proxy_pool/ProxyGetter/getFreeProxy.py

# -*- coding: utf-8 -*-
# !/usr/bin/env python
"""
-------------------------------------------------
   File Name：     GetFreeProxy.py
   Description :  抓取免费代理
   Author :       JHao
   date：          2016/11/25
-------------------------------------------------
   Change Activity:
                   2016/11/25:
-------------------------------------------------
"""
import re
import sys
import requests

sys.path.append('..')

from Util.WebRequest import WebRequest
from Util.utilFunction import getHtmlTree

# for debug to disable insecureWarning
requests.packages.urllib3.disable_warnings()


class GetFreeProxy(object):
    """
    proxy getter
    """

    @staticmethod
    def freeProxy01():
        """
        无忧代理 http://www.data5u.com/
        几乎没有能用的
        :return:
        """
        url_list = [
            'http://www.data5u.com/',
        ]
        for url in url_list:
            html_tree = getHtmlTree(url)
            ul_list = html_tree.xpath('//ul[@class="l2"]')
            for ul in ul_list:
                try:
                    yield ':'.join(ul.xpath('.//li/text()')[0:2])
                except Exception as e:
                    print(e)

    @staticmethod
    def freeProxy02(count=20):
        """
        代理66 http://www.66ip.cn/
        :param count: 提取数量
        :return:
        """
        urls = [
            "http://www.66ip.cn/mo.php?sxb=&tqsl={}&port=&export=&ktip=&sxa=&submit=%CC%E1++%C8%A1&textarea=",
            "http://www.66ip.cn/nmtq.php?getnum={}&isp=0&anonymoustype=0&s"
            "tart=&ports=&export=&ipaddress=&area=0&proxytype=2&api=66ip"
        ]

        try:
            import execjs
            import requests

            headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:34.0) Gecko/20100101 Firefox/34.0',
                       'Accept': '*/*',
                       'Connection': 'keep-alive',
                       'Accept-Language': 'zh-CN,zh;q=0.8'}
            session = requests.session()
            src = session.get("http://www.66ip.cn/", headers=headers).text
            src = src.split("</script>")[0] + '}'
            src = src.replace("<script>", "function test() {")
            src = src.replace("while(z++)try{eval(", ';var num=10;while(z++)try{var tmp=')
            src = src.replace(");break}", ";num--;if(tmp.search('cookie') != -1 | num<0){return tmp}}")
            ctx = execjs.compile(src)
            src = ctx.call("test")
            src = src[src.find("document.cookie="): src.find("};if((")]
            src = src.replace("document.cookie=", "")
            src = "function test() {var window={}; return %s }" % src
            cookie = execjs.compile(src).call('test')
            js_cookie = cookie.split(";")[0].split("=")[-1]
        except Exception as e:
            print(e)
            return

        for url in urls:
            try:
                html = session.get(url.format(count), cookies={"__jsl_clearance": js_cookie}, headers=headers).text
                ips = re.findall(r"\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}:\d{1,5}", html)
                for ip in ips:
                    yield ip.strip()
            except Exception as e:
                print(e)
                pass

    @staticmethod
    def freeProxy03(page_count=1):
        """
        西刺代理 http://www.xicidaili.com
        :return:
        """
        url_list = [
            'http://www.xicidaili.com/nn/',  # 高匿
            'http://www.xicidaili.com/nt/',  # 透明
        ]
        for each_url in url_list:
            for i in range(1, page_count + 1):
                page_url = each_url + str(i)
                tree = getHtmlTree(page_url)
                proxy_list = tree.xpath('.//table[@id="ip_list"]//tr[position()>1]')
                for proxy in proxy_list:
                    try:
                        yield ':'.join(proxy.xpath('./td/text()')[0:2])
                    except Exception as e:
                        pass

    @staticmethod
    def freeProxy04():
        """
        guobanjia http://www.goubanjia.com/
        :return:
        """
        url = "http://www.goubanjia.com/"
        tree = getHtmlTree(url)
        proxy_list = tree.xpath('//td[@class="ip"]')
        # 此网站有隐藏的数字干扰，或抓取到多余的数字或.符号
        # 需要过滤掉<p style="display:none;">的内容
        xpath_str = """.//*[not(contains(@style, 'display: none'))
                                        and not(contains(@style, 'display:none'))
                                        and not(contains(@class, 'port'))
                                        ]/text()
                                """
        for each_proxy in proxy_list:
            try:
                # :符号裸放在td下，其他放在div span p中，先分割找出ip，再找port
                ip_addr = ''.join(each_proxy.xpath(xpath_str))

