Python文件操作指南之CSV文件读写之csv模块详解
作者:星河耀银海
CSV(Comma-Separated Values)是最常见的数据交换格式之一,本文将系统讲解Python标准库csv模块的核心功能,从基本的reader和writer到高级的DictReader和DictWriter,帮你轻松读写CSV
一、开篇:表格数据的通用格式
CSV(Comma-Separated Values)是最常见的数据交换格式之一。Excel可以打开它,数据库可以导入它,几乎所有的数据分析工具都支持它。Python的csv模块专门处理CSV文件——处理引号、转义、各种方言。
基本使用:
import csv
# 写入CSV
with open("users.csv", "w", newline="", encoding="utf-8-sig") as f:
writer = csv.writer(f)
writer.writerow(["姓名", "年龄", "城市"]) # 表头
writer.writerow(["张三", 25, "北京"])
writer.writerow(["李四", 30, "上海"])
# 读取CSV
with open("users.csv", "r", encoding="utf-8-sig") as f:
reader = csv.reader(f)
for row in reader:
print(row)
# ['姓名', '年龄', '城市']
# ['张三', '25', '北京']
# ['李四', '30', '上海']
二、csv.reader() —— 读取CSV
2.1 基本读取
import csv
from io import StringIO
# 直接解析CSV字符串
csv_data = """姓名,年龄,城市
张三,25,北京
李四,30,上海
王五,28,广州"""
reader = csv.reader(StringIO(csv_data))
for row in reader:
print(f" {row}")
# 读取文件
# with open("data.csv", "r", encoding="utf-8") as f:
# reader = csv.reader(f)
# headers = next(reader) # 读取表头
# print(f"表头: {headers}")
# for row in reader:
# print(f"数据: {row}")
2.2 处理不同的分隔符和格式
import csv
# CSV不一定是逗号分隔——可以用制表符、分号等
# TSV文件(制表符分隔)
tsv_data = """姓名\t年龄\t城市
张三\t25\t北京
李四\t30\t上海"""
# 指定分隔符
reader = csv.reader(StringIO(tsv_data), delimiter="\t")
for row in reader:
print(row)
# 处理引号中的逗号
# "张三, Jr.",25,"北京, 中国"
data_with_quotes = '''"张三",25,"北京, 中国"
"李四",30,上海'''
reader = csv.reader(StringIO(data_with_quotes))
for row in reader:
print(f" {row}")
# ['张三', '25', '北京, 中国'] —— 引号中的逗号没有被分割
# 常用参数
# delimiter="," —— 分隔符
# quotechar='"' —— 引号字符
# skipinitialspace=True —— 跳过分隔符后的空格
三、csv.DictReader() —— 字典读取
import csv
# DictReader —— 用表头作为键,每行变成字典
csv_data = """姓名,年龄,城市
张三,25,北京
李四,30,上海
王五,28,广州"""
reader = csv.DictReader(StringIO(csv_data))
for row in reader:
print(f" {row['姓名']}, {row['年龄']}岁, 来自{row['城市']}")
# 张三, 25岁, 来自北京
# 李四, 30岁, 来自上海
# 如果没有表头——可以手动指定
data_no_header = """张三,25,北京
李四,30,上海"""
reader = csv.DictReader(
StringIO(data_no_header),
fieldnames=["姓名", "年龄", "城市"] # 手动指定列名
)
for row in reader:
print(f" {row}")
四、csv.writer() —— 写入CSV
4.1 基本写入
import csv
with open("output.csv", "w", newline="", encoding="utf-8-sig") as f:
writer = csv.writer(f)
# 写入一行
writer.writerow(["产品", "价格", "库存"])
# 写入多行
rows = [
["笔记本", 5999, 50],
["鼠标", 199, 200],
["键盘", 899, 150],
]
writer.writerows(rows)
# ⚠️ 一定要设置 newline=""——防止Windows上出现多余空行
4.2 csv.DictWriter() —— 字典写入
import csv
# DictWriter —— 用字典写入(更直观)
fieldnames = ["name", "age", "city"]
with open("users_dict.csv", "w", newline="", encoding="utf-8-sig") as f:
writer = csv.DictWriter(f, fieldnames=fieldnames)
# 写入表头
writer.writeheader()
# 写入数据行——字典的键对应表头的列
writer.writerow({"name": "张三", "age": 25, "city": "北京"})
writer.writerow({"name": "李四", "age": 30, "city": "上海"})
writer.writerow({"city": "广州", "name": "王五", "age": 28})
