如何为 Python 配置代理以实现稳定的数据解析

import requests
import os
# Utilizing environment variables prevents credentials from leaking into repositories
# Format: http://login:password@ip:port
PROXY_URL = os.getenv("PROXY_URL", "http://user:pass@51.77.190.247:5959")
proxies = {
    "http": PROXY_URL,
    "https": PROXY_URL
}
try:
    # The timeout parameter is critical to prevent thread lockups
    response = requests.get("https://httpbin.org/ip", proxies=proxies, timeout=10)
    print(f"Outbound connection IP: {response.json().get('origin')}")
except requests.exceptions.RequestException as e:
    print(f"Routing failure: {e}")

pip install requests[socks]
# or
pip install pysocks

import requests
socks_proxy = "socks5h://user:pass@51.77.190.247:9595"
proxies = {
    "http": socks_proxy,
    "https": socks_proxy
}
try:
    response = requests.get("https://httpbin.org/ip", proxies=proxies, timeout=10)
    print(f"Your IP via SOCKS5: {response.json()['origin']}")
except Exception as e:
    print(f"Error: {e}")

pip install curl_cffi

from curl_cffi import requests
# Proxies use the identical format found in standard requests
proxies = {"https": "http://user:pass@51.77.190.247:5959"}
# The impersonate argument generates a valid JA3 fingerprint for Chrome 124
response = requests.get(
    "https://tls.browserleaks.com/json", 
    impersonate="chrome124", 
    proxies=proxies,
    timeout=15
)
# The target server interprets the handshake as a legitimate user
print(response.json())

pip install selenium-wire

# Crucial: import the webdriver explicitly from seleniumwire
from seleniumwire import webdriver
PROXY_HOST = "51.77.190.247"
PROXY_PORT = "5959" # Port for HTTP
PROXY_USER = "auth_user"
PROXY_PASS = "auth_pass"
# Construct the options dictionary
proxy_options = {
    'proxy': {
        'http': f'http://{PROXY_USER}:{PROXY_PASS}@{PROXY_HOST}:{PROXY_PORT}',
        'https': f'http://{PROXY_USER}:{PROXY_PASS}@{PROXY_HOST}:{PROXY_PORT}',
        'no_proxy': 'localhost,127.0.0.1' # Localhost traffic bypasses the tunnel
    }
}
# Initialize the browser instance with custom options
driver = webdriver.Chrome(seleniumwire_options=proxy_options)
print("Browser started, checking IP...")
driver.get("https://httpbin.org/ip")
print(driver.find_element("tag name", "body").text)
driver.quit()

from seleniumwire import webdriver
PROXY_HOST = "51.77.190.247"
PROXY_PORT = "9595" # Ensure this port is designated for SOCKS5
PROXY_USER = "auth_user"
PROXY_PASS = "auth_pass"
proxy_options = {
    'proxy': {
        # The scheme instructs the interceptor to use the SOCKS tunnel
        'http': f'socks5://{PROXY_USER}:{PROXY_PASS}@{PROXY_HOST}:{PROXY_PORT}',
        'https': f'socks5://{PROXY_USER}:{PROXY_PASS}@{PROXY_HOST}:{PROXY_PORT}',
        'no_proxy': 'localhost,127.0.0.1'
    }
}
driver = webdriver.Chrome(seleniumwire_options=proxy_options)
try:
    driver.get("https://httpbin.org/ip")
    print(driver.find_element("tag name", "body").text)
finally:
    driver.quit()

pip install aiohttp-socks

import asyncio
import aiohttp
from aiohttp_socks import ProxyConnector
async def fetch_page(url: str, session: aiohttp.ClientSession):
    try:
        # The proxy parameter is no longer required within the get method
        async with session.get(url, timeout=15) as response:
            return await response.text()
    except Exception as e:
        return f"Failure: {e}"
async def main():
    # Authentication credentials embed directly within the URI schema
    socks_url = "socks5://user:pass@51.77.190.247:9595"
    
    # rdns=True forcefully pushes DNS resolution to the remote node
    # This is MANDATORY for secure routing
    connector = ProxyConnector.from_url(socks_url, rdns=True)
    
    # Assign the connector at the session level
    async with aiohttp.ClientSession(connector=connector) as session:
        urls = ["https://httpbin.org/ip" for _ in range(5)]
        
        # Concurrent execution of coroutines
        tasks = [fetch_page(url, session) for url in urls]
        results = await asyncio.gather(*tasks, return_exceptions=True)
        
        for res in results:
            print(res)
if __name__ == '__main__':
    asyncio.run(main())

export HTTP_PROXY="http://user:pass@51.77.190.247:5959"

import requests
# No proxy arguments need to be passed
# The library finds the system settings automatically
requests.get("https://httpbin.org/ip")