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

Add initialAmount parsing

Browse Source
This commit is contained in:
Benjamin Loison 2023-06-21 00:57:16 +02:00
parent 6ced1c0db0
commit 5f439c0e61
Signed by: Benjamin_Loison
SSH Key Fingerprint: SHA256:BtnEgYTlHdOg1u+RmYcDE0mnfz1rhv5dSbQ2gyxW8B8
1 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
bnp_pdf_statement_parser.py
View File

@ -28,11 +28,12 @@ def getTextFromPdf(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}')
for folder in os.listdir():
for file in os.listdir(folder):
folder = '2022'
file = '20220321.pdf'
#folder = '2022'
#file = '20220321.pdf'
print(folder, file)
filePath = f'{folder}/{file}'
content = getTextFromPdf(filePath)
@ -40,10 +41,14 @@ for folder in os.listdir():
started = False
firstPage = True
payment = []
initialAmount = None
for line in lines:
if not started:
# We are interested in the content after this line:
if line.startswith('SOLDE CREDITEUR AU') or (line.startswith('Date Nature des opérations Valeur Débit Crédit') and not firstPage):
if soldeCrediteurAuRegex.match(line) != 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(' ', ''))
print(initialAmount)
started = True
continue
else: