python爬虫：urllib库的简单使用

1 import urllib.request
2 #获取一个get请求
3 response = urllib.request.urlopen("http://www.baidu.com")

    打开网页并返回网页内容给response
 print(response.read().decode(‘utf-8‘)) #对获取到的网页进行utf-8解码

1 #获取一个post请求
2 
3 import urllib.parse
4 data = bytes(urllib.parse.urlencode({"hello":"world"}),encoding="utf-8")
5 response = urllib.request.urlopen("http://httpbin.org/post",data= data)
6 print(response.read().decode("utf-8"))

#获取一个get请求
 import urllib.parse
 response = urllib.request.urlopen("http://httpbin.org/get")
 print(response.read().decode("utf-8"))

#超时处理
try:
     response = urllib.request.urlopen("http://httpbin.org/get", timeout=10)
     print(response.read().decode("utf-8")) #对网页信息进行utf-8解码
except urllib.error.URLError as e: 
     print("time out!")

response = urllib.request.urlopen("http://www.baidu.com")
print(response.status) #查看状态信息(200/404/500/418)
print(response.getheaders())#查看Response Headers中的信息 
print(response.getheader("Server"))#查看Response Headers中的Server属性值(查看单一属性值)