Develop Reference

Why I cannot extract file with Python

I don't understand why I cannot extract file and why Python print KeyError: There is no item named eurofxref.zip in the archive lang interpreter see file as eurofxref.csv
import os
import zipfile
from file_from_web_class import FileFromWeb
if __name__ == "__main__":
url = "https://www.ecb.europa.eu/stats/eurofxref/eurofxref.zip"
dir = point_file_from_cwd("temp", "eurofxref.zip")
with FileFromWeb(url, dir) as f:
with zipfile.ZipFile(f.temp_file, "r") as z:
path = point_from_cwd("temp")
a_file = z.namelist()[0]
print(a_file) #? eurofxref.csv
os.chdir(path)
z.extract("eurofxref.zip", '.', None) #? I don't understand.
More details:
import os
import zipfile
import requests
class FileFromWeb:
def __init__(self, url, temp_file):
self.url = url
self.temp_file = temp_file
def __enter__(self):
response = requests.get(self.url)
with open(self.temp_file, "wb") as reading_file:
reading_file.write(response.content)
return self
def __exit__(self, exc_type, exc_val, exc_tb):
pass
Method on main.py file:
def point_from_cwd(rel_path):
defined_path = os.getcwd() + "\\" + rel_path
print("You want point dir: ", os.getcwd() + "\\" + rel_path)
return defined_path
def point_file_from_cwd(rel_path, file_name):
defined_path = os.getcwd() + "\\" + rel_path + "\\" + file_name
print("You want point file in dir: ", os.getcwd() + "\\" + rel_path + "\\" + file_name)
return defined_path

KeyError is a self-explanatory exception and it basically says "there is no item named eurofxref.zip in the archive" so probably you are trying to extract eurofxref.csv but providing wrong item.
It should be fine when you change this line if I understand your question with given details:
z.extract("eurofxref.zip", '.', None) #? I don't understand.
as:
z.extract("eurofxref.csv", '.', None) #? I don't understand.

ZipFile.extract extracts only specified member from the archive. Try:
z.extract("eurofxref.csv", '.', None)
or:
z.extractall()

why the python file handling not recognizing file name?

I want to replace a string with another string in a file. I have below program to perform the task.
import os
import sys
import traceback
from glob import iglob
def usage():
print('Usage: python FindAndReplace.py [Old String] [New String] '
'[File Filters(default:".txt,.xml")] [Directory To Check(.)]')
def search_replace_string(fileName, old_str, new_str):
if not(os.path.isfile(fileName) and os.access(fileName, os.W_OK)):
print("Warning: Skipping..File does not exist or and is not writeable:" + filename)
return False
fileupdated = False
# Read the old file
with open(fileName, 'r') as f:
newlines = []
for lines in f.readlines():
if old_str in lines:
fileupdated = True
line = lines.replace(old_str, new_str)
newlines.append(line)
# Write changes to same file
if fileupdated:
print("string Found and Updating File: " + fileName)
try:
with open(fileName, 'w') as f:
for line in newlines:
f.write(line)
except:
print("Error: Cannot open/access existing file for writing: " + fileName)
return fileupdated
def main():
try:
DEFAULT_PATH = iglob(str('<path_to_file.xml'))
if len(sys.argv) < 3:
usage()
# old/new string required parameters, exit if not supplied
sys.exit(-1)
else:
oldString = sys.argv[1]
newString = sys.argv[2]
if len(sys.argv) < 4:
patterns = ['.xml', '.txt']
else:
stringFilter = sys.argv[3]
patterns = stringFilter.split(',')
if len(sys.argv) < 5:
path = DEFAULT_PATH
else:
path = sys.argv[4]
print('[Old String] :' + oldString)
print('[New String] :' + newString)
print('[File Filters] :' + ', '.join(patterns))
print('[Directory To Check] :' + path)
if not os.path.exists(path):
raise Exception("Selected path does not exist: " + path)
# Walk through directory structure looking for files matching patterns
matchingFileList = [os.path.join(dp, f) for dp, dn, filenames in os.walk(path) for f in filenames if os.path.splitext(f)[1] in patterns]
print('Files found matching patterns: ' + str(len(matchingFileList)))
filecount = 0
filesReplaced = 0
for currFile in matchingFileList:
filecount += 1
filesReplaced = search_replace_string(currFile, old_str, new_str)
if filesReplaced:
filesReplaced += 1
print("Total Files Searched :" + str(filecount))
print("Total Files Replaced/Updated :" + str(filesReplaced))
except Exception as err:
print(traceback.format_exception_only(type(err), err)[0].rstrip())
sys.exit(-1)
if __name__ == '__main__':
main()
When I am executing it from a command line I am getting below error:
(null): can't open file 'uro.py': [Errno 2] No such file or directory
Below is the command line argument I am giving
python uro.py <file_path> <old_str> <new_str>
NOTE: I am using xml file.
I wanted to develop a logic that will take file_name, old and new string as a command line argument. In the error one can see that the program is considering the python file a input file. While it should take the path of the file that I give with CMD argument.
What's the mistake here? Please suggest. Thank you

