天天看点

Python:Selenium + Chrome添加认证代理

添加无认证代理,以参数形式添加

chromeOptions = webdriver.ChromeOptions()
chromeOptions.add_argument('--proxy-server=http://ip:port')  
driver = webdriver.Chrome(chrome_options=chromeOptions)      

添加认证代理,以插件的形式添加

1、新建扩展文件夹 Chrome-proxy-helper添加两个文件

Chrome-proxy-helper/
    background.js
    manifest.json      

内容如下

(1)background.js

var config = {
        mode: "fixed_servers",
        rules: {
          singleProxy: {
            scheme: "http",
            host: "%proxy_host",
            port: parseInt(%proxy_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']
);
      

(2)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"
}
      

2、动态生成插件并使用

# -*- coding: utf-8 -*-

import os
import re
import time
import zipfile
from selenium import webdriver

# Chrome代理模板插件(https://github.com/RobinDev/Selenium-Chrome-HTTP-Private-Proxy)目录
CHROME_PROXY_HELPER_DIR = 'Chrome-proxy-helper'
# 存储自定义Chrome代理扩展文件的目录
CUSTOM_CHROME_PROXY_EXTENSIONS_DIR = 'chrome-proxy-extensions'


def get_chrome_proxy_extension(proxy):
    """
    获取一个Chrome代理扩展,里面配置有指定的代理(带用户名密码认证)
    proxy - 指定的代理,格式: username:password@ip:port
    """
    m = re.compile('([^:]+):([^\@]+)\@([\d\.]+):(\d+)').search(proxy)
    if m:
        # 提取代理的各项参数
        username = m.groups()[0]
        password = m.groups()[1]
        ip = m.groups()[2]
        port = m.groups()[3]

        # 创建一个定制Chrome代理扩展(zip文件)
        if not os.path.exists(CUSTOM_CHROME_PROXY_EXTENSIONS_DIR):
            os.mkdir(CUSTOM_CHROME_PROXY_EXTENSIONS_DIR)
        extension_file_path = os.path.join(CUSTOM_CHROME_PROXY_EXTENSIONS_DIR, '{}.zip'.format(proxy.replace(':', '_')))

        if not os.path.exists(extension_file_path):
            # 扩展文件不存在,创建
            zf = zipfile.ZipFile(extension_file_path, mode='w')
            zf.write(os.path.join(CHROME_PROXY_HELPER_DIR, 'manifest.json'), 'manifest.json')

            # 替换模板中的代理参数
            background_content = open(os.path.join(CHROME_PROXY_HELPER_DIR, 'background.js')).read()
            background_content = background_content.replace('%proxy_host', ip)
            background_content = background_content.replace('%proxy_port', port)
            background_content = background_content.replace('%username', username)
            background_content = background_content.replace('%password', password)
            zf.writestr('background.js', background_content)
            zf.close()

        return extension_file_path
    else:
        raise Exception('Invalid proxy format. Should be username:password@ip:port')


if __name__ == '__main__':
    # 测试
    options = webdriver.ChromeOptions()
    # 添加一个自定义的代理插件(配置特定的代理,含用户名密码认证)
    options.add_extension(get_chrome_proxy_extension(proxy="username:password@ip:port"))
    driver = webdriver.Chrome(options=options)
    # 访问一个IP回显网站,查看代理配置是否生效了
    driver.get('http://httpbin.org/ip')
    print(driver.page_source)
    time.sleep(60)
    driver.close()
    driver.quit()
      

参考:

Selenium + Chrome Diver使用带用户名密码认证的HTTP代理的方法

Selenium Chrome HTTP Private Proxy

How to override basic authentication in selenium2 with Java using chrome driver?