import urllib.request
import random
url = ['http://www.baidu.com',"https://www.360.com/","https://www.163.com/","https://www.bilibili.com/","http://www.materializecss.cn/","https://www.mdui.org/","https://www.csdn.net/","https://www.cnblogs.com/","https://www.huya.com/","https://wwww.nuxt.com/"]
# 浏览器头部0
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36",
}
def File(data,link):
fileData = open(link.split('.')[1]+'.html','w',encoding='utf-8')
fileData.write(data)
fileData.close()
def Crawling(link):
print(link)
req = urllib.request.Request(url=link,headers=headers)
response = urllib.request.urlopen(req)
html = response.read().decode('utf-8')
File(html,link)
def main():
randomList = []
while len(randomList) <3:
randomTemp = random.randint(0,len(url)-1)#随机抓取一个网站
if randomTemp in randomList:
print("该随机数重复")
else:
randomList.append(randomTemp)
Crawling(url[randomTemp])
if __name__ == '__main__':
main()
