import requests

from pyquery import PyQuery as pq

base_headers = {

    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.71 Safari/537.36',

    'Accept-Encoding': 'gzip, deflate, sdch',

    'Accept-Language': 'zh-CN,zh;q=0.8'

}

def get_page(url):

    headers = dict(base_headers)

    print('Getting',url)

    try:

        r = requests.get(url,headers=headers)

        print('Getting result',url,r.status_code)

        if r.status_code == 200:

            return r.text

    except ConnectionError:

        pritn('Cramling Failed',url)

        return None

# 道生一：创建抽取代理的metaclass

class ProxyMetaclass(type):

    """

        元类，在FreeProxyGetter类中加入

        __CrawlName__,__CrawlFunc__和__CrawlFuncCount__

        三个参数，分别表示爬虫函数名，函数实例和爬虫函数的数量。

    """

    # __new__控制__init__的执行，所以在其执行之前

    # cls:代表要__init__的类，此参数在实例化时由Python解释器自动提供

    # name:类名

    # bases：代表继承父类的集合

    # attrs：类的方法及属性的集合

    def __new__(cls, name, bases, attrs):

        count = 0

        # 在attrs字典加入两个key,key的值是个列表

        attrs['__CrawlFunc__'] = []

        attrs['__CrawlName__'] = []

        for k, v in attrs.items():

            if 'crawl_' in k:

                attrs['__CrawlName__'].append(k) #函数名依次添加进attrs['__CrawlName__']列表

                attrs['__CrawlFunc__'].append(v) #函数实例依次添加进attrs['__CrawlFunc__']列表

                print(k,v)

                #print(attrs['__CrawlName__'])

                count += 1

        for k in attrs['__CrawlName__']:

            # 剔除原有的字典键值对

            attrs.pop(k)

        attrs['__CrawlFuncCount__'] = count

        print(attrs)

        return type.__new__(cls, name, bases, attrs)

# 一生二：创建代理获取类

class ProxyGetter(object, metaclass=ProxyMetaclass):

    def get_raw_proxies(self, site):

        proxies = []

        print('Site', site)

        for func in self.__CrawlFunc__:

            if func.__name__==site:

                this_page_proxies = func(self)

                for proxy in this_page_proxies:

                    print('Getting', proxy, 'from', site)

                    proxies.append(proxy)
　　　　　　　　　　print(proxies)

        return proxies

    def crawl_daili66(self, page_count=4):

        start_url = 'http://www.66ip.cn/{}.html'

        urls = [start_url.format(page) for page in range(1, page_count + 1)] # format和%s的用法一样

        for url in urls:

            print('Crawling', url)

            html = get_page(url)

            if html:

                doc = pq(html)

                trs = doc('.containerbox table tr:gt(0)').items()

                for tr in trs:

                    ip = tr.find('td:nth-child(1)').text()

                    port = tr.find('td:nth-child(2)').text()

                    yield ':'.join([ip, port])

　　'''

    def crawl_proxy360(self):

        start_url = 'http://www.proxy360.cn/Region/China'

        print('Crawling', start_url)

        html = get_page(start_url)

        if html:

            doc = pq(html)

            lines = doc('div[name="list_proxy_ip"]').items()

            for line in lines:

                ip = line.find('.tbBottomLine:nth-child(1)').text()

                port = line.find('.tbBottomLine:nth-child(2)').text()

                yield ':'.join([ip, port])

　　'''

    def crawl_goubanjia(self):

        start_url = 'http://www.goubanjia.com/free/gngn/index.shtml'

        html = get_page(start_url)

        if html:

            doc = pq(html)

            tds = doc('td.ip').items()

            for td in tds:

                td.find('p').remove()

                yield td.text().replace(' ', '')

if __name__ == '__main__':

    # 二生三：实例化ProxyGetter

    crawler = ProxyGetter()

    print(crawler.__CrawlName__)

    # 三生万物

    for site_label in range(crawler.__CrawlFuncCount__):

        site = crawler.__CrawlName__[site_label] # site_label是列表的索引值

        myProxies = crawler.get_raw_proxies(site)

运行结果

D:\pythontest>python proxy_ip.py

crawl_goubanjia <function ProxyGetter.crawl_goubanjia at 0x00000000035D2510>

crawl_daili66 <function ProxyGetter.crawl_daili66 at 0x00000000035D2488>

{'__qualname__': 'ProxyGetter', '__module__': '__main__', '__CrawlName__': ['cra

wl_goubanjia', 'crawl_daili66'], '__CrawlFunc__': [<function ProxyGetter.crawl_g

oubanjia at 0x00000000035D2510>, <function ProxyGetter.crawl_daili66 at 0x000000

00035D2488>], 'get_raw_proxies': <function ProxyGetter.get_raw_proxies at 0x0000

0000035D2400>, '__CrawlFuncCount__': }

['crawl_goubanjia', 'crawl_daili66']

Site crawl_goubanjia

Getting http://www.goubanjia.com/free/gngn/index.shtml

Getting result http://www.goubanjia.com/free/gngn/index.shtml 403

[]

