003 Urllib库的使用

二、Urllib库的基本使用

1.Urllib

是一个Python内置的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.robotparser robots.txt解析模块

2.与Python2的变化

Python2

import urllib2
response = urllib2.urlopen('http://www.baidu.com')

Python3

import urllib.request
response = urllib.request.urlopen('http://www.baidu.com')

3.urllib用法详解

1.urlopen

urllib.request.urlopen(url,data=None,[timeout,]*,cafile=None,capath=None,cadefault=False,context=None)

import urllib.request

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

import urllib.parse
import urllib.request

data = bytes(urllib.parse.urlencode({'word':'hello'}),encoding='utf-8')
response = urllib.request.urlopen('http://httpbin.org/post',data=data)
print(response.read())

import urllib.request

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

import socket
import urllib.request
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')

2.Response(响应)

1.响应类型

import urllib.request

response = urllib.request.urlopen('https://www.python.org')
print(type(response))

2.状态码、响应头

import urllib.request

response = urllib.reuqest.urlopen('https://www.python.org')
print(response.status)
print(response.getheaders())
print(response.getheader('Server'))

3.响应体

import urllib.request

response = urllib.request.urlopen('https://www.python.org')
print(response.read().decode('utf-8'))

3.Request

import urllib.request

request = urllib.request.Request('https://python.org')
response = urllib.request.urlopen(request)
print(response.read().decode('utf-8'))

from urllib import request,parse

url = 'http://httpbin.org/post'
headers = {
    'User-Agent':'Mozilla/4.0(compatible;MSIE5.5;Windows NT)',
    'Host':'httpbin.org'
}
dict = {
    'name':'Germey'
}
data = bytes(parse.urlencode(dict),encoding='utf8')
req = request.Request(url=url,data=data,headers=headers,method='POST')
response = request.urlopen(req)
print(response.read().decode('utf-8'))

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,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'))

4.Handler

1.代理

import urllib.request

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/get')
print(response.read())

2.Cookie

获取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)

保存Cookie两种方式

import http.cookiejar,urllib.request
filename = 'cookie.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)

import http.cookiejar,urllib.request
filename = 'cookie.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)

读取Cookie

import http.cookiejar,urllib.request
cookie = http.cookiejar.LWPCookieJar()
cookie.load('cookie.txt',ignore_discard=True,ignore_expires=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'))

5.异常处理

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

from urllib import request,error

try:
    response = request.urlopen('http://cuiqingcai.com/index.html')
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')

import socket
import urllib.request
import urllib.error

try:
   response = urllib.request.urlopen('https://www.baidu.com',timeout=0.01)
except urllib.error.URLError as e:
    print(type(e.reason))
    if isinstance(e.reason,socket.timeout):
        print('TIME OUT')

6.URL解析(工具模块，可以直接使用)

1.urlparse

urllib.parse.urlparse(urlstring,scheme='',allow_fragments=True)

from urllib.parse import urlparse

result = urlparse('http://wwww.baidu.com/index.html;user?id=5#comment')
print(type(result),result)

from urllib.parse import urlparse

result = urlparse('www.baidu.com/index.html;user?id=5#comment',scheme='https')
print(result)

from urllib.parse import urlparse

result = urlparse('http://www.baidu.com/index_html;user?id=5#comment',scheme='https')
print(result)

from urllib.parse import urlparse

result = urlparse('http://www.baidu.com/index.html;user?id=5#comment',allow_fragments=False)
print(result)

from urllib.parse import urlparse

result = urlparse('http://www.baidu.com/index.html#comment',allow_fragments=False)
print(result)

2.urlunparse

urlparse的反函数 作用是将URL进行拼接，结果是得到一个完整的URL

from urllib.parse import urlunparse

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

3.urljoin

urljoin是用来拼接url的
url都可以分成六个字段，后面的字段名会覆盖前面的字段名
如果后面的字段在前面的url中不存在，就会用前面的字段来补充；如果后面的字段是存在的那么就全部以后面的为基准

from urllib.parse import urljoin

4.urlencode

可以把一个字典对象转化成一个GET请求参数

from urllib.parse import urlencode

params = {
    'name':'germey',
    'age':22,
}
base_url = 'http://www.baidu.com?'
url = base_url + urlencode(params)
print(url)