在python中壓縮文件

Question

我的程序運行平穩，但是我希望ftp中的文件以zip格式存儲在本地驅動器中

我的問題：調用main（）函數后僅壓縮1個文件

這是我的代碼：

主要

import os
import upload
import download
import zipfile
import ConfigParser
import ftputil

def main():

    #create a folder Temp on d drive for later use
    path = r'D:\Temp'
    os.mkdir(path)

    #parse all the  values at config.ini file
    config = ConfigParser.ConfigParser()
    config.readfp(open('config.ini'))
    server = config.get('main', 'Server')
    username = config.get('main', 'Username')
    password = config.get('main', 'Password')
    uploads = config.get('main', 'Upload folder')
    downloads = config.get('main', 'Download folder')

    #connect to ftp
    ftp = ftputil.FTPHost(server, username, password)

    dirlist = ftp.listdir(downloads)

    for list in dirlist:
        ftp.chdir(downloads)
        target = os.path.join(path, list)
        ftp.download(list, target)


    #########################################################
    #   THis section is where algo fails but the program run#
    ########################################################

    #zipping files
    absolute_path = r'D:\Temp'
    dirlist = os.listdir(absolute_path)
    filepath = r'D:\Temp\project2.zip'
    for list in dirlist:
        get_file = os.path.join(absolute_path, list)
        zip_name = zipfile.ZipFile(filepath, 'w')
        zip_name.write(get_file, 'Project2b\\' + list)




if __name__ == '__main__':
    print "cannot be"

Answer 1

當您這樣做時：

for list in dirlist:
        get_file = os.path.join(absolute_path, list)
        zip_name = zipfile.ZipFile(filepath, 'w')
        zip_name.write(get_file, 'Project2b\\' + list)

您為要壓縮的每個文件重新創建一個ZipFile， "w"模式表示您從頭開始重新創建它。

嘗試以下操作（在循環之前創建zip文件）：

zip_name = zipfile.ZipFile(filepath, 'w')
for list in dirlist:
        get_file = os.path.join(absolute_path, list)
        zip_name.write(get_file, 'Project2b\\' + list)

或這樣，它將以附加模式打開zipfile：

for list in dirlist:
        get_file = os.path.join(absolute_path, list)
        zip_name = zipfile.ZipFile(filepath, 'a')
        zip_name.write(get_file, 'Project2b\\' + list)

Answer 2

看一下shutil模塊。 有一個使用shutil.make_archive（）的示例：

http://docs.python.org/library/shutil.html

Answer 3

如果您有很多文件，可以並行壓縮它們：

import zipfile
from pathlib import Path, WindowsPath
from typing import List, Text
import logging
from time import time
from concurrent.futures import ThreadPoolExecutor

logging.basicConfig(
    format="%(asctime)s - %(message)s", datefmt="%H:%M:%S", level=logging.DEBUG
)

PATH = (r"\\some_directory\subdirectory\zipped")


def file_names() -> List[WindowsPath]:
    p = Path(PATH)
    file_names = list(p.glob("./*.csv"))
    logging.info("There are %d files", len(file_names))
    return file_names


def zip_file(file: WindowsPath) -> None:
    zip_file_name = Path(PATH, f"{file.stem}.zip")
    with zipfile.ZipFile(zip_file_name, "w") as zip:
        zip.write(file, arcname=file.name, compress_type=zipfile.ZIP_DEFLATED)


def main(files: List[Text]) -> None:
    t0 = time()
    number_of_files = len(files)
    with ThreadPoolExecutor() as executor:
        for counter, _ in enumerate(executor.map(zip_file, files), start=1):
            # update progress every 100 files
            if counter % 100 == 0:
                logging.info(
                    "Processed %d/%d. TT: %d:%d",
                    counter,
                    number_of_files,
                    *divmod(int(time() - t0), 60),
                )

    logging.info(
        "Finished zipping %d files. Total time: %d:%d",
        len(files),
        *divmod(int(time() - t0), 60),
    )


if __name__ == "__main__":
    files = file_names()
    main(files)

Answer 4

最好的方法是將調試語句放在for循環中，這有兩種可能：

一個是第一個forloop僅從ftp文件夾下載一個文件

第二個是第一個循環下載所有文件，但第二個循環僅壓縮其中一個

使用打印語句查看循環中已下載/壓縮的文件，祝您好運