将多个.txt文件转换为单个.csv文件（python）

Question

在这里你可以看到我正在处理的一些文件。

与我最相似的问题是这个问题（将一个文本文件文件夹合并到一个CSV中，每个内容都在一个单元格中），但我无法实现那里提出的任何解决方案。

我尝试的最后一个是Nathaniel Verhaaren在前面提到的问题中提出的Python代码，但我得到了与问题作者完全相同的错误（即使在实施了一些建议之后）：

import os
import csv

dirpath = 'path_of_directory'
output = 'output_file.csv'
with open(output, 'w') as outfile:
    csvout = csv.writer(outfile)
    csvout.writerow(['FileName', 'Content'])

    files = os.listdir(dirpath)

    for filename in files:
        with open(dirpath + '/' + filename) as afile:
            csvout.writerow([filename, afile.read()])
            afile.close()

    outfile.close()

与我类似的其他问题（例如，Python：将多个。txt文件解析为一个。csv文件？、将多个。txt文件合并为一个csv文件以及将1000个文本文件转换为一个csv文件）并不能解决我提出的问题（而且我不能根据我的情况调整提出的解决方案）。

Answer 1

我也有类似的要求，所以我写了下面的类

import os
import pathlib
import glob
import csv
from collections import defaultdict

class FileCsvExport:
    """Generate a CSV file containing the name and contents of all files found"""
    def __init__(self, directory: str, output: str, header = None, file_mask = None, walk_sub_dirs = True, remove_file_extension = True):
        self.directory = directory
        self.output = output
        self.header = header
        self.pattern = '**/*' if walk_sub_dirs else '*'
        if isinstance(file_mask, str):
            self.pattern = self.pattern + file_mask
        self.remove_file_extension = remove_file_extension
        self.rows = 0

    def export(self) -> bool:
        """Return True if the CSV was created"""
        return self.__make(self.__generate_dict())

    def __generate_dict(self) -> defaultdict:
        """Finds all files recursively based on the specified parameters and returns a defaultdict"""
        csv_data = defaultdict(list)
        for file_path in glob.glob(os.path.join(self.directory, self.pattern),  recursive = True):
            path = pathlib.Path(file_path)
            if not path.is_file():
                continue
            content = self.__get_content(path)
            name = path.stem if self.remove_file_extension else path.name
            csv_data[name].append(content)
        return csv_data

    @staticmethod
    def __get_content(file_path: str) -> str:
        with open(file_path) as file_object:
            return file_object.read()

    def __make(self, csv_data: defaultdict) -> bool:
        """
        Takes a defaultdict of {k, [v]} where k is the file name and v is a list of file contents.
        Writes out these values to a CSV and returns True when complete.
        """
        with open(self.output, 'w', newline = '') as csv_file:
            writer = csv.writer(csv_file, quoting = csv.QUOTE_ALL)
            if isinstance(self.header, list):
                writer.writerow(self.header)
            for key, values in csv_data.items():
                for duplicate in values:
                    writer.writerow([key, duplicate])
                    self.rows = self.rows + 1
        return True

可以像这样使用

...
myFiles = r'path/to/files/'
outputFile = r'path/to/output.csv'

exporter = FileCsvExport(directory = myFiles, output = outputFile, header = ['File Name', 'Content'], file_mask = '.txt')
if exporter.export():
    print(f"Export complete. Total rows: {exporter.rows}.")

在我的示例目录中，返回

"File Name","Content"
"Test1","This is from Test1"
"Test2","This is from Test2"
"Test3","This is from Test3"
"Test4","This is from Test4"
"Test5","This is from Test5"
"Test5","This is in a sub-directory"

null