def parse_document(self, input_uri, processor_id, token_path, project_id):
# Instantiates a client
credentials = service_account.Credentials.from_service_account_file(
token_path)
client_options = {"api_endpoint": "eu-documentai.googleapis.com"}
client = documentai.DocumentProcessorServiceClient(
credentials=credentials, client_options=client_options)
name = f"projects/{project_id}/locations/eu/processors/{processor_id}"
with self.fs.open(input_uri, "rb") as image:
image_content = image.read()
# Read the file into memory
document = {"content": image_content, "mime_type": "application/pdf"}
# Configure the process request
request = documentai.types.ProcessRequest(name=name,
document=document,
skip_human_review=False)
# Recognizes text entities in the PDF document
result = client.process_document(request=request)
document = result.document
self.document = document
def quickstart(project_id: str, location: str, processor_id: str,
file_path: str):
client = documentai.DocumentProcessorServiceClient()
# The full resource name of the processor, e.g.:
# projects/project-id/locations/location/processor/processor-id
# You must create new processors in the Cloud Console first
name = f"projects/{project_id}/locations/{location}/processors/{processor_id}"
# Read the file into memory
with open(file_path, "rb") as image:
image_content = image.read()
document = {"content": image_content, "mime_type": "application/pdf"}
# Configure the process request
request = {"name": name, "document": document}
result = client.process_document(request=request)
document = result.document
document_pages = document.pages
# For a full list of Document object attributes, please reference this page: https://googleapis.dev/python/documentai/latest/_modules/google/cloud/documentai_v1beta3/types/document.html#Document
# Read the text recognition output from the processor
print("The document contains the following paragraphs:")
for page in document_pages:
paragraphs = page.paragraphs
for paragraph in paragraphs:
print(paragraph)
paragraph_text = get_text(paragraph.layout, document)
print(f"Paragraph text: {paragraph_text}")
def parse_document(self,
input_uri,
token_path,
project_id,
processor_id="643a05097d4ab993"):
"""
Facilitates sending a request to the Doc AI API (via a specified
processor) and saves the response (a 'document') as a class attribute.
Arguments:
input_uri: The gcs location of a pdf to be processed by Doc AI
token_path: Path to the location of json key for authorisation
project_id: The gcp project id
processor_id: The id of the processor created in the cloud
console
Returns:
None
Raises:
None
"""
# Instantiates a client
credentials = service_account.Credentials.from_service_account_file(
token_path)
client_options = {"api_endpoint": "eu-documentai.googleapis.com"}
client = documentai.DocumentProcessorServiceClient(
credentials=credentials, client_options=client_options)
name = f"projects/{project_id}/locations/eu/processors/{processor_id}"
# Read the file into memory
with self.fs.open(input_uri, "rb") as image:
image_content = image.read()
document = {"content": image_content, "mime_type": "application/pdf"}
# Configure the process request
request = documentai.types.ProcessRequest(name=name,
document=document,
skip_human_review=True)
# Recognizes text entities in the PDF document
result = client.process_document(request=request)
self.document = result.document
def process_document_sample(project_id: str, location: str, processor_id: str,
file_path: str):
from google.cloud import documentai_v1beta3 as documentai
# You must set the api_endpoint if you use a location other than 'us', e.g.:
opts = {}
if location == "eu":
opts = {"api_endpoint": "eu-documentai.googleapis.com"}
client = documentai.DocumentProcessorServiceClient(client_options=opts)
# The full resource name of the processor, e.g.:
# projects/project-id/locations/location/processor/processor-id
# You must create new processors in the Cloud Console first
name = f"projects/{project_id}/locations/{location}/processors/{processor_id}"
with open(file_path, "rb") as image:
image_content = image.read()
# Read the file into memory
document = {"content": image_content, "mime_type": "application/pdf"}
# Configure the process request
request = {"name": name, "document": document}
# Recognizes text entities in the PDF document
result = client.process_document(request=request)
document = result.document
print("Document processing complete.")
# For a full list of Document object attributes, please reference this page: https://googleapis.dev/python/documentai/latest/_modules/google/cloud/documentai_v1beta3/types/document.html#Document
document_pages = document.pages
# Read the text recognition output from the processor
print("The document contains the following paragraphs:")
for page in document_pages:
paragraphs = page.paragraphs
for paragraph in paragraphs:
paragraph_text = get_text(paragraph.layout, document)
print(f"Paragraph text: {paragraph_text}")
def batch_process_documents(
project_id,
location,
processor_id,
gcs_input_uri,
gcs_output_uri,
gcs_output_uri_prefix,
timeout: int = 300,
):
# You must set the api_endpoint if you use a location other than 'us', e.g.:
opts = {}
if location == "eu":
opts = {"api_endpoint": "eu-documentai.googleapis.com"}
client = documentai.DocumentProcessorServiceClient(client_options=opts)
destination_uri = f"{gcs_output_uri}/{gcs_output_uri_prefix}/"
# 'mime_type' can be 'application/pdf', 'image/tiff',
# and 'image/gif', or 'application/json'
input_config = documentai.types.document_processor_service.BatchProcessRequest.BatchInputConfig(
gcs_source=gcs_input_uri, mime_type="application/pdf")
# Where to write results
output_config = documentai.types.document_processor_service.BatchProcessRequest.BatchOutputConfig(
gcs_destination=destination_uri)
# Location can be 'us' or 'eu'
name = f"projects/{project_id}/locations/{location}/processors/{processor_id}"
request = documentai.types.document_processor_service.BatchProcessRequest(
name=name,
input_configs=[input_config],
output_config=output_config,
)
operation = client.batch_process_documents(request)
# Wait for the operation to finish
operation.result(timeout=timeout)
# Results are written to GCS. Use a regex to find
# output files
match = re.match(r"gs://([^/]+)/(.+)", destination_uri)
output_bucket = match.group(1)
prefix = match.group(2)
storage_client = storage.Client()
bucket = storage_client.get_bucket(output_bucket)
blob_list = list(bucket.list_blobs(prefix=prefix))
print("Output files:")
for i, blob in enumerate(blob_list):