I got it fixed, there was some path issue. Thank you.

How to zip a folder in python with password?

With pyminizip i am able to zip a file with password in python :
filepath=r"C:\Users\xxx\Desktop\myFolder\file.txt"
import pyminizip
pyminizip.compress(filepath, None,"output.zip", "password", 0)
But how do I zip the whole folder 'myFolder' into a zip file with password?
I tried removing the filename from the path but it gives the error
OSError: error in opening C:\Users\xxx\Desktop\myFolder for reading
EDIT :
The below link has a function which will zip the directory. But It wont add a password.
https://www.calazan.com/how-to-zip-an-entire-directory-with-python/
If anyone can let me know if it is possible to add a password to an existing zip file, that will solve my problem. Is that possible?

I was finally able to accomplish encryping the whole directory(including all subfolder struncture and files) using a library called 'pyzipper' suggested by Anupam Chaplot.
Here is the solution :
def zip_folderPyzipper(folder_path, output_path):
"""Zip the contents of an entire folder (with that folder included
in the archive). Empty subfolders will be included in the archive
as well.
"""
parent_folder = os.path.dirname(folder_path)
# Retrieve the paths of the folder contents.
contents = os.walk(folder_path)
try:
zip_file = pyzipper.AESZipFile('new_test.zip','w',compression=pyzipper.ZIP_DEFLATED,encryption=pyzipper.WZ_AES)
zip_file.pwd=b'PASSWORD'
for root, folders, files in contents:
# Include all subfolders, including empty ones.
for folder_name in folders:
absolute_path = os.path.join(root, folder_name)
relative_path = absolute_path.replace(parent_folder + '\\',
'')
print ("Adding '%s' to archive." % absolute_path)
zip_file.write(absolute_path, relative_path)
for file_name in files:
absolute_path = os.path.join(root, file_name)
relative_path = absolute_path.replace(parent_folder + '\\',
'')
print ("Adding '%s' to archive." % absolute_path)
zip_file.write(absolute_path, relative_path)
print ("'%s' created successfully." % output_path)
except IOError as message:
print (message)
sys.exit(1)
except OSError as message:
print(message)
sys.exit(1)
except zipfile.BadZipfile as message:
print (message)
sys.exit(1)
finally:
zip_file.close()
Since I am new in python i cant explain the code in detail. Here are the references :
https://pypi.org/project/pyzipper/
https://www.calazan.com/how-to-zip-an-entire-directory-with-python/
To extract the Generated ZIP file in windows :
Right Click - > Unzip(Encripted)
If you directly click Extract All option, then it will give error

Try this:
Firstly check here please for pynzip. After that try it.
import pyminizip as pyzip
compression = 8
pyzip.compress("test.txt", "test.zip", "Pswrd", compression)

