Linux上使用Python的文件自动化

Question

使用Python在Linux中自动化文件组织的项目。在我知道如何编码之前，我一直想用这种方式来做这个项目。现在我做了，我想改进它更多。

使用的语言: Python。

兼容系统: Linux。

已使用模块:操作系统模块。

它的工作原理:当您将文件保存/移动/复制到一个主目录(例如:下载，Documents...etc)时，它将自动将其移动到其指定的目录中。它将同时使用扩展名和我在文件名开头提供的2/3字母代码。一旦我打开电脑，它就会在后台运行。

这个程序只在文件上工作，而不是目录(我通常没有它们，当我这样做的时候，我想亲自去做)。

问题

1. 我的代码可读性如何？
2. 有什么我不知道的逻辑错误吗？
3. 如何改进？
4. 有没有更好的方法来解决这个问题？
5. 总的来说，你如何评价它的10个？

提前谢谢你。

码

FileOrganizer.py：

#!/usr/bin/env python

import os
import time
import os.path
from random import randint
from ExtraInfo import types, locations, docs, working_directories


class FileOrganizer:

    def __init__(self, directory_path):
        self.directory_path = directory_path

    def path_maker(self, root, file_name):
        """(str, str) -> str

        Returns a string containing the full path of a file,
        from root of the file and its name.

        >>> path_maker("/home/hama/Downloads", "area.cpp")
        "/home/hama/Downloads/area.cpp"
        >>> path_maker("/home/hama/Downloads/", "FuzzBuzz.py")
        "/home/hama/Downloads/FuzzBuzz.py"
        """

        return os.path.join(root, file_name)

    def extension_finder(self, path):
        """(str) -> str

        Takes in a string of full path of a file. If exists,
        returns a string of its extension, else returns False.

        >>> extension_finder("/home/hama/Downloads/area.cpp")
        ".cpp"
        >>> extension_finder("/home/hama/Downloads/FuzzBuzz.py")
        ".py"
        """

        if os.path.exists(path):
            if os.path.isfile(path):
                return os.path.splitext(path)[1]
        return False

    def category_selector(self, extension):
        """(str) -> str

        Takes in a string of an extension of a file. If not False,
        returns the category of the extension, else returns False.

        Precondition: The extension must be in one of the categories.

        >>> category_selector(".cpp")
        "programming-files"
        >>> category_selector(".mp4")
        "video"
        """

        if extension != False:
            for category in types:
                if extension in types[category]:
                    return category
                    break
            return False

    def get_prefix(self, path):
        """(str) -> str

        Takes in a string of full path of a file. If it is one of the doc
        categories returns the first 3 characters of name of the file, else 2.

        Precondition: A prefix of a specific directory should be provided
        at the beginning of the name of the file.

        >>> get_prefix("/home/hama/Downloads/umaMath-week11.pdf")
        "uma"
        >>> get_prefix("/home/hama/Downloads/pyFuzzBuzz.py")
        "py"
        """

        prefix = os.path.basename(path)
        if self.category_selector(self.extension_finder(path)) not in docs:
            return prefix[:2]
        else:
            return prefix[:3]

    def get_original_name(self, path):
        """(str) -> str

        Takes in a string of full path of a file. returns a string of
        the original file name without any prefix.

        Precondition: A prefix of a specific directory should be provided
        at the beginning of the name of the file.

        >>> get_original_name("/home/hama/Downloads/umaMath-week11.pdf")
        "Math-week11.pdf"
        >>> get_original_name("/home/hama/Downloads/pyFuzzBuzz.py")
        "FuzzBuzz.py"
        """

        file_name = os.path.basename(path)
        if self.category_selector(self.extension_finder(path)) not in docs:
            return file_name[2:]
        else:
            return file_name[3:]

    def random_name_generator(self, path):
        """(str) -> str

        Takes in a string of full path of a file. Generates a random
        integer at the end of the name of the file, the returns the new name.