# 键的顺序不重要——DictWriter按fieldnames顺序写入
# 批量写入
users = [
{"name": "赵六", "age": 22, "city": "深圳"},
{"name": "钱七", "age": 35, "city": "杭州"},
]
with open("users_dict.csv", "w", newline="", encoding="utf-8-sig") as f:
writer = csv.DictWriter(f, fieldnames=fieldnames)
writer.writeheader()
writer.writerows(users)
# 处理缺少字段的行——用extrasaction参数
writer = csv.DictWriter(
f, fieldnames=fieldnames, extrasaction="ignore"
)
# extrasaction="ignore":忽略字典中多余的键
# extrasaction="raise":多余的键会导致ValueError
五、CSV方言(Dialect)
import csv
# 不同的系统和应用有不同的CSV"方言"
# csv模块提供了一些预定义的方言
# 查看已注册的方言
print(csv.list_dialects()) # ['excel', 'excel-tab', 'unix']
# 创建自定义方言
csv.register_dialect("my_dialect", delimiter="|", quotechar="'", quoting=csv.QUOTE_MINIMAL)
with open("custom.csv", "w", newline="", encoding="utf-8") as f:
writer = csv.writer(f, dialect="my_dialect")
writer.writerow(["name", "value"])
writer.writerow(["item1", "100"])
writer.writerow(["item|2", "200"]) # 包含分隔符——会被引号包裹
# quoting参数控制引号行为:
# csv.QUOTE_MINIMAL —— 只在必要时加引号(默认)
# csv.QUOTE_ALL —— 所有字段都加引号
# csv.QUOTE_NONNUMERIC —— 非数字字段加引号
# csv.QUOTE_NONE —— 不加引号(危险——含分隔符的数据会出错)
六、实战:数据分析工作流
import csv
from collections import defaultdict
def analyze_sales_csv(filepath):
"""分析销售CSV数据"""
stats = {
"total_sales": 0,
"total_revenue": 0.0,
"by_category": defaultdict(lambda: {"count": 0, "revenue": 0.0}),
"by_month": defaultdict(float),
}
with open(filepath, "r", encoding="utf-8-sig", newline="") as f:
reader = csv.DictReader(f)
for row in reader:
qty = int(row.get("quantity", 0))
price = float(row.get("price", 0))
revenue = qty * price
category = row.get("category", "未分类")
month = row.get("date", "0000-00")[:7]
stats["total_sales"] += qty
stats["total_revenue"] += revenue
stats["by_category"][category]["count"] += qty
stats["by_category"][category]["revenue"] += revenue
stats["by_month"][month] += revenue
return stats
# 创建测试数据
with open("sales.csv", "w", newline="", encoding="utf-8-sig") as f:
writer = csv.DictWriter(f, ["date", "product", "category", "quantity", "price"])
writer.writeheader()
writer.writerows([
{"date": "2024-01-15", "product": "A", "category": "电子", "quantity": 2, "price": 100},
{"date": "2024-01-20", "product": "B", "category": "电子", "quantity": 1, "price": 200},
{"date": "2024-02-10", "product": "C", "category": "服装", "quantity": 3, "price": 50},
])
stats = analyze_sales_csv("sales.csv")
print(f"总销量: {stats['total_sales']}件")
print(f"总营收: ¥{stats['total_revenue']:.2f}")
七、总结
CSV是最基础也最重要的数据交换格式。Python的csv模块让读写CSV变得简单可靠。
核心要点:
- 读写用
csv.reader()/csv.writer()—— 列表形式 - 字典用
DictReader/DictWriter—— 更直观 - 必须设置
newline=""——防止Windows多余空行 - 编码选
utf-8-sig——Excel友好(处理BOM) - 分隔符可选——逗号、制表符、分号都支持
CSV→List用reader,CSV→Dict用DictReader,写入时记得newline=""和正确的编码。
到此这篇关于Python文件操作指南之CSV文件读写之csv模块详解的文章就介绍到这了,更多相关Python CSV文件读写内容请搜索脚本之家以前的文章或继续浏览下面的相关文章希望大家以后多多支持脚本之家!
