在 Python 中从文件中分离值

Question

假设我将这个 txt 文件格式化为（值）（空格）（值），并且有第二组数字用（制表符）分隔。这里给出了一个示例文件：

Header
5 5 6 7 8   7 8 9 0 1
7 6 3 4 1   1 3 6 8 1
8 7 4 1 3   1 9 8 5 1

现在我正在使用此代码打印 txt 文件中显示的所有值：

NEWLINE = "\n"

def readBoardFromFile():
    inputFileOK = False
    aBoard = []

    while (inputFileOK == False):
        try:
            inputFileName = input("Enter the name of your file: ")
            inputFile = open(inputFileName, "r")
            print("Opening File " + inputFileName + "for reading")

            currentRow = 0
            next(inputFile)

            for line in inputFile:
                aBoard.append([])

                for ch in line:
                    if (ch != NEWLINE):
                        aBoard[currentRow].append(ch)

                currentRow = currentRow + 1

            inputFileOK = True
            print("Completed reading of file " + inputFileName)

        except IOError:
            print("Error: File couldn't be opened")

    numRows = len(aBoard)
    numColumns = len(aBoard[0])

    return(aBoard,numRows,numColumns)

def display(aBoard, numRows, numColumns):

    currentRow = 0
    currentColumn = 0
    print("DISPLAY")

    while (currentRow < numRows):
        currentColumn = 0
        while (currentColumn < numColumns):
            print("%s" %(aBoard[currentRow][currentColumn]), end="")
            currentColumn = currentColumn + 1
        currentRow = currentRow + 1
        print()

    for currentColumn in range (0,numColumns,1):
        print("*", end ="")

    print(NEWLINE)

def start():
    aBoard,numRows,numColumns = readBoardFromFile()
    display(aBoard,numRows,numColumns)



start()

通常当我运行此代码时，这是输出：

DISPLAY
5 5 6 7 8       7 8 9 0 1
7 6 3 4 1       1 3 6 8 1
8 7 4 1 3       1 9 8 5 1
*******************

我怎样才能使输出为：

DISPLAY
5 5 6 7 8       
7 6 3 4 1       
8 7 4 1 3       

只显示左半边的数字？

Answer 1

也许您可以尝试使用 csv 模块并使用制表符分隔符打开文件。 然后假设您使用列表方法，您只能打印每行的第一个元素。

类似：

import csv
with open("a.txt") as my_file:

    reader = csv.reader(my_file, delimiter ='\t')

    next(reader) # to skip header if exists
    for line in reader:
        print(line[0])

Answer 2

据我所知，您没有在代码中考虑制表符，这可能是您在输出中包含其他字符的原因。

这是我将采用的方法，在处理字符串时利用 Python 的强大功能。

我会鼓励你在编写 Python 时使用这种方法，因为它会让你更容易喜欢。

NEWLINE = "\n"

def read_board_from_file():
    input_file_OK = False
    a_board = []

    while not input_file_OK:
        try:
            input_file_name = input("Enter the name of your file: ")

            with open(input_file_name, "r") as input_file:
                # A file-like object (as returned by open())
                # can be simply iterated 
                for line in input_file:

                    # Skip header line if present
                    # (not sure how you would want to handle the
                    # header.
                    if "header" in line.lower():
                        continue

                    # Strip NEWLINE from each line,
                    # then split the line at the tab character.
                    # See comment above.
                    parts = line.strip(NEWLINE).split("\t")

                    # parts is a list, we are only interested
                    # in the first bit.
                    first_part = parts[0]

                    # Split the left part at all whitespaces.
                    # I'm assuming that this is what you want.
                    # A more complex treatment might make sense here,
                    # depending on your use-case.
                    entries = first_part.split()

                    # entries is a list, so we just need to append it
                    # to the board
                    a_board.append(entries)

            input_file_OK = True
            print(f"Completed reading of file {input_file_name}")

        except IOError:
            print("Error: File {input_file_name} couldn't be opened.")

    return a_board

def display_board(a_board):
    print("DISPLAY")

    longest_row = 0

    # a_board is a list of lists,
    # no need to keep track of the number of rows and columns,
    # we can just iterate it.
    for row in a_board:
        # row is a list of entries, we can use str.join() to add a space
        # between the parts and format the row nicely.
        row_str = " ".join(row)

        # At the same time we can keep track of the longest row
        # for printing the footer later.
        len_row_str = len(row_str)
        if len_row_str > longest_row:
            longest_row = len_row_str

        print(row_str)

    # The footer is simply the asterisk character
    # printed as many times as the longest row.
    footer = "*" * longest_row
    print(footer, end="")

    print(NEWLINE)

def start():
    a_board = read_board_from_file()

    display_board(a_board)

start()

Answer 3

我会在输入、输出和数据处理之间进行更多分离。您的输入是文件名，辅助输入是实际文件内容。数据处理步骤是获取文件内容，并返回一些板集合的内部表示。输出显示第一块板。

from typing import Iterable, List

def parse(lines: Iterable[str], board_sep: str = "\t") -> List[List[List[str]]]:
    boards = []
    for i, line in enumerate(lines):
        # list of the same line from each board
        board_lines = line.split(board_sep)
        if i == 0:
            # this only happens once at the start
            # each board can be a list of lists. so boards is a list of "list of lists"
            # we're going to append lines to each board, so we need some initial setup
            # of boards
            boards = [[] for _ in range(len(board_lines))]

        for board_idx, board_line in enumerate(board_lines):
            # then just add each line of each board to the corresponding section
            boards[board_idx].append(board_line.split())
    return boards


def show_board(board: List[List[str]]) -> None:
    for row in board:
        print(" ".join(row))

现在我们可以将所有这些放在一起。我们需要：

1. 获取文件名
2. 打开文件
3. 过滤掉“标题”和任何空行
4. 将其余行传递给parse() 函数
5. 获得第一块板
6. 使用上下文打印它

from typing import Tuple

def get_board_dimensions(board: List[List[str]]) -> Tuple[int, int]:
    """ Returns a tuple of (rows, cols) """
    return len(board), len(board[0])


def get_filtered_file(filename: str) -> Iterable[str]:
    with open(filename) as f:
        for line in f:
            if not line or line.lower() == "header":
                continue
            yield line


def main():
    filename = input("Enter the name of your file: ")
    filtered_lines = get_filtered_file(filename)
    boards = parse(filtered_lines)

    # now we can show the first one
    b = boards[0]
    _, cols = get_board_dimensions(b)
    print("DISPLAY")
    show_board(b)
    print("*" * (2 * cols - 1))  # columns plus gaps