gctools/pdf/pdf_test.py

import os
import pdfplumber
import re
import json
from pathlib import Path
from datetime import datetime, timedelta


def current_date_test(base_dir: str):
    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        'outdated': []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(base_dir).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                errors['outdated'].append([f.name, report_date.group()])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))


def missing_data(base_dir: str):
    os.makedirs(base_dir + '/leer', exist_ok=True)

    errors = []
    for f in Path(base_dir).glob('*.pdf'):
        with pdfplumber.open(str(f)) as pdf:
            pages = len(pdf.pages)
            text = pdf.pages[0].extract_text()

        # print(text)
        if pages < 2 and any([
            re.search(r'Daten nicht verf', text),
            text.endswith('unprod.abw.'),
            (len(text) < 650 and text.count('\n') < 8)
        ]):
            errors.append(f.name)
            f.rename(base_dir + '/leer/' + f.name)

    return errors


if __name__ == '__main__':
    # current_date_test('C:\\GAPS_BMW\\Portal\\Publish\\daten\\GAPS_BMW_neu')
    missing_data('C:\\GlobalCube\\ReportOutput\\raw')