Python Urllib库详解

Urllib库详解

什么是Urllib?

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

相比Python2变化

python2

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

python3

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

urllib

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='utf8')
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')

响应

响应类型

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

状态码、响应头

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

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/5.0 (Macintosh; Intel Mac OS X 10_13_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36',
    'Host':'httpbin.org'
}
dict = {
    'name':'puqunzhu'
}
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':'puqunzhu'
}
data = bytes(parse.urlencode(dict),encoding='utf8')
req = request.Request(url=url,data=data,method='POST')
req.add_header('User-Agent','Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.100 Safari/537.36')
response = request.urlopen(req)
print(response.read().decode('utf-8'))

Handler

代理

import urllib.request
proxy_handler = urllib.request.ProxyHandler({
    'http':'http://61.135.217.7:80',
    'https':'https://61.150.96.27:46111',
})
opener = urllib.request.build_opener(proxy_handler)
response = opener.open('http://www.baidu.com')
print(response.read())

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)

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)

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'))

异常处理

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

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 Successfully")

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

URL解析

urlparse

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

from urllib.parse import urlparse
result = urlparse('http://www.baidu.com/index.html;urser?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)

utlunoarse

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

urljoin

from urllib.parse import urljoin
print(urljoin('http://www.baidu.com','?category=2#comment'))
print(urljoin('htttp://www.baidu.com/about.html','htttp://www.baidu.com/FAQ.html'))

urlencode

from urllib.parse import urlencode
params = {
    'name':'puqunzhu',
    'age':23
}
base_url="http://www.baidu.com?"
url=base_url + urlencode(params)
print(url)