BadZipFile: File is not a zip file

Question

This is my code. I get the error when I try to execute this script

 Error    raise BadZipFile("File is not a zip file")  
          BadZipFile: File is not a zip file

This is my source directorypath

data_dir = r'L:\DataQA\Python Unzip Files\Source Zipped'

I have multiple zipped folders within ‘Source Zipped’(uncompressed) folder. The same code works when I zip all the subfolder of source Zipped into single zipped folder. But I don’t want this approach.

import os
import zipfile
import shutil
import json
import logging
import logging.config
import time

def my_start_time():
    global start_time, cumulative_time, start_time_stamp
    start_time = time.time()
    this_time = time.localtime(start_time)
    start_time_stamp = '{:4d}{:02d}{:02d} {:02d}:{:02d}:{:02d}'.format(\
                    this_time.tm_year, this_time.tm_mon, this_time.tm_mday,\
                    this_time.tm_hour, this_time.tm_min, this_time.tm_sec)
    cumulative_time = start_time - start_time 
    logging.info('Initial Setup: {:s}'.format(start_time_stamp))

def my_time():
    global cumulative_time
    time_taken = time.time() - start_time
    incremental_time = time_taken - cumulative_time
    cumulative_time = time_taken
    logging.info("Started: %s  Complete:  Cumulative: %.4f s  Incremental: %.4f s\n" \
          % (start_time_stamp, cumulative_time, incremental_time) )

logging.basicConfig(filename='myunzip_task_log.txt',level=logging.DEBUG)
my_start_time()

logging.info('Initial Setup...')

def write_to_json(data, file):
    value = False
    with open(file, 'w') as f:
        json.dump(json.dumps(data, sort_keys=True),f)   
        f.close()
        value = True
    return value


data_dir = r'L:\DataQA\Python Unzip Files\Source Zipped'
temp_dir =  r'L:\DataQA\Python Unzip Files\temp1'
new_dir = r'L:\DataQA\Python Unzip Files\temp2'
final_dir = r'L:\DataQA\Python Unzip Files\Destination Unzipped files'





big_list = os.listdir(data_dir)

archive_count = 0
file_count = 152865
basename1 = os.path.join(final_dir,'GENERIC_ROUGHDRAFT')
basename2 = os.path.join(final_dir,'XACTDOC')

my_time()
archive_count = len(big_list)
logging.info('Unzipping {} archives...'.format(archive_count))
for folder in big_list:
    prior_count = file_count
    logging.info('Starting: {}'.format(folder))

    try:
        shutil.rmtree(temp_dir)
    except FileNotFoundError: 
        pass
    os.mkdir(temp_dir)
    with zipfile.ZipFile(os.path.join(data_dir,folder),mode='r') as a_zip:
        a_zip.extractall(path = temp_dir)
        archive_count += 1
        logging.info('Cumulative total of {} archive(s) unzipped'.format(archive_count))
        bigger_list = os.listdir(temp_dir)
        logging.info('Current archive contains {} subfolders'.format(len(bigger_list)))
        for sub_folder in bigger_list:
            with zipfile.ZipFile(os.path.join(temp_dir,sub_folder),mode='r') as b_zip:
                b_zip.extractall(path = new_dir)
            file1 = "%s (%d).%s" % (basename1, file_count, 'xml')
            file2 = "%s (%d).%s" % (basename2, file_count, 'xml')
            shutil.copy(os.path.join(new_dir, 'GENERIC_ROUGHDRAFT.xml'), file1)
            shutil.copy(os.path.join(new_dir, 'XACTDOC.xml'), file2)
            file_count += 1
        logging.info('{} subfolders unzipped'.format(file_count - prior_count))
    #os.remove(data_dir)
    shutil.rmtree(data_dir)
    os.mkdir(data_dir)
    #os.unlink(data_dir)
    my_time()
logging.info('Total of {0} files -- {1} pairs -- should be in {2}'.format(2*(file_count-1), file_count-1, final_dir))

time.sleep(1)

my_time()

Solution

in both zip archive open statements:

with zipfile.ZipFile(os.path.join(data_dir,folder),mode='r')

and

with zipfile.ZipFile(os.path.join(temp_dir,sub_folder),mode='r')

nothing (at least nothing that we can check) guarantees that the file names you're passing are actually .zip files. It could be a directory, an already extracted file, some file that was already there...

I suggest that you check the file extension prior to extracting, for instance:

import fnmatch
zfn = os.path.join(temp_dir,sub_folder)
if fnmatch.fnmatch(zfn,"*.zip"):
    with zipfile.ZipFile(zfn,mode='r') as whatever:

Some .zip files could be corrupt, but that's less likely. Also, if you wanted to extract .jar and other zip-structured files with a different extension, replace the fnmatch by

if zfn.lower().endswith(('.zip','.jar','.docx')):