Python httpx库终极指南实战案例

# 基础安装
pip install httpx
# 完整功能安装（HTTP/2 + 代理支持）
pip install "httpx[http2,socks]"

import httpx
# 同步客户端
with httpx.Client() as client:
    # RESTful 全方法支持
    client.get(url, params={...})
    client.post(url, json={...})
    client.put(url, data={...})
    client.patch(url, files={...})
    client.delete(url)
# 异步客户端
async with httpx.AsyncClient() as client:
    await client.get(...)

response = httpx.get("https://api.example.com/data")
# 常用属性和方法
print(response.status_code)     # HTTP 状态码
print(response.headers)         # 响应头
print(response.text)            # 文本内容
print(response.json())          # JSON 解码
print(response.content)         # 二进制内容
print(response.stream())        # 流式访问

# 启用 HTTP/2
client = httpx.Client(http2=True)
response = client.get("https://http2.example.com")
print(response.http_version)  # 输出: "HTTP/2"

# 优化连接参数
custom_client = httpx.Client(
    limits=httpx.Limits(
        max_keepalive_connections=20,  # 长连接上限
        max_connections=100,           # 总连接数
        keepalive_expiry=30            # 空闲时间(s)
    ),
    timeout=10.0                       # 默认超时
)

from tenacity import retry, stop_after_attempt, wait_exponential
@retry(stop=stop_after_attempt(3), wait=wait_exponential())
def reliable_request():
    response = httpx.get("https://unstable-api.example.com")
    response.raise_for_status()
    return response

# OpenTelemetry 集成
from opentelemetry.instrumentation.httpx import HTTPXClientInstrumentor
HTTPXClientInstrumentor().instrument()
async def tracked_request():
    async with httpx.AsyncClient() as client:
        await client.get("https://api.example.com")  # 自动生成追踪 Span

# 证书配置
secure_client = httpx.Client(
    verify="/path/to/ca-bundle.pem",  # 自定义 CA
    cert=("/path/to/client-cert.pem", "/path/to/client-key.pem")
)
# 敏感信息处理
import os
client = httpx.Client(
    headers={"Authorization": f"Bearer {os.environ['API_TOKEN']}"}
)

# SOCKS 代理
from httpx_socks import AsyncProxyTransport
proxy_transport = AsyncProxyTransport.from_url("socks5://user:pass@host:port")
async with httpx.AsyncClient(transport=proxy_transport) as client:
    await client.get("https://api.example.com")

# 基准测试结果（1000 请求）
| 场景          | requests (s) | httpx 同步 (s) | httpx 异步 (s) |
|---------------|--------------|-----------------|-----------------|
| 短连接 HTTP/1 | 12.3         | 11.8 (+4%)      | 2.1 (+83%)      |
| 长连接 HTTP/2 | N/A          | 9.5             | 1.7             |

import httpx
import asyncio
async def fetch(url: str, client: httpx.AsyncClient):
    response = await client.get(url)
    return response.text[:100]  # 截取部分内容
async def main():
    urls = [f"https://httpbin.org/get?q={i}" for i in range(10)]
    async with httpx.AsyncClient(timeout=10.0) as client:
        tasks = [fetch(url, client) for url in urls]
        results = await asyncio.gather(*tasks)
    for url, result in zip(urls, results):
        print(f"{url}: {result}")
asyncio.run(main())

from httpx import OAuth2, AsyncClient
async def oauth2_flow():
    auth = OAuth2(
        client_id="CLIENT_ID",
        client_secret="SECRET",
        token_endpoint="https://auth.example.com/oauth2/token",
        grant_type="client_credentials"
    )
    async with AsyncClient(auth=auth) as client:
        # 自动处理 Token 获取和刷新
        response = await client.get("https://api.example.com/protected")
        return response.json()

import httpx
from tqdm import tqdm
def chunked_upload(url: str, file_path: str, chunk_size: int = 1024*1024):
    with open(file_path, "rb") as f:
        file_size = f.seek(0, 2)
        f.seek(0)
        with tqdm(total=file_size, unit="B", unit_scale=True) as pbar:
            with httpx.Client(timeout=None) as client:  # 禁用超时
                while True:
                    chunk = f.read(chunk_size)
                    if not chunk:
                        break
                    response = client.post(
                        url,
                        files={"file": chunk},
                        headers={"Content-Range": f"bytes {f.tell()-len(chunk)}-{f.tell()-1}/{file_size}"}
                    )
                    pbar.update(len(chunk))
                return response.status_code

