I am writing a Python script in Windows. I'm processed Zip File from the folder if the file is completed copied and start the program it is working fine, but I encounter with Problem when the program is running and start Copy file in the folder. It's giving error and closed.
How can I process only which files have been copied completely?
Or check if the file size is increasing it does not process in 30 seconds interval if file size does not increase then it processed?
My code:
import zipfile
import os
import xml.etree.ElementTree as ET
import shutil
import configparser
import time
#function used to read zip and xml
def read_zipfile(file):
with zipfile.ZipFile(file,'r') as zf:
for name in zf.namelist():
if name.endswith('.xml'):
#open Zip and read Xml
xml_content=zf.open(name)
# here you do your magic with [f] : parsing, etc
return xml_content
#Function use to parsing XML file
def XMl_Parsa(f):
tree=ET.parse(f)
root=tree.getroot()
# attribute are iterated attribute to get value of tag;
for node in tree.iter('attribute'):
if(node.attrib['name']=='ProductNameCont'):
zone = str(node.text)
return zone
#fucnction used to move file
def move_zipFile(zone,out_put,in_xml,file):
#defing destination path
Product_zone=(os.path.join(out_put,zone))
print(Product_zone)
#Moveing fine for base folder to Product folder
try:
os.makedirs(Product_zone,exist_ok=True)
print("Directory '%s' created successfully" % zone)
except OSError as error:
print("Directory '%s' Exist " % error)
try:
#unziping zip file
shutil.unpack_archive(os.path.join(in_xml, file),os.path.join(Product_zone,os.path.splitext(file)[0]))
os.remove(os.path.join(in_xml, file))
print("File '%s' moved to successfully" % file)
except OSError as error:
print("File '%s' Exist " % error)
#Function use for read Config File
def config_read():
config = configparser.ConfigParser()
config.read('./Config.ini')
xml_path = config.get('Path', 'xml_path')
dest = config.get('Path', 'dest')
return xml_path,dest
def main():
in_xml=config_read()[0]
out_put=config_read()[1]
for file in os.listdir(in_xml):
move_zipFile(XMl_Parsa(read_zipfile(os.path.join(in_xml, file))),out_put,in_xml,file)
if __name__=="__main__":
while 1:
time.sleep(10)
main()
Error
Traceback (most recent call last):
File "Clero_zipFile_transfer - Copy.py", line 65, in <module>
File "Clero_zipFile_transfer - Copy.py", line 60, in main
File "Clero_zipFile_transfer - Copy.py", line 9, in read_zipfile
File "zipfile.py", line 1268, in __init__
File "zipfile.py", line 1335, in _RealGetContents
zipfile.BadZipFile: File is not a zip file
[2916] Failed to execute script Clero_zipFile_transfer - Copy
Related
I would like to decompress a bunch of .bz2 files contained in a folder (where there are also .zst files). What I am doing is the following:
destination_folder = "/destination_folder_path/"
compressed_files_path="/compressedfiles_folder_path/"
dirListing = os.listdir(compressed_files_path)
for file in dirListing:
if ".bz2" in file:
unpackedfile = bz2.BZ2File(file)
data = unpackedfile.read()
open(destination_folder, 'wb').write(data)
But I keep on getting the following error message:
Traceback (most recent call last):
File "mycode.py", line 34, in <module>
unpackedfile = bz2.BZ2File(file)
File ".../miniconda3/lib/python3.9/bz2.py", line 85, in __init__
self._fp = _builtin_open(filename, mode)
FileNotFoundError: [Errno 2] No such file or directory: 'filename.bz2'
Why do I receive this error?
You must be sure that all the file paths you are using exist.
It is better to use the full path to the file being opened.
import os
import bz2
# this path must exist
destination_folder = "/full_path_to/folder/"
compressed_files_path = "/full_path_to_other/folder/"
# get list with filenames (strings)
dirListing = os.listdir(compressed_files_path)
for file in dirListing:
# ^ this is only filename.ext
if ".bz2" in file:
# concatenation of directory path and filename.bz2
existing_file_path = os.path.join(compressed_files_path, file)
# read the file as you want
unpackedfile = bz2.BZ2File(existing_file_path)
data = unpackedfile.read()
new_file_path = os.path.join(destination_folder, file)
with bz2.open(new_file_path, 'wb') as f:
f.write(data)
You can also use the shutil module to copy or move files.
os.path.exists
os.path.join
shutil
bz2 examples
I have created the basic script below that scans a directory for wav files and copies them into a nested directory based on file attributes.