Here is how to copy all a directory with its subdirectories and its files, then compress it and encrypt a zip, with password and without needing an associated backup file, here we will see how to authorize a mac address to execute the decryption. So then it's up to you to change or improve the script.
But the essentials work very well.
After a lot of research, testing and thinking, I created this effective solution
my setup:
Python 3.8 64:bits on windows 7 64:bits
Usage terminology:
First step, we need to import the cryptography module
check for support or other is here https://cryptography.io/en/latest/installation/
command:
pip install cryptography
Then we will use the fernet object resulting from this module
https://cryptography.io/en/latest/fernet/
with password
https://cryptography.io/en/latest/fernet/#using-passwords-with-fernet
and shutil:
https://docs.python.org/3/library/shutil.html
file second.py:
import os
import re, uuid
import string
import shutil
import zlib
from cryptography.fernet import Fernet
from cryptography.hazmat.primitives import hashes
from cryptography.hazmat.primitives.kdf.pbkdf2 import PBKDF2HMAC
import base64
import zipfile
class zipy:
def __init__(self, pathDir=None):
"""If pathDir optional is none, this script copy all directory in current execution."""
if pathDir != None:
if os.path.isdir(pathDir):
pathDir = pathDir.replace(os.sep, '/')
if pathDir.endswith('/'):
self.root = pathDir
else:
self.root = pathDir + '/'
else:
self.root = os.getcwd()+os.sep
self.root = self.root.replace(os.sep, '/')
else:
self.root = os.getcwd()+os.sep
self.root = self.root.replace(os.sep, '/')
os.chdir(self.root)
self.name = 'sauvegarde'
self.dirSauvegarde = self.root+self.name
self.dirSauvegarde = self.dirSauvegarde.replace(os.sep, '/')
lectureDossier = os.listdir(self.root)
print(lectureDossier)
self.path_system = {}
for element in lectureDossier:
if os.path.isdir(element):
if element != '__pycache__':
self.path_system[element] = self.root + element + os.sep.replace(os.sep, '/')
self.path_system[element] = self.path_system[element].replace(os.sep, '/')
else:
pass
elif os.path.isfile(element):
self.path_system[element] = self.root + element
self.path_system[element] = self.path_system[element].replace(os.sep, '/')
else:
pass
self.zipi = myZip(self.dirSauvegarde)
def save(self):
"""sauvegarde le fichier"""
self.createDir(self.dirSauvegarde)
chemin_src = ""
chemin_dist = ""
for element in self.path_system:
if element != self.dirSauvegarde:
chemin_src = self.root+element
chemin_dest = self.dirSauvegarde + os.sep + element
chemin_dest = chemin_dest.replace(os.sep, '/')
if os.path.isdir(chemin_src):
self.copyDir(chemin_src, chemin_dest)
else:
self.copyFile(chemin_src, chemin_dest)
self.zipi.zip(zip_exist=True)
self.delDir(self.dirSauvegarde)
def copyDir(self, src, dest):
try:
shutil.copytree(src, dest, dirs_exist_ok=True)
except:
pass
def copyFile(self, src, dest):
try:
shutil.copyfile(src, dest)
except:
pass
def createDir(self, dirPath):
if os.path.isdir(dirPath):
self.delDir(dirPath)