        >>> random_name_generator("/home/hama/Downloads/umaMath-week11.pdf")
        "Math-week11.pdf"
        >>> random_name_generator("/home/hama/Downloads/pyFuzzBuzz.py")
        "FuzzBuzz.py"
        """

        file_name = os.path.splitext(path)[0]
        extension = os.path.splitext(path)[1]
        return f"""{file_name}-{randint(1, 250) % randint(1, 250)}{extension}"""

    def copy(self, file_source, destination_root):
        """(str, str) -> str

        Returns a string containing the full path of the newly moved file,
        from a full path of a file and root of the destination.

        Note: If a file with the same name already exists, a new name will be generated.

        >>> copy("/home/hama/Downloads/area.cpp", "/home/hama/Codes/C++/")
        "/home/hama/Codes/C++/area.cpp"
        >>> copy("/home/hama/Downloads/FuzzBuzz.py", "/home/hama/Codes/Python/")
        "/home/hama/Codes/Python/FuzzBuzz.py"
        """

        if not os.path.exists(self.path_maker(destination_root, self.get_original_name(file_source))):
            file_name = os.path.basename(file_source)
            file_destination = self.path_maker(
                destination_root, self.get_original_name(file_source))
            os.system(f"cp -pa {file_source} {file_destination}")
            return file_destination
        else:
            file_name = self.random_name_generator(self.path_maker(
                destination_root, self.get_original_name(file_source)))
            file_destination = self.path_maker(destination_root, file_name)
            os.system(f"cp -pa {file_source} {file_destination}")
            return file_destination


# Activated on these directories
paths = [FileOrganizer(f"{directory}") for directory in working_directories]
while True:
    for path in paths:
        # Get the files and directories in the root directory.
        for root, directories, files in os.walk(path.directory_path):
            root, directories, files = root, directories, files
            break

        # List the files in the directory
        list_of_files = []
        for file in files:
            list_of_files.append(path.path_maker(root, file))

        # Loop through the files and copy each one of them.
        proccess = True
        for file in list_of_files:
            if proccess:
                current_file = file

                file_category = path.category_selector(
                    path.extension_finder(current_file))
                if file_category in locations:
                    if locations[file_category].get(path.get_prefix(current_file)) != None:
                        destination_root = locations[file_category].get(
                            path.get_prefix(current_file))

                        # Check if there is a whitespace in the path, cause it cause infinite loop.
                        if not (" " in current_file):
                            new_file_destination = path.copy(
                                current_file, destination_root)
                        else:
                            continue
                        if os.path.exists(new_file_destination):
                            os.remove(current_file)

                        # Check if the file is moved and the proccess is done, otherwise wait until it is done.
                        if not os.path.exists(current_file) and os.path.exists(new_file_destination):
                            proccess = True
                        else:
                            proccess = False
                            while not proccess:
                                if not os.path.exists(current_file) and os.path.exists(new_file_destination):
                                    proccess = True
                                else:
                                    proccess = False
                                time.sleep(10)

        time.sleep(5)

# By: Hama
# Software Engineer to be.

ExtraInfo.py：

#!/usr/bin/env python
types = {

    'audio': ['.wpl', '.wma', '.wav', '.ogg', '.mpa', '.mp3', '.mid', '.midi', '.cda', '.aif'],

    'database': ['.csv', '.dat', '.db', '.dbf', 'log', '.mdb', '.sav', 'sqlite', '.sql', '.tar', '.xml'],

    'fonts': ['.fnt', '.fon', '.otf', '.ttf'],

    'image': ['.ai', '.bmp', '.gif', '.ico', '.jpeg', '.jpg', '.png', '.ps', '.psd', '.svg', '.tif', '.tiff'],

    'doc-presentation': ['.key', '.odp', '.pps', '.ppt', '.pptx'],

    'internet': ['.asp', '.srt', '.aspx', '.cer', '.cfm', '.cgi', '.htm', '.jsp', '.part', '.rss', '.xhtml', '.torrent'],

    'programming-files': ['.c', '.class', '.cpp', '.cs', '.h', '.java', '.pl', '.sh', '.swift', '.vb', '.php', '.html', '.css', '.js', '.py'],