# 原 Requests 代码
import requests
resp = requests.get(
    "https://api.example.com/data",
    params={"page": 2},
    headers={"X-API-Key": "123"}
)
# 等效 httpx 代码
import httpx
resp = httpx.get(
    "https://api.example.com/data",
    params={"page": 2},
    headers={"X-API-Key": "123"}
)

# Requests
requests.get(url, timeout=(3.05, 27))
# httpx
httpx.get(url, timeout=30.0)  # 统一超时控制

# Requests
with requests.Session() as s:
    s.get(url)
# httpx
with httpx.Client() as client:
    client.get(url)

import logging
import httpx
# 配置详细日志记录
logging.basicConfig(level=logging.DEBUG)
# 自定义日志格式
httpx_logger = logging.getLogger("httpx")
httpx_logger.setLevel(logging.DEBUG)
# 示例请求
client = httpx.Client(event_hooks={
    "request": [lambda req: print(f">>> 发送请求: {req.method} {req.url}")],
    "response": [lambda res: print(f"<<< 收到响应: {res.status_code}")],
})
client.get("https://httpbin.org/get")

try:
    response = httpx.get(
        "https://example.com",
        timeout=3.0,
        follow_redirects=True  # 自动处理重定向
    )
    response.raise_for_status()
except httpx.HTTPStatusError as e:
    print(f"HTTP 错误: {e.response.status_code}")
    print(f"响应内容: {e.response.text}")
except httpx.ConnectTimeout:
    print("连接超时，请检查网络或增加超时时间")
except httpx.ReadTimeout:
    print("服务器响应超时")
except httpx.TooManyRedirects:
    print("重定向次数过多，请检查 URL")
except httpx.RequestError as e:
    print(f"请求失败: {str(e)}")

from httpx import Auth, AsyncClient
import time
class JWTAuth(Auth):
    def __init__(self, token_url, client_id, client_secret):
        self.token_url = token_url
        self.client_id = client_id
        self.client_secret = client_secret
        self.access_token = None
        self.expires_at = 0
    async def async_auth_flow(self, request):
        if time.time() > self.expires_at - 30:  # 提前30秒刷新
            await self._refresh_token()
        request.headers["Authorization"] = f"Bearer {self.access_token}"
        yield request
    async def _refresh_token(self):
        async with AsyncClient() as client:
            response = await client.post(
                self.token_url,
                data={
                    "grant_type": "client_credentials",
                    "client_id": self.client_id,
                    "client_secret": self.client_secret
                }
            )
            token_data = response.json()
            self.access_token = token_data["access_token"]
            self.expires_at = time.time() + token_data["expires_in"]
# 使用示例
auth = JWTAuth(
    token_url="https://auth.example.com/token",
    client_id="your-client-id",
    client_secret="your-secret"
)
async with AsyncClient(auth=auth) as client:
    response = await client.get("https://api.example.com/protected")

# 需要安装 httpx-auth
from httpx_auth import AwsAuth
auth = AwsAuth(
    aws_access_key_id="AKIA...",
    aws_secret_access_key="...",
    aws_session_token="...",  # 可选
    region="us-west-2",
    service="execute-api"
)
response = httpx.get(
    "https://api.example.com/aws-resource",
    auth=auth
)

import httpx
import os
from tqdm import tqdm
def upload_large_file(url, file_path, chunk_size=1024*1024):
    file_size = os.path.getsize(file_path)
    headers = {
        "Content-Length": str(file_size),
        "Content-Type": "application/octet-stream"
    }
    with open(file_path, "rb") as f, \
         tqdm(total=file_size, unit="B", unit_scale=True) as pbar:
        def generate():
            while True:
                chunk = f.read(chunk_size)
                if not chunk:
                    break
                pbar.update(len(chunk))
                yield chunk
        with httpx.Client(timeout=None) as client:
            response = client.post(
                url,
                content=generate(),
                headers=headers
            )
            return response.status_code
# 使用示例
upload_large_file(
    "https://httpbin.org/post",
    "large_file.zip",
    chunk_size=5*1024*1024  # 5MB 分块
)

async def process_streaming_response():
    async with httpx.AsyncClient() as client:
        async with client.stream("GET", "https://stream.example.com/live-data") as response:
            async for chunk in response.aiter_bytes():
                # 实时处理数据块
                print(f"收到 {len(chunk)} 字节数据")
                process_data(chunk)  # 自定义处理函数

