Selenium使用亿牛云爬虫代理的方案
作者:互联网
from selenium import webdriver
import string
import zipfile
# 代理服务器
proxyHost = "t.16yun.cn"
proxyPort = "31111"
# 代理隧道验证信息
proxyUser = "username"
proxyPass = "password"
def create_proxy_auth_extension(proxy_host, proxy_port,
proxy_username, proxy_password,
scheme='http', plugin_path=None):
if plugin_path is None:
plugin_path = r'C:/{}_{}@t.16yun.zip'.format(proxy_username, proxy_password)
manifest_json = """
{
"version": "1.0.0",
"manifest_version": 2,
"name": "16YUN Proxy",
"permissions": [
"proxy",
"tabs",
"unlimitedStorage",
"storage",
"",
"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: [""]},
['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
proxy_auth_plugin_path = create_proxy_auth_extension(
proxy_host=proxyHost,
proxy_port=proxyPort,
proxy_username=proxyUser,
proxy_password=proxyPass)
option = webdriver.ChromeOptions()
option.add_argument("--start-maximized")
option.add_extension(proxy_auth_plugin_path)
driver = webdriver.Chrome(chrome_options=option)
driver.get("http://httpbin.org/ip")
标签:亿牛云,username,plugin,Selenium,爬虫,proxy,path,password,port 来源: https://blog.51cto.com/14201222/2360231