SoFunction
Updated on 2024-11-20

Batch decompress zip archives with passwords using python

Project Address:

/Mario-Hero/toolUnRar

environmental needs

  • Windows system
  • Python 3
  • For extracting RAR files, you need to install WinRAR.
  • For decompressing 7z/zip and other files that 7-Zip supports, you need to install 7-Zip.

Usage

Directly drag in a folder or zip file to batch extract zip files containing passwords. If you drag in a folder, it will extract the zip files under the folder, but not go to the next level directory. Set the dictionary by setting PASSWD, and set whether to delete the successfully unzipped zip file after unzipping by setting DELETEIT. This script will recognize if the file is a zip file by its suffix.

You can copy the WinRAR directory and the 7-Zip directory directly into the same directory as this file so that you can carry it around and use it.

Parameters

  • PASSWD = ["hello", "123456"] : your passphrase, the script will keep experimenting with passwords from this array to unzip until it succeeds.
  • DELETEIT : A dangerous parameter. When true, the script will simply delete the successfully decompressed zip file. If false, it will not.
  • LOC_WINRAR = "C:\Program Files\WinRAR\" The location of your WinRAR installation. Even if this variable is not set correctly, the program will look for the corresponding program in the possible locations.
  • LOC_7Z: 7-Zip installation location.
  • SAVE_MODE = True: If the script is unable to determine whether this is a compressed file or not by the suffix, it will not operate on the file.

Full Code

#!/usr/bin/python3
# -*- coding: UTF-8 -*-

# Created by Mario Chen, 04.04.2021, Shenzhen
# My Github site: /Mario-Hero

import sys
import os
import subprocess

# you can change it >>>>>

PASSWD     = ["123456","hello"]  # the possible passwords
DELETEIT   = False                                     # DANGER!! If it is True,will delete rar file after extraction
LOC_WINRAR = "C:\\Program Files\\WinRAR\\"              # location of WinRAR
LOC_7Z     = "C:\\Program Files\\7-Zip\\"               # location of 7-Zip
SAVE_MODE  = True                                       # if the suffix of file doesn't look like a compressed file, then do nothing with it.

# <<<<< you can change it


PROGRAM_RAR  = "" # the program we use
PROGRAM_7Z   = ""    # the program we use
LOC_S_WINRAR = ["C:\\Program Files\\WinRAR\\","C:\\Program Files (x86)\\WinRAR\\","./",""] # some possible locations of WinRAR
LOC_S_7Z     = ["C:\\Program Files\\7-Zip\\","C:\\Program Files (x86)\\7-Zip\\","./",""]   # some possible locations of 7-Zip
RAR_FILE     = ["rar","zip","7z","tar","gz","xz","bzip2","gzip","wim","arj","cab","chm","cpio","cramfs","deb","dmg","fat","hfs","iso","lzh","lzma","mbr","msi","nsis","ntfs","rpm","squashfs","udf","vhd","xar","z"]
NOT_RAR_FILE = ["jpg","exe","png","mkv","mp4","mp3","avi","mov","jpeg","wav","gif","mpeg","webp","txt","doc","docx","ppt","pptx","xls","xlsx","html","wps","torrent","swf","bmp","crdownload","xltd","downloading"]
ENABLE_RAR = False         # initial state only
ENABLE_7Z = False          # initial state only

# for guessing >>>
GUESS_FLAG_INIT     = ["Password.", "Code.", "password", "Password"]    #0
GUESS_FLAG_START_1  = [":", ":"]                            #1
GUESS_FLAG_START_2  = ["Yes.", "for", "is", "are"," "]          #1
GUESS_FLAG_END      = ["\n","   "]                           #2
GUESS_FLAG_DIVIDE   = ["or", "or", " or "]                 #3
# <<< for guessing


