在 Python 中使用 httpx 配置代理

在 Python 中使用 httpx 配置代理

httpx 与代理

httpx 是一个现代的 Python HTTP 库，同时支持同步和异步两种运行模式。它的一大优势是无需额外库即可内置支持 HTTP/2 和 SOCKS 代理。

安装

pip install httpx
# SOCKS 支持：
pip install httpx[socks]
# HTTP/2 支持：
pip install httpx[http2]

同步模式

HTTP 代理

import httpx

proxy = "http://user:pass@proxy_ip:port"
response = httpx.get("https://httpbin.org/ip", proxy=proxy)
print(response.json())

为 HTTP 和 HTTPS 设置不同代理

proxies = {
    "http://": "http://proxy1:port",
    "https://": "http://proxy2:port",
}

with httpx.Client(proxy=proxies) as client:
    response = client.get("https://httpbin.org/ip")
    print(response.json())

SOCKS5 代理

import httpx

proxy = "socks5://user:pass@proxy_ip:port"
with httpx.Client(proxy=proxy) as client:
    response = client.get("https://httpbin.org/ip")
    print(response.json())

异步模式

基础示例

import httpx
import asyncio

async def fetch():
    proxy = "http://user:pass@proxy_ip:port"
    async with httpx.AsyncClient(proxy=proxy) as client:
        response = await client.get("https://httpbin.org/ip")
        print(response.json())

asyncio.run(fetch())

并发请求

import httpx
import asyncio

async def fetch_url(client, url):
    try:
        response = await client.get(url, timeout=10)
        return response.text
    except Exception as e:
        return None

async def main():
    proxy = "http://user:pass@proxy_ip:port"
    urls = [f"https://example.com/page/{i}" for i in range(50)]

    async with httpx.AsyncClient(proxy=proxy) as client:
        tasks = [fetch_url(client, url) for url in urls]
        results = await asyncio.gather(*tasks)
        success = sum(1 for r in results if r)
        print(f"Success: {success}/{len(urls)}")

asyncio.run(main())

经代理的 HTTP/2

httpx 是少数支持 HTTP/2 的 Python 库之一：

import httpx

proxy = "http://user:pass@proxy_ip:port"
with httpx.Client(proxy=proxy, http2=True) as client:
    response = client.get("https://httpbin.org/ip")
    print(f"HTTP version: {response.http_version}")
    print(response.json())

经代理的 HTTP/2 通过 CONNECT 方法实现——代理建立一条 TCP 隧道，再通过该隧道与服务器建立 HTTP/2 连接。

代理轮换

import httpx
import random

PROXIES = [
    "http://user:pass@proxy1:port",
    "http://user:pass@proxy2:port",
    "http://user:pass@proxy3:port",
]

def get_random_proxy():
    return random.choice(PROXIES)

# 同步轮换
for i in range(10):
    proxy = get_random_proxy()
    with httpx.Client(proxy=proxy) as client:
        resp = client.get("https://httpbin.org/ip")
        print(resp.json())

异步轮换

import httpx
import asyncio
import random

PROXIES = [
    "http://user:pass@proxy1:port",
    "http://user:pass@proxy2:port",
    "http://user:pass@proxy3:port",
]

async def fetch_with_rotation(url):
    proxy = random.choice(PROXIES)
    async with httpx.AsyncClient(proxy=proxy) as client:
        try:
            resp = await client.get(url, timeout=10)
            return resp.text
        except Exception:
            return None

async def main():
    urls = ["https://example.com"] * 20
    tasks = [fetch_with_rotation(url) for url in urls]
    results = await asyncio.gather(*tasks)
    print(f"Success: {sum(1 for r in results if r)}")

asyncio.run(main())

客户端配置

超时

timeout = httpx.Timeout(
    connect=5.0,    # 连接代理和服务器
    read=10.0,      # 读取响应
    write=5.0,      # 发送请求
    pool=5.0        # 在连接池中等待
)

client = httpx.Client(proxy=proxy, timeout=timeout)

请求头与 Cookie

headers = {
    "User-Agent": "Mozilla/5.0 ...",
    "Accept-Language": "en-US,en;q=0.9",
}

client = httpx.Client(
    proxy=proxy,
    headers=headers,
    follow_redirects=True,
    max_redirects=10
)

连接池

limits = httpx.Limits(
    max_connections=100,          # 连接总数
    max_keepalive_connections=20  # keep-alive 连接数
)

client = httpx.AsyncClient(proxy=proxy, limits=limits)

错误处理

import httpx

async def safe_fetch(client, url):
    try:
        response = await client.get(url)
        response.raise_for_status()
        return response.text
    except httpx.ProxyError as e:
        print(f"Proxy error: {e}")
    except httpx.ConnectTimeout:
        print("Connection timeout")
    except httpx.ReadTimeout:
        print("Read timeout")
    except httpx.HTTPStatusError as e:
        print(f"HTTP {e.response.status_code}")
    except httpx.RequestError as e:
        print(f"Request error: {e}")
    return None

httpx、requests 与 aiohttp 对比

从 requests 迁移

httpx 的设计目标是成为 requests 的直接替代品，迁移成本极低：

# requests
import requests
resp = requests.get(url, proxies={"https": proxy})

# httpx
import httpx
resp = httpx.get(url, proxy=proxy)

主要区别：httpx 使用 proxy 参数（单数形式）代替 proxies。

结论

对于需要代理功能的新 Python 项目，httpx 是最佳选择。它内置支持 HTTP/2、SOCKS5 以及同步和异步两种模式，是一款通用性很强的工具。兼容 requests 的 API 也让既有项目的迁移变得简单。