About selenium: headless, IP proxy, header settings

chrome configuration

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
options = Options()
options.binary_location = "C:\\Program Files\\Google\\Chrome\\Application\\chrome.exe"
driver = webdriver.Chrome(options=options)#executable_path="D:\Program Files\python3.7\chromedriver.exe"
#sleep(2)
driver.get('https://www.baidu.com/')
h = driver.page_source
print(h)

phantomjs

Set ip

method 1

service_args = [
    '--proxy=%s' % ip_html,    # 代理 IP：prot    （eg：192.168.0.28:808）
    '--proxy-type=http’,            # 代理类型：http/https
    ‘--load-images=no’,           # 关闭图片加载（可选）
    '--disk-cache=yes’,            # 开启缓存（可选）
    '--ignore-ssl-errors=true’    # 忽略https错误（可选）
]
driver = webdriver.PhantomJS(service_args=service_args)

Method 2

browser=webdriver.PhantomJS(PATH_PHANTOMJS)

# 利用DesiredCapabilities(代理设置)参数值，重新打开一个sessionId，我看意思就相当于浏览器清空缓存后，加上代理重新访问一次url
proxy=webdriver.Proxy()
proxy.proxy_type=ProxyType.MANUAL
proxy.http_proxy='1.9.171.51:800'

# 将代理设置添加到webdriver.DesiredCapabilities.PHANTOMJS中
proxy.add_to_capabilities(webdriver.DesiredCapabilities.PHANTOMJS)
browser.start_session(webdriver.DesiredCapabilities.PHANTOMJS)
browser.get('http://1212.ip138.com/ic.asp')

print('1: ',browser.session_id)
print('2: ',browser.page_source)
print('3: ',browser.get_cookies())

Revert to system proxy

# 还原为系统代理
proxy=webdriver.Proxy()
proxy.proxy_type=ProxyType.DIRECT
proxy.add_to_capabilities(webdriver.DesiredCapabilities.PHANTOMJS)
browser.start_session(webdriver.DesiredCapabilities.PHANTOMJS)
browser.get('http://1212.ip138.com/ic.asp')

Set request header

import random,requests,json
from selenium import webdriver
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
from selenium.webdriver.common.proxy import ProxyType


#随机获取一个ip
def proxies():
    r = requests.get("http://120.26.166.214:9840/JProxy/update/proxy/scoreproxy")
    rr = json.loads(r.text)
    hh = rr['ip'] + ":" + "8907"
    print(hh)
    return hh
ips =proxies()


#设置phantomjs请求头和代理方法一：
#-------------------------------------------------------------------------------------
# 设置代理
service_args = [
    '--proxy=%s' % ips,  # 代理 IP：prot    （eg：192.168.0.28:808）
    '--ssl-protocol=any',           #忽略ssl协议
    '--load - images = no',         # 关闭图片加载（可选）
    '--disk-cache=yes',             # 开启缓存（可选）
    '--ignore-ssl-errors=true'     # 忽略https错误(可选)
]

#设置请求头
user_agent = (
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_4) " +
    "AppleWebKit/537.36 (KHTML, like Gecko) Chrome/29.0.1547.57 Safari/537.36"
    )
dcap = dict(DesiredCapabilities.PHANTOMJS)
dcap["phantomjs.page.settings.userAgent"] = user_agent
driver = webdriver.PhantomJS(executable_path=r"C:\soft\phantomjs-2.1.1-windows\bin\phantomjs.exe",
                             desired_capabilities=dcap,service_args=service_args)

driver.get(url='http://www.baidu.com')
page=driver.page_source
print(page)

#设置phantomjs请求头和代理方法二：
#-------------------------------------------------------------------------------------
desired_capabilities = DesiredCapabilities.PHANTOMJS.copy()
# 从USER_AGENTS列表中随机选一个浏览器头，伪装浏览器
desired_capabilities["phantomjs.page.settings.userAgent"] = (random.choice('请求头池'))

