爬虫21-selenium用法

1.获取cookie信息

from selenium import webdriver


driver=webdriver.Firefox()
driver.get("https://www.baidu.com")

for cookie in driver.get_cookies():
    print(cookie)#获得所有cookie
print(driver.get_cookie("PSTM"))#获得指定cookie
driver.delete_cookie("PSTM")#删除cookie
driver.delete_all_cookies()#删除所有cookie

　　

2.页面等待

from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
driver=webdriver.Firefox()
driver.get("https://www.baidu.com")

driver.implicitly_wait(20)#等待二十秒再抛异常，隐式等待

WebDriverWait(driver,10).until(#等待十秒，显式等待
    EC.presence_of_element_located(By.ID,'safasefsd')#不存在的情况
)

driver.find_elements_by_id("sdasdsdsdwqenjas")

　　

3.多页面

from selenium import webdriver
from selenium.webdriver.common.action_chains import ActionChains

driver=webdriver.Chrome()
driver.get("https://www.baidu.com")

driver.execute_script("window.open('https://www.douban.com')")#打开新的标签、
driver.switch_to.window(driver.window_handles[1])
print(driver.current_url)#显示当前driver所在页面
print(driver.page_source)#打印网页内容

　　

4.代理

from selenium import webdriver
from selenium.webdriver.common.action_chains import ActionChains

options=webdriver.FirefoxOptions()
options.add_argument("--proxy-server=http://125.110.75.250:9000")
driver=webdriver.Firefox()
driver.get("http://www.httpbin.org/ip")