def guessWDComment(comment):
    guess_flag = 0
    guess_wd: list[str] = []
    guess_ps = 0
    cutIn = 0
    cutOut = 0
    while True:
        if guess_flag == 0:
            guess_newPs = len(comment)
            guess_len = 0
            for initStr in GUESS_FLAG_INIT:
                ps_temp = (initStr, guess_ps)
                if ps_temp == -1:
                    continue
                else:
                    if ps_temp<guess_newPs:
                        guess_newPs = ps_temp
                        guess_len = len(initStr)
            if guess_newPs == len(comment):
                if not guess_wd:
                    cutIn = 0
                    cutOut = len(comment)
                    guess_flag = 3
                else:
                    break
            else:
                guess_ps = guess_newPs + guess_len
                guess_flag = 1
        elif guess_flag == 1:
            found_temp = False
            found_temp_2 = False
            guess_newPs = len(comment)
            for startStr in GUESS_FLAG_START_1:
                ps_temp = (startStr, guess_ps, guess_ps + 20)
                if ps_temp == -1:
                    continue
                else:
                    if ps_temp < guess_newPs:
                        found_temp = True
                        guess_newPs = ps_temp + len(startStr)
                        guess_flag = 2
            if found_temp:
                guess_ps = guess_newPs
                cutIn = guess_ps
                continue
            else:
                guess_newPs = len(comment)
                for startStr in GUESS_FLAG_START_2:
                    ps_temp = (startStr, guess_ps, guess_ps + 20)
                    if ps_temp == -1:
                        continue
                    else:
                        if ps_temp < guess_newPs:
                            found_temp_2 = True
                            guess_newPs = ps_temp + len(startStr)
                            guess_flag = 2
            if found_temp_2:
                guess_ps = guess_newPs
            cutIn = guess_ps
            guess_flag = 2
        elif guess_flag == 2:
            guess_newPs = len(comment)
            for endStr in GUESS_FLAG_END:
                ps_temp = (endStr, guess_ps)
                if ps_temp == -1:
                    continue
                else:
                    if ps_temp < guess_newPs:
                        guess_newPs = ps_temp
            guess_ps = guess_newPs
            guess_flag = 3
            cutOut = guess_ps
        elif guess_flag == 3:
            found_cut_temp = False
            for divideStr in GUESS_FLAG_DIVIDE:
                if (divideStr, cutIn, cutOut) != -1:
                    found_cut_temp = True
                    for wd in comment[cutIn:cutOut].split(divideStr):
                        guess_wd.append(())
                    break
            if not found_cut_temp:
                guess_wd.append(comment[cutIn:cutOut].strip())
            guess_flag = 0
        else:
            guess_flag = 0
    return guess_wd


def isCompressedFile(file):
    file = ()
    for rar in RAR_FILE:
        if ("." + rar):
            return True
    for media in NOT_RAR_FILE:
        if ("." + media):
            return False
    return not SAVE_MODE


def utfIsNumber(uchar):
    return uchar >= u'\u0030' and uchar<=u'\u0039'


def winRarDo(folder, file, wd):
    extractStr = " x -y -p" + wd + " \"" + folder + "\\" + file + "\" \"" + folder + "\\\""
    extM = ("@\""+LOC_WINRAR+PROGRAM_RAR+"\""+extractStr,shell=True)     
    if extM == 1:    # not rar file
        return 2
    elif extM == 11: # wrong password
        return 1
    elif extM != 0:  # error
        return 1
    else:
        return 0


def z7Do(folder, file, wd):
    extractStr = " x -y -p" + wd + " \"" + folder + "\\" + file + "\" -o\"" + folder + "\\\"" 
    extM = ("@\""+LOC_7Z+PROGRAM_7Z+"\""+extractStr,shell=True)
    if extM !=0: # error
        return 1
    else:
        return 0