# 不载入图片，爬页面速度会快很多
desired_capabilities["phantomjs.page.settings.loadImages"] = False

# 利用DesiredCapabilities(代理设置)参数值，重新打开一个sessionId，我看意思就相当于浏览器清空缓存后，加上代理重新访问一次url
proxy = webdriver.Proxy()
proxy.proxy_type = ProxyType.MANUAL
proxy.http_proxy = random.choice('ip池')
proxy.add_to_capabilities(desired_capabilities)
phantomjs_driver = r'C:\phantomjs-2.1.1-windows\bin\phantomjs.exe'
# 打开带配置信息的phantomJS浏览器
driver = webdriver.PhantomJS(executable_path=phantomjs_driver,desired_capabilities=desired_capabilities)
driver.start_session(desired_capabilities)


driver.get(url='http://www.baidu.com')
page=driver.page_source
print(page)


# 隐式等待5秒，可以自己调节
driver.implicitly_wait(5)
# 设置10秒页面超时返回，类似于requests.get()的timeout选项，driver.get()没有timeout选项
# 以前遇到过driver.get(url)一直不返回，但也不报错的问题，这时程序会卡住，设置超时选项能解决这个问题。
driver.set_page_load_timeout(20)
# 设置10秒脚本超时时间
driver.set_script_timeout(20)



#翻页命令
driver.execute_script('window.scrollTo(0, document.body.scrollHeight)')

firefox

import time 
from selenium.webdriver.common.proxy import* 

myProxy = '202.202.90.20:8080'

proxy = Proxy({
    
    
  'proxyType': ProxyType.MANUAL, 
  'httpProxy': myProxy, 
  'ftpProxy': myProxy, 
  'sslProxy': myProxy, 
  'noProxy': ''
 })

profile = webdriver.FirefoxProfile()
if proxy:
    profile = get_firefox_profile_with_proxy_set(profile, proxy)
if user_agent:
    profile.set_preference("general.useragent.override", user_agent)

driver=webdriver.Firefox(proxy=proxy,profile=profile) 
driver.get('https://www.baidu.com') 
time.sleep(3) 
driver.quit()

firefox headless mode

from selenium import webdriver

# 创建的新实例驱动
options = webdriver.FirefoxOptions()
#火狐无头模式
options.add_argument('--headless')
options.add_argument('--disable-gpu')
# options.add_argument('window-size=1200x600')

executable_path='./source/geckodriver/geckodriver.exe'
driver_path = webdriver.Firefox(firefox_options=options,executable_path=executable_path)

chrome

# !/usr/bin/python
# -*- coding: utf-8 -*-

from selenium import webdriver

# 进入浏览器设置
options = webdriver.ChromeOptions()
#谷歌无头模式
options.add_argument('--headless')
options.add_argument('--disable-gpu')
# options.add_argument('window-size=1200x600')
# 设置中文
options.add_argument('lang=zh_CN.UTF-8')
# 更换头部
options.add_argument('user-agent="Mozilla/5.0 (iPod; U; CPU iPhone OS 2_1 like Mac OS X; ja-jp) AppleWebKit/525.18.1 (KHTML, like Gecko) Version/3.1.1 Mobile/5F137 Safari/525.20"')
#设置代理
if proxy:
    options.add_argument('proxy-server=' + proxy)
if user_agent:
    options.add_argument('user-agent=' + user_agent)

browser = webdriver.Chrome(chrome_options=options)
url = "https://httpbin.org/get?show_env=1"
browser.get(url)
browser.quit()

selenium set chrome--cookie

# !/usr/bin/python
# -*- coding: utf-8 -*-

from selenium import webdriver
browser = webdriver.Chrome()

url = "https://www.baidu.com/"
browser.get(url)
# 通过js新打开一个窗口
newwindow='window.open("https://www.baidu.com");'
# 删除原来的cookie
browser.delete_all_cookies()
# 携带cookie打开
browser.add_cookie({
    
    'name':'ABC','value':'DEF'})
# 通过js新打开一个窗口
browser.execute_script(newwindow)
input("查看效果")
browser.quit()

Selenium set chrome-picture not to load

from selenium import webdriver

options = webdriver.ChromeOptions()
prefs = {
    
    
    'profile.default_content_setting_values': {
    
    
        'images': 2
    }
}
options.add_experimental_option('prefs', prefs)
browser = webdriver.Chrome(chrome_options=options)

# browser = webdriver.Chrome()
url = "http://image.baidu.com/"
browser.get(url)
input("是否有图")
browser.quit()

Reprinted from https://cloud.tencent.com/developer/article/1406611