else:
pass
os.makedirs(dirPath, exist_ok=True)
def delDir(self, dir):
if os.path.isdir(dir):
if len(os.listdir(dir)) > 0:
try:
print('rmtree')
shutil.rmtree(dir, ignore_errors=True)
except:
pass
else:
try:
os.rmdir(dir)
except:
pass
def decrypt(self):
self.zipi.unzip()
class myZip:
def __init__(self, dir):
self.pathDir = dir
self.nom = os.path.basename(dir)
self.pathZip = self.pathDir + '.zip'
self.crypt = Encryptor()
def zip(self, zip_exist=False):
if zip_exist == False:
pass
else:
if os.path.isfile(self.pathZip):
try:
os.remove(self.pathZip)
except:
pass
shutil.make_archive(os.path.splitext(self.pathZip)[0], 'zip', self.pathDir)
key = self.crypt.key_create()
#TEST
self.crypt.file_encrypt(key, self.pathZip, self.pathZip)
self.crypt.key_write(self.pathZip, key)
def unzip(self):
#TEST
if self.crypt.checkPass(self.pathZip):
#print('ok adresse mac autoriser')
key = self.crypt.key_load(self.pathZip)
self.crypt.file_decrypt(key, self.pathZip, self.pathZip)
else:
print('pas ok adresse mac erroner')
class Encryptor:
def __init__(self):
self.salto = None
def key_create(self):
password = self.getMac()
password = bytes(password, encoding="utf-8")
self.salto = os.urandom(16)
print(self.salto)
kdf = PBKDF2HMAC(
algorithm=hashes.SHA256(),
length=32,
salt=self.salto,
iterations=100,
)
key = base64.urlsafe_b64encode(kdf.derive(password))
return key
def key_write(self, pathZip, key):
with zipfile.ZipFile(pathZip, 'a') as zip:
zip.comment = key + bytes(' byMe ', encoding="utf-8") + self.salto
def key_load(self, pathZip):
stri = []
with zipfile.ZipFile(pathZip, 'a') as zip:
stri = zip.comment.split(b' byMe ')
print(stri[0])
print(stri[1])
key = stri[0]
self.salto = stri[1]
return key
def checkPass(self, pathZip):
key = base64.urlsafe_b64decode(self.key_load(pathZip))
salt = self.salto
mdp = self.getMac()
mdp = bytes(mdp, encoding="utf-8")
kdf = PBKDF2HMAC(
algorithm=hashes.SHA256(),
length=32,
salt=salt,
iterations=100,
)
retour = False
try:
kdf.verify(mdp, key)
retour = True
except:
retour = False
return retour
def file_encrypt(self, key, original_file, encrypted_file):
f = Fernet(key)
with open(original_file, 'rb') as file:
original = file.read()
encrypted = f.encrypt(original)
with open (encrypted_file, 'wb') as file:
file.write(encrypted)
def file_decrypt(self, key, encrypted_file, decrypted_file):
f = Fernet(key)
with open(encrypted_file, 'rb') as file:
encrypted = file.read()
decrypted = f.decrypt(encrypted)
with open(decrypted_file, 'wb') as file:
file.write(decrypted)
def getMac(self):
return "".join(re.findall('..', '%012x' % uuid.getnode()))
Use like this:
file : main.py
from second import zipy
#If the argument is empty, the script will make a copy of the directory being executed, otherwise the script will work and output the zip in the place indicated in argument
dd = zipy("E:/path")
#or dd = zipy("E:/path/") or dd = zipy() if you give arg, give absolute path
#Save the zip and encrypt it. Change second.py to directly give it a password as an argument
dd.save()
#decrypt zip
dd.decrypt()

