import re
data = 'Date : 2020-09-06 20:43:00Ack No : 3320000266Original for RecipientInvoice No.: IN05200125634Date of Issue: 06.09.2015TAX INVOICE(Issued u/s 31(1) of GST Act, 2017)POLO INDUSTRIES LIMITEDCIN: K253648B85PLC015063GSTIN: 3451256132uuy668803E1Z9PAN: BBB7653279K .....'
regex_ack_no = re.compile(r"Ack No\s*:\s*(\d+)")
regex_due_date = re.compile(r"Date of Issue\s*:\s*(\d\d\.\d\d\.\d{4})")
regex_CIN = re.compile(r"CIN:\s*(\w+?)GSTIN:")
ack_no = re.search(regex_ack_no, data)
if ack_no:
ack_no = ack_no.group(1)
else:
ack_no = 'Ack No not found'
due_date = re.search(regex_due_date, data)
if due_date:
due_date = due_date.group(1)
else:
due_date = 'Due date not found'
cin = re.search(regex_CIN, data)
if cin:
cin = cin.group(1)
else:
cin = 'CIN not found'
print([ack_no, due_date, cin])
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