"""
Script that copies data from Peersonic RPA3 into directory
using file name, date and time
"""
import datetime as dt
import os
import shutil
import time
from pathlib import Path
# Function to check if survey is dusk or dawn
def duskdawn(file):
filetime = dt.datetime.fromtimestamp(os.path.getmtime(file))
if file_time.time() > dt.time(12):
return "Dusk"
else:
return "Dawn"
def file_date(file):
return time.strftime('%d.%m.%Y', time.localtime(os.path.getmtime(file)))
def client(file):
return file.name[0:3]
client_lst = ['IES', 'DEC', 'TEP']
# Directory of files
path = "/Volumes/BATrecorder/WAVFILES.DIR"
for entry in os.scandir(path):
source = entry.path
perm = os.stat(entry).st_mode
client_name = (client(entry))
if entry.name.endswith(".WAV"):
if client_name in client_lst:
client_name = client_name
else:
client_name = "unknown"
destination = f"/Volumes/Seagate Exp/Work 2020/Bat recordings/{client_name}/{file_date(entry)}/{duskdawn(entry)}"
Path(destination).mkdir(parents=True, exist_ok=True)
shutil.copy2(source, destination)
Initially I used the standard shutil.copy() function and this worked fine. However, I need to keep the original file metadata so need to use shutil.copy2() instead. When I use this one I get the following error:
Traceback (most recent call last):
File "/Volumes/Seagate Exp/Work 2020/file_copy.py", line 43, in <module>
shutil.copy2(source, destination)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/shutil.py", line 258, in copy2
copystat(src, dst, follow_symlinks=follow_symlinks)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/shutil.py", line 218, in copystat
lookup("chflags")(dst, st.st_flags, follow_symlinks=follow)
PermissionError: [Errno 1] Operation not permitted: '/Volumes/Seagate Exp/Work 2020/Bat recordings/unknown/31.12.2014/Dusk/#AAA_000.WAV'
What is going on here that causes this issue?
In conjunction with my last question, I'm onto printing the filenames with their sizes next to them in a sort of list. Basically I am reading filenames from one file (which are added by the user), taking the filename and putting it in the path of the working directory to print it's size one-by-one, however I'm having an issue with the following block:
print("\n--- Stats ---\n")
with open('userdata/addedfiles', 'r') as read_files:
file_lines = read_files.readlines()
# get path for each file and find in trackedfiles
# use path to get size
print(len(file_lines), "files\n")
for file_name in file_lines:
# the actual files should be in the same working directory
cwd = os.getcwd()
fpath = os.path.join(cwd, file_name)
fsize = os.path.getsize(fpath)
print(file_name.strip(), "-- size:", fsize)
which is returning this error:
tolbiac wpm-public → ./main.py --filestatus
--- Stats ---
1 files
Traceback (most recent call last):
File "./main.py", line 332, in <module>
main()
File "./main.py", line 323, in main
parseargs()
File "./main.py", line 317, in parseargs
tracking()
File "./main.py", line 204, in tracking
fsize = os.path.getsize(fpath)
File "/usr/lib/python3.4/genericpath.py", line 50, in getsize
return os.stat(filename).st_size
FileNotFoundError: [Errno 2] No such file or directory: '/home/tolbiac/code/wpm-public/file.txt\n'
tolbiac wpm-public →
So it looks like something is adding a \n to the end of file_name, I'm not sure if thats something used in the getsize module, I tried this with os.stat, but it did the same thing.
Any suggestions? Thanks.
When you're reading in a file, you need to be aware of how the data is being seperated. In this case, the read-in file has a filename once per line seperated out by that \n operator. Need to strip it then before you use it.
for file_name in file_lines:
file_name = file_name.strip()
# rest of for loop
I have a compressed .zip file that i want to convert to an uncompressed .tar file.
I made this function to do it:
def decompress(filepath):
devname = re.search("_(.+?)_.+?\.zip", filepath).group(1)
with zipfile.ZipFile(filepath, 'r') as zip:
path = os.path.join(start_dir, "Downloads", devname, str(os.path.basename(filepath))[:-4])
zip.extractall(path)
with tarfile.open(path + ".tar", 'w') as tar:
for object in os.listdir(path):
tar.add(os.path.join(path, object), arcname=object)
time.sleep(2)
shutil.rmtree(path, ignore_errors=False, onerror=onError)
time.sleep(0.5)
os.remove(filepath)
return path + ".tar"
I am getting this error when running it:
Traceback (most recent call last):
File "File.py", line 195, in <module>
main()
File "File.py", line 184, in main
dld = download()
File "File.py", line 132, in download
filename = decompress(os.path.join(start_dir, "Downloads", devname, filename
))
File "File.py", line 103, in decompress
shutil.rmtree(path, ignore_errors=False, onerror=onError)
File "C:\Program Files (x86)\python27\lib\shutil.py", line 247, in rmtree
rmtree(fullname, ignore_errors, onerror)
File "C:\Program Files (x86)\python27\lib\shutil.py", line 247, in rmtree
rmtree(fullname, ignore_errors, onerror)
File "C:\Program Files (x86)\python27\lib\shutil.py", line 256, in rmtree
onerror(os.rmdir, path, sys.exc_info())
File "C:\Program Files (x86)\python27\lib\shutil.py", line 254, in rmtree
os.rmdir(path)
WindowsError: [Error 145] The directory is not empty: 'C:\\Users\\Vaibhav\\Deskt
op\\Folder\\Downloads\\toro\\_toro_nightly_test\\system\\app'
Here is my onError that I got from https://stackoverflow.com/a/2656405/2518263:
def onError(func, path, exc_info):
"""
Error handler for ``shutil.rmtree``.
