Python 爬取各大代理IP网站(元类封装)

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

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 ...
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 ...
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 ...
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 ...
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 ...
学以致用&colon;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 ...
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 ...
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 ...
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 ...

随机推荐

三部曲二（基本算法、动态规划、搜索）-1004-Instant Complexity
Instant Complexity Time Limit : 2000/1000ms (Java/Other) Memory Limit : 20000/10000K (Java/Other) ...
linux下查看分区信息和剩余空间大小
1. 查看Linux系统分区信息,使用命令“fdisk -l” 2.使用命令”df -l和df -h“具体查看分区使用状况.实际这两个命令具有一样的作用区别是显示的容量单位不一样,当然也可以直接使用明 ...
dedecms织梦如何删除所有的文章？
dedecms织梦如何删除所有的文章?dede一键删除所有文章的SQL命令: DELETE FROM dede_addonarticle WHERE aid >= 1 and aid<= ...
String or binary data would be truncated
在使用Typed Dataset进行数据的插入时,会报这样的错:String or binary data would be truncated. 我碰到的原因是数据库中字段的长度过段,插入时内容被 ...
javascript 滚动条下拉导航fixed
<!doctype html> <html> <style> body{ margin:; padding:; } #top{ background:#; widt ...
php数字转中文
function number2Chinese($num, $m = 1) { switch($m) { case 0: $CNum = array( array('零','壹','贰','叁','肆 ...
SQL远程备份
原文:SQL远程备份 set ANSI_NULLS ON set QUOTED_IDENTIFIER ON go -- ====================================== ...
Mac 安装python ，anaconda。彻底卸载anaconda的方法
To uninstall Anaconda open a terminal window and remove the entire anaconda install directory: rm -r ...
前端之旅HTML与CSS篇之清除浮动塌陷
以下内容为转载. 方法1:给浮动的元素的上级添加高度如果一个元素要浮动,那么它的祖先元素一定要有高度.高度的盒子,才能关住浮动.只要浮动在一个有高度的盒子中,那么这个浮动就不会影响后面的浮动元素.所以 ...
C&num; NPOI生成Excel文档（简单样式）
效果图: 代码: /// <summary> /// 导出Excel /// </summary> /// <param name="DeptId" ...