Site crawl_daili66

Crawling=== http://www.66ip.cn/1.html

Getting http://www.66ip.cn/1.html

Getting result http://www.66ip.cn/1.html 200

Getting 123.163.97.198: from crawl_daili66

Getting 36.249.109.21: from crawl_daili66

Getting 163.204.245.52: from crawl_daili66

Getting 222.189.247.207: from crawl_daili66

Getting 87.250.218.12: from crawl_daili66

Getting 118.172.176.61: from crawl_daili66

Getting 134.119.214.206: from crawl_daili66

Getting 110.74.208.154: from crawl_daili66

Crawling=== http://www.66ip.cn/2.html

Getting http://www.66ip.cn/2.html

Getting result http://www.66ip.cn/2.html 200

Getting 120.234.138.102: from crawl_daili66

Getting 110.86.136.127: from crawl_daili66

Getting 59.57.38.197: from crawl_daili66

Getting 202.62.86.94: from crawl_daili66

Getting 210.22.176.146: from crawl_daili66

Getting 180.183.136.212: from crawl_daili66

Getting 183.87.153.98: from crawl_daili66

Getting 222.124.2.186: from crawl_daili66

Getting 123.169.126.9: from crawl_daili66

Getting 123.169.126.93: from crawl_daili66

Getting 158.255.249.58: from crawl_daili66

Getting 1.198.72.242: from crawl_daili66

Crawling=== http://www.66ip.cn/3.html

Getting http://www.66ip.cn/3.html

Getting result http://www.66ip.cn/3.html 200

Getting 163.204.246.10: from crawl_daili66

Getting 186.159.112.6: from crawl_daili66

Getting 163.204.246.102: from crawl_daili66

Getting 88.87.72.72: from crawl_daili66

Getting 193.169.118.6: from crawl_daili66

Getting 196.216.220.204: from crawl_daili66

Getting 185.109.62.124: from crawl_daili66

Getting 1.193.246.78: from crawl_daili66

Getting 188.131.239.119: from crawl_daili66

Getting 1.10.188.93: from crawl_daili66

Getting 182.116.237.203: from crawl_daili66

Getting 139.99.223.230: from crawl_daili66

Crawling=== http://www.66ip.cn/4.html

Getting http://www.66ip.cn/4.html

Getting result http://www.66ip.cn/4.html 200

Getting 163.204.246.232: from crawl_daili66

Getting 117.28.96.105: from crawl_daili66

Getting 202.29.220.34: from crawl_daili66

Getting 123.169.114.80: from crawl_daili66

Getting 115.42.34.3: from crawl_daili66

Getting 41.84.131.78: from crawl_daili66

Getting 123.163.96.207: from crawl_daili66

Getting 182.35.83.12: from crawl_daili66

Getting 191.241.226.230: from crawl_daili66

Getting 202.138.236.35: from crawl_daili66

Getting 194.1.193.226: from crawl_daili66

Getting 202.158.77.122: from crawl_daili66

['123.163.97.198:9999', '36.249.109.21:9999', '163.204.245.52:9999', '222.189.247.207:9999', '87.250.218.12:44168',
'118.172.176.61:8080', '134.119.214.206:1080', '110.74.208.154:21776', '120.234.138.102:53779', '110.86.136.127:9999',
'59.57.38.197:9999', '202.62.86.94:83', '210.22.176.146:37299', '180.183.136.212:8080', '183.87.153.98:49602',
'222.124.2.186:8080', '123.169.126.9:3', '123.169.126.93:9999', '158.255.249.58:50100', '1.198.72.242:9999',
'163.204.246.10:2', '186.159.112.6:53281', '163.204.246.102:9999', '88.87.72.72:8080', '193.169.118.6:53281',
'185.109.62.124:808', '1.193.246.78:9999', '188.131.239.119:8118', '1.10.188.93:34871', '182.116.237.203:9999',
'139.99.223.230:8080', '163.204.246.232:9999', '117.28.96.105:9999', '202.29.220.34:38961', '123.169.114.80:9999',
'115.42.34.3:8080', '41.84.131.78:53281', '123.163.96.207:9999', '182.35.83.12:9999', '191.241.226.230:53281',
'202.138.236.35:56413', '194.1.193.226:35646','196.216.220.204:36739', '202.158.77.122:47284']



//看来只有一个代理网站能爬到数据


												


											
Python 爬取各大代理IP网站(元类封装)的更多相关文章
	

    
								
  1. python爬取高匿代理IP（再也不用担心会进小黑屋了）
		
    为什么要用代理IP 很多人学习python,不知道从何学起.很多人学习python,掌握了基本语法过后,不知道在哪里寻找案例上手.很多已经做案例的人,却不知道如何去学习更加高深的知识.那么针对这三类人 ...
    
		
    2. 
						
  2. 利用Python爬取可用的代理IP
		
    前言 就以最近发现的一个免费代理IP网站为例:http://www.xicidaili.com/nn/.在使用的时候发现很多IP都用不了. 所以用Python写了个脚本,该脚本可以把能用的代理IP检测 ...
    
		
    3. 
						
