def read_docx_text(filepath, supplierID):
imageInfo = image_detect(filepath)
flagList = []
flagDetails = {}
data_text = docx2txt.process(filepath)
rm_newline_char = data_text.rstrip('\n').split(',')
rp_newline_empty = [i.replace('\n', ' ') for i in rm_newline_char]
rp_newline_empty = [i.replace('\t', ' ') for i in rp_newline_empty]
text_oneline = str(rp_newline_empty)
email_url_phone = utility.email_phone_url(text_oneline)
email_url_phoneFlags = email_url_phone[0]
flagDetails = email_url_phone[1]
supplierInfo = detect_supplier_info(data_text, supplierID)
supplierBoolean = supplierInfo[0]
imageBoolean = imageInfo[0]
if imageBoolean[0]:
flagList.append(imageBoolean)
imageValue = imageInfo[1]
flagDetails['image'] = imageValue
else:
flagList.append(imageBoolean)
flagList.append(email_url_phoneFlags)
suppliers = []
if supplierBoolean:
supplierVals = supplierInfo[1]
flagDetails['suppliers'] = supplierVals
suppliers.append(1)
flagList.append(suppliers)
else:
suppliers.append(0)
flagList.append(suppliers)
return flagList, flagDetails
def read_rtf_text_catdoc(filepath):
image = image_detect(filepath)
data_text = ''
flagList = []
fileopen = os.popen('catdoc -w "%s"' % filepath)
data_text = fileopen.read()
rm_dump_spaces = data_text.rstrip('\n').split(',')
data = [i.replace('\n', ' ') for i in rm_dump_spaces]
text_oneline = str(data)
email_url_phone = utility.email_phone_url(text_oneline)
supplier = detect_supplier_info(data_text)
flagList.append(image)
flagList.append(email_url_phone)
flagList.append(supplier)
return flagList
def read_pdf_text(filepath, supplierID):
imageInfo = image_detect(filepath)
data_text = ''
flagList = []
flagDetails = {}
# pdf_file_object = open(filepath, 'rb')
# pdf_file = PdfFileReader(pdf_file_object)
# for page in pdf_file.pages:
# data_text += page.extractText()
# make the text in oneline remove new line charecter
parsed = parser.from_file(filepath)
data_text += parsed["content"]
rm_newline_char = data_text.rstrip('\n').split(',')
rp_newline_empty = [i.replace('\n', ' ') for i in rm_newline_char]
rp_newline_empty = [i.replace('\t', ' ') for i in rp_newline_empty]
text_oneline = str(rp_newline_empty)
email_url_phone = utility.email_phone_url(text_oneline)
email_url_phoneFlags = email_url_phone[0]
flagDetails = email_url_phone[1]
supplierInfo = detect_supplier_info(data_text, supplierID)
supplierBoolean = supplierInfo[0]
imageBoolean = imageInfo[0]
if imageBoolean[0]:
flagList.append(imageBoolean)
imageValue = imageInfo[1]
flagDetails['image'] = imageValue
else:
flagList.append(imageBoolean)
flagList.append(email_url_phoneFlags)
suppliers = []
if supplierBoolean:
supplierVals = supplierInfo[1]
flagDetails['suppliers'] = supplierVals
suppliers.append(1)
flagList.append(suppliers)
else:
suppliers.append(0)
flagList.append(suppliers)
return flagList, flagDetails
def read_odt_text(filepath, supplierID):
imageInfo = image_detect(filepath)
flagList = []
flagDetails = {}
data_text = ''
popen_param = ['odt2txt', filepath]
popen_output = Popen(popen_param, stdout=PIPE)
stdout, stderr = popen_output.communicate()
data_text += stdout.decode('ascii', 'ignore')
rm_newline_char = data_text.rstrip('\n').split(',')
rp_newline_empty = [i.replace('\n', ' ') for i in rm_newline_char]
rp_newline_empty = [i.replace('\t', ' ') for i in rp_newline_empty]
text_oneline = str(rp_newline_empty)
email_url_phone = utility.email_phone_url(text_oneline)
email_url_phoneFlags = email_url_phone[0]
flagDetails = email_url_phone[1]
supplierInfo = detect_supplier_info(data_text, supplierID)
supplierBoolean = supplierInfo[0]
imageBoolean = imageInfo[0]
if imageBoolean[0]:
flagList.append(imageBoolean)
imageValue = imageInfo[1]
flagDetails['image'] = imageValue
else:
flagList.append(imageBoolean)
flagList.append(email_url_phoneFlags)
suppliers = []
if supplierBoolean:
supplierVals = supplierInfo[1]
flagDetails['suppliers'] = supplierVals
suppliers.append(1)
flagList.append(suppliers)
else:
suppliers.append(0)
flagList.append(suppliers)
return flagList, flagDetails