Python 提取数据和创建数据

Question

我有一个 100GB 数据的 txt 文件... txt 文件示例：

(1, 'Dog', '', '3', 'Brown','Female,)
(2, 'Primate', 'Orangutan', '10', 'Orange','Male,)

我想作为输出：

List number: 1               Age: 3
Type: Dog                    Hair Color: Brown
Race: None                   Sex: Female
-------------------------------------------------------
List number: 2               Age: 10
Type: Primate                Hair Color: Orange
Race: Orangutan              Sex: Male

如何在 python 上实现这一点？？？ 谢谢你，我真的很感激你的帮助！！

Answer 1

您可以使用str.ljust() 获取第一项之后的空格。

data = [
    (1, 'Dog', '', '3', 'Brown', 'Female'),
    (2, 'Primate', 'Orangutan', '10', 'Orange', 'Male')
]


first = True
for i, type_, race, age, hair_color, sex in data:
    if not first:
        print("-" * 80)
    else:
        first = False
    print(f"List number: {str(i).ljust(30)}Age: {age or None}")
    print(f"Type: {str(type_ or None).ljust(37)}Hair Color: {hair_color or None}")
    print(f"Race: {str(race or None).ljust(37)}Sex: {sex or None}")

输出

List number: 1                             Age: 3
Type: Dog                                  Hair Color: Brown
Race: None                                 Sex: Female
--------------------------------------------------------------------------------
List number: 2                             Age: 10
Type: Primate                              Hair Color: Orange
Race: Orangutan                            Sex: Male

为什么是 30 和 37？
30 是一个随机值。
37 = 30 + (len("List number: ") - len("Type: "))（"Race: " 相同）。

Answer 2

我认为你可以先创建一个带有输出模板的字符串，然后用像这样的格式函数填充它：

data = [
    (1, 'Dog', '', '3', 'Brown', 'Female'),
    (2, 'Primate', 'Orangutan', '10', 'Orange', 'Male')
]

template = """List number: {0:<23} Age: {3:<10}
Type: {1:<30} Hair Color: {4:<30}
Race: {2:<30} Sex: {5:<30}
"""

for idx, _ in enumerate(data):
    print('-'*70) if idx > 0 else None
    print(template.format(*_))

使用上下文管理器：

with open(filename) as file:
    for line in file:
        data = split_line_to_list(line)
        print('-'*70)
        print(template.format(*data))

Answer 3

我使用了@AndyPavlov生成的模板

import sys
import re

__Animal_attributes__ = {
    'id': int,
    'type': str,
    'race': str,
    'age': int,
    'hair_color': str,
    'sex': str
}

class TxtFileHandler:
    @staticmethod
    def parse(data):
        if len(data.strip()) > 0:
            return [a.strip() for a in re.sub(re.compile(r'[\(\)\r\n\']'), '', data).split(',')]
        else:
            raise Exception(f'Error parsing data [{data}]')

    @staticmethod
    def read(filename:str, fn, data: list = list()):
        try:
            file = open(filename, 'r')
        except OSError as e:
            print(e)
        with file:
            for line in file:
                try:
                    data.append(fn(line))
                except Exception as e:
                    print(f'Error executing callback [{fn}] with data [{line}]. Received exception: {e}')
            return data

class Animal:
    def __init__(self, *args):
        for idx, (attribute, parsing_fn) in enumerate(__Animal_attributes__.items()):
            setattr(self, attribute, parsing_fn(args[idx]))

    def __str__(self) -> str:
        template = """List number: {0:<23} Age: {3:<10}
Type: {1:<30} Hair Color: {4:<30}
Race: {2:<30} Sex: {5:<30}"""
        return template.format(*[getattr(animal, a) for a in __Animal_attributes__.keys()])

if __name__ == '__main__':
    filename = sys.argv[1]
    animals = TxtFileHandler.read(filename, lambda line: Animal(*TxtFileHandler.parse(line)))
    for idx, animal in enumerate(animals):
        print(animal, f'\n{"-"*70 if idx < len(animals)-1 else ""}')