seleniumのchromeブラウザuserAgentとエージェントipの設定
4232 ワード
1.user-agentの設定 option = ChromeOptions()
#
option.add_argument("--headless")
option.add_experimental_option('excludeSwitches', ['enable-automation'])
option.add_experimental_option('useAutomationExtension', False)
# user-agent
option.add_argument('user-agent=ywy')
driver = webdriver.Chrome(options=option)
2.user-agentプールでuser-agentを置き換える pip install fake_useragent
from fake_useragent import UserAgent
headers = {
‘User-Agent’: UserAgent().random,
}
3.エージェントipの設定
3.1ユーザー名パスワード認証のないエージェントへの接続
chromeOptions = webdriver.ChromeOptions()
chromeOptions.add_argument('--proxy-server=http://ip:port')
driver = webdriver.Chrome(chrome_options=chromeOptions)
3.2ユーザー名とパスワードの接続
from selenium import webdriver
def create_proxyauth_extension(proxy_host, proxy_port,
proxy_username, proxy_password,
scheme='http', plugin_path=None):
"""Proxy Auth Extension
args:
proxy_host (str): domain or ip address, ie proxy.domain.com
proxy_port (int): port
proxy_username (str): auth username
proxy_password (str): auth password
kwargs:
scheme (str): proxy scheme, default http
plugin_path (str): absolute path of the extension
return str -> plugin_path
"""
import string
import zipfile
if plugin_path is None:
plugin_path = 'd:/webdriver/vimm_chrome_proxyauth_plugin.zip'
manifest_json = """
{
"version": "1.0.0",
"manifest_version": 2,
"name": "Chrome 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
proxyauth_plugin_path = create_proxyauth_extension(
proxy_host="proxy.crawlera.com",
proxy_port=8010,
proxy_username="username",
proxy_password="password"
)
co = webdriver.ChromeOptions()
co.add_argument("--start-maximized")
co.add_extension(proxyauth_plugin_path)
driver = webdriver.Chrome(chrome_options=co)
driver.get("http://www.amazon.com/")
4.Selenium chrome構成画像をロードしない prefs = {"profile.managed_default_content_settings.images":2}
chrome_options.add_experimental_option("prefs",prefs)
option = ChromeOptions()
#
option.add_argument("--headless")
option.add_experimental_option('excludeSwitches', ['enable-automation'])
option.add_experimental_option('useAutomationExtension', False)
# user-agent
option.add_argument('user-agent=ywy')
driver = webdriver.Chrome(options=option)
pip install fake_useragent
from fake_useragent import UserAgent
headers = {
‘User-Agent’: UserAgent().random,
}
3.エージェントipの設定
3.1ユーザー名パスワード認証のないエージェントへの接続
chromeOptions = webdriver.ChromeOptions()
chromeOptions.add_argument('--proxy-server=http://ip:port')
driver = webdriver.Chrome(chrome_options=chromeOptions)
3.2ユーザー名とパスワードの接続
from selenium import webdriver
def create_proxyauth_extension(proxy_host, proxy_port,
proxy_username, proxy_password,
scheme='http', plugin_path=None):
"""Proxy Auth Extension
args:
proxy_host (str): domain or ip address, ie proxy.domain.com
proxy_port (int): port
proxy_username (str): auth username
proxy_password (str): auth password
kwargs:
scheme (str): proxy scheme, default http
plugin_path (str): absolute path of the extension
return str -> plugin_path
"""
import string
import zipfile
if plugin_path is None:
plugin_path = 'd:/webdriver/vimm_chrome_proxyauth_plugin.zip'
manifest_json = """
{
"version": "1.0.0",
"manifest_version": 2,
"name": "Chrome 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
proxyauth_plugin_path = create_proxyauth_extension(
proxy_host="proxy.crawlera.com",
proxy_port=8010,
proxy_username="username",
proxy_password="password"
)
co = webdriver.ChromeOptions()
co.add_argument("--start-maximized")
co.add_extension(proxyauth_plugin_path)
driver = webdriver.Chrome(chrome_options=co)
driver.get("http://www.amazon.com/")
4.Selenium chrome構成画像をロードしない prefs = {"profile.managed_default_content_settings.images":2}
chrome_options.add_experimental_option("prefs",prefs)
chromeOptions = webdriver.ChromeOptions()
chromeOptions.add_argument('--proxy-server=http://ip:port')
driver = webdriver.Chrome(chrome_options=chromeOptions)
from selenium import webdriver
def create_proxyauth_extension(proxy_host, proxy_port,
proxy_username, proxy_password,
scheme='http', plugin_path=None):
"""Proxy Auth Extension
args:
proxy_host (str): domain or ip address, ie proxy.domain.com
proxy_port (int): port
proxy_username (str): auth username
proxy_password (str): auth password
kwargs:
scheme (str): proxy scheme, default http
plugin_path (str): absolute path of the extension
return str -> plugin_path
"""
import string
import zipfile
if plugin_path is None:
plugin_path = 'd:/webdriver/vimm_chrome_proxyauth_plugin.zip'
manifest_json = """
{
"version": "1.0.0",
"manifest_version": 2,
"name": "Chrome 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
proxyauth_plugin_path = create_proxyauth_extension(
proxy_host="proxy.crawlera.com",
proxy_port=8010,
proxy_username="username",
proxy_password="password"
)
co = webdriver.ChromeOptions()
co.add_argument("--start-maximized")
co.add_extension(proxyauth_plugin_path)
driver = webdriver.Chrome(chrome_options=co)
driver.get("http://www.amazon.com/")
prefs = {"profile.managed_default_content_settings.images":2}
chrome_options.add_experimental_option("prefs",prefs)