selenium爬取优酷页面并下载图片

Posted 2021-01-30 sunzhiqi

 1 from selenium import webdriver
 2 import requests
 3 driver = webdriver.Chrome()
 4 #打开优酷
 5 driver.get("http://www.youku.com")
 6 #点开优酷片库
 7 driver.find_element_by_xpath("//*[@id=‘m_2544‘]/div/ul/li[6]/span[1]/a").click()
 8 #获取所有img元素
 9 listImg = driver.find_elements_by_xpath("//div[@class=‘vaule_main‘]//li/div/div/img")
10 #取img的src值
11 listSrc = []
12 for img in listImg:
13     src = img.get_attribute(‘src‘)
14     listSrc.append(src)
15 print(len(listImg))
16 #下载图片
17 session = requests.session()
18 for index,value in enumerate(listSrc):
19     response = session.get(value)
20     with open(str(index)+‘.png‘,mode=‘wb‘) as f:
21         f.write(response.content)