"""
#最基本,请求地址无参数
# response=urllib.request.urlopen("https://www.scetc.edu.cn")
#
# html=response.read().decode("utf-8")
#
# print(html)
#最基本,请求地址无参数
# response=urllib.request.urlopen("https://www.scetc.edu.cn")
#
# html=response.read().decode("utf-8")
#
# print(html)
#第二种,传参数的情况
#参数的转换 参数的原始数据
# key_value={'kw' : '胡歌'}
# #要使用urllib.parse模块下的urllencode对原始数据进行转换,并且encode进行编码
# data=bytes(urllib.parse.urlencode(key_value).encode('utf-8'))
#
# response=urllib.request.urlopen("http://tieba.baidu.com/f?",data=data)
#
# html=response.read().decode('utf-8')
# print(html)
#第三种,传参数的情况
#timeout是指等待响应的时间
#timeout是指等待响应的时间
response=urllib.request.urlopen("http://www.scetc.cn",timeout=5)
html=response.read().decode('utf-8')
print(html)
print(html)
import urllib.request
"""
HttpResponse对象的三个参数属性
"""
HttpResponse对象的三个参数属性
"""
response=urllib.request.urlopen("https://www.tmall.com")
back_url=response.geturl()
print("响应的url:",back_url)
print("响应的url:",back_url)
back_code=response.getcode();
print("响应的状态码:",back_code)
print("响应的状态码:",back_code)
back_info=response.info()
print("响应的信息:",back_info)
print("响应的信息:",back_info)
"""
构造Request对象
"""
import urllib.request
import urllib.parse
import urllib.parse
#头文件的数据
header={"User-Agent":"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT6.1; Trident/5.0)"}
#发送请求参数数据
params={"news_id":174,"page":1}
data=bytes(urllib.parse.urlencode(params).encode('utf-8'))
#封装request对象
#地址
url="http://www.scetc.cn/index!detail"
request=urllib.request.Request(url,data=data,headers=header)
#连接类型
request.add_header("Connection", "keep-alive")
header={"User-Agent":"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT6.1; Trident/5.0)"}
#发送请求参数数据
params={"news_id":174,"page":1}
data=bytes(urllib.parse.urlencode(params).encode('utf-8'))
#封装request对象
#地址
url="http://www.scetc.cn/index!detail"
request=urllib.request.Request(url,data=data,headers=header)
#连接类型
request.add_header("Connection", "keep-alive")
#封装完毕之后openurl方法只需要传入这个Request对象就可以了
response=urllib.request.urlopen(request)
response=urllib.request.urlopen(request)
html=response.read().decode('utf-8')
print(html)
#代理ip
proxy_list=[
{"http": "124.88.67.81:80"},
{"http" : "127.88.67.81:80"},
{"http" : "121.82.67.81:80"},
{"http" : "124.55.67.81:80"},
{"http" : "124.56.67.81:80"},
{"http" : "124.78.67.81:80"},
]
#随机选取代理服务器地址
ran_proxy=random.choice(proxy_list)
#创建handler对象
httpproxy_handler = urllib.request.ProxyHandler(ran_proxy)
#获取opener对象
opener = urllib.request.build_opener(httpproxy_handler)
#构建Request对象
header={"User-Agent":"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT6.1; Trident/5.0)"}
request=urllib.request.Request('http://www.scetc.net',headers=header)
#请求访问
response=opener.open(request)
#获取响应内容
html=response.read().decode('utf-8')
print(html)