DocumentAnalysisClient Classe

Analizzare il testo del campo e i valori semantici da un documento specificato.

Novità nella versione 2023-07-31: argomento delle funzionalità .

begin_analyze_document(model_id: str, document: bytes | IO[bytes], **kwargs: Any) -> LROPoller[AnalyzeResult]

Parametri

Restituisce

Istanza di un'istanza di LROPoller. Chiamare result() nell'oggetto poller per restituire un AnalyzeResultoggetto .

Tipo restituito

Eccezioni

Esempio

Analizzare una fattura. Per altri esempi, vedere la cartella esempi .

   from azure.core.credentials import AzureKeyCredential
   from azure.ai.formrecognizer import DocumentAnalysisClient

   endpoint = os.environ["AZURE_FORM_RECOGNIZER_ENDPOINT"]
   key = os.environ["AZURE_FORM_RECOGNIZER_KEY"]

   document_analysis_client = DocumentAnalysisClient(
       endpoint=endpoint, credential=AzureKeyCredential(key)
   )
   with open(path_to_sample_documents, "rb") as f:
       poller = document_analysis_client.begin_analyze_document(
           "prebuilt-invoice", document=f, locale="en-US"
       )
   invoices = poller.result()

   for idx, invoice in enumerate(invoices.documents):
       print(f"--------Analyzing invoice #{idx + 1}--------")
       vendor_name = invoice.fields.get("VendorName")
       if vendor_name:
           print(
               f"Vendor Name: {vendor_name.value} has confidence: {vendor_name.confidence}"
           )
       vendor_address = invoice.fields.get("VendorAddress")
       if vendor_address:
           print(
               f"Vendor Address: {vendor_address.value} has confidence: {vendor_address.confidence}"
           )
       vendor_address_recipient = invoice.fields.get("VendorAddressRecipient")
       if vendor_address_recipient:
           print(
               f"Vendor Address Recipient: {vendor_address_recipient.value} has confidence: {vendor_address_recipient.confidence}"
           )
       customer_name = invoice.fields.get("CustomerName")
       if customer_name:
           print(
               f"Customer Name: {customer_name.value} has confidence: {customer_name.confidence}"
           )
       customer_id = invoice.fields.get("CustomerId")
       if customer_id:
           print(
               f"Customer Id: {customer_id.value} has confidence: {customer_id.confidence}"
           )
       customer_address = invoice.fields.get("CustomerAddress")
       if customer_address:
           print(
               f"Customer Address: {customer_address.value} has confidence: {customer_address.confidence}"
           )
       customer_address_recipient = invoice.fields.get("CustomerAddressRecipient")
       if customer_address_recipient:
           print(
               f"Customer Address Recipient: {customer_address_recipient.value} has confidence: {customer_address_recipient.confidence}"
           )
       invoice_id = invoice.fields.get("InvoiceId")
       if invoice_id:
           print(
               f"Invoice Id: {invoice_id.value} has confidence: {invoice_id.confidence}"
           )
       invoice_date = invoice.fields.get("InvoiceDate")
       if invoice_date:
           print(
               f"Invoice Date: {invoice_date.value} has confidence: {invoice_date.confidence}"
           )
       invoice_total = invoice.fields.get("InvoiceTotal")
       if invoice_total:
           print(
               f"Invoice Total: {invoice_total.value} has confidence: {invoice_total.confidence}"
           )
       due_date = invoice.fields.get("DueDate")
       if due_date:
           print(f"Due Date: {due_date.value} has confidence: {due_date.confidence}")
       purchase_order = invoice.fields.get("PurchaseOrder")
       if purchase_order:
           print(
               f"Purchase Order: {purchase_order.value} has confidence: {purchase_order.confidence}"
           )
       billing_address = invoice.fields.get("BillingAddress")
       if billing_address:
           print(
               f"Billing Address: {billing_address.value} has confidence: {billing_address.confidence}"
           )
       billing_address_recipient = invoice.fields.get("BillingAddressRecipient")
       if billing_address_recipient:
           print(
               f"Billing Address Recipient: {billing_address_recipient.value} has confidence: {billing_address_recipient.confidence}"
           )
       shipping_address = invoice.fields.get("ShippingAddress")
       if shipping_address:
           print(
               f"Shipping Address: {shipping_address.value} has confidence: {shipping_address.confidence}"
           )
       shipping_address_recipient = invoice.fields.get("ShippingAddressRecipient")
       if shipping_address_recipient:
           print(
               f"Shipping Address Recipient: {shipping_address_recipient.value} has confidence: {shipping_address_recipient.confidence}"
           )
       print("Invoice items:")
       for idx, item in enumerate(invoice.fields.get("Items").value):
           print(f"...Item #{idx + 1}")
           item_description = item.value.get("Description")
           if item_description:
               print(
                   f"......Description: {item_description.value} has confidence: {item_description.confidence}"
