一文带你搞懂Python如何解析CSV文件

"aaa","b 
bb","ccc" 
"aaa","b""bb","ccc"

id,name,age,city
1,Alice,30,New York
2,Bob,25,Los Angeles
3,Charlie,35,Chicago
4,David,40,Houston

import csv

# 1. 读取 CSV 文件
with open('data.csv', mode='r', newline='', encoding='utf-8') as file:
    reader = csv.reader(file)
    data = list(reader)

# 2. 取行/列数据
# 取第二行数据
print("\n第二行数据:", data[1])

# 取第三列数据
column_index = 2
column_data = [row[column_index] for row in data]
print("\n第三列数据:", column_data)

# 3. 遍历数据
print("\n遍历数据:")
for row in data:
    print(row)

# 4. 批量修改某行/列数据
# 批量修改第二行数据
new_row_data = ['5', 'Eva', '28', 'San Francisco']
data[1] = new_row_data

# 批量修改第三列数据
new_column_data = ['31', '26', '36', '41']
for i, row in enumerate(data[1:], start=1):  # Skip header row
    row[column_index] = new_column_data[i - 1]

# 5. 修改某个具体的值
# 修改第一行第二列的具体值
data[0][1] = 'Alicia'

# 6. 增加某行/列数据
# 增加新行
new_row = ['5', 'Eva', '28', 'San Francisco']
data.append(new_row)

# 增加新列
new_column_data = ['USA'] * len(data)  # New column data
for row, value in zip(data, new_column_data):
    row.append(value)

# 7. 删除某行/列数据
# 删除第二行
del data[1]

# 删除第三列
for row in data:
    del row[2]

# 8. 存储数据
# 保存修改后的数据
with open(file_path, mode='w', newline='', encoding='utf-8') as file:
    writer = csv.writer(file)
    writer.writerows(data)

print("\n修改后的数据:")
for row in data:
    print(row)

import pandas as pd
# 1. 读取 CSV 文件
df = pd.read_csv('data.csv')

# 2. 取行/列数据
# 取第一行数据
print("\n第一行数据:")
print(df.iloc[0])

# 取 'name' 列的数据
print("\n'name' 列的数据:")
print(df['name'])

# 3. 遍历数据
print("\n遍历数据:")
for index, row in df.iterrows():
    print(f"ID: {row['id']}, Name: {row['name']}, Age: {row['age']}, City: {row['city']}")

# 4. 批量修改某行/列数据
# 修改 'age' 列中所有人的年龄，加5岁
df['age'] = df['age'] + 5

# 修改 'city' 列中 'New York' 的值为 'NYC'
df.loc[df['city'] == 'New York', 'city'] = 'NYC'

# 5. 修改某个具体的值
# 修改 ID 为 2 的人的 'age' 为 28
df.loc[df['id'] == 2, 'age'] = 28

# 删除 'city' 列
df = df.drop(columns=['city'])

# 6. 增加行/列，并填充数据
# 增加一列 'email' 并填充默认值 'unknown'
df['email'] = 'unknown'

# 增加一行数据
new_row = {'id': 5, 'name': 'Eve', 'age': 22, 'email': 'eve@example.com'}
df.loc[len(df)] = new_row

# 7. 删除某行/列数据
# 删除 ID 为 4 的行
df = df[df['id'] != 4]

# 删除 'city' 列
df = df.drop(columns=['city'])

# 8. 存储数据
df.to_csv('modified_data.csv', index=False)

print("\n修改后的数据:")
print(df)

DataFrame.to_csv(path_or_buf=None, sep=', ', na_rep='', float_format=None,
                columns=None, header=True, index=True, index_label=None, mode='w',
                encoding=None, compression=None, quoting=None, quotechar='"',
                line_terminator='\n', chunksize=None, tupleize_cols=None, 
                date_format=None, doublequote=True,escapechar=None, decimal='.')