代理配置:
proxy_url = "http://{}:{}@{}:{}/".format(proxyUser, proxyPass, proxyHost, proxyPort)
proxies = {'https': proxy_url, 'http': proxy_url}
1. requests
response = requests.get(url, proxies=proxies)
2. pdfkit
pdfkit.from_url(url, "filename.pdf", options={"bypass-proxy-for": proxy_url})
3. zeep
client = Client(BI_WDSL_URL)
client.transport.session.proxies = proxies
4. selenium + chrome
def create_proxy_auth_extension(proxy_host, proxy_port,
proxy_username, proxy_password,
scheme='http', plugin_path=None):
if plugin_path is None:
# default_plugin_path为任意可访问路径
plugin_path = r'{}/{}_{}@http-pro.abuyun.com_9010.zip'.format(default_plugin_path,
proxy_username, proxy_password)
manifest_json = """
{
"version": "1.0.0",
"manifest_version": 2,
"name": "Abuyun 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
def get_driver():
app.logger.info("open the brower")
options = webdriver.ChromeOptions()
options.add_argument("start-maximized")
options.add_argument("enable-automation")
options.add_argument("--no-sandbox")
options.add_argument("--disable-infobars")
options.add_argument("--disable-dev-shm-usage")
options.add_argument("--disable-browser-side-navigation")
options.add_argument("--disable-gpu")
if proxyUsed:
proxy_auth_plugin_path = create_proxy_auth_extension(
proxy_host=proxyHost,
proxy_port=proxyPort,
proxy_username=proxyUser,
proxy_password=proxyPass)
options.add_extension(proxy_auth_plugin_path)
else:
options.add_argument("--headless")
driver = webdriver.Chrome(chrome_options=options)
return driver
Ps. 代理有权限验证时Chrome必须有图像化界面