               )
           item_quantity = item.value.get("Quantity")
           if item_quantity:
               print(
                   f"......Quantity: {item_quantity.value} has confidence: {item_quantity.confidence}"
               )
           unit = item.value.get("Unit")
           if unit:
               print(f"......Unit: {unit.value} has confidence: {unit.confidence}")
           unit_price = item.value.get("UnitPrice")
           if unit_price:
               unit_price_code = unit_price.value.code if unit_price.value.code else ""
               print(
                   f"......Unit Price: {unit_price.value}{unit_price_code} has confidence: {unit_price.confidence}"
               )
           product_code = item.value.get("ProductCode")
           if product_code:
               print(
                   f"......Product Code: {product_code.value} has confidence: {product_code.confidence}"
               )
           item_date = item.value.get("Date")
           if item_date:
               print(
                   f"......Date: {item_date.value} has confidence: {item_date.confidence}"
               )
           tax = item.value.get("Tax")
           if tax:
               print(f"......Tax: {tax.value} has confidence: {tax.confidence}")
           amount = item.value.get("Amount")
           if amount:
               print(
                   f"......Amount: {amount.value} has confidence: {amount.confidence}"
               )
       subtotal = invoice.fields.get("SubTotal")
       if subtotal:
           print(f"Subtotal: {subtotal.value} has confidence: {subtotal.confidence}")
       total_tax = invoice.fields.get("TotalTax")
       if total_tax:
           print(
               f"Total Tax: {total_tax.value} has confidence: {total_tax.confidence}"
           )
       previous_unpaid_balance = invoice.fields.get("PreviousUnpaidBalance")
       if previous_unpaid_balance:
           print(
               f"Previous Unpaid Balance: {previous_unpaid_balance.value} has confidence: {previous_unpaid_balance.confidence}"
           )
       amount_due = invoice.fields.get("AmountDue")
       if amount_due:
           print(
               f"Amount Due: {amount_due.value} has confidence: {amount_due.confidence}"
           )
       service_start_date = invoice.fields.get("ServiceStartDate")
       if service_start_date:
           print(
               f"Service Start Date: {service_start_date.value} has confidence: {service_start_date.confidence}"
           )
       service_end_date = invoice.fields.get("ServiceEndDate")
       if service_end_date:
           print(
               f"Service End Date: {service_end_date.value} has confidence: {service_end_date.confidence}"
           )
       service_address = invoice.fields.get("ServiceAddress")
       if service_address:
           print(
               f"Service Address: {service_address.value} has confidence: {service_address.confidence}"
           )
       service_address_recipient = invoice.fields.get("ServiceAddressRecipient")
       if service_address_recipient:
           print(
               f"Service Address Recipient: {service_address_recipient.value} has confidence: {service_address_recipient.confidence}"
           )
       remittance_address = invoice.fields.get("RemittanceAddress")
       if remittance_address:
           print(
               f"Remittance Address: {remittance_address.value} has confidence: {remittance_address.confidence}"
           )
       remittance_address_recipient = invoice.fields.get("RemittanceAddressRecipient")
       if remittance_address_recipient:
           print(
               f"Remittance Address Recipient: {remittance_address_recipient.value} has confidence: {remittance_address_recipient.confidence}"
           )

Analizzare un documento personalizzato. Per altri esempi, vedere la cartella esempi .

   from azure.core.credentials import AzureKeyCredential
   from azure.ai.formrecognizer import DocumentAnalysisClient

   endpoint = os.environ["AZURE_FORM_RECOGNIZER_ENDPOINT"]
   key = os.environ["AZURE_FORM_RECOGNIZER_KEY"]
   model_id = os.getenv("CUSTOM_BUILT_MODEL_ID", custom_model_id)

   document_analysis_client = DocumentAnalysisClient(
       endpoint=endpoint, credential=AzureKeyCredential(key)
   )

   # Make sure your document's type is included in the list of document types the custom model can analyze
   with open(path_to_sample_documents, "rb") as f:
       poller = document_analysis_client.begin_analyze_document(
           model_id=model_id, document=f
       )
   result = poller.result()

   for idx, document in enumerate(result.documents):
       print(f"--------Analyzing document #{idx + 1}--------")
       print(f"Document has type {document.doc_type}")
       print(f"Document has document type confidence {document.confidence}")
       print(f"Document was analyzed with model with ID {result.model_id}")
       for name, field in document.fields.items():
           field_value = field.value if field.value else field.content
           print(
               f"......found field of type '{field.value_type}' with value '{field_value}' and with confidence {field.confidence}"
           )

   # iterate over tables, lines, and selection marks on each page
   for page in result.pages:
       print(f"\nLines found on page {page.page_number}")
       for line in page.lines:
           print(f"...Line '{line.content}'")
       for word in page.words:
           print(f"...Word '{word.content}' has a confidence of {word.confidence}")
       if page.selection_marks:
           print(f"\nSelection marks found on page {page.page_number}")
           for selection_mark in page.selection_marks:
               print(
                   f"...Selection mark is '{selection_mark.state}' and has a confidence of {selection_mark.confidence}"
               )

   for i, table in enumerate(result.tables):
       print(f"\nTable {i + 1} can be found on page:")
       for region in table.bounding_regions:
           print(f"...{region.page_number}")
       for cell in table.cells:
           print(
               f"...Cell[{cell.row_index}][{cell.column_index}] has text '{cell.content}'"
           )
   print("-----------------------------------")

Analizzare il testo del campo e i valori semantici da un documento specificato. L'input deve essere il percorso (URL) del documento da analizzare.

Novità nella versione 2023-07-31: argomento delle funzionalità .

begin_analyze_document_from_url(model_id: str, document_url: str, **kwargs: Any) -> LROPoller[AnalyzeResult]

Parametri

Restituisce

Istanza di un'istanza di LROPoller. Chiamare result() nell'oggetto poller per restituire un AnalyzeResultoggetto .

Tipo restituito

Eccezioni

Esempio

Analizzare una ricevuta. Per altri esempi, vedere la cartella esempi .

   from azure.core.credentials import AzureKeyCredential
   from azure.ai.formrecognizer import DocumentAnalysisClient

   endpoint = os.environ["AZURE_FORM_RECOGNIZER_ENDPOINT"]
   key = os.environ["AZURE_FORM_RECOGNIZER_KEY"]

   document_analysis_client = DocumentAnalysisClient(
       endpoint=endpoint, credential=AzureKeyCredential(key)
   )
   url = "https://raw.githubusercontent.com/Azure/azure-sdk-for-python/main/sdk/formrecognizer/azure-ai-formrecognizer/tests/sample_forms/receipt/contoso-receipt.png"
   poller = document_analysis_client.begin_analyze_document_from_url(
       "prebuilt-receipt", document_url=url
   )
   receipts = poller.result()

   for idx, receipt in enumerate(receipts.documents):
       print(f"--------Analysis of receipt #{idx + 1}--------")
       print(f"Receipt type: {receipt.doc_type if receipt.doc_type else 'N/A'}")
       merchant_name = receipt.fields.get("MerchantName")
       if merchant_name:
           print(
               f"Merchant Name: {merchant_name.value} has confidence: "
               f"{merchant_name.confidence}"
           )
       transaction_date = receipt.fields.get("TransactionDate")
       if transaction_date:
           print(
               f"Transaction Date: {transaction_date.value} has confidence: "
               f"{transaction_date.confidence}"
           )
       if receipt.fields.get("Items"):
           print("Receipt items:")
           for idx, item in enumerate(receipt.fields.get("Items").value):
               print(f"...Item #{idx + 1}")
               item_description = item.value.get("Description")
               if item_description:
                   print(
                       f"......Item Description: {item_description.value} has confidence: "
                       f"{item_description.confidence}"
                   )
               item_quantity = item.value.get("Quantity")
               if item_quantity:
                   print(
                       f"......Item Quantity: {item_quantity.value} has confidence: "
                       f"{item_quantity.confidence}"
                   )
               item_price = item.value.get("Price")
               if item_price:
                   print(
                       f"......Individual Item Price: {item_price.value} has confidence: "
                       f"{item_price.confidence}"
                   )
               item_total_price = item.value.get("TotalPrice")
               if item_total_price:
                   print(
                       f"......Total Item Price: {item_total_price.value} has confidence: "
                       f"{item_total_price.confidence}"
                   )
       subtotal = receipt.fields.get("Subtotal")
       if subtotal:
           print(f"Subtotal: {subtotal.value} has confidence: {subtotal.confidence}")
       tax = receipt.fields.get("TotalTax")
       if tax:
           print(f"Total tax: {tax.value} has confidence: {tax.confidence}")
       tip = receipt.fields.get("Tip")
       if tip:
           print(f"Tip: {tip.value} has confidence: {tip.confidence}")
       total = receipt.fields.get("Total")
       if total:
           print(f"Total: {total.value} has confidence: {total.confidence}")
       print("--------------------------------------")

Classificare un documento usando un classificatore di documenti. Per altre informazioni su come creare un modello di classificatore personalizzato, vedere https://aka.ms/azsdk/formrecognizer/buildclassifiermodel.