If the error is due to an access error (read only file)
it attempts to add write permission and then retries.
If the error is for another reason it re-raises the error.
Usage : ``shutil.rmtree(path, onerror=onerror)``
"""
if not os.access(path, os.W_OK):
# Is the error an access error ?
os.chmod(path, stat.S_IWUSR)
func(path)
else:
raise
I only get the error on random occasions. The decompress function works 75% of the time.
I don't know why I'm getting this error. Can someone suggest a better way to do this or a way to solve this error.
I just replaced:
shutil.rmtree(path, ignore_errors=False, onerror=onError)
with:
for root, dirs, files in os.walk(path, topdown=False):
for name in files:
filename = os.path.join(root, name)
os.chmod(filename, stat.S_IWUSR)
os.remove(filename)
for name in dirs:
os.rmdir(os.path.join(root, name))
time.sleep(0.5)
os.rmdir(path)
Now it works like a charm.
EDIT:
Never mind! I still get the error but just less often, now its about 20% of the time!! Please help!
EDIT 2:
OK, so I don't get the error if i extract to a temporary file so I am using this code:
import tempfile
def decompress(filepath):
with zipfile.ZipFile(filepath) as zip:
tmp = tempfile.mkdtemp(dir=os.getcwd())
zip.extractall(tmp)
with tarfile.open(filepath[:-4] + ".tar", 'w') as tar:
for object in os.listdir(tmp):
tar.add(os.path.join(tmp, object), arcname=object)
time.sleep(1)
shutil.rmtree(tmp)
os.remove(filepath)
return filepath[:-4] + ".tar"
I works now! (hopefully the error won't occur again)
EDIT 3:
I got the error again!!!!!!!!!! this is really getting on my nerves. Please help someone.
Looks like some process in your OS manages to create another file in the directory you are in process of deletion of.
I can suggest you to avoid creation of temporary files and feed decompressed parts of original ZIP directly into new TAR file.
This require matching ZipInfo fields to TarInfo ones but it should be straightforward.
Here's my take on it:
def zip2tar(zipname, tarname):
zipf = zipfile.ZipFile(zipname, 'r')
tarf = tarfile.TarFile(tarname, 'w')
timeshift = int((datetime.datetime.now() -
datetime.datetime.utcnow()).total_seconds())
for zipinfo in zipf.infolist():
tarinfo = tarfile.TarInfo()
tarinfo.name = zipinfo.filename
tarinfo.size = zipinfo.file_size
tarinfo.mtime = calendar.timegm(zipinfo.date_time) - timeshift
if zipinfo.internal_attr & 1:
tarinfo.mode = 0666
tarinfo.type = tarfile.REGTYPE
else:
tarinfo.mode = 0777
tarinfo.type = tarfile.DIRTYPE
infile = zipf.open(zipinfo.filename)
tarf.addfile(tarinfo, infile)
zipf.close()
tarf.close()
I'm writing a python script to reformat the names of the files in my music folder, using the mutagen library. Here's the script:
from mutagen.easyid3 import EasyID3
import os
print "input directory for processing: "
path = raw_input()
os.chdir(path)
file_list = filter((lambda x: '.mp3' in x), os.listdir(path))
for i in file_list:
current = EasyID3(i)
newname = current["title"][0] + ".mp3"
newname.replace(" ", "_")
del current
print "renaming "+i+" to "+newname
os.rename(i, newname)
Here's what happens when I try to run it:
$ python rename_music.py
input directory for processing:
/home/james/Music/inscrutable_numbers
Traceback (most recent call last):
File "rename_music.py", line 11, in <module>
current = EasyID3(i)
File "/usr/local/lib/python2.7/dist-packages/mutagen/easyid3.py", line 167, in __init__
self.load(filename)
File "/usr/local/lib/python2.7/dist-packages/mutagen/id3.py", line 139, in load
for frame in self.__read_frames(data, frames=frames):
File "/usr/local/lib/python2.7/dist-packages/mutagen/id3.py", line 317, in __read_frames
try: yield self.__load_framedata(tag, flags, framedata)
File "/usr/local/lib/python2.7/dist-packages/mutagen/id3.py", line 340, in __load_framedata
return tag.fromData(self, flags, framedata)
File "/usr/local/lib/python2.7/dist-packages/mutagen/id3.py", line 1085, in fromData
raise ID3BadUnsynchData, '%s: %r' % (err, data)
mutagen.id3.ID3BadUnsynchData: invalid sync-safe string: '\x00j\x01\x0c\x00\x12(...lots of unicode...)\x12\xff\xff\xff\x00'
Does anyone know what the problem is here?
EDIT: turns out mutagen doesn't work with certain files. I added a try clause and skipped errors, it works now