# If JSON file, download the contents of this blob as a bytes object.
if ".json" in blob.name:
blob_as_bytes = blob.download_as_bytes()
document = documentai.types.Document.from_json(blob_as_bytes)
print(f"Fetched file {i + 1}")
# For a full list of Document object attributes, please reference this page:
# https://cloud.google.com/document-ai/docs/reference/rpc/google.cloud.documentai.v1beta3#document
# Read the text recognition output from the processor
for page in document.pages:
for form_field in page.form_fields:
field_name = get_text(form_field.field_name, document)
field_value = get_text(form_field.field_value, document)
print("Extracted key value pair:")
print(f"\t{field_name}, {field_value}")
for paragraph in document.pages:
paragraph_text = get_text(paragraph.layout, document)
print(f"Paragraph text:\n{paragraph_text}")
else:
print(f"Skipping non-supported file type {blob.name}")
load_job.result() # Waits for the job to complete.
destination_table = bq_client.get_table(table_id) # Make an API request.
print("Loaded {} rows".format(destination_table.num_rows) + " to " +
table_id)
#---------------------------------------------------------------------------------------------------------------------
### Instantiate processor
processor_name = f'projects/{projectid}/locations/{location}/processors/{processorid}'
with open(sample_invoice, 'rb') as image:
document = {'content': image.read(), 'mime_type': 'application/pdf'}
request = {'name': processor_name, 'document': document}
### Capture processor results
results = documentai.DocumentProcessorServiceClient().process_document(
request=request)
#---------------------------------------------------------------------------------------------------------------------
### We will be using the parse data / entities for two tables viz., invoice and inventory
### Invoice Data --- add processor results to a Pandas Dataframe and transform for BQ ingestion
results_frame = [[
entity.type_, entity.mention_text,
round(entity.confidence, 4)
] for entity in results.document.entities]
df = pd.DataFrame(results_frame, columns=['type', 'value', 'confidence'])
df_t = df.rename(columns={'type': 'index'}).drop(columns=['confidence']).T
df_t.columns = df_t.iloc[0]
df_t = df_t.drop(df_t.index[0])
df_t = df_t.reset_index(drop=True)
# transform amount columns and create
for num_col in [col for col in df_t.columns if '_amount' in col]:
def batch_process_documents(
project_id,
location,
processor_id,
gcs_input_uri,
gcs_output_uri,
gcs_output_uri_prefix,
):
client = documentai.DocumentProcessorServiceClient()
destination_uri = f"{gcs_output_uri}/{gcs_output_uri_prefix}/"
# 'mime_type' can be 'application/pdf', 'image/tiff',
# and 'image/gif', or 'application/json'
input_config = documentai.types.document_processor_service.BatchProcessRequest.BatchInputConfig(
gcs_source=gcs_input_uri, mime_type="application/pdf")
# Where to write results
output_config = documentai.types.document_processor_service.BatchProcessRequest.BatchOutputConfig(
gcs_destination=destination_uri)
# Location can be 'us' or 'eu'
name = f"projects/{project_id}/locations/{location}/processors/{processor_id}"
request = documentai.types.document_processor_service.BatchProcessRequest(
name=name,
input_configs=[input_config],
output_config=output_config,
)
operation = client.batch_process_documents(request)
# Wait for the operation to finish
operation.result()
# Results are written to GCS. Use a regex to find
# output files
match = re.match(r"gs://([^/]+)/(.+)", destination_uri)
output_bucket = match.group(1)
prefix = match.group(2)
storage_client = storage.Client()
bucket = storage_client.get_bucket(output_bucket)
blob_list = list(bucket.list_blobs(prefix=prefix))
print("Output files:")
for i, blob in enumerate(blob_list):
# Download the contents of this blob as a bytes object.
blob_as_bytes = blob.download_as_bytes()
document = documentai.types.Document.from_json(blob_as_bytes)
print(f"Fetched file {i + 1}")
# For a full list of Document object attributes, please reference this page: https://googleapis.dev/python/documentai/latest/_modules/google/cloud/documentai_v1beta3/types/document.html#Document
# Read the text recognition output from the processor
for page in document.pages:
for form_field in page.form_fields:
field_name = get_text(form_field.field_name, document)
field_value = get_text(form_field.field_value, document)
print("Extracted key value pair:")
print(f"\t{field_name}, {field_value}")
for paragraph in document.pages:
paragraph_text = get_text(paragraph.layout, document)
print(f"Paragraph text:\n{paragraph_text}")
print("Error: path to TIF files does not exists.")
sys.exit(1)
else:
path = sys.argv[1]
# Check if there is a creds.json file
if not os.path.isfile("{}/creds.json".format(os.getcwd())):
print("Error: creds.json missing.")
sys.exit(1)
else:
os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = "{}/creds.json".format(
os.getcwd())
# Load google vision
opts = {}
client = documentai.DocumentProcessorServiceClient(client_options=opts)
name = f"projects/{settings.project_id}/locations/{settings.location}/processors/{settings.processor_id}"
# https://github.com/googleapis/python-documentai/blob/master/samples/snippets/parse_form_v1beta2.py
def _get_text(el):
"""Convert text offset indexes into text snippets."""
response = ""
# If a text segment spans several lines, it will
# be stored in different text segments.
for segment in el.text_anchor.text_segments:
start_index = segment.start_index
end_index = segment.end_index
response += document.text[start_index:end_index]
return response
