| 1234567891011121314151617181920212223242526272829 |
- import pdfplumber
- import re
- import json
- from pathlib import Path
- from datetime import datetime, timedelta
- today = datetime.now()
- yesterday = today - timedelta(days=1)
- current_date = [today.strftime('%d.%m.%Y'), today.strftime('%d/%m/%Y'), yesterday.strftime('%d.%m.%Y'), yesterday.strftime('%d/%m/%Y')]
- errors = {
- 'empty': [],
- 'outdated': []
- }
- files = [f for f in Path('C:\\GAPS_BMW\\Portal\\Publish\\daten\\GAPS_BMW_neu').glob('*.pdf')]
- files_count = len(files)
- for i, f in enumerate(files):
- print(f'({i}/{files_count}) {f.name} ', end='\r')
- with pdfplumber.open(str(f)) as pdf:
- text = pdf.pages[0].extract_text()
- if re.search(r'\d+ von \d+$', text):
- errors['empty'].append(f.name)
- report_date = re.search(r'\d{2}[\./]\d{2}[\./]\d{4}', text.split('\n')[0])
- if report_date is not None and report_date.group() not in current_date:
- errors['outdated'].append([f.name, report_date.group()])
- print()
- print(json.dumps(errors, indent=2))
|
