DocumentAnalysisClient Klass

Analysera fälttext och semantiska värden från ett visst dokument.

Ny i version 2023-07-31: Nyckelordsargumentet funktioner .

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

Parametrar

Returer

En instans av en LROPoller. Anropa result() på pollerobjektet för att returnera en AnalyzeResult.

Returtyp

Undantag

Exempel

Analysera en faktura. Fler exempel finns i exempelmappen.

   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}"
           )

Analysera ett anpassat dokument. Fler exempel finns i exempelmappen.

   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("-----------------------------------")

Analysera fälttext och semantiska värden från ett visst dokument. Indata måste vara platsen (URL) för dokumentet som ska analyseras.

Ny i version 2023-07-31: Nyckelordsargumentet funktioner .

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

Parametrar

Returer

En instans av en LROPoller. Anropa result() på pollerobjektet för att returnera en AnalyzeResult.

Returtyp

Undantag

Exempel

Analysera ett kvitto. Fler exempel finns i exempelmappen.

   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("--------------------------------------")

Klassificera ett dokument med hjälp av en dokumentklassificerare. Mer information om hur du skapar en anpassad klassificerarmodell finns i https://aka.ms/azsdk/formrecognizer/buildclassifiermodel.

Ny i version 2023-07-31: Den begin_classify_document-klientmetoden .

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

Parametrar

Returer

En instans av en LROPoller. Anropa result() på pollerobjektet för att returnera en AnalyzeResult.

Returtyp

Undantag

Exempel

Klassificera ett dokument. Fler exempel finns i exempelmappen.

   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]}"
       )

Klassificera ett visst dokument med en dokumentklassificerare. Mer information om hur du skapar en anpassad klassificerarmodell finns i https://aka.ms/azsdk/formrecognizer/buildclassifiermodel. Indata måste vara platsen (URL) för dokumentet som ska klassificeras.

Ny i version 2023-07-31: Begin_classify_document_from_url-klientmetoden.

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

Parametrar

Returer

En instans av en LROPoller. Anropa result() på pollerobjektet för att returnera en AnalyzeResult.

Returtyp

Undantag

Exempel

Klassificera ett dokument. Fler exempel finns i exempelmappen.

   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]}"
       )

DocumentAnalysisClient Stäng sessionen.

close() -> None

Undantag

Kör en nätverksbegäran med hjälp av klientens befintliga pipeline.

Begärande-URL:en kan vara relativ till bas-URL:en. Den tjänst-API-version som används för begäran är samma som klientens om inget annat anges. Att åsidosätta klientens konfigurerade API-version i relativ URL stöds på klienten med API-version 2022-08-31 och senare. Åsidosätter i absolut URL som stöds på klienten med valfri API-version. Den här metoden utlöser inte om svaret är ett fel. om du vill skapa ett undantag anropar du raise_for_status() på det returnerade svarsobjektet. Mer information om hur du skickar anpassade begäranden med den här metoden finns i https://aka.ms/azsdk/dpcodegen/python/send_request.

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

Parametrar

Returer

Svaret på ditt nätverksanrop. Felhantering sker inte för ditt svar.

Returtyp

Undantag