Python编程：HTTP进阶编程

HTTP编程不仅仅是发送简单的GET/POST请求，还涉及性能优化、安全实践、高级协议特性等。

1. 连接管理与性能优化

连接池管理

import requests
from requests.adapters import HTTPAdapter
from urllib3.util.retry import Retry

# 创建自定义会话
session = requests.Session()

# 配置重试策略
retry_strategy = Retry(
    total=3,
    backoff_factor=1,
    status_forcelist=[408, 429, 500, 502, 503, 504]
)

# 配置适配器
adapter = HTTPAdapter(
    max_retries=retry_strategy,
    pool_connections=10,  # 连接池大小
    pool_maxsize=10
)

# 挂载适配器
session.mount("http://", adapter)
session.mount("https://", adapter)

异步HTTP请求

import aiohttp
import asyncio

async def fetch(session, url):
    async with session.get(url) as response:
        return await response.text()

async def main():
    async with aiohttp.ClientSession() as session:
        html = await fetch(session, 'http://example.com')
        print(html)

asyncio.run(main())

2. 安全实践

HTTPS证书验证

# 严格证书验证
response = requests.get('https://example.com', verify=True)

# 自定义CA包
response = requests.get('https://example.com', verify='/path/to/cacert.pem')

# 证书双向验证
response = requests.get(
    'https://example.com',
    cert=('/path/client.cert', '/path/client.key'),
    verify='/path/to/cacert.pem'
)

安全头部处理

# 设置安全头部
headers = {
    'Content-Security-Policy': "default-src 'self'",
    'X-Content-Type-Options': 'nosniff',
    'X-Frame-Options': 'DENY',
    'Strict-Transport-Security': 'max-age=63072000; includeSubDomains; preload'
}

3. 高级协议特性

HTTP/2支持

import httpx

# 使用支持HTTP/2的客户端
with httpx.Client(http2=True) as client:
    response = client.get('https://http2.pro/api/v1')
    print(response.http_version)  # 输出: "HTTP/2"

WebSocket通信

import websockets
import asyncio

async def websocket_client():
    async with websockets.connect('ws://example.com/ws') as websocket:
        await websocket.send("Hello Server!")
        response = await websocket.recv()
        print(f"Received: {response}")

asyncio.get_event_loop().run_until_complete(websocket_client())

4. 高级请求处理

流式请求与响应

# 流式上传大文件
def generate_large_file():
    for i in range(1000):
        yield f"data chunk {i}\n".encode()

requests.post('http://example.com/upload', data=generate_large_file())

# 流式下载
response = requests.get('http://example.com/large_file', stream=True)
for chunk in response.iter_content(chunk_size=8192):
    process_chunk(chunk)

多部分表单高级用法

# 复杂多部分表单
files = {
    'file': ('report.xls', open('report.xls', 'rb'), 'application/vnd.ms-excel'),
    'metadata': ('metadata.json', json.dumps({'author': 'John'}), 'application/json')
}

requests.post('http://example.com/upload', files=files)

5. 监控与调试

请求追踪

# 启用调试日志
import logging
import http.client

http.client.HTTPConnection.debuglevel = 1
logging.basicConfig()
logging.getLogger().setLevel(logging.DEBUG)
requests_log = logging.getLogger("requests.packages.urllib3")
requests_log.setLevel(logging.DEBUG)
requests_log.propagate = True

requests.get('https://example.com')

性能分析

import time
from pyinstrument import Profiler

profiler = Profiler()
profiler.start()

# 执行HTTP请求
response = requests.get('https://example.com')

profiler.stop()
print(profiler.output_text(unicode=True, color=True))

6. 协议扩展

GRPC集成

import grpc
import my_proto_pb2
import my_proto_pb2_grpc

channel = grpc.insecure_channel('localhost:50051')
stub = my_proto_pb2_grpc.MyServiceStub(channel)
response = stub.MyMethod(my_proto_pb2.MyRequest(name='value'))

GraphQL请求

query = """
{
  user(id: "1") {
    name
    email
  }
}
"""

response = requests.post(
    'https://api.example.com/graphql',
    json={'query': query}
)

7. 测试与Mock

请求Mock测试

from unittest.mock import patch

def test_http_call():
    with patch('requests.get') as mock_get:
        mock_get.return_value.status_code = 200
        mock_get.return_value.json.return_value = {'key': 'value'}
        
        response = requests.get('http://example.com/api')
        assert response.status_code == 200
        assert response.json()['key'] == 'value'

使用responses库

import responses

@responses.activate
def test_my_api():
    responses.add(
        responses.GET,
        'http://example.com/api',
        json={'error': 'not found'},
        status=404
    )
    
    response = requests.get('http://example.com/api')
    assert response.status_code == 404
    assert response.json()['error'] == 'not found'

实践总结

1. 连接管理：使用会话和连接池提高性能

2. 错误处理：实现健壮的重试机制

3. 安全优先：强制HTTPS、验证证书、设置安全头部

4. 协议支持：根据需求选择HTTP/1.1、HTTP/2或WebSocket

5. 资源优化：对大文件使用流式处理

6. 可观测性：添加日志和监控

7. 测试覆盖：使用Mock进行HTTP调用测试