近期需求:网站首页截图功能,需要将8万个网站全部截取首页图片,并保存下来。
其中chromedriver需要自行下载;
直接上代码!
from selenium import webdriver
# 获取网页截图
def road_situation(url):
# 初始化一个谷歌浏览器实例
chrome_driver = 'C:\chromedriver.exe'
driver = webdriver.Chrome(executable_path=chrome_driver)
driver.maximize_window()
driver.get(url)
if 'http://' in url:
name = url.replace('http://', '')
else:
name = url.replace('https://', '')
driver.get_screenshot_as_file("D:\\python\\2020-12-23【网页截图】\\cover\\%s.png" % name)
driver.quit()
if __name__ == "__main__":
f = open('./link.txt', 'r', encoding='utf-8')
data = f.read().split("\n")
for link in data:
print(link)
road_situation(link)
print('end')