原文出处:https://blog.csdn.net/zwq912318834/article/details/78933910
chromeOptions 是一个配置 chrome 启动是属性的类。通过这个类,我们可以为chrome配置如下参数(这个部分可以通过selenium源码看到):
设置 chrome 二进制文件位置 (binary_location)
添加启动参数 (add_argument)
添加扩展应用 (add_extension, add_encoded_extension)
添加实验性质的设置参数 (add_experimental_option)
设置调试器地址 (debugger_address)
源代码:
# .\Lib\site-packages\selenium\webdriver\chrome\options.py
class Options(object):
def __init__(self):
# 设置 chrome 二进制文件位置
self._binary_location = ''
# 添加启动参数
self._arguments = []
# 添加扩展应用
self._extension_files = []
self._extensions = []
# 添加实验性质的设置参数
self._experimental_options = {}
# 设置调试器地址
self._debugger_address = None
# 设置默认编码为 utf-8,也就是中文
from selenium import webdriver
options = webdriver.ChromeOptions()
options.add_argument('lang=zh_CN.UTF-8')
driver = webdriver.Chrome(chrome_options = options)
# 设置默认编码为 utf-8,也就是中文
from selenium import webdriver
options = webdriver.ChromeOptions()
options.add_argument('lang=zh_CN.UTF-8')
driver = webdriver.Chrome(chrome_options = options)
# 通过设置user-agent,用来模拟移动设备
# 比如模拟 android QQ浏览器
options.add_argument('user-agent="MQQBrowser/26 Mozilla/5.0 (Linux; U; Android 2.3.7; zh-cn; MB200 Build/GRJ22; CyanogenMod-7) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1"')
# 模拟iPhone 6
options.add_argument('user-agent="Mozilla/5.0 (iPhone; CPU iPhone OS 9_1 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Version/9.0 Mobile/13B143 Safari/601.1"')
# 禁止图片的加载
from selenium import webdriver
chrome_options = webdriver.ChromeOptions()
prefs = {"profile.managed_default_content_settings.images": 2}
chrome_options.add_experimental_option("prefs", prefs)
# 启动浏览器,并设置好wait
browser = webdriver.Chrome(chrome_options=chrome_options)
browser.set_window_size(configure.windowHeight, configure.windowWidth) # 根据桌面分辨率来定,主要是为了抓到验证码的截屏
wait = WebDriverWait(browser, timeout = configure.timeoutMain)
from selenium import webdriver
# 静态IP:102.23.1.105:2005
# 阿布云动态IP:http://D37EPSERV96VT4W2:[email protected]:9020
PROXY = "proxy_host:proxy:port"
options = webdriver.ChromeOptions()
desired_capabilities = options.to_capabilities()
desired_capabilities['proxy'] = {
"httpProxy": PROXY,
"ftpProxy": PROXY,
"sslProxy": PROXY,
"noProxy": None,
"proxyType": "MANUAL",
"class": "org.openqa.selenium.Proxy",
"autodetect": False
}
driver = webdriver.Chrome(desired_capabilities = desired_capabilities)
selenium一般打开的是不带扩展的纯净的浏览器,但是有时候我们爬取数据时需要借助一些插件,比如解析类xpath helper,翻译类,获取额外信息(销量)等。那我们怎么在启动chromedriver时,带上一些我们需要的插件呢?
下面以在chrome中加载Xpath Helper插件为例:
# 添加xpath helper应用
from selenium import webdriver
chrome_options = webdriver.ChromeOptions()
# 设置好应用扩展
extension_path = 'D:/extension/XPath-Helper_v2.0.2.crx'
chrome_options.add_extension(extension_path)
# 启动浏览器,并设置好wait
browser = webdriver.Chrome(chrome_options=chrome_options)
# 第一种方式
# chrome浏览器的扩展程序都在:C:\Users\Administrator\AppData\Local\Google\Chrome\User Data\Profile 2\Extensions\下
chrome_options.add_argument("user-data-dir=C:/Users/Administrator/AppData/Local/Google/Chrome/User Data")
# 加载所有Chrome配置, 用Chrome地址栏输入chrome://version/,查看自己的“个人资料路径”,然后在浏览器启动时,调用这个配置文件,代码如下:
from selenium import webdriver
option = webdriver.ChromeOptions()
option.add_argument('--user-data-dir=C:\Users\Administrator\AppData\Local\Google\Chrome\User Data') #设置成用户自己的数据目录
driver = webdriver.Chrome(chrome_options=option)
# 出现错误结果
第一,所有浏览器窗口,包括自己打开的都会被控制住。
第二,其他动作不起作用,而且会crash。
Traceback (most recent call last):
File "E:/PyCharmCode/taobaoProductSelenium/taobaoSelenium.py", line 40, in <module>
# 启动浏览器,并设置好wait
File "E:\Miniconda\lib\site-packages\selenium\webdriver\chrome\webdriver.py", line 69, in __init__
desired_capabilities=desired_capabilities)
File "E:\Miniconda\lib\site-packages\selenium\webdriver\remote\webdriver.py", line 151, in __init__
self.start_session(desired_capabilities, browser_profile)
File "E:\Miniconda\lib\site-packages\selenium\webdriver\remote\webdriver.py", line 240, in start_session
response = self.execute(Command.NEW_SESSION, parameters)
File "E:\Miniconda\lib\site-packages\selenium\webdriver\remote\webdriver.py", line 308, in execute
self.error_handler.check_response(response)
File "E:\Miniconda\lib\site-packages\selenium\webdriver\remote\errorhandler.py", line 194, in check_response
raise exception_class(message, screen, stacktrace)
selenium.common.exceptions.WebDriverException: Message: unknown error: Chrome failed to start: crashed
(Driver info: chromedriver=2.32.498550 (9dec58e66c31bcc53a9ce3c7226f0c1c5810906a),platform=Windows NT 6.1.7601 SP1 x86_64)
from time import sleep
from selenium import webdriver
from selenium.webdriver.common.by import By
options = webdriver.ChromeOptions()
prefs = {}
# 设置这两个参数就可以避免密码提示框的弹出
prefs[“credentials_enable_service”] = False
prefs[“profile.password_manager_enabled”] = False
options.add_experimental_option(“prefs”, prefs)
browser = webdriver.Chrome(chrome_options=options)
browser.get('https://www.baidu.com/')