    'doc-spreadsheet': ['.ods', '.xls', '.xlsm', '.xlsx'],

    'video': ['.3g2', '.3gp', '.avi', '.flv', '.h264', '.264', '.m4v', '.mkv', '.mov', '.mp4', '.mpg', '.mpeg', '.rm', '.swf', '.vob', '.wmv'],

    'doc-word': ['.doc', '.docx', '.odt', '.rtf', '.tex', '.wpd'],

    'doc-pdf': ['.pdf', '.epub', '.mobi'],

    'text': ['.txt']

}

locations = {

    'audio': {'na': '/home/hama/Music/Others'},

    'database': {'na': '/home/hama/Documents/Others/Database'},

    'fonts': {'na': '/home/hama/Documents/Others/Fonts'},

    'internet': {'na': "/home/hama/Documents/Others/Internet-Related"},

    'image': {'my': '/home/hama/Pictures/Myself', 'ot': '/home/hama/Pictures/Others', 'wa': '/home/hama/Pictures/Wallpapers'},

    'video': {'my': '/home/hama/Videos/Myself', 'ot': '/home/hama/Videos/Others', 'mv': '/home/hama/Videos/Movies', 'tu': '/home/hama/Videos/Tutorials', 'se': '/home/hama/Videos/Series'},

    'programming-files': {'ot': '/home/hama/Codes/Others', 'wb': '/home/hama/Codes/Web', 'cp': '/home/hama/Codes/C++', 'py': '/home/hama/Codes/Python'},

    'doc-spreadsheet': {'bop': "/home/hama/Documents/Books/Programming-Books", 'bon': "/home/hama/Documents/Books/Novels", 'boo': "/home/hama/Documents/Books/Others", 'duc': "/home/hama/Documents/Documents/Spreadsheet", 'tmp': "/home/hama/Documents/Temp", 'uot': "/home/hama/Documents/UKH/Undergraduate-I/Other-Documents", 'uma': "/home/hama/Documents/UKH/Undergraduate-I/Semester-II/Engineering-Mathematics-II", 'udl': "/home/hama/Documents/UKH/Undergraduate-I/Semester-II/Introduction-to-Digital-Logic-&-Electronics", 'usp': "/home/hama/Documents/UKH/Undergraduate-I/Semester-II/Structured-Programming", 'uen': "/home/hama/Documents/UKH/Undergraduate-I/Semester-II/English-Composition-II"},

    'doc-presentation': {'bop': "/home/hama/Documents/Books/Programming-Books", 'bon': "/home/hama/Documents/Books/Novels", 'boo': "/home/hama/Documents/Books/Others", 'duc': "/home/hama/Documents/Documents/Presentations", 'tmp': "/home/hama/Documents/Temp", 'uot': "/home/hama/Documents/UKH/Undergraduate-I/Other-Documents", 'uma': "/home/hama/Documents/UKH/Undergraduate-I/Semester-II/Engineering-Mathematics-II", 'udl': "/home/hama/Documents/UKH/Undergraduate-I/Semester-II/Introduction-to-Digital-Logic-&-Electronics", 'usp': "/home/hama/Documents/UKH/Undergraduate-I/Semester-II/Structured-Programming", 'uen': "/home/hama/Documents/UKH/Undergraduate-I/Semester-II/English-Composition-II"},

    'doc-word': {'bop': "/home/hama/Documents/Books/Programming-Books", 'bon': "/home/hama/Documents/Books/Novels", 'boo': "/home/hama/Documents/Books/Others", 'duc': "/home/hama/Documents/Documents/Word", 'tmp': "/home/hama/Documents/Temp", 'uot': "/home/hama/Documents/UKH/Undergraduate-I/Other-Documents", 'uma': "/home/hama/Documents/UKH/Undergraduate-I/Semester-II/Engineering-Mathematics-II", 'udl': "/home/hama/Documents/UKH/Undergraduate-I/Semester-II/Introduction-to-Digital-Logic-&-Electronics", 'usp': "/home/hama/Documents/UKH/Undergraduate-I/Semester-II/Structured-Programming", 'uen': "/home/hama/Documents/UKH/Undergraduate-I/Semester-II/English-Composition-II"},

