直入正题:
我们一般代理有两种:
- ip + 端口 直接使用
- 用到用户名密码才能使用,(某布云)
第一种:
chromedriver = "chromedriver.exe"
chrome_opt = webdriver.ChromeOptions()
chrome_opt.add_argument("--proxy-server=http://111.11.1.111:8080")
dirver = webdriver.Chrome(executable_path=chromedriver, chrome_options=chrome_opt)
第二种:
首先定义一个代理插件
import string
import zipfile
def proxy_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
使用插件:
from selenium import webdriver
proxy_plugin = proxy_extension(
proxy_host="XXXXX.com",
proxy_port=9999,
proxy_username="XXXXXXX",
proxy_password="XXXXXXX"
)
co = webdriver.ChromeOptions()
# co.add_argument("--start-maximized")
co.add_extension(proxy_plugin)
driver = webdriver.Chrome(executable_path="chromedriver.exe", chrome_options=co)
driver.get("http://httpbin.org/ip")
print(driver.page_source)
完!