Here's a snippet with pyminizip: gets a list of files and zips the whole thing.
import pyminizip
import os
def get_paths_recursively(src_root_path):
files = []
if src_root_path is not None:
for root, directories, filenames in os.walk(src_root_path):
entries = []
for filename in filenames:
full_file_name = os.path.join(root, filename)
if os.path.isfile(full_file_name) and not filename.startswith('.'):
files.append(os.path.join(root, filename))
return files
def pyminizip_zipper(folder_path, output_path, password):
paths = get_paths_recursively(folder_path)
roots = []
for path in paths:
roots.append(os.path.dirname(path.replace(os.path.dirname(folder_path), './')))
pyminizip.compress_multiple(paths, roots, output_path, password, 5)

How to skip unhashable (corrupt) files while md5 fingerprinting?

The code below makes an md5/metadata fingerprint, but crashes on files with unknown corruption (e.g., files, that can be copied, mostly even opened, but that can not be hashed or zipped up [to disguise their corruption]).
Question: How one makes this code to skip or ignore any and all problem files and just do the rest? Imagine 1 million files on 8 TB. Otherwise I leave it running and having no real-time monitoring of progress, 2 days later I find out that nothing got hashed because a couple problem files made the code hung.
Part of the code (see full code below):
def createBasicInfoListFromDisk():
global diskCompareListDetails, onlyFileNameOnDisk, driveLetter,walk_dir
walk_dir = os.path.abspath(walk_dir)
for root, subdirs, files in os.walk(walk_dir, topdown=True, onerror=None, followlinks=True ):
for filename in files:
file_path = os.path.join(root, filename)
temp = file_path.split(":")
driveLetter = temp[0]
filePathWithoutDriveLetter = temp[1]
fileSize = os.path.getsize(file_path)
mod_on = get_last_write_time(file_path)
print('\t- file %s (full path: %s)' % (filename, file_path))
print('FileName : {filename} is of size {size} and was modified on{mdt}'.format(filename=file_path,size=fileSize,mdt=mod_on ))
diskCompareListDetails.append("\"" + filePathWithoutDriveLetter+"\",\""+str(fileSize) + "\",\"" + mod_on +'"')
onlyFileNameOnDisk.append("\""+filePathWithoutDriveLetter+"\"")
return
Error:
FileName : T:\problemtest\problemfile.doc is of size 27136 and was modified on2010-10-10 13:58:32
Traceback (most recent call last):
File "t:\scripts\test.py", line 196, in <module>
createBasicInfoListFromDisk()
File "t:\scripts\test.py", line 76, in createBasicInfoListFromDisk
mod_on = get_last_write_time(file_path)
File "t:\scripts\test.py", line 61, in get_last_write_time
convert_time_to_human_readable = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(st.st_mtime))
OSError: [Errno 22] Invalid argument
Full code:
import os
import sys
import time
import datetime
import difflib
import decimal
import hashlib
from pip._vendor.distlib.compat import raw_input
csvListDetails = list()
csvCompareListDetails = list()
diskCompareListDetails = list()
onlyFileNameOnDisk = list()
addedFiles = list()
removedFiles = list()
driveLetter =""
finalFilesToChange=list()
finalFilesToDelete=list()
changedFiles=list()
csvfilewithPath="md5.csv"
import shutil
walk_dir=""
def findAndReadCSVFile(fileName):
global csvListDetails
global csvCompareListDetails
haveIgnoredLine = 0
foundFile=0
try :
inputFileHandler = open(fileName,"rt",encoding='utf-8')
update_time = get_last_write_time(fileName)
print("\n Found md5.csv, last updated on: %s" % update_time)
foundFile=1
except (OSError, IOError, FileNotFoundError):
print("\n md5.csv not found. Will create a new one.")
return foundFile
for line in inputFileHandler:
if (haveIgnoredLine==0):
haveIgnoredLine=1
continue
rowItem = line.replace("\n","").split('","')
csvCompareListDetails.append('"' + rowItem[3]+',"'+rowItem[2]+'","' +rowItem[1]+'"')
lineDetails = list()
for detailNum in range (0,len(rowItem)):
lineDetails.append('"' + (rowItem[detailNum].replace('"','')) + '"')
csvListDetails.append(lineDetails)
inputFileHandler.close()
return foundFile
def get_last_write_time(filename):
st = os.stat(filename)
convert_time_to_human_readable = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(st.st_mtime))
return convert_time_to_human_readable
def createBasicInfoListFromDisk():
global diskCompareListDetails, onlyFileNameOnDisk, driveLetter,walk_dir
walk_dir = os.path.abspath(walk_dir)
for root, subdirs, files in os.walk(walk_dir, topdown=True, onerror=None, followlinks=True ):
for filename in files:
file_path = os.path.join(root, filename)
