0724py:urllib.request模块爬虫初步了解

import urllib.request 

url = "https://www.chinaoption.com"

# urlopen(url)打开链接，获取对象，和文件打开相似
url_open  = urllib.request.urlopen(url)
# <http.client.HTTPResponse object at 0x000001F6671DC978>,这个对象两个属性，status状态码，reason，状态原因
# print(url_open.status)
# print(url_open.reason)

# 获取网页响应的头部,这次是一个列表
url_open_getheaders = url_open.getheaders()

print(url_open_getheaders)
for vax in url_open_getheaders:
	print(vax)


# 获取的对象可以read()方法读取，是二进制的
url_open_read = url_open.read()

print(type(url_open_read))

# 读取内容是二级制字节，用decode()解码,获取一个字符串
url_open_read_decode = url_open_read.decode()

print(type(url_open_read_decode))

print(url_open_read_decode)