getrti_new.py

#!/home/ounis/pyapps/virtual_env/getrti/bin/python

# by OuNiS 04.2023
# wyciągane do schowka tekstu z pliku .pdf
#
# moduły:
# pyperclip https://pypi.org/project/pyperclip/
# pyPdf https://pypi.org/project/pypdf/
# tqdm https://pypi.org/project/tqdm/

import sys
import os
import argparse
from time import sleep

import pyperclip
from pypdf import PdfReader
from tqdm import tqdm

TEXT_2_FIND = "abonamentowa za"
WIATRACZEK = ["-", "\\", "|", "/", "-","\\", "|", "/"]
# WIATRACZEK = [".", "o", "O", "o"]

def arguments():
    parser = argparse.ArgumentParser(prog="getrti.py", description="szuka frazy w pliku .pdf")
    parser.add_argument("filename",help="plik .pdf")
    parser.add_argument("text_2_find", help="szukana fraza")

    return parser.parse_args()



def main(args):

    # w razie błęddu z pyperclip:
    # https://pyperclip.readthedocs.io/en/latest/index.html#not-implemented-error
    # pyperclip.copy("SURFACE!!!")
    # print(pyperclip.paste())

    # parser = argparse.ArgumentParser(prog="getrti.py", description="szuka frazy w pliku .pdf")
    # parser.add_argument("filename",help="plik .pdf")
    # parser.add_argument("text_2_find", help="szukana fraza")

    # args = parser.parse_args()

    args = arguments()


    filename = args.filename
    text_2_find = args.text_2_find
    founded_texts = []
    if os.path.isfile(filename):
        print("\nOtwieranie pliku: %s" % filename)
        reader = PdfReader(filename)
        number_of_pages = len(reader.pages)

        print("\nIlość stron w dokumencie: %d" % number_of_pages)
        print(f"Wyszukiwana fraza: \"{text_2_find}\"\n")

        #for p_num, page in tqdm(enumerate(reader.pages,1), total=number_of_pages):


        for p_num, page in enumerate(reader.pages,1):

            text = page.extract_text()
            lines = text.split("\n")
            # print("\nStrona %d" % p_num)
            # print("Ilość linii na stronie: %d" % len(lines))
            # print("Tytuł(y) przelewów:")
            sys.stdout.write('Wyszukiwanie... {0}\r'.format(WIATRACZEK[p_num % len(WIATRACZEK)]))
            sys.stdout.flush()
            # opóźnieni do testów
            # sleep(.011)
            for line_num, line in enumerate(lines, 1):
                if line.find(text_2_find) > -1:

                    '''
                    { "line" : <str>,
                       "page_num" : <int>,
                       "line_num_on_page" : <int>
                    }
                    '''
                    founded_texts.append({"line":line, "page_num":p_num, "line_num_on_page":line_num})
                    # founded_texts.append([line, p_num, line_num])
                    print("\a", end="")
                    print(flush=True, end="")
                    # found = True
                    # print("\tznaleziono: '%s' na stronie: %d" % (line, p_num))
                    # answ = input("Akcja: ([s] - skopiuj, [q] - zakończ, [ENTER] - dalej)?: ").lower()
                    # # answ = answ.lower()
                    # match answ:
                    #     case "s":
                    #     # if answ.lower() == "s":
                    #         found = True
                    #         pyperclip.copy(line)
                    #         print("Skopiowano...")
                    #         continue
                    #     case "q":
                    #     # if answ.lower() == "q":
                    #         break_main_loop = True
                    #         break
        # list pusta? nic nie znaleziono...
        if not founded_texts :
            print("\n\t - brak, nie znaleziono wzorca: '%s'" % text_2_find)
        else:
            print()
            print("Znalezione frazy: ")
            '''
            line_info is a list of dicts like that:
            { "line" : <str>,
               "page_num" : <int>,
               "line_num_on_page" : <int>
            }
            '''
            for id, line_info in enumerate(founded_texts, 1):
                print(f'\t{id}. {line_info.get("line")}, \n\t\tstrona {line_info.get("page_num")}, linia {line_info.get("line_num_on_page")}')
            print(f"Wybierz numer w celu skopiowania do schowka(1 - {len(founded_texts)}) (q - koniec) ")
            while (True):
                answ = input(">")
                if answ.isalpha() and answ in ["q", "Q"]:
                    break
                elif answ.isnumeric():
                    num = int(answ)-1
                    if num in range(len(founded_texts)):
                        pyperclip.copy(founded_texts[num].get("line"))
                        print("Skopiowane...")
                        break
    else:
        print("ERR: plik: '%s' nie istnieje!!!" % filename)



# if "main" in dir():
if __name__ == "__main__":
    sys.exit(main(sys.argv))
# else:
#     print("ERR: no main() func. to execute...")