def post(self):
try:
ts = time.time()
save_path = PDF_UPLOAD_DIRECTORY
file = request.files['file']
xml_file = request.files['xml_file']
xml_file_name = xml_file.filename.replace(' ', '_')
file_name = file.filename.replace(' ', '_')
file_name_without_ext = os.path.basename(file_name).split('.')[0]
file_name_without_ext = file_name_without_ext + "_" + str(
uuid.uuid1())
extension = path.splitext(file_name)[1]
file_name = file_name_without_ext + extension #path.splitext(file_name)[1]
doc_dir_location = os.path.join(save_path, file_name_without_ext)
if not os.path.exists(doc_dir_location):
os.makedirs(doc_dir_location)
file_location = os.path.join(doc_dir_location, file_name)
xml_file_location = ""
xml_file_location = os.path.join(doc_dir_location, xml_file_name)
print(f"-----CML_file--->{xml_file_location}")
xml_file.save(os.path.join(doc_dir_location, xml_file_name))
file.save(file_location)
#erosion_val = [0, 3, 2, 4]
erosion_val = [0]
#erosion_val = [0]
max_try = len(erosion_val) - 1
for index, e_val in enumerate(erosion_val):
print("EROSION_VALUE-------->", e_val)
if extension.lower() in ['.jpg', '.jpeg', '.png']:
result = read_scanned_image(file_location,
doc_dir_location, e_val)
else:
result = read_scanned_pdf(file_location, doc_dir_location,
e_val)
text_file_path = os.path.join(PDF_UPLOAD_DIRECTORY,
file_name_without_ext, 'texts',
'stitched.txt')
#with open( text_file_path ) as fp:
# contents = fp.readlines()
#result = get_extraction()
#result = get_fidelity_extraction(xml_file_location)
#print(f"1*****RESULT*****{result}")
result = extract_data(
os.path.join(PDF_UPLOAD_DIRECTORY, file_name_without_ext,
'texts'), xml_file_location)
#print(f"2*****RESULT*****{result}")
result['pdf_file_path'] = 'pdf_file/' + file_name_without_ext
result[
'excel_file_path'] = 'text_file/' + file_name_without_ext
#parse_all_fields(contents, result)
te = time.time()
print(f"Time Taken---->{ts - te}")
#print(f"Time Taken---->{result}")
return jsonify({"data": result})
except CustomClassifierException as e:
print("1***ERROR***", e)
logging.error("Error {} has occurred in controller".format(e))
return e.response, e.http_code
except Exception as e:
print("2***ERROR***", e)
logging.error("Error in service = {}".format(e), exc_info=True)
return InternalServerErrorException(
error_code=500,
error_message="Data Extraction failed!").response, 500
finally:
logging.info("API Call Finished Successfully - 200")
# exit()
#else:
# continue
print("fp---->", fp, os.path.basename(fp).split('.')[0])
extension = os.path.basename(fp).split('.')[1]
if extension in ['png', 'jpg', 'jpeg']:
continue
if fp.startswith('.'):
continue
file_name_without_ext = os.path.basename(fp).split('.')[0]
filename = path + '/' + fp
doc_dir_location = os.path.join(upload_path, file_name_without_ext)
if not os.path.exists(doc_dir_location):
os.makedirs(doc_dir_location)
result = read_scanned_pdf(filename, doc_dir_location)
try:
text_file_path = os.path.join(upload_path, file_name_without_ext,
'texts', 'stitched.txt')
with open(text_file_path) as fp1:
contents = fp1.readlines()
result = parse_all_fields(contents, {})
print("RESULT**************************>", result)
if result["username"] == "":
name_count = name_count + 1
if result["program_name"] == "":
program_name_count = program_name_count + 1
def post(self):
try:
save_path = PDF_UPLOAD_DIRECTORY
file = request.files['file']
file_name = file.filename.replace(' ', '_')
file_name_without_ext = os.path.basename(file_name).split('.')[0]
file_name_without_ext = file_name_without_ext + "_" + str(
uuid.uuid1())
file_name = file_name_without_ext + path.splitext(file_name)[1]
doc_dir_location = os.path.join(save_path, file_name_without_ext)
if not os.path.exists(doc_dir_location):
os.makedirs(doc_dir_location)
print(doc_dir_location)
file_location = os.path.join(doc_dir_location, file_name)
print(file_location)
file.save(file_location)
#result = read_scanned_pdf(req_payload.get('pdf_path'), req_payload.get('output_dir_location'))
result = read_scanned_pdf(file_location, doc_dir_location)
parse_file = result['parse_file']
template_file = self.create_template(doc_dir_location)
"""
print("RESULT--->", result)
stitched_pdf_path = result['stitched_pdf_path']
template_file_path = os.path.dirname(result['stitched_pdf_path'])
abby_file_path = os.path.dirname(result['stitched_pdf_path']).replace('pages', 'texts')
#abby_text_path = os.path.join(abby_file_path, 'output.txt' )
abby_text_path = os.path.join(abby_file_path, 'stitched.txt' )
print("stitched_pdf_path-->", stitched_pdf_path)
print("abby_file_path----->", abby_file_path)
print("abby_text_path----->", abby_text_path)
#extract_to_docx( stitched_pdf_path, abby_text_path)
template_file = self.create_template( template_file_path )
"""
#===START=
print("==0==", parse_file)
with open(parse_file, encoding='utf-8') as fp:
contents = fp.readlines()
print("==1==")
obj = ModelPdfData(contents)
obj.prepare_data()
obj.compare_with_keywords(keywords)
obj.list_data()
print("TEMPLATe_FILE**", template_file)
ew = ExcelWriter(template_file)
ew.update(obj.data)
#===END===
result['excel_file_path'] = 'excel_file/' + file_name_without_ext
result['pdf_file_path'] = 'pdf_file/' + file_name_without_ext
return jsonify({"data": result})
#return formulate_response(result, 200, "Successfully Extracted")
except CustomClassifierException as e:
print("1***ERROR***", e)
logging.error("Error {} has occurred in controller".format(e))
return e.response, e.http_code
except Exception as e:
print("2***ERROR***", e)
logging.error("Error in service = {}".format(e), exc_info=True)
return InternalServerErrorException(
error_code=500,
error_message="Data Extraction failed!").response, 500
finally:
logging.info("API Call Finished Successfully - 200")