temp = file_path.split(":")
driveLetter = temp[0]
filePathWithoutDriveLetter = temp[1]
fileSize = os.path.getsize(file_path)
mod_on = get_last_write_time(file_path)
print('\t- file %s (full path: %s)' % (filename, file_path))
print('FileName : {filename} is of size {size} and was modified on{mdt}'.format(filename=file_path,size=fileSize,mdt=mod_on ))
diskCompareListDetails.append("\"" + filePathWithoutDriveLetter+"\",\""+str(fileSize) + "\",\"" + mod_on +'"')
onlyFileNameOnDisk.append("\""+filePathWithoutDriveLetter+"\"")
return
def compareLogAndDiskLists():
global addedFiles, removedFiles
diff = difflib.unified_diff(csvCompareListDetails, diskCompareListDetails, fromfile='file1', tofile='file2', lineterm='', n=0)
lines = list(diff)[2:]
addedFiles = [line[1:] for line in lines if line[0] == '+']
removedFiles = [line[1:] for line in lines if line[0] == '-']
return
def displayInfoForUserInput():
global finalFilesToChange, finalFilesToDelete
changedOrNewFileCount = 0
noLongerExistingFilesCount = 0
totalSizeOfChange = 0
for line in addedFiles:
if line not in removedFiles:
changedOrNewFileCount = changedOrNewFileCount +1
elements = line.replace("\n","").split('","')
sizeOfFile= int(elements[1].replace('"',''))
totalSizeOfChange = totalSizeOfChange + sizeOfFile
finalFilesToChange.append(elements[0] +'"')
for line in removedFiles:
elements = line.split('","')
if elements[0]+'"' not in onlyFileNameOnDisk:
noLongerExistingFilesCount = noLongerExistingFilesCount + 1
finalFilesToDelete.append(elements[0]+'"')
GBModSz= decimal.Decimal(totalSizeOfChange) / decimal.Decimal('1073741824')
print("\n New or modified files on drive: {} (need to hash)".format(changedOrNewFileCount))
print (" Obsolete lines in md5.csv (files modified or not on drive): {} (lines to delete)".format(noLongerExistingFilesCount))
print (" {} files ({:.2f} GB) needs to be hashed.".format(changedOrNewFileCount,GBModSz))
userInput = raw_input("\n Proceed with hash? (Y/N, Yes/No) ")
if (userInput.strip().upper() == "Y" or userInput.strip().upper() == "YES"):
print("Continuing Processing...")
else:
print("You opted not to continue, Exiting")
sys.exit()
return
def processFiles(foundFile):
if (foundFile==1):
oldFileName = walk_dir+"/md5.csv"
shutil.copy( oldFileName, getTargetFileName(oldFileName))
BLOCKSIZE = 1048576*4
global changedFiles
for fileToHash in finalFilesToChange:
hasher = hashlib.new('md5')
fileToUse=driveLetter+":"+fileToHash.replace('"','')
with open(fileToUse, 'rb') as afile:
buf = afile.read(BLOCKSIZE)
while len(buf) > 0:
hasher.update(buf)
buf = afile.read(BLOCKSIZE)
fileDetails = list()
fileDetails.append(hasher.hexdigest())
fileDetails.append(get_last_write_time(fileToUse))
fileDetails.append(os.path.getsize(fileToUse))
fileDetails.append(fileToHash)
changedFiles.append(fileDetails)
return
def getTargetFileName(oldFileName):
targetFileName= walk_dir+"/generated_on_" + get_last_write_time(oldFileName).replace(" ","_").replace("-","").replace(":","")
targetFileName = targetFileName + "__archived_on_" + datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
targetFileName = targetFileName + "__md5.csv"
return targetFileName
def writeCSVFile(fileName):
try :
outputFileHandler=open(fileName,"wt",encoding='utf-8')
outputFileHandler.write("\"md5Hash\",\"LastWriteTime\",\"Length\",\"FullName\"\n")
for details in csvListDetails:
if details[3] in finalFilesToDelete:
continue
if details[3] in finalFilesToChange:
continue
outputFileHandler.write("{},{},{},{}\n".format(details[0],details[1],details[2],details[3]))
for details in changedFiles:
outputFileHandler.write("\"{}\",\"{}\",\"{}\",{}\n".format(details[0],details[1],details[2],details[3]))
outputFileHandler.close()
except (OSError, IOError, FileNotFoundError) as e:
print("ERROR :")
print("File {} is either not writable or some other error: {}".format(fileName,e))
return
if __name__ == '__main__':
walk_dir = raw_input("\n Enter drive or directory to scan: ")
csvfilewithPath=walk_dir+"/md5.csv"
print("\n Drive to scan: " + walk_dir)
foundFile = 0
foundFile=findAndReadCSVFile(csvfilewithPath)
createBasicInfoListFromDisk()
compareLogAndDiskLists()
displayInfoForUserInput()
processFiles(foundFile)
writeCSVFile(csvfilewithPath)
Trying this fix, no luck:
def get_last_write_time(filename):
try:
st = os.stat(filename)
convert_time_to_human_readable = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(st.st_mtime))
return convert_time_to_human_readable
except OSError:
pass
return "ERROR"
def createBasicInfoListFromDisk():

