python csv库

python csv库

水一水又是一篇，乐

读取

import csv  
  
# 打开 CSV 文件  
with open('example.csv', mode='r', newline='') as file:  
    csv_reader = csv.reader(file)  
      
    # 读取文件头（可选）  
    headers = next(csv_reader)  
    print(f"Headers: {headers}")  
      
    # 读取每一行数据  
    for row in csv_reader:  
        print(row)

写入

import csv  
  
# 要写入的数据  
data = [  
    ['Name', 'Age', 'City'],  
    ['Alice', 30, 'New York'],  
    ['Bob', 25, 'Los Angeles'],  
    ['Charlie', 35, 'Chicago']  
]  
  
# 打开 CSV 文件  
with open('output.csv', mode='w', newline='') as file:  
    csv_writer = csv.writer(file)  
      
    # 写入数据  
    csv_writer.writerows(data)

读取csv为字典

import csv  
  
# 打开 CSV 文件  
with open('example.csv', mode='r', newline='') as file:  
    csv_reader = csv.DictReader(file)  
      
    # 读取每一行数据  
    for row in csv_reader:  
        print(row)

写入字典到csv

import csv  
  
# 要写入的数据  
data = [  
    {'Name': 'Alice', 'Age': 30, 'City': 'New York'},  
    {'Name': 'Bob', 'Age': 25, 'City': 'Los Angeles'},  
    {'Name': 'Charlie', 'Age': 35, 'City': 'Chicago'}  
]  
  
# 获取字典的键作为表头  
fieldnames = data[0].keys()  
  
# 打开 CSV 文件  
with open('output.csv', mode='w', newline='') as file:  
    csv_writer = csv.DictWriter(file, fieldnames=fieldnames)  
      
    # 写入表头  
    csv_writer.writeheader()  
      
    # 写入数据  
    csv_writer.writerows(data)

处理带有特定分隔符的 CSV 文件

​ 默认情况下，CSV 文件使用逗号作为分隔符，但你可以通过 delimiter 参数来指定其他分隔符，例如制表符（\t）。

import csv  
  
# 读取使用制表符分隔的 CSV 文件  
with open('tab_separated.csv', mode='r', newline='') as file:  
    csv_reader = csv.reader(file, delimiter='\t')  
      
    # 读取每一行数据  
    for row in csv_reader:  
        print(row)

羊城杯2024 data-analy1
某位✌的wp

import csv
import re

p=[734, 735, 736, 737, 738, 739, 747, 748, 750, 751, 752, 757, 758, 759, 772,
778, 782, 783, 784, 787, 788, 795, 798, 730, 731, 732, 740, 745, 746, 755,
756, 766, 767, 771, 775, 776, 785, 786, 796, 733, 749, 753, 773, 774, 777,
780, 781, 789, 790, 791, 793, 799]

def cd(data,k):
    if not isinstance(data,str):
        return None
    elif data.isdigit() and 1<= int(data) and int(data)<=10002:
        return 0
    elif data in ['男','女']:
        return 4
    elif re.search("[\u4e00-\u9fa5]",data[0]): # 中文范围
        return 3
    elif data.isdigit() and len(data)==8: # 出生日期
        return 5
    elif len(data)==32: # 
        return 2
    elif len(data)==18 and data[6:14] in k: # 身份证与出生日期对应
        return 6
    elif len(data)==11 and data.isdigit() and int(data[0:3]) in p: # 手机号
        return 7
    else:
        return 1
rows=[]
with open('C:\\Users\\21609\\Downloads\\Compressed\\data-analy1的附件\\tempdir\\DS附件\\附件\\person_data.csv','r',encoding='utf-8') as fp:
    csv_reader=csv.reader(fp)
    for num,row in enumerate(csv_reader,start=1):
        if row== ['编号', '用户名', '密码', '姓名', '性别', '出生日期', '身份证号', '手机号码']:
            rows.append(row)
            continue
        new=[0]*8
        for i in row:
            new[cd(i,row)]=i
        rows.append(new)
with open('C:\\Users\\21609\\Downloads\\Compressed\\data-analy1的附件\\tempdir\\DS附件\\附件\\person_data_new.csv',mode='w',newline="",encoding='utf-8') as fp:
    #newline指定行尾，默认为\r\n
    csv_writer = csv.writer(fp)
    csv_writer.writerows(rows)

数据->从文本/csv->导入，可看到编码正确的文档