小白学爬虫-设置Selenium+Chrome代理

微博登录限制了错误次数···加上Cookie大批账号被封需要从Cookie池中 剔除被封的账号··· 需要使用代理··· 无赖百度了大半天都是特么的啥玩意儿？？？结果换成了 Google手到擒来 分分钟解决（那么问题来了？百度除了卖假药还会干啥？）

Selenium+Chrome认证代理不能通过options处理。只能换个方法使用扩展解决

原文地址：https://stackoverflow.com/questions/29983106/how-can-i-set-proxy-with-authentication-in-selenium-chrome-web-driver-using-pyth#answer-30953780 （Stack Overflow 这是个好地方啊）

# -*- coding: utf-8 -*-
# @Time    : 2017/11/15 9:50
# @Author  : 哎哟卧槽
# @Site    :
# @File    : pubilc.py
# @Software: PyCharm

import string
import zipfile

def create_proxyauth_extension(proxy_host, proxy_port,
                               proxy_username, proxy_password,
                               scheme='http', plugin_path=None):
    """代理认证插件

    args:
        proxy_host (str): 你的代理地址或者域名（str类型）
        proxy_port (int): 代理端口号（int类型）
        proxy_username (str):用户名（字符串）
        proxy_password (str): 密码 （字符串）
    kwargs:
        scheme (str): 代理方式 默认http
        plugin_path (str): 扩展的绝对路径

    return str -> plugin_path
    """

    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

使用方法：

from selenium import webdriver
from common.pubilc import create_proxyauth_extension  

proxyauth_plugin_path = create_proxyauth_extension(
    proxy_host="XXXXX.com",
    proxy_port=9020,
    proxy_username="XXXXXXX",
    proxy_password="XXXXXXX"
)  

co = webdriver.ChromeOptions()
# co.add_argument("--start-maximized")
co.add_extension(proxyauth_plugin_path)  

driver = webdriver.Chrome(executable_path="C:\chromedriver.exe", chrome_options=co)
driver.get("http://ip138.com/")
print(driver.page_source)  

无认证代理：

options = webdriver.ChromeOptions()
options.add_argument('--proxy-server=http://ip:port')
driver = webdriver.Chrome(executable_path="C:\chromedriver.exe", chrome_options=0ptions)
driver.get("http://ip138.com/")
print(driver.page_source)