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    'outdated': []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            errors['outdated'].append([f.name, report_date.group()])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))