python中httpx库的详细使用方法及案例详解

import httpx

# 发送 GET 请求
response = httpx.get('https://httpbin.org/get')
print(response.status_code)  # 状态码
print(response.text)         # 响应内容

# 发送 POST 请求
data = {'key': 'value'}
response = httpx.post('https://httpbin.org/post', json=data)
print(response.json())  # 解析 JSON 响应

headers = {'User-Agent': 'my-app/1.0.0'}
response = httpx.get('https://httpbin.org/headers', headers=headers)
print(response.json())

params = {'key1': 'value1', 'key2': 'value2'}
response = httpx.get('https://httpbin.org/get', params=params)
print(response.json())

try:
    response = httpx.get('https://httpbin.org/delay/5', timeout=2.0)
except httpx.TimeoutException:
    print("请求超时")

import httpx
import asyncio

async def fetch(url):
    async with httpx.AsyncClient() as client:
        response = await client.get(url)
        print(response.text)

asyncio.run(fetch('https://httpbin.org/get'))

async def post_data(url, data):
    async with httpx.AsyncClient() as client:
        response = await client.post(url, json=data)
        print(response.json())

asyncio.run(post_data('https://httpbin.org/post', {'key': 'value'}))

async def fetch_multiple(urls):
    async with httpx.AsyncClient() as client:
        tasks = [client.get(url) for url in urls]
        responses = await asyncio.gather(*tasks)
        for response in responses:
            print(response.text)

urls = ['https://httpbin.org/get', 'https://httpbin.org/ip']
asyncio.run(fetch_multiple(urls))

# 启用 HTTP/2
client = httpx.Client(http2=True)
response = client.get('https://httpbin.org/get')
print(response.http_version)  # 输出协议版本

files = {'file': open('example.txt', 'rb')}
response = httpx.post('https://httpbin.org/post', files=files)
print(response.json())

# 流式上传
def generate_data():
    yield b"part1"
    yield b"part2"

response = httpx.post('https://httpbin.org/post', data=generate_data())
print(response.json())

# 流式下载
with httpx.stream('GET', 'https://httpbin.org/stream/10') as response:
    for chunk in response.iter_bytes():
        print(chunk)

try:
    response = httpx.get('https://nonexistent-domain.com')
except httpx.NetworkError:
    print("网络错误")

response = httpx.get('https://httpbin.org/status/404')
if response.status_code == 404:
    print("页面未找到")

client = httpx.Client(timeout=10.0)
response = client.get('https://httpbin.org/get')
print(response.text)

proxies = {
    "http://": "http://proxy.example.com:8080",
    "https://": "http://proxy.example.com:8080",
}
client = httpx.Client(proxies=proxies)
response = client.get('https://httpbin.org/get')
print(response.text)

client = httpx.Client(base_url='https://httpbin.org')
response = client.get('/get')
print(response.text)

import httpx
from bs4 import BeautifulSoup

# 抓取网页
response = httpx.get('https://example.com')
html = response.text

# 解析网页
soup = BeautifulSoup(html, 'lxml')
title = soup.find('title').text
print("网页标题:", title)

import httpx
from bs4 import BeautifulSoup

# 抓取网页
url = 'https://example.com'
response = httpx.get(url)
html = response.text

# 解析网页
soup = BeautifulSoup(html, 'lxml')

# 提取标题
title = soup.find('title').text
print("网页标题:", title)

# 提取所有链接
links = soup.find_all('a', href=True)
for link in links:
    href = link['href']
    text = link.text
    print(f"链接文本: {text}, 链接地址: {href}")