Novità nella versione 2023-07-31: metodo client begin_classify_document .

begin_classify_document(classifier_id: str, document: bytes | IO[bytes], **kwargs: Any) -> LROPoller[AnalyzeResult]

Parametri

Restituisce

Istanza di un'istanza di LROPoller. Chiamare result() nell'oggetto poller per restituire un AnalyzeResultoggetto .

Tipo restituito

Eccezioni

Esempio

Classificare un documento. Per altri esempi, vedere la cartella esempi .

   from azure.core.credentials import AzureKeyCredential
   from azure.ai.formrecognizer import DocumentAnalysisClient

   endpoint = os.environ["AZURE_FORM_RECOGNIZER_ENDPOINT"]
   key = os.environ["AZURE_FORM_RECOGNIZER_KEY"]
   classifier_id = os.getenv("CLASSIFIER_ID", classifier_id)

   document_analysis_client = DocumentAnalysisClient(
       endpoint=endpoint, credential=AzureKeyCredential(key)
   )
   with open(path_to_sample_documents, "rb") as f:
       poller = document_analysis_client.begin_classify_document(
           classifier_id, document=f
       )
   result = poller.result()

   print("----Classified documents----")
   for doc in result.documents:
       print(
           f"Found document of type '{doc.doc_type or 'N/A'}' with a confidence of {doc.confidence} contained on "
           f"the following pages: {[region.page_number for region in doc.bounding_regions]}"
       )

Classificare un documento specificato con un classificatore di documenti. Per altre informazioni su come creare un modello di classificatore personalizzato, vedere https://aka.ms/azsdk/formrecognizer/buildclassifiermodel. L'input deve essere il percorso (URL) del documento da classificare.

Novità nella versione 2023-07-31: metodo client begin_classify_document_from_url .

begin_classify_document_from_url(classifier_id: str, document_url: str, **kwargs: Any) -> LROPoller[AnalyzeResult]

Parametri

Restituisce

Istanza di un'istanza di LROPoller. Chiamare result() nell'oggetto poller per restituire un AnalyzeResultoggetto .

Tipo restituito

Eccezioni

Esempio

Classificare un documento. Per altri esempi, vedere la cartella esempi .

   from azure.core.credentials import AzureKeyCredential
   from azure.ai.formrecognizer import DocumentAnalysisClient

   endpoint = os.environ["AZURE_FORM_RECOGNIZER_ENDPOINT"]
   key = os.environ["AZURE_FORM_RECOGNIZER_KEY"]
   classifier_id = os.getenv("CLASSIFIER_ID", classifier_id)

   document_analysis_client = DocumentAnalysisClient(
       endpoint=endpoint, credential=AzureKeyCredential(key)
   )

   url = "https://raw.githubusercontent.com/Azure/azure-sdk-for-python/main/sdk/formrecognizer/azure-ai-formrecognizer/tests/sample_forms/forms/IRS-1040.pdf"

   poller = document_analysis_client.begin_classify_document_from_url(
       classifier_id, document_url=url
   )
   result = poller.result()

   print("----Classified documents----")
   for doc in result.documents:
       print(
           f"Found document of type '{doc.doc_type or 'N/A'}' with a confidence of {doc.confidence} contained on "
           f"the following pages: {[region.page_number for region in doc.bounding_regions]}"
       )

Chiudere la DocumentAnalysisClient sessione.

close() -> None

Eccezioni

Esegue una richiesta di rete usando la pipeline esistente del client.

L'URL della richiesta può essere relativo all'URL di base. La versione dell'API del servizio usata per la richiesta è uguale a quella del client, a meno che non sia specificato in altro modo. L'override della versione dell'API configurata del client nell'URL relativo è supportata nel client con API versione 2022-08-31 e versioni successive. Override nell'URL assoluto supportato nel client con qualsiasi versione dell'API. Questo metodo non genera se la risposta è un errore; per generare un'eccezione, chiamare raise_for_status() nell'oggetto risposta restituito. Per altre informazioni su come inviare richieste personalizzate con questo metodo, vedere https://aka.ms/azsdk/dpcodegen/python/send_request.

send_request(request: HttpRequest, *, stream: bool = False, **kwargs) -> HttpResponse

Parametri

Restituisce

Risposta della chiamata di rete. Non esegue la gestione degli errori nella risposta.

Tipo restituito

Eccezioni