urllib 库的基本使用

　　1.url.request(get)

import urllib.request

response = urllib.request.urlopen('http://www.baidu.com')
print(response.read().decode('utf-8'))

　　2.url.request (post)

import urllib.parse
import urllib.request

data=bytes(urllib.parse.urlencode({'word':'hello'}),encoding='utf8')
response = urllib.request.urlopen('http://httpbin.org/post',data=data)
print(response.read())

　　3.url.request(超时正确)

import urllib.request

response = urllib.request.urlopen('http://httpbin.org/get',timeout=1)
print(response.read())

　　4.url.request(超时错误)

import urllib.request
import socket
import urllib.error

try:
    response = urllib.request.urlopen('http://httpbin.org/get',timeout=0.1)
except urllib.error.URLError as e:
    if isinstance(e.reason, socket.timeout):
        print('Time Out')

　　5.状态头，响应码

import urllib.request

response = urllib.request.urlopen('http://www.python.org')
print(type(response))
print(response.status)
print(response.getheaders())
print(response.getheader('Server'))

　　6.Request

import urllib.request

request = urllib.request.Request('http://www.baidu.com')
response=urllib.request.urlopen(request)
print(response.read().decode('utf-8'))

　　6.1.参数的使用

from urllib import request,parse

url = 'http://httpbin.org/post'
headers = {
    'User-Agent':'Mozilla/4.0(compatible;MSIE 5.5;Windows NT)',
    'Host':'httpbin.org'
}
dict = {
    'name':'Germey'
}
data = bytes(parse.urlencode(dict),encoding='utf-8')
req = request.Request(url=url,data=data,headers=headers,method='POST')
response = request.urlopen(req)
print(response.read().decode('utf-8'))

　　6.2.追加的方法

from urllib import request,parse

url = 'http://httpbin.org/post'
dict = {
    'name':'Germey',
}
data = bytes(parse.urlencode(dict),encoding='utf8')
req = request.Request(url=url,data=data,headers=headers,method='POST')
req.add_header('User-Agent','Mozilla/4.0(compatible;MSIE 5.5;Windows NT)')
response = request.urlopen(req)
print(response.read().decode('utf-8'))

　　handler
　　7. 代理

import urllib.request

proxy_handler = urllib.request.ProxyHandler({
    'http':'http://localhost:9743',
    'https':'https://localhost:9743'
})
opener = urllib.request.build_opener(proxy_handler)
response = opener.open('http://www.baidu.com')
print(response.read())

　　8.Cookie

import http.cookiejar,urllib.request
cookie = http.cookiejar.CookieJar()
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
for item in cookie:
    print(item.name+"="+item.value)

　　8.1.Cookie保存到本地

　　方式一：

import http.cookiejar,urllib.request
filename = "coookie.txt"
cookie=http.cookiejar.MozillaCookieJar(filename)
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
cookie.save(ignore_discard=True,ignore_expires=True)

　　方式二：

import http.cookiejar,urllib.request
filename = "coookie1.txt"
cookie=http.cookiejar.LWPCookieJar(filename)
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
cookie.save(ignore_discard=True,ignore_expires=True)

　　8.2.读取cookie 文件

　　

（1）
from urllib import request,error
try:
    response = request.urlopen('http://cuiqingcai.com/index.html')
except error.URLError as e:
    print(e.reason)

（2）
from urllib import request,error
try:
    response = 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 Sucessfully')

　　9.URL解析：

（1）
from urllib.parse import urlparse
result = urlparse('http://www.baidu.com/index.html;user?id=5#comment')
print(type(result),result)
（2）
from urllib.parse import urlparse
result = urlparse('www.baidu.com/index.html;user?id=5#comment',scheme='https')
print(result)
（3）
from urllib.parse import urlparse
result = urlparse('http://www.baidu.com/index.html;user?id=5#comment',scheme='https')
print(result)
（4）
from urllib.parse import urlparse
result = urlparse('http://www.baidu.com/index.html;user?id=5#comment',allow_fragments=False)
print(result)
（5）
from urllib.parse import urlparse
result = urlparse('http://www.baidu.com/index.html#comment',allow_fragments=False)
print(result)

　　10.urlunparse:(url参数拼接)

from urllib.parse import urlunparse
data=['http','www.baidu.com','index.html','user','a=6','comment']
print(urlunparse(data))

　　11.urljoin:(url追加，后者如果完整会覆盖掉前者，如果不完整就拼接)

from urllib.parse import urljoin
print(urljoin('http://www.baidu.com','FAQ.html'))
print(urljoin('http://www.baidu.com','https://cuiqingcai.com/FAQ.html'))
print(urljoin('http://www.baidu.com','https://cuiqingcai.com/FAQ.html?question=2'))
print(urljoin('http://www.baidu.com','https://cuiqingcai.com/index.php'))
print(urljoin('http://www.baidu.com?wd=abc','https://cuiqing.com/index.php'))
print(urljoin('http://www.baidu.com','?category=2#comment'))
print(urljoin('www.baidu.com','?category=2#comment'))
print(urljoin('www.baidu.com#comment','?category=2'))

这里由于运行结果太多，有的直接就是html代码就不展示运行结果了。希望对初学者有所帮助。