爬虫基础框架 之urllib(一) --- urllib基础

1 import ssl
2 ssl._create_default_https_context = ssl._create_unverified_context 

1 from urllib import request

1 url = "http://www.baidu.com/"

1 response = request.urlopen(url=url)
2 print(response)

3 结果 ：<http.client.HTTPResponse object at 0x10be801d0>

1 print(response.headers)

1 print(response.url)        #打印url 
2 print(response.status)     #打印状态码

1 res = response.read()       # 读取的是二进制  
2 print(res)                  # 读取到的响应体是一个二进制字符串  
3 print(res.decode("utf-8"))  # 对响应体进行解码 

1 res = response.readline()      # 读取一行 
2 res1 = response.readline()     # 读取下一行  
3 res2 = response.readlines()    # 读取多行。得到一个列表 每个元素是一行  
4 print(res)                     # 打印

1 res3 = request.urlretrieve(url=url,filename="./baidu.html") 
2 print(res3)     # 获取url 保存到baidu.html中 并打印

1 from urllib import parse

1 url = "https://www.baidu.com/s?"

1 dic= {"ie":"utf-8","wd":"奔驰"}

1 parames = parse.urlencode(dic)

1 url += parames
2 request.urlopen(url=url)