  3. 手把手教你使用Python爬取西刺代理数据（下篇）
		
    /1 前言/ 前几天小编发布了手把手教你使用Python爬取西次代理数据(上篇),木有赶上车的小伙伴,可以戳进去看看.今天小编带大家进行网页结构的分析以及网页数据的提取,具体步骤如下. /2 首页分析 ...
    
		
    4. 
						
  4. python scrapy 爬取西刺代理ip(一基础篇)（ubuntu环境下）  -赖大大
		
    第一步:环境搭建 1.python2 或 python3 2.用pip安装下载scrapy框架 具体就自行百度了,主要内容不是在这. 第二步:创建scrapy(简单介绍) 1.Creating a p ...
    
		
    5. 
						
  5. python+scrapy 爬取西刺代理ip(一)
		
    转自:https://www.cnblogs.com/lyc642983907/p/10739577.html 第一步:环境搭建 1.python2 或 python3 2.用pip安装下载scrap ...
    
		
    6. 
						
  6. 学以致用:Python爬取廖大Python教程制作pdf
		
    当我学了廖大的Python教程后,感觉总得做点什么,正好自己想随时查阅,于是就开始有了制作PDF这个想法. 想要把教程变成PDF有三步: 先生成空html,爬取每一篇教程放进一个新生成的div,这样就 ...
    
		
    7. 
						
  7. 深夜，我用python爬取了整个斗图网站，不服来斗
		
    QQ.微信斗图总是斗不过,索性直接来爬斗图网,我有整个网站的图,不服来斗. 废话不多说,选取的网站为斗图啦,我们先简单来看一下网站的结构 网页信息 从上面这张图我们可以看出,一页有多套图,这个时候我们 ...
    
		
    8. 
						
  8. Scrapy爬取西刺代理ip流程
		
    西刺代理爬虫 1. 新建项目和爬虫 scrapy startproject daili_ips ...... cd daili_ips/ #爬虫名称和domains scrapy genspider  ...
    
		
    9. 
						
  9. python爬取网站数据
		
    开学前接了一个任务,内容是从网上爬取特定属性的数据.正好之前学了python,练练手. 编码问题 因为涉及到中文,所以必然地涉及到了编码的问题,这一次借这个机会算是彻底搞清楚了. 问题要从文字的编码讲 ...
    
		
    10. 
		

	


随机推荐
	

    
									
  1. PHP FILTER_CALLBACK 过滤器
			
    定义和用法 FILTER_CALLBACK 过滤器调用用户自定义函数来过滤数据. 该过滤器为我们提供了对数据过滤的完全控制. 指定的函数必须存入名为 "options" 的关联数组 ...
    
			
    2. 
						
  2. <自动化测试>之<Selenium API 的用法1>
			
    今天,简单,举例说一下在用python+selenium中元素定位的主要方法,第一部分是单个元素的操作,第二部分是一类元素的操作,实际操作中注意区分 #!/usr/bin/env python # - ...
    
			
    3. 
						
  3. 【Spring Boot】Spring Boot项目设置多个配置文件，并在生产环境中的Tomcat设置对应的配置文件
			
    1.修改Spring Boot项目配置文件 除了主配置文件,另外创建2个配置文件,注意命名要用application-*.properties 主配置文件中写入,使用dev作为开发配置 spring. ...
    
			
    4. 
						
  4. C++ placement new与内存池
			
    参考:https://blog.csdn.net/Kiritow/article/details/51314612 有些时候我们需要能够长时间运行的程序(例如监听程序,服务器程序)对于这些7*24运行 ...
    
			
    5. 
						
  5. 将libvex移植到Visual Studio编译平台下的经验总结
			
    1. 两难 将libvex从Linux移植到Windows,移植工作聚集于Cross-Compiler,而不是预料的Cross-Platform. VC++ Compiler到目前为止只支持C89标准 ...
    
			
    6. 
						
  6. LeetCode题：旋转链表
			
    原题: 给定一个链表,旋转链表,将链表每个节点向右移动 k 个位置,其中 k 是非负数. 示例 1: 输入: 1->2->3->4->5->NULL, k = 2输出:  ...
    
			
    7. 
						
  7. JVM系列文章合集
			
    博客作者:纯洁的微笑 JVM系列(①):java类的加载机制 JVM系列(②):JVM内存结构 JVM系列(③):GC算法 垃圾收集器 JVM系列(④):jvm调优-命令大全(jps jstat jm ...
    
			
    8. 
						
  8. Java内部类成员
			
    内部类可以访问其所有实例成员,实例字段和其封闭类的实例方法.参考如下实例 - 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 2 ...
    
			
    9. 
						
  9. TP5.1/TP框架的访问控制，访问不存在的模块、控制器、方法等控制
			
    TP框架的访问控制,默认模块.控制器.方法等 在tp框架中,config文件夹下的app.php文件可以设置默认的空模块名,默认的空控制器名. 举例:以上项目中有admin.common.api.er ...
    
			
    10. 
						
  10. CentOS 7 安装 nginx1.15
			
    1,安装依赖 yum -y install gcc zlib zlib-devel pcre-devel openssl openssl-devel SSL功能需要openssl库 gzip模块需要z ...
    
			
    11.