python爬虫学习之urllib库

urlopen

1. get类型的网页：

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

    

2. post类型的网页：

   import urllib.request
   import urllib.parse
   data=bytes(urllib.parse.urlencode({'word':'hello'}),encoding='utf-8')
   response = urllib.request.urlopen("http://httpbin.org/post",data=data)#做http测试的网址
   print(response.read())

    

3.  超时

   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

状态码、响应头

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")

 Request

1. import urllib.request
   
   request = urllib.request.Request('http://www.baidu.com')
   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;MSIE ;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'))
   
   也可以写成
   
   from urllib import request,parse
   url = "http://httpbin.org/post"
   dict = {
       'name':'Germey'
   }
   data  = bytes(parse.urlencode(dict),encoding='utf-8')
   req = request.Request(url=url,data=data,method='POST')
   req.add_header( 'User-Agent','Mozilla/4.0(compatible;MSIE ;Windows NT)')
   response = request.urlopen(req)
   print(response.read().decode('utf-8'))

    

 

 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' #代理网址
   })
   opener = urllib.request.build_opener(proxy_handler)
   response = opener.open("http://www.baidu.com")
   print(response.read())

    

cookie（检查-application） 

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)

存储 

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)

 读取

import http.cookiejar,urllib.request
cookie = http.cookiejar.MozillaCookieJar()
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://www.cuiqingcai.com/index.htm")
except error.URLError as e:
    print(e.reason)

好的写法：

from urllib import request,error

try:
    response = request.urlopen("http://cuiqingcai.com/index.htm")
except error.HTTPError as e: #先捕捉子类异常
    print(e.reason,e.code,e.headers,sep='\n')
except error.URLError as e:  #后捕捉父类异常
    print(e.reason)
else :
    print("Request Successfully")

import socket
import urllib.request
import urllib.error

try:
    response = urllib.request.urlopen('http://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")

URL解析

1. urlparse

   from urllib.parse import urlparse
   
   result = urlparse('http://www.baidu.com/index.html;user?id=5#comment')
   result = urlparse('www.baidu.com/index.html;user?id=5#comment',scheme='https')# scheme为https
   result = urlparse('http://www.baidu.com/index.html;user?id=5#comment',scheme='https') #scheme仍为http
   result = urlparse('http://www.baidu.com/index.html;user?id=5#comment',allow_fragments=False)# fragment会拼接到query上
   result = urlparse('http://www.baidu.com/index.html#comment',allow_fragments=False)# fragment会拼接到params上
   print(type(result),result)
   
   

    

2. urlunparse

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

    

3. urljoin

   from urllib.parse import urljoin
   
   print(urljoin('http://www.baidu.com','FAQ.html'))#此类可以连接，如果两个都是http(s)开头那么会覆盖
   

    

4. urlencode

   from urllib.parse import urlencode
   
   params = {
       'name':'gemey',
       'age':22
   }
   base_url = "http://www.baidu.com?"
   
   url = base_url + urlencode(params)
   print(url)