from httpx import AsyncClient, Request, Response
import httpx
class RetryMiddleware:
    def __init__(self, max_retries=3):
        self.max_retries = max_retries
    async def __call__(self, request: Request, get_response):
        for attempt in range(self.max_retries + 1):
            try:
                response = await get_response(request)
                if response.status_code >= 500:
                    raise httpx.HTTPStatusError("Server error", request=request, response=response)
                return response
            except (httpx.RequestError, httpx.HTTPStatusError) as e:
                if attempt == self.max_retries:
                    raise
                await asyncio.sleep(2 ** attempt)
        return response  # 永远不会执行此处
# 创建自定义客户端
client = AsyncClient(
    transport=httpx.AsyncHTTPTransport(
        retries=3,
        middleware=[RetryMiddleware(max_retries=3)]
)

def add_custom_header_middleware():
    async def middleware(request: Request, get_response):
        request.headers["X-Request-ID"] = str(uuid.uuid4())
        response = await get_response(request)
        return response
    return middleware
client = AsyncClient(
    event_hooks={
        "request": [add_custom_header_middleware()]
    }
)

# 使用 cProfile 分析请求性能
import cProfile
import httpx
def profile_requests():
    with httpx.Client() as client:
        for _ in range(100):
            client.get("https://httpbin.org/get")
if __name__ == "__main__":
    cProfile.run("profile_requests()", sort="cumtime")

optimized_client = httpx.AsyncClient(
    limits=httpx.Limits(
        max_connections=200,           # 最大连接数
        max_keepalive_connections=50,  # 保持活跃的连接数
        keepalive_expiry=60            # 空闲连接存活时间
    ),
    timeout=httpx.Timeout(
        connect=5.0,                   # 连接超时
        read=20.0,                     # 读取超时
        pool=3.0                       # 连接池等待超时
    ),
    http2=True                        # 启用 HTTP/2
)

from fastapi import FastAPI, Depends
from httpx import AsyncClient
app = FastAPI()
async def get_async_client():
    async with AsyncClient(base_url="https://api.example.com") as client:
        yield client
@app.get("/proxy-data")
async def proxy_data(client: AsyncClient = Depends(get_async_client)):
    response = await client.get("/remote-data")
    return response.json()

from celery import Celery
from httpx import AsyncClient
app = Celery("tasks", broker="pyamqp://guest@localhost//")
@app.task
def sync_http_request():
    with httpx.Client() as client:
        return client.get("https://api.example.com/data").json()
@app.task
async def async_http_request():
    async with AsyncClient() as client:
        response = await client.get("https://api.example.com/data")
        return response.json()

# 使用指纹验证证书
client = httpx.Client(
    verify=True,
    limits=httpx.Limits(max_keepalive_connections=5),
    cert=("/path/client.crt", "/path/client.key"),
    # 证书指纹校验
    transport=httpx.HTTPTransport(
        verify=httpx.SSLConfig(
            cert_reqs="CERT_REQUIRED",
            ca_certs="/path/ca.pem",
            fingerprint="sha256:..."
        )
    )
)

from pydantic import SecretStr
class SecureClient:
    def __init__(self, api_key: SecretStr):
        self.client = httpx.Client(
            headers={"Authorization": f"Bearer {api_key.get_secret_value()}"},
            timeout=30.0
        )
    def safe_request(self):
        try:
            return self.client.get("https://secure-api.example.com")
        except httpx.RequestError:
            # 记录错误但不暴露密钥
            log.error("API请求失败")
# 使用
secure_client = SecureClient(api_key=SecretStr("s3cr3t"))

import httpx
import asyncio
from bs4 import BeautifulSoup
from urllib.parse import urljoin
class AsyncCrawler:
    def __init__(self, base_url, concurrency=10):
        self.base_url = base_url
        self.seen_urls = set()
        self.semaphore = asyncio.Semaphore(concurrency)
        self.client = httpx.AsyncClient(timeout=10.0)
    async def crawl(self, path="/"):
        url = urljoin(self.base_url, path)
        if url in self.seen_urls:
            return
        self.seen_urls.add(url)
        async with self.semaphore:
            try:
                response = await self.client.get(url)
                if response.status_code == 200:
                    await self.parse(response)
            except httpx.RequestError as e:
                print(f"请求失败: {url} - {str(e)}")
    async def parse(self, response):
        soup = BeautifulSoup(response.text, "html.parser")
        # 提取数据
        print(f"解析页面: {response.url}")
        # 提取链接继续爬取
        for link in soup.find_all("a", href=True):
            await self.crawl(link["href"])
    async def run(self):
        await self.crawl()
        await self.client.aclose()
# 启动爬虫
async def main():
    crawler = AsyncCrawler("https://example.com")
    await crawler.run()
asyncio.run(main())