Python(15)_爬区百度网页并保存

import  urllib.request
url ='http://www.baidu.com'
response = urllib.request.urlopen(url=url)
#print(response)  # 打印对象
#print(type(response))
'''获取返回的内容,read()得到的是二进制的,要将二进制转换为str型,需要decode()方法'''
# print(response.read().decode())  #
# with open('baidu.html','w',encoding='utf-8',) as fp:
#     fp.write(response.read().decode())
# 根据响应内容获取到请求url
print("根据响应内容获取请求url: "+response.geturl())

#print(response.getheaders())       # 得到是列表,获取请求头
print(dict(response.getheaders()))  # 列表转换成字典,就可以获取对应的键值对了

print(response.getcode())  # 获取返回码
# print(response.readlines())  按行读取,一般不用
''' 直接以二进制保存下来'''
with open('baidu1.html','wb') as fp1:
    fp1.write(response.read())

原文地址:https://www.cnblogs.com/sunnybowen/p/10171672.html