python urllib库详解

Python的内置HTTP请求库

urllib.request  请求模块

urllib.error  异常处理模块

urllib.parse   url解析模块

urllib.robotparse    robots.txt解析模块

import urllib.request
from urllib.parse import urlparse,urlunparse,urljoin,urlencode
import http.cookiejar
from urllib import error
import socket
#urlopen
#请求
# data = bytes(urllib.parse.urlencode({'world':'hello'}),encoding='utf-8')
# response = urllib.request.urlopen('http://httpbin.org/post',data=data)#post请求
# print(response.read())
#
# #响应
# #响应类型
# response = urllib.request.urlopen('https://www.python.org')
# print(type(response))
#
# #状态码、响应头
# response = urllib.request.urlopen('http://www.python.org')
# print(response.status)
# print(response.getheaders())
# print(response.getheader('Server'))
#
# #获取响应体的内容
# response = urllib.request.urlopen('http://www.python.org')
# print(response.read().decode('utf-8'))
# #Request
# request = urllib.request.Request('http://www.python.org')
# response = urllib.request.urlopen(request)
# print(response.read().decode('utf-8'))

#构建post请求加点headers
# url = 'http://httpbin.org/post'
# headers = {
#     'User-Agent':'Mozilla/4.0(compatible;MSE 5.5;Windows NT)',
#     'Host':'httpbin.org'
# }
# dict = {
#     'name':'Germey'
# }
# data = bytes(urllib.parse.urlencode(dict),encoding='utf-8')#form
# req = urllib.request.Request(url=url,data=data,headers=headers,method='POST')
# response = urllib.request.urlopen(req)
# print(response.read().decode('utf-8'))
#
# #Habdler
# #代理,切换ip
# proxy_handler = urllib.request.ProxyHandler({
#     'http':'http://127.0.0.1:9743',
#     'https':'https://127.0.0.1:9743'
# })
# opener = urllib.request.build_opener(proxy_handler)
# response = opener.open('http://httpbin.org/post')
# print(response.read())
#cookie是用来记录用户身份，维持登录状态
cookie = http.cookiejar.CookieJar()
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://baidu.com')
for item in cookie:
    print(item.name+'='+item.value)

# #用来保持登录信息所以可以把cookie保存文本信息
# filename = 'cookie.txt'
# cookie = http.cookiejar.LWPCookieJar(filename)
# handler = urllib.request.HTTPCookieProcessor(cookie)
# opener = urllib.request.build_opener(handler)
# response = opener.open('http://baidu.com')
# cookie.save(ignore_discard=True,ignore_expires=True)
# #读取cookie文本文件
# cookie = http.cookiejar.LWPCookieJar()
# cookie.load('cookie.txt',ignore_expires=True,ignore_discard=True)
# handler = urllib.request.HTTPCookieProcessor(cookie)
# opener = urllib.request.build_opener(handler)
# response = opener.open('http://www.baidu.com')
# print(response.read().decode('utf-8'))

#异常处理,urllib库的异常大类就HTTPError,URLError两类
try:
    response = urllib.request.urlopen('http://cuiqingcai.com/index.htm')
except error.HTTPError as e:
    print(e.reason,e.code,e.headers,sep='\n')
except error.URLError as e:
    print(e.reason)
else:
    print("Request Successfully")

#具体验证是哪种异常：isinstance
try:
    response = urllib.request.urlopen('http://www.baidu.com',timeout=0.01)
except error.URLError as e:
    print(type(e.reason))
    if isinstance(e.reason,socket.timeout):
        print('TIME OUT')

#URL解析
#urllib.parse.urlparse(url,scheme='',allow_fragments=True)
#urlparse将URL分割进行赋值,协议类型，域名，路径,参数等
result = urlparse('http://www.baidu.com/index.html;user?id=5#comment')
print(type(result),result)

#只有URL没有协议类型,URL有协议类型，scheme不会生效
result = urlparse('www.baidu.com/index.html;user?id=5#comment',scheme='https')
print(result)

#fragment是锚点连接，令其为False会将fragment的内容加到前面的参数里
result = urlparse('http://www.baidu.com/index.html;user?id=5#comment',allow_fragments=False)
print(result)

#urlunparse是将URL进行拼接
data = {'http','www.baidu.com','index.html','user','a=6','comment'}
print(urlunparse(data))#user://www.baidu.com/http;index.html?comment#a=6

#urljoin拼接URL，后面的字段名会覆盖前面的字段名
print(urljoin('http://www.baidu.com','FAQ.html'))#http://www.baidu.com/FAQ.html
print(urljoin('http://www.baidu.com','https://cuiqingcai.com/FAQ.html'))#https://cuiqingcai.com/FAQ.html

#urlencode将字典对象转化为get请求参数
params = {
    'name':'gemmey',
    'age':22
}
base_url = 'http://www.baidu.com?'
url = base_url+urlencode(params)
print(url)