Untitled

import os
import zipfile
import re
from PyPDF2 import PdfReader
import re
import pandas as pd
from tabula import read_pdf
import pdfplumber
import tabula
import shutil
import numpy as np

path = 'C:/Users/Maria Smirnova/Desktop/КУ/5k/MVP_mcko/Исходники 547/zip'
path_to_exctract = 'C:/Users/Maria Smirnova/Desktop/КУ/5k/MVP_mcko/Исходники 547/zip/unpacked'
for file in os.listdir(path):
    file_path = path+'/'+file
    archive = zipfile.ZipFile(file_path)
    for entry in archive.infolist():
        encoding='cp866'
        encode = 'cp437'
        name = entry.filename.encode(encode).decode(encoding)
        if ('код' in name.lower()) & ('pdf' in name.lower()):
            #print('file in zip name with codes:', name)
            #print('is there re search', re.search('.*/.*/.*', name))
            if re.search('.*/.*/.*', name) == None:
                archive.extract(entry.filename, path_to_exctract)
                os.rename(path_to_exctract + '/' + entry.filename, path_to_exctract + '/' + name)
            else:
                archive.extract(entry.filename, path_to_exctract)            
                old_name = os.path.dirname(path_to_exctract  + '/' + entry.filename) + '/' + os.path.basename(entry.filename)
                new_name = os.path.dirname(path_to_exctract + '/' + entry.filename) + '/' + os.path.basename(name)
                os.rename(old_name, new_name)
    try:
        old_folder = os.path.dirname(path_to_exctract  + '/' + entry.filename)
        new_folder = path_to_exctract  + '/' + os.path.dirname(name)
        #print(old_folder)
        #print(new_folder)
        os.rename(old_folder, new_folder)
    except:
        pass

columns_names = ['фио обучающегося', 'индивидуальный\rкод диагностики', 'код диагностики', 'код', 'пароль', 'класс', 'комплект']
df_codes = pd.DataFrame(columns=columns_names)
for address, dirs, files in os.walk(path_to_exctract):
    for name in files:
        file_path = os.path.join(address, name)
        #print(file_path)
        for d in tabula.read_pdf(file_path, pages="all"):
            d.columns = [x.lower() for x in d.columns]
            if 'фио обучающегося' in d.columns:               
                df_codes = pd.concat([df_codes, d], ignore_index=True)

                
df_codes.loc[df_codes['код'].isna(), 'код'] = df_codes[df_codes['код'].isna()]['код диагностики']
df_codes.loc[df_codes['код'].isna(), 'код'] = df_codes[df_codes['код'].isna()]['индивидуальный\rкод диагностики']
df_codes = df_codes.drop(['код диагностики','индивидуальный\rкод диагностики'], axis=1)
df_codes.to_excel('df_codes.xlsx')

def read_result(text):
    school : str = re.search(r'Государственное.*', text)[0]
    subject : str = re.search(r'Предмет: [а-яА-ЯёЁ]*\b ', text)[0]
    subject = re.sub(r'Предмет: ', '', subject)
    class_name : str = re.search(r'Класс: [0-9а-яА-ЯёЁ]*\b', text)[0]
    class_name = re.sub(r'Класс: ', '', class_name)
    mcko_date = re.search(r'Дата: .*\d\d\d\d', text)[0]
    mcko_date = re.sub(r'Дата: ', '', mcko_date)
    return [school, subject, class_name, mcko_date]


path = 'C:/Users/Maria Smirnova/Desktop/КУ/5k/MVP_mcko/Исходники 547/results'
df_res = pd.DataFrame()
for address, dirs, files in os.walk(path):
    for name in files:
        if 'pdf' in name:
            file_path = os.path.join(address, name)
            #print(file_path)
            reader = PdfReader(file_path)
            number_of_pages = len(reader.pages)
            page = reader.pages[0]
            text = page.extract_text()
            info_arr = read_result(text)
            #df = pd.concat([df,d], ignore_index=True)
            for d in tabula.read_pdf(file_path, pages="all"):
                if "Код диагн." in d.columns:
                    #info = pd.DataFrame(np.repeat(info_arr, len(d), axis=0))
                    #print(info)
                    #info.columns = ['school', 'subject', 'class_name', 'mcko_date']
                    #info.rename(columns = ['school', 'subject', 'class_name', 'mcko_date'] 
                    d['school'] = info_arr[0]
                    d['subject'] = info_arr[1]
                    d['class_name'] = info_arr[2]
                    d['mcko_date'] = info_arr[3]
                    #d = pd.concat([d, info], axis=1, ignore_index=True)
                    df_res = pd.concat([df_res,d], ignore_index=True)

df_res = df_res.rename(columns={'Код диагн.': 'код'})
df_res.to_excel('df_res.xlsx')

df_codes['код']=df_codes['код'].astype(str)
df_res['код']=df_res['код'].astype(str)

df_final = df_res.set_index('код').join(df_codes.set_index('код'), on='код', how='left', lsuffix='', rsuffix='')


print(df_final)