这是我的代码。当我试图执行这个脚本时,我得到了错误
Error raise BadZipFile("File is not a zip file")
BadZipFile: File is not a zip file
这是源目录路径
数据目录= r'L:\DataQA\Python解压缩文件\源压缩'
我有多个压缩文件夹内的'源压缩'(未压缩)文件夹。同样的代码工作时,我压缩所有子文件夹的源压缩到一个压缩文件夹。但我不想这种做法。
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()
1条答案
按热度按时间8zzbczxx1#
在两个zip存档打开语句中:
以及
没有任何东西(至少没有任何东西 * 我们 * 可以检查)可以保证你传递的文件名是
.zip
文件。它可能是一个目录,一个已经解压缩的文件,一些已经存在的文件...我建议您在解压之前检查文件扩展名,例如:
某些.zip文件可能会损坏,但这种可能性较小。此外,如果您希望解压缩
.jar
和其他具有不同扩展名的zip结构文件,请将fnmatch
替换为