一文带你玩转Python必备的几种数据格式

import json

# Python对象转JSON字符串
data = {"name": "张三", "age": 25, "is_student": True}
json_str = json.dumps(data, ensure_ascii=False)  # ensure_ascii=False支持中文
print(json_str)  # 输出: {"name": "张三", "age": 25, "is_student": true}

# JSON字符串转Python对象
python_obj = json.loads(json_str)
print(python_obj["name"])  # 输出: 张三

# 读写JSON文件
with open('data.json', 'w', encoding='utf-8') as f:
    json.dump(data, f, ensure_ascii=False)

with open('data.json', 'r', encoding='utf-8') as f:
    loaded_data = json.load(f)

import csv

# 写入CSV文件
data = [
    ['姓名', '年龄', '城市'],
    ['张三', '25', '北京'],
    ['李四', '30', '上海']
]

with open('data.csv', 'w', newline='', encoding='utf-8') as f:
    writer = csv.writer(f)
    writer.writerows(data)

# 读取CSV文件
with open('data.csv', 'r', encoding='utf-8') as f:
    reader = csv.reader(f)
    for row in reader:
        print(row)

# 使用DictReader更友好
with open('data.csv', 'r', encoding='utf-8') as f:
    reader = csv.DictReader(f)
    for row in reader:
        print(row['姓名'], row['年龄'])

import xml.etree.ElementTree as ET

# 创建XML
root = ET.Element("catalog")
book1 = ET.SubElement(root, "book", id="1")
ET.SubElement(book1, "title").text = "Python编程"
ET.SubElement(book1, "author").text = "张三"
ET.SubElement(book1, "price").text = "59.00"

tree = ET.ElementTree(root)
tree.write("books.xml", encoding="utf-8", xml_declaration=True)

# 解析XML
tree = ET.parse("books.xml")
root = tree.getroot()

for book in root.findall("book"):
    title = book.find("title").text
    price = book.find("price").text
    print(f"书名: {title}, 价格: {price}")

import yaml

# 写入YAML文件
data = {
    'name': '张三',
    'age': 25,
    'skills': ['Python', 'Java', 'SQL'],
    'address': {
        'city': '北京',
        'postcode': '100000'
    }
}

with open('data.yaml', 'w', encoding='utf-8') as f:
    yaml.dump(data, f, allow_unicode=True)

# 读取YAML文件
with open('data.yaml', 'r', encoding='utf-8') as f:
    loaded_data = yaml.safe_load(f)
    print(loaded_data['name'])

import pickle

# 序列化对象
data = {'a': [1, 2, 3], 'b': ('string', '另一个字符串'), 'c': None}
with open('data.pkl', 'wb') as f:
    pickle.dump(data, f)

# 反序列化
with open('data.pkl', 'rb') as f:
    loaded_data = pickle.load(f)
    print(loaded_data)

import pandas as pd
import pyarrow.parquet as pq

# 创建示例DataFrame
df = pd.DataFrame({
    'name': ['张三', '李四', '王五'],
    'age': [25, 30, 35],
    'city': ['北京', '上海', '广州']
})

# 写入Parquet文件
df.to_parquet('data.parquet')

# 读取Parquet文件
df_read = pd.read_parquet('data.parquet')
print(df_read.head())

syntax = "proto3";

message Person {
    string name = 1;
    int32 age = 2;
    repeated string emails = 3;
}

protoc --python_out=. person.proto

import person_pb2

# 创建并序列化
person = person_pb2.Person()
person.name = "张三"
person.age = 25
person.emails.append("zhangsan@example.com")

serialized = person.SerializeToString()

# 反序列化
new_person = person_pb2.Person()
new_person.ParseFromString(serialized)
print(new_person.name)

import json
import csv

with open('data.json', 'r', encoding='utf-8') as f:
    data = json.load(f)

# 假设data是列表形式的JSON
with open('output.csv', 'w', newline='', encoding='utf-8') as f:
    writer = csv.DictWriter(f, fieldnames=data[0].keys())
    writer.writeheader()
    writer.writerows(data)

import csv
import json

with open('data.csv', 'r', encoding='utf-8') as f:
    reader = csv.DictReader(f)
    data = [row for row in reader]

with open('output.json', 'w', encoding='utf-8') as f:
    json.dump(data, f, ensure_ascii=False, indent=2)

import pandas as pd

# 读取各种格式
df_json = pd.read_json('data.json')
df_csv = pd.read_csv('data.csv')
df_parquet = pd.read_parquet('data.parquet')

# 写入各种格式
df.to_json('output.json', orient='records', force_ascii=False)
df.to_csv('output.csv', index=False)
df.to_parquet('output.parquet')