I agree with IMCoins and I'm very qurius on why except isn't catching the error.
So first thing I would do is to go to the source where the OSError is being raised and try to catch it explicity.
def get_last_write_time(filename):
try:
st = os.stat(filename)
convert_time_to_human_readable = time.strftime("%Y-%m-%d %H:%M:%S",
time.localtime(st.st_mtime)
return convert_time_to_human_readable
except OSError:
pass
return "ERROR" #or whatever string you want add

Updated answer, for updated post.
As stated earlier, except statement with exception type specified catches everything. So, in order to do what want... I'm afraid possible answer are either :
To make a method that identifies corrupted files, and handles it properly.
Make try, except statement that encapsulate every part of your code where there could be an error.
Let me warn you about the second solution though, as sometimes, there are system errors that you do not want to avoid. I believe you should print the exception that you catch, in order to identify further problems you may encounter.
Just so you know, as you may not : your error is not in a try, except statement. Your error is in (if I copied and pasted properly in my editor) line 196, createBasicinfoListFromDisk(), then line 76, mod_on = get_last_write_time(file_path)
As you also mentioned you are using python 3.x, I suggest you are looking into the suppress function (https://docs.python.org/3/library/contextlib.html#contextlib.suppress).
I hope it helped you.

How to unzip a file with Python 2.4?

I'm having a hard time figuring out how to unzip a zip file with 2.4. extract() is not included in 2.4. I'm restricted to using 2.4.4 on my server.
Can someone please provide a simple code example?

You have to use namelist() and extract(). Sample considering directories
import zipfile
import os.path
import os
zfile = zipfile.ZipFile("test.zip")
for name in zfile.namelist():
(dirname, filename) = os.path.split(name)
print "Decompressing " + filename + " on " + dirname
if not os.path.exists(dirname):
os.makedirs(dirname)
zfile.extract(name, dirname)

There's some problem with Vinko's answer (at least when I run it). I got:
IOError: [Errno 13] Permission denied: '01org-webapps-countingbeads-422c4e1/'
Here's how to solve it:
# unzip a file
def unzip(path):
zfile = zipfile.ZipFile(path)
for name in zfile.namelist():
(dirname, filename) = os.path.split(name)
if filename == '':
# directory
if not os.path.exists(dirname):
os.mkdir(dirname)
else:
# file
fd = open(name, 'w')
fd.write(zfile.read(name))
fd.close()
zfile.close()

Modifying Ovilia's answer so that you can specify the destination directory as well:
def unzip(zipFilePath, destDir):
zfile = zipfile.ZipFile(zipFilePath)
for name in zfile.namelist():
(dirName, fileName) = os.path.split(name)
if fileName == '':
# directory
newDir = destDir + '/' + dirName
if not os.path.exists(newDir):
os.mkdir(newDir)
else:
# file
fd = open(destDir + '/' + name, 'wb')
fd.write(zfile.read(name))
fd.close()
zfile.close()

Not fully tested, but it should be okay:
import os
from zipfile import ZipFile, ZipInfo
class ZipCompat(ZipFile):
def __init__(self, *args, **kwargs):
ZipFile.__init__(self, *args, **kwargs)
def extract(self, member, path=None, pwd=None):
if not isinstance(member, ZipInfo):
member = self.getinfo(member)
if path is None:
path = os.getcwd()
return self._extract_member(member, path)
def extractall(self, path=None, members=None, pwd=None):
if members is None:
members = self.namelist()
for zipinfo in members:
self.extract(zipinfo, path)
def _extract_member(self, member, targetpath):
if (targetpath[-1:] in (os.path.sep, os.path.altsep)
and len(os.path.splitdrive(targetpath)[1]) > 1):
targetpath = targetpath[:-1]
if member.filename[0] == '/':
targetpath = os.path.join(targetpath, member.filename[1:])
else:
targetpath = os.path.join(targetpath, member.filename)
targetpath = os.path.normpath(targetpath)
upperdirs = os.path.dirname(targetpath)
if upperdirs and not os.path.exists(upperdirs):
os.makedirs(upperdirs)
if member.filename[-1] == '/':
if not os.path.isdir(targetpath):
os.mkdir(targetpath)
return targetpath
target = file(targetpath, "wb")
try:
target.write(self.read(member.filename))
finally:
target.close()
return targetpath

I am testing in Python 2.7.3rc2 and the the ZipFile.namelist() is not returning an entry with just the sub directory name for creating a sub directory, but only a list of file names with sub directory, as follows:
['20130923104558/control.json', '20130923104558/test.csv']
Thus the check
if fileName == '':
does not evaluate to True at all.
So I modified the code to check if the dirName exists inside destDir and to create dirName if it does not exist. File is extracted only if fileName part is not empty. So this should take care of the condition where a directory name can appear in ZipFile.namelist()
def unzip(zipFilePath, destDir):
zfile = zipfile.ZipFile(zipFilePath)
for name in zfile.namelist():
(dirName, fileName) = os.path.split(name)
# Check if the directory exisits
newDir = destDir + '/' + dirName
if not os.path.exists(newDir):
os.mkdir(newDir)
if not fileName == '':
# file
fd = open(destDir + '/' + name, 'wb')
fd.write(zfile.read(name))
fd.close()
zfile.close()