I am trying to extract text from pdf using document intelligence from azure, code I am using:
from azure.ai.formrecognizer import DocumentAnalysisClient
from azure.core.credentials import AzureKeyCredential
endpoint = "https://xyz.cognitiveservices.azure.com/"
key = ""
def format_bounding_region(bounding_regions):
if not bounding_regions:
return "N/A"
return ", ".join("Page #{}: {}".format(region.page_number, format_polygon(region.polygon)) for region in bounding_regions)
def format_polygon(polygon):
if not polygon:
return "N/A"
return ", ".join(["[{}, {}]".format(p.x, p.y) for p in polygon])
def analyze_general_documents():
# sample document
docUrl = "https://raw.githubusercontent.com/Azure-Samples/cognitive-services-REST-api-samples/master/curl/form-recognizer/sample-layout.pdf"
document_analysis_client = DocumentAnalysisClient(endpoint=endpoint, credential=AzureKeyCredential(key))
poller = document_analysis_client.begin_analyze_document_from_url(
"prebuilt-document", docUrl)
result = poller.result()
for style in result.styles:
if style.is_handwritten:
print("Document contains handwritten content: ")
print(",".join([result.content[span.offset:span.offset + span.length] for span in style.spans]))
print("----Key-value pairs found in document----")
for kv_pair in result.key_value_pairs:
if kv_pair.key:
print(
"Key '{}' found within '{}' bounding regions".format(
kv_pair.key.content,
format_bounding_region(kv_pair.key.bounding_regions),
)
)
if kv_pair.value:
print(
"Value '{}' found within '{}' bounding regions\n".format(
kv_pair.value.content,
format_bounding_region(kv_pair.value.bounding_regions),
)
)
for page in result.pages:
print("----Analyzing document from page #{}----".format(page.page_number))
print(
"Page has width: {} and height: {}, measured with unit: {}".format(
page.width, page.height, page.unit
)
)
for line_idx, line in enumerate(page.lines):
print(
"...Line # {} has text content '{}' within bounding box '{}'".format(
line_idx,
line.content,
format_polygon(line.polygon),
)
)
for word in page.words:
print(
"...Word '{}' has a confidence of {}".format(
word.content, word.confidence
)
)
for selection_mark in page.selection_marks:
print(
"...Selection mark is '{}' within bounding box '{}' and has a confidence of {}".format(
selection_mark.state,
format_polygon(selection_mark.polygon),
selection_mark.confidence,
)
)
for table_idx, table in enumerate(result.tables):
print(
"Table # {} has {} rows and {} columns".format(
table_idx, table.row_count, table.column_count
)
)
for region in table.bounding_regions:
print(
"Table # {} location on page: {} is {}".format(
table_idx,
region.page_number,
format_polygon(region.polygon),
)
)
for cell in table.cells:
print(
"...Cell[{}][{}] has content '{}'".format(
cell.row_index,
cell.column_index,
cell.content,
)
)
for region in cell.bounding_regions:
print(
"...content on page {} is within bounding box '{}'\n".format(
region.page_number,
format_polygon(region.polygon),
)
)
print("----------------------------------------")
if __name__ == "__main__":
analyze_general_documents()
error:
Traceback (most recent call last):
File "c:\Users\SESA70\Desktop\azure\text_extract.py", line 116, in <module>
analyze_general_documents()
File "c:\Users\SESA737860\Desktop\azure\text_extract.py", line 24, in analyze_general_documents
poller = document_analysis_client.begin_analyze_document_from_url(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\SESA70\AppData\Local\Programs\Python\Python311\Lib\site-packages\azure\core\tracing\decorator.py", line 78, in wrapper_use_tracer
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\SESA70\AppData\Local\Programs\Python\Python311\Lib\site-packages\azure\ai\formrecognizer\_document_analysis_client.py", line 198, in begin_analyze_document_from_url
return _client_op_path.begin_analyze_document( # type: ignore
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\SESA70\AppData\Local\Programs\Python\Python311\Lib\site-packages\azure\core\tracing\decorator.py", line 78, in wrapper_use_tracer
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\SESA70\AppData\Local\Programs\Python\Python311\Lib\site-packages\azure\ai\formrecognizer\_generated\v2023_07_31\operations\_document_models_operations.py", line 518, in begin_analyze_document
raw_result = self._analyze_document_initial( # type: ignore
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\SESA70\AppData\Local\Programs\Python\Python311\Lib\site-packages\azure\ai\formrecognizer\_generated\v2023_07_31\operations\_document_models_operations.py", line 443, in _analyze_document_initial
raise HttpResponseError(response=response)
azure.core.exceptions.HttpResponseError: (AuthenticationTypeDisabled) Key based authentication is disabled for this resource.
Code: AuthenticationTypeDisabled
Message: Key based authentication is disabled for this resource.
I believe the code is perfectly fine, why is it I am getting this error is it because my organisation didnt provide rights to use this resource or am i missing anything.
I am new to azure please correct me where I'm going wrong, thankyou.
I have checked the provided code, it seems to be working fine.
Output:
The issue you're encountering may be due to the authentication method for the Azure Document Analysis Resource. If API keys have been disabled and role assignments have been set up, the portal will use role assignments for authentication instead. For more details you can check this documentation.
To resolve this, you need to have access enabled for key-based authentication. Once this is done, you should be able to use your subscription key to authenticate the request. Ensure that you have the necessary permissions to manage role assignments.
One you have the access you'll be able to use your subscription key to authenticate above request.