Python 利用CSV模块处理数据的实现实例

id,name,hire_date, salary ,bonus
1,Vincent,2024/1/1," 1,000.00 ",100
2,Victor,2024/1/2," 2,000.00 ",200
3,Grace,2024/1/3," 3,000.00 ",300

input_file = 'salary.csv'
with open(input_file, 'r', newline='') as fi:
        header = fi.readline()
        header = header.strip()
        header_list = header.split(',')
        print(header_list)
        for row  in fi:
            field_list = row.strip().split(',')
            print(field_list)

import csv
input_file = 'salary.csv'
output_file = 'results.csv'
with open(input_file, 'r', newline='') as fi:
    with open(output_file, 'w', newline='') as fo:
        reader = csv.reader(fi, delimiter=',')    # 默认分隔符就是逗号，delimiter=','也可省略
        writer = csv.writer(fo)
        header = next(reader)    # 读取第一行标题
        print(header)
        writer.writerow(header)    # 先将标题写入文件
        for row in reader:
            salary = float(row[3].replace(',', ''))    # 去除逗号并转换为float型
            if salary > 1000:
                print(row)
                writer.writerow(row)

import csv
from collections import namedtuple
input_file = 'salary.csv'
output_file = 'results.csv'
with open(input_file, 'r', newline='') as fi:
    with open(output_file, 'w', newline='') as fo:
        reader = csv.reader(fi, delimiter=',')    # 默认分隔符就是逗号，delimeter=','也可省略
        writer = csv.writer(fo)
        header = next(reader)    # 读取第一行标题
        print(header)
        writer.writerow(header)    # 先将标题写入文件
        
        namedrow = namedtuple('namedrow', header)    #  命名元组定义
        for row in reader:
            row = namedrow(*row)    # 转换为命名元组
            salary = float(row.salary.replace(',', ''))    # 通过row.salary引用salary列
            if salary > 1000:
                print(row)
                writer.writerow(row)

import csv
input_file = 'salary.csv'
output_file = 'results.csv'
with open(input_file, 'r', newline='') as fi:
    with open(output_file, 'w', newline='') as fo:
        reader = csv.reader(fi, delimiter=',')    # 默认分隔符就是逗号，delimiter=','也可省略
        writer = csv.writer(fo)
        header = next(reader)    # 读取第一行标题

        columns = ['id', 'name', 'salary']    # 需要的列
        col_idx = []
        for idx in range(len(header)):
            if header[idx] in columns:    # 如果在选取的范围内，保存索引
                col_idx.append(idx)               
        writer.writerow(columns)    # 先将标题写入文件

        for row in reader:
            results = []
            for idx in col_idx:
                results.append(row[idx])    # 通过索引只保留需要的列
            print(results)
            writer.writerow(results)