    'doc-pdf': {'bop': "/home/hama/Documents/Books/Programming-Books", 'bon': "/home/hama/Documents/Books/Novels", 'boo': "/home/hama/Documents/Books/Others", 'duc': "/home/hama/Documents/Documents/PDF", 'tmp': "/home/hama/Documents/Temp", 'uot': "/home/hama/Documents/UKH/Undergraduate-I/Other-Documents", 'uma': "/home/hama/Documents/UKH/Undergraduate-I/Semester-II/Engineering-Mathematics-II", 'udl': "/home/hama/Documents/UKH/Undergraduate-I/Semester-II/Introduction-to-Digital-Logic-&-Electronics", 'usp': "/home/hama/Documents/UKH/Undergraduate-I/Semester-II/Structured-Programming", 'uen': "/home/hama/Documents/UKH/Undergraduate-I/Semester-II/English-Composition-II"},

    'text': {'tx': "/home/hama/Documents/Documents/PDF"}
}

docs = ['doc-spreadsheet', 'doc-presentation', 'doc-word', 'doc-pdf']

working_directories = ["/home/hama/Downloads/", "/home/hama/Documents/", "/home/hama/Codes/",
                    "/home/hama/Desktop/", "/home/hama/Music/", "/home/hama/Pictures/", "/home/hama/Videos/"]

script.sh：

#!/bin/bash
nohup python3 -u /home/hama/Codes/Python/FileAutomationV1.0/FileOrganizer.py &

Answer 1

除了其他人已经说过的话之外，最重要的是，您正在为更改进行投票，这是浪费的。

在Linux上，正确的解决方案是使用一些绑定到inotify API，以便您可以在所监视的目录上接收IN_CLOSE_WRITE和IN_MOVED_TO事件。这样，您的监视进程就可以无限期地休眠，当有工作要做时，内核将唤醒它。

Answer 2

我同意回答中@AlexPovel提到的所有要点，我不打算重复它们。

让我感到奇怪的是，这个类名为FileOrganizer，但它所做的只是为处理路径提供了方便的函数。它没有显式地组织您的文件！它作为独立代码留在类之外。

我会把移动代码作为课堂的一部分。这意味着您的全局文件类型数据结构可能应该是类属性。之后你可以做：

file_organizers = [FileOrganizer(path) for path in paths]
while True:
    for file_organizer in file_organizers:
        file_organizer.organize()
    time.sleep(5)

目前，您还在运行一个循环，直到文件复制完成，如果文件还在，每10秒检查一次。我要么选择全异步 (并跟踪当前正在复制的文件)，要么使用subprocess.run (Python3.5+)，它只在命令完成后才返回。

该方法可以如下所示：

import subprocess

class FileOrganizer:

    ...

    def move(self, file, destination):
        ... # get the right names
        subprocess.run(["cp", "-pa", file, destination])
        if os.path.exists(destination):
            os.remove(file)
        else:
            print(f"Moving {file} failed.")
        return destination

    def organize(self):
        # Get the files and directories in the root directory.
        root, directories, files = next(os.walk(self.directory_path))
        root = Path(root)
        # List the files in the directory
        files = (root.joinpath(file) for file in files if " " not in file)

        # Loop through the files and copy each one of them.
        for file in files:
            file_category = self.category_selector(file.suffix)
            location = self.locations.get(file_category)
            if location is None:
                print("{file_category} is not a valid category")
                continue
            prefix = self.get_prefix(file)
            destination_root = location.get(prefix)
            if destination_root is None:
                print(f"{prefix} is not a valid prefix")
                continue
            self.move(file, destination_root)

请注意，我添加了一些调试输出，以便更容易地查看脚本正在做什么。您可能希望最终使用logging模块将其移动到日志文件中。