• 爬虫urlib库的一些用法


    1.urlopen函数

    1 from urllib import request
    2 resp = request.urlopen('http://www.google.com')
    3 print(resp.readline()

    2.urlretrieve函数

    1 from urllib import request
    2 
    3 request.urlretrieve('http://www.huacolor.com/article/UploadPic/2016-8/201684181124814.jpg','鲁班.jpg')

    3.urlencode函数

    1 from urllib import parse
    2 params = {'name':'张三','age':18,'greet':'hello world'}
    3 result = parse.urlencode(params)
    4 print(result)

    4.request.Request类

     1 from urllib import request
     2 
     3 url = 'https://www.lagou.com/jobs/list_python?labelWords=&fromSearch=true&suginput='
     4 headers = {
     5     'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.75 Safari/537.36'
     6 }
     7 req = request.Request(url,headers=headers)
     8 resp = request.urlopen(req)
     9 print(resp.read())
    10 
    11 from urllib import request
    12 from urllib import parse
    13 url = 'https://movie.douban.com/chart'
    14 
    15 headers = {
    16     'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.75 Safari/537.36',
    17     'Referer':'https://movie.douban.com/chart'
    18 }
    19 data = {
    20     'first':'true',
    21     'pn':1,
    22     'kd':'python'
    23 }
    24 
    25 req = request.Request(url,headers=headers,data=parse.urlencode(data).encode('utf-8'),method='POST')
    26 resp = request.urlopen(req)
    27 print(resp.read().decode('utf-8'))
    
    

    5.ProxyHandler处理器

     1 from urllib import request
     2 
     3 #没有使用代理的
     4 url = 'http://httpbin.org/ip'
     5 resp = request.urlopen(url)
     6 print(resp.read())
     7 
     8 #使用代理的
     9 from urllib import request
    10 #1.使用PronxyHandler,传入代理构建一个handler
    11 url = 'http://httpbin.org/ip'
    12 handler = request.ProxyHandler({'http':'60.179.237.106:6666'})
    13 #2.使用上面创建的handler构建一个opener
    14 opener = request.build_opener(handler)
    15 
    16 #3.使用open去发送一个请求
    17 resp = opener.open(url)
    18 print(resp.read())
    19 '''
    20 1:代理的原理:在请求目标网站之前,先请求服务器,然后让代理服务器代理服务器去请求目的网站,
    21     代理服务器达到目的网站数据后,再转发给我们代码。
    22 2:http://httpbin.org:这个网站可以方便的查看http请求的一些参数。
    23 3:在代码中使用代理:
    24         *使用'urllib.request.ProxyHandler',传入一个代理。这个代理是一个字典,字典的key
    25         依赖于代理服务器能够接受的类型,一般是'http'或者‘https’,值是‘ip:port'。
    26         
    27         *使用上一步创建的'handler',以及'request.build_opener'创建一个'opener'对象
    28         
    29         *使用上一部创建的'opener',调用’open‘函数,发起请求
    30 '''

    6.cookie库和HTTPCookieProcessor模拟登录

     1 from urllib import request
     2 dapeng_url = 'http://www.renren.com/880151247/profile'
     3 headers = {
     4     'User-Agent':'ozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) 
    Chrome/68.0.3440.75 Safari/537.36
    ', 5 # 'Referer':'http://browse.renren.com/s/all?from=opensearch&q=%E5%A4%A7%E9%B9%8F%E8%91%A3%E6%88%90%E9%B9%8F' 6 'Cookie':'anonymid=jl6nqsuu44h803; depovince=GW; _r01_=1; JSESSIONID=abc_hQ0r79a4SbMk3kNvw; ick_login=8189308
        9-8787-4d1b-8d91-093a5608ae53; ick=948391ec-cf0c-4e1a-b488-65a5fdadccec; t=92ad1c02b8570a1c8c691a5d2f4628eb9; soci
        etyguester=92ad1c02b8570a1c8c691a5d2f4628eb9; id=967709729; xnsid=98d2e93c; XNESSESSIONID=1706376df76c; wp_fold=0;
        jebecookies=454f9f2b-7352-46de-a69e-5ee9ffbb1e34|||||; jebe_key=c4f55e14-a6fe-45f6-a80e-13d17265ba82%7C1f4466a4eb
        a75f8ec6ca90b9b13e94ae%7C1535035343188%7C1; BAIDU_SSP_lcr=http://localhost:63342/S1/renren.html?_ijt=3shk5scmj5l77
        d13j4mu526npu
    ' 7 } 8 req = request.Request(url=dapeng_url,headers=headers) 9 resp = request.urlopen(req) 10 with open('renren.html','w',encoding='utf-8') as fp: 11 ''' 12 write函数必须写入一个str数据类型 13 resp.read()读出来是一个bytes数据类型 14 bytes --> decode --> str 15 str --> encode -->bytes 16 ''' 17 fp.write(resp.read().decode('utf-8'))

    7.http.cookiejar模块:

     1 from urllib import request
     2 from urllib import parse
     3 from http.cookiejar import CookieJar
     4 
     5 headers ={
     6 'User-Agent':'ozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.75 Safari/537.36'
     7 }
     8 
     9 #1:登录
    10 def get_opener():
    11     # 1.1创建一个cookiejar对象
    12     cookiejar = CookieJar()
    13     # 1.2使用cookiejar创建一个HTTPCookieProcessor对象
    14     handler = request.HTTPCookieProcessor(cookiejar)
    15     #1.3使用上一步创建的handler创建一个opener
    16     opener = request.build_opener(handler)
    17     return opener
    18 
    19 def login_renren(opener):
    20     #1.4使用opener发送登录请求(人人网邮箱和密码)
    21     data = {
    22         'email':'970138074@qq.com',
    23         'password':'pythonspider'
    24     }
    25     login_url = 'http://www.renren.com/PLogin.do'
    26     req = request.Request(login_url,data=parse.urlencode(data).encode('utf-8'),headers=headers)
    27     opener.open(req)
    28 
    29 #2.访问个人主页
    30 def visit_profile(opener):
    31     dapeng_url = 'http://www.renren.com/880151247/profile'
    32     #获取个人主页不需要新建一个opener
    33     #而应该使用之前的那个opener,因为之前那个opener已经包含了
    34     #登录所需要的cookie信息
    35     req = request.Request(dapeng_url,headers=headers)
    36     resp = opener.open(req)
    37     with open('renren.html','w',encoding='utf-8') as f:
    38         f.write(resp.read().decode('utf-8'))
    39 
    40 
    41 opener = get_opener()
    42 login_renren(opener)
    43 visit_profile(opener)
    
    
    
     
     
     
     
     
  • 相关阅读:
    【Python教程】3道循环结构练习题
    python3中实现print不换行的方法
    零基础学Python:字典(Dictionary)详细教程
    TS错误提示
    v-slot的简单理解应用
    Typora使用方法简单整理
    Java基础系列(6)- 面向对象(中)
    monkey基础 (7)
    monkey基础 (6)
    monkey基础 (5)
  • 原文地址:https://www.cnblogs.com/rcat/p/9527533.html
Copyright © 2020-2023  润新知