def unrarFile(folder, file):
    successThisFile = False
    fileNameEncrypted = True
    if not folder:
        cutPos = ("\\")
        folder = file[:cutPos]
        file = file[cutPos+1:]
        #print(folder)
        #print(file)
    if ENABLE_RAR and (".rar"):
        winRarReturn = winRarDo(folder, file, PASSWD[0])
        #print(winRarReturn)
        if winRarReturn == 0:
            #successThisFile = True
            return True
        elif winRarReturn == 2:
            pass
        else:
            getCommentStr = " l -p0 -z" + " \"" + folder + "\\" + file + "\""
            commentNumber = ("@\""+LOC_WINRAR+PROGRAM_RAR+"\""+getCommentStr,shell=True)
            #commentNumber = 1
            if commentNumber == 0:
                commentM = ("@\""+LOC_WINRAR+PROGRAM_RAR+"\""+getCommentStr)
                if commentM[0] == 0:
                    fileNameEncrypted = False
                    comment = commentM[1][(commentM[1].index("\n\n")+2):commentM[1].index(folder)]
                    comment = comment[0:("\n\n")]
                    #print(comment)
                    if comment:
                        wdArray = guessWDComment(comment)
                        print("Possible passwords:", wdArray)
                        for wd in wdArray:
                            winRarReturn = winRarDo(folder, file, wd)
                            if winRarReturn == 1:
                                continue
                            elif winRarReturn == 0:
                                successThisFile = True
                                break
                            elif winRarReturn == 2:
                                break
                            else:
                                break
            if successThisFile:
                return True
            for index in range(1,len(PASSWD)):
                winRarReturn = winRarDo(folder, file, PASSWD[index])
                if winRarReturn == 1:
                    continue
                elif winRarReturn == 0:
                    successThisFile = True
                    PASSWD[0],PASSWD[index]=PASSWD[index],PASSWD[0]
                    break
                elif winRarReturn == 2:
                    break
                else:
                    break
            
    if not successThisFile:
        if ENABLE_7Z:
            for index in range(len(PASSWD)):
                z7Return = z7Do(folder, file, PASSWD[index])
                if z7Return == 1:
                    continue
                else:
                    successThisFile = True
                    PASSWD[0],PASSWD[index]=PASSWD[index],PASSWD[0]
                    break
                     
    if not successThisFile: 
        print("Failed:"+file)
    return successThisFile


def unrar(folder):
    if (folder):
        print(folder)
        file_list = (folder)
        for file in file_list:
            if (folder + "/" + file):
                #print(folder +"/"+ file)
                #unrar(folder +"/"+file)
                pass
            else:
                if isCompressedFile(file):
                    if unrarFile(folder, file):
                        if DELETEIT:
                            (folder + "/" + file)
    else:
        if isCompressedFile(folder):
            if unrarFile("", folder):
                if DELETEIT:
                    (folder)
                  

if __name__ == '__main__':
    if len() <= 1:
        (1)
    testRar = ("\""+LOC_WINRAR+PROGRAM_RAR+"\"").read()    
    if not testRar:
       for loc in LOC_S_WINRAR:
           testRar = ("\""+loc+PROGRAM_RAR+"\"").read()
           if testRar:
               LOC_WINRAR = loc
               ENABLE_RAR = True
               break
    else:
        ENABLE_RAR = True

    test7z = ("\""+LOC_7Z+PROGRAM_7Z+"\"").read()    
    if not test7z:
       for loc in LOC_S_7Z:
           test7z = ("\""+loc+PROGRAM_7Z+"\"").read()
           if test7z:
               LOC_7Z = loc
               ENABLE_7Z = True
               break
    else:
        ENABLE_7Z = True

    if (not ENABLE_RAR) and (not ENABLE_7Z):
        print("Cannot find winRAR and 7-zip")
        (1)
    while len(PASSWD) < 2:
        ("0")   
    for folder in [1:]:
        #print(folder)
        unrar(folder)
    print("Finish.")
    #("pause",shell=True)
    (0)

Above is the details of batch decompression of zip archives with password in python, for more information about python batch decompression of zip archives, please pay attention to my other related articles!