python爬虫Socks代理

requests请求网页(无用户认证)

session = requests.session()
session.proxies = {'http': 'socks5://127.0.0.1:9050',
                   'https': 'socks5://127.0.0.1:9050'}
resp = session.get('https://api.github.com', auth=('user', 'pass'))
print(resp.status_code)

requests请求网页(有用户认证)

http/https网页均可适用
运行环境要求:requests >= 2.10.0
socks支持是requests的额外特性,需要安装才能使用: pip install requests[socks]

import requests

# 要访问的目标网页
page_url = "http://dev.kdlapi.com/testproxy"

# 代理服务器 提示:生成api链接时代理类型请勾选socks4/socks5
proxy = "59.38.241.25:23916"

# 用户名和密码(私密代理/独享代理)
username = "myusername"
password = "mypassword"

proxies = {
    'http': 'socks5://%s:%s@%s' % (username, password, proxy),
    'https': 'socks5://%s:%s@%s' % (username, password, proxy),
    # 提示:如果希望在代理服务器上进行dns解析,把socks5替换成socks5h
}

headers = {
    "Accept-Encoding": "gzip",  # 使用gzip压缩传输数据让访问更快
}


r = requests.get(page_url, proxies=proxies, headers=headers)

print(r.status_code)  # 获取Response的返回码

if r.status_code == 200:
    print(r.text)  # 获取页面内容

selenium请求网页(无用户认证)

运行环境要求selenium + chrome + chromedriver
socks5代理网页均可适用
请先下载chromedriver并将chromedriver添加到环境变量中

from selenium import webdriver

# 代理服务器
proxy_ip_port = '42.49.11.109:21080'
proxy = 'socks5://' + proxy_ip_port

# 目标网页
page_url = "https://dev.kuaidaili.com/testproxy"

co = webdriver.ChromeOptions()
co.add_argument('--proxy-server=%s' % proxy) # 设置代理
co.add_argument('--headless')  # 无窗口模式, 可选

# 启动chrome
driver = webdriver.Chrome(chrome_options=co)

# 抓取网页
driver.get(page_url)

# 输出网页内容
print(driver.page_source)

# 退出chrome
driver.quit()

selenium请求网页(有用户认证)

运行环境要求selenium + chrome + chromedriver
socks5代理网页均可适用
请先下载chromedriver并将chromedriver添加到环境变量中

from selenium import webdriver

proxyauth_plugin_path = create_proxyauth_extension(
    proxy_host="42.49.11.109",  # 代理服务器ip
    proxy_port=21080,           # 代理服务器端口
    proxy_username="yourusername",    # 用户名
    proxy_password="yourpassword",  # 密码
    scheme='socks5',  # socks5协议
)

# 目标网页
page_url = "https://dev.kuaidaili.com/testproxy"

co = webdriver.ChromeOptions()
co.add_argument("--start-maximized")  # 最大化窗口, 不加可能报错
co.add_extension(proxyauth_plugin_path) # 添加扩展

# 启动chrome, 抓取网页
driver = webdriver.Chrome(chrome_options=co)
driver.get("https://dev.kuaidaili.com/testproxy")

# 输出网页内容
print(driver.page_source)

# 自动生成扩展的函数
def create_proxyauth_extension(proxy_host, proxy_port,
                               proxy_username, proxy_password,
                               scheme='http', plugin_path=None):
    import string
    import zipfile

    if plugin_path is None:
        plugin_path = 'vimm_chrome_proxyauth_plugin.zip'

    manifest_json = """
    {
        "version": "1.0.0",
        "manifest_version": 2,
        "name": "Chrome Proxy",
        "permissions": [
            "proxy",
            "tabs",   
            "unlimitedStorage",
            "storage",
            "<all_urls>",
            "webRequest",
            "webRequestBlocking"
        ],
        "background": {
            "scripts": ["background.js"]
        },
        "minimum_chrome_version":"22.0.0"
    }
    """

    background_js = string.Template(
    """
    var config = {
            mode: "fixed_servers",
            rules: {
              singleProxy: {
                scheme: "${scheme}",
                host: "${host}",
                port: parseInt(${port})
              },
              bypassList: ["foobar.com"]
            }
          };

    chrome.proxy.settings.set({value: config, scope: "regular"}, function() {});

    function callbackFn(details) {
        return {
            authCredentials: {
                username: "${username}",
                password: "${password}"
            }
        };
    }

    chrome.webRequest.onAuthRequired.addListener(
                callbackFn,
                {urls: ["<all_urls>"]},
                ['blocking']
    );
    """
    ).substitute(
        host=proxy_host,
        port=proxy_port,
        username=proxy_username,
        password=proxy_password,
        scheme=scheme,
    )
    with zipfile.ZipFile(plugin_path, 'w') as zp:
        zp.writestr("manifest.json", manifest_json)
        zp.writestr("background.js", background_js)

    return plugin_path

本文转载出处https://www.kuaidaili.com/doc/dev/sdk_socks/

原创文章 6 获赞 19 访问量 5071

猜你喜欢

转载自blog.csdn.net/weixin_43078957/article/details/97922946