For a full list of `Document` object attributes, reference this page:
# https://cloud.google.com/document-ai/docs/reference/rest/v1/Document
document = result.document
# Read the text recognition output from the processor
print("The document contains the following text:")
print(document.text)
# [END documentai_quickstart]
return processor