Benjamin_Loison/BNP_PDF_statement_parser
1
0
Fork 0
Code Issues 2 Pull Requests Packages Projects Releases Wiki Activity

Uppercase constants

Browse Source
This commit is contained in:
Benjamin Loison 2024-10-03 17:43:44 +02:00
parent ee6e850174
commit 17acc478b7
Signed by: Benjamin_Loison
SSH Key Fingerprint: SHA256:BtnEgYTlHdOg1u+RmYcDE0mnfz1rhv5dSbQ2gyxW8B8
1 changed files with 12 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
bnp_pdf_statement_parser.py
View File

@ -9,9 +9,9 @@ import matplotlib.pyplot as plt
import matplotlib.ticker as ticker
from datetime import datetime
path = f'/home/benjamin/Desktop/bens_folder/bazaar/documents/bnp/bank_statements/compte_de_cheques/'
PATH = f'/home/benjamin/Desktop/bens_folder/bazaar/documents/bnp/bank_statements/compte_de_cheques/'
os.chdir(path)
os.chdir(PATH)
'''
Assuming file hierarchy like:
@ -30,10 +30,10 @@ def execute(command):
def getTextFromPdf(pdfPath):
return execute(['pdftotext', '-raw', pdfPath, '-'])
firstLineOfPaymentRegex = re.compile('\\d{2}\\.\\d{2} \\d{2}\\.\\d{2} \\d+,\\d{2}')
endPageAfterTheFirstOneRegex = re.compile('P\\. \\d+/\\d+')
soldeCrediteurAuRegex = re.compile('SOLDE CREDITEUR AU \\d{2}\\.\\d{2}\\.\\d{4}')
totalDesOperationsRegex = re.compile('TOTAL\\ DES\\ OPERATIONS\\ ([0-9 ]+,\\d{2})\\ ([0-9 ]+,\\d{2})')
FIRST_LINE_OF_PAYMENT_REGEX = re.compile('\\d{2}\\.\\d{2} \\d{2}\\.\\d{2} \\d+,\\d{2}')
END_PAGE_AFTER_THE_FIRST_ONE_REGEX = re.compile('P\\. \\d+/\\d+')
SOLDE_CREDITEUR_AU_REGEX = re.compile('SOLDE CREDITEUR AU \\d{2}\\.\\d{2}\\.\\d{4}')
TOTAL_DES_OPERATIONS_REGEX = re.compile('TOTAL\\ DES\\ OPERATIONS\\ ([0-9 ]+,\\d{2})\\ ([0-9 ]+,\\d{2})')
PRINT_TRANSACTIONS = False
@ -61,9 +61,9 @@ for folder in sorted(os.listdir()):
for line in lines:
if not started:
# We are interested in the content after this line:
if soldeCrediteurAuRegex.match(line) is not None or (line.startswith('Date Nature des opérations Valeur Débit Crédit') and not firstPage):
if soldeCrediteurAuRegex.match(line):
initialAmount = float(soldeCrediteurAuRegex.sub('', line).replace(',', '.').replace(' ', ''))
if SOLDE_CREDITEUR_AU_REGEX.match(line) is not None or (line.startswith('Date Nature des opérations Valeur Débit Crédit') and not firstPage):
if SOLDE_CREDITEUR_AU_REGEX.match(line):
initialAmount = float(SOLDE_CREDITEUR_AU_REGEX.sub('', line).replace(',', '.').replace(' ', ''))
currentAmount = initialAmount
print('Initial amount', initialAmount)
print()
@ -72,13 +72,13 @@ for folder in sorted(os.listdir()):
continue
else:
# We aren't interested in the content after this line:
if line.startswith('BNP PARIBAS SA au capital de') or endPageAfterTheFirstOneRegex.match(line) is not None:
if line.startswith('BNP PARIBAS SA au capital de') or END_PAGE_AFTER_THE_FIRST_ONE_REGEX.match(line) is not None:
firstPage = False
started = False
continue
# We aren't interested in the content after this line
elif line.startswith('TOTAL DES OPERATIONS'):
totalDesOperationsRegexMatch = totalDesOperationsRegex.match(line)
totalDesOperationsRegexMatch = TOTAL_DES_OPERATIONS_REGEX.match(line)
totalMonthlyDebit, totalMonthlyCredit = [float(group.replace(',', '.').replace(' ', '')) for group in totalDesOperationsRegexMatch.groups()]
print(f'Total monthly debit: {totalMonthlyDebit}')
print(f'Total monthly credit: {totalMonthlyCredit}')
@ -87,7 +87,7 @@ for folder in sorted(os.listdir()):
totalMonthlyDifference = totalMonthlyCredit - totalMonthlyDebit
totalMonthlyDifferences += [totalMonthlyDifference]
break
if firstLineOfPaymentRegex.match(line) is not None:
if FIRST_LINE_OF_PAYMENT_REGEX.match(line) is not None:
if date is not None and PRINT_TRANSACTIONS:
print(date, valeur, amount, currentAmount)
print('\n'.join(comment))