Copy link to clipboard
Copied
I am using standard python code (with AWS adobe API) to extract text and tables. My pdf is about 19MB (much lessr than the limit specified. I am getting timeout. Can you please help?
INFO:adobe.pdfservices.operation.pdfops.extract_pdf_operation:All validations successfully done. Beginning ExtractPDF operation execution
ERROR:root:Exception encountered while executing operation
Traceback (most recent call last):
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\urllib3\connectionpool.py", line 699, in urlopen
httplib_response = self._make_request(
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\urllib3\connectionpool.py", line 394, in _make_request
conn.request(method, url, **httplib_request_kw)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\urllib3\connection.py", line 234, in request
super(HTTPConnection, self).request(method, url, body=body, headers=headers)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\http\client.py", line 1256, in request
self._send_request(method, url, body, headers, encode_chunked)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\http\client.py", line 1302, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\http\client.py", line 1251, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\http\client.py", line 1050, in _send_output
self.send(chunk)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\http\client.py", line 972, in send
self.sock.sendall(data)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\ssl.py", line 1204, in sendall
v = self.send(byte_view[count:])
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\ssl.py", line 1173, in send
return self._sslobj.write(data)
socket.timeout: The write operation timed out
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\requests\adapters.py", line 439, in send
resp = conn.urlopen(
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\urllib3\connectionpool.py", line 755, in urlopen
retries = retries.increment(
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\urllib3\util\retry.py", line 531, in increment
raise six.reraise(type(error), error, _stacktrace)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\urllib3\packages\six.py", line 734, in reraise
raise value.with_traceback(tb)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\urllib3\connectionpool.py", line 699, in urlopen
httplib_response = self._make_request(
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\urllib3\connectionpool.py", line 394, in _make_request
conn.request(method, url, **httplib_request_kw)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\urllib3\connection.py", line 234, in request
super(HTTPConnection, self).request(method, url, body=body, headers=headers)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\http\client.py", line 1256, in request
self._send_request(method, url, body, headers, encode_chunked)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\http\client.py", line 1302, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\http\client.py", line 1251, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\http\client.py", line 1050, in _send_output
self.send(chunk)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\http\client.py", line 972, in send
self.sock.sendall(data)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\ssl.py", line 1204, in sendall
v = self.send(byte_view[count:])
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\ssl.py", line 1173, in send
return self._sslobj.write(data)
urllib3.exceptions.ProtocolError: ('Connection aborted.', timeout('The write operation timed out'))
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\adobe\pdfservices\operation\internal\http\http_client.py", line 70, in _execute_request
response = requests.post(url=http_request.url,
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\requests\api.py", line 119, in post
return request('post', url, data=data, json=json, **kwargs)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\requests\api.py", line 61, in request
return session.request(method=method, url=url, **kwargs)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\requests\sessions.py", line 542, in request
resp = self.send(prep, **send_kwargs)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\requests\sessions.py", line 655, in send
r = adapter.send(request, **kwargs)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\requests\adapters.py", line 498, in send
raise ConnectionError(err, request=request)
requests.exceptions.ConnectionError: ('Connection aborted.', timeout('The write operation timed out'))
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "c:\users\milin\nlp\read pdf\adobe-dc-pdf-services-sdk-extract-python-samples\src\extractpdf\milind_extract_info_from_pdf.py", line 61, in <module>
result: FileRef = extract_pdf_operation.execute(execution_context)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\adobe\pdfservices\operation\pdfops\extract_pdf_operation.py", line 131, in execute
location = ExtractPDFAPI.extract_pdf(execution_context, self._source_file_ref, self._extract_pdf_options)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\adobe\pdfservices\operation\internal\service\extract_pdf_api.py", line 42, in extract_pdf
location = CPFApi.cpf_create_ops_api(context, cpf_content_analyzer_req, [file_ref],
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\adobe\pdfservices\operation\internal\api\cpf_api.py", line 63, in cpf_create_ops_api
response = http_client.process_request(http_request=http_request,
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\adobe\pdfservices\operation\internal\http\http_client.py", line 41, in process_request
response = _execute_request(http_request)
File "C:\Users\milin\Anaconda3\envs\nlp_dev38\lib\site-packages\adobe\pdfservices\operation\internal\http\http_client.py", line 81, in _execute_request
raise SdkException("Request could not be completed. Possible cause attached!", sys.exc_info())
adobe.pdfservices.operation.exception.exceptions.SdkException: description =Request could not be completed. Possible cause attached!, requestTrackingId=(<class 'requests.exceptions.ConnectionError'>, ConnectionError(ProtocolError('Connection aborted.', timeout('The write operation timed out'))), <traceback object at 0x0000024BEEE09EC0>)
Copy link to clipboard
Copied
Moderator: product is Document Services APIs
Copy link to clipboard
Copied
I've moved your post from Using the Community (for questions about the forums) to Document Services APIs, as per @Test Screen Name 's post.
Jane