python第一个爬虫程序

python爬取新浪首页程序

import urllib.request

url = "http://www.sina.com.cn"

# 发送请求
response = urllib.request.urlopen(url)

# 读取数据
data = response.read()
print(data)

# with open("sina.html","wb") as f:
#     f.write(data)
#     print("新浪页面采集完成")

# 如果对数据进行操作，要转成字符串操作
html = data.decode("utf-8")
print(html)
with open("sina2.html","w",encoding="utf-8") as f:
    f.write(html)