                # HTML中的port是随机数，真正的端口编码在class后面的字母中。
                # 比如这个：
                # <span class="port CFACE">9054</span>
                # CFACE解码后对应的是3128。
                port = 0
                for _ in each_proxy.xpath(".//span[contains(@class, 'port')]"
                                          "/attribute::class")[0]. \
                        replace("port ", ""):
                    port *= 10
                    port += (ord(_) - ord('A'))
                port /= 8

                yield '{}:{}'.format(ip_addr, int(port))
            except Exception as e:
                pass

    @staticmethod
    def freeProxySixth():
        """
        讯代理 http://www.xdaili.cn/  已停用
        :return:
        """
        url = 'http://www.xdaili.cn/ipagent/freeip/getFreeIps?page=1&rows=10'
        request = WebRequest()
        try:
            res = request.get(url, timeout=10).json()
            for row in res['RESULT']['rows']:
                yield '{}:{}'.format(row['ip'], row['port'])
        except Exception as e:
            pass

    @staticmethod
    def freeProxySeventh():
        """
        快代理 https://www.kuaidaili.com
        """
        url_list = [
            'https://www.kuaidaili.com/free/inha/',
            'https://www.kuaidaili.com/free/intr/'
        ]
        for url in url_list:
            tree = getHtmlTree(url)
            proxy_list = tree.xpath('.//table//tr')
            for tr in proxy_list[1:]:
                yield ':'.join(tr.xpath('./td/text()')[0:2])

    @staticmethod
    def freeProxyEight():
        """
        秘密代理 http://www.mimiip.com  已停用
        """
        url_gngao = ['http://www.mimiip.com/gngao/%s' % n for n in range(1, 2)]  # 国内高匿
        url_gnpu = ['http://www.mimiip.com/gnpu/%s' % n for n in range(1, 2)]  # 国内普匿
        url_gntou = ['http://www.mimiip.com/gntou/%s' % n for n in range(1, 2)]  # 国内透明
        url_list = url_gngao + url_gnpu + url_gntou

        request = WebRequest()
        for url in url_list:
            r = request.get(url, timeout=10)
            proxies = re.findall(r'<td>(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})</td>[\w\W].*<td>(\d+)</td>', r.text)
            for proxy in proxies:
                yield ':'.join(proxy)

    @staticmethod
    def freeProxyNinth():
        """
        码农代理 https://proxy.coderbusy.com/ 已停用
        :return:
        """
        urls = ['https://proxy.coderbusy.com/classical/country/cn.aspx?page=1']
        request = WebRequest()
        for url in urls:
            r = request.get(url, timeout=10)
            proxies = re.findall('data-ip="(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})".+?>(\d+)</td>', r.text)
            for proxy in proxies:
                yield ':'.join(proxy)

    @staticmethod
    def freeProxyTen():
        """
        云代理 http://www.ip3366.net/free/
        :return:
        """
        urls = ['http://www.ip3366.net/free/']
        request = WebRequest()
        for url in urls:
            r = request.get(url, timeout=10)
            proxies = re.findall(r'<td>(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})</td>[\s\S]*?<td>(\d+)</td>', r.text)
            for proxy in proxies:
                yield ":".join(proxy)

    @staticmethod
    def freeProxyEleven():
        """
        IP海 http://www.iphai.com/free/ng
        :return:
        """
        urls = [
            'http://www.iphai.com/free/ng',
            'http://www.iphai.com/free/np',
            'http://www.iphai.com/free/wg',
            'http://www.iphai.com/free/wp'
        ]
        request = WebRequest()
        for url in urls:
            r = request.get(url, timeout=10)
            proxies = re.findall(r'<td>\s*?(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})\s*?</td>[\s\S]*?<td>\s*?(\d+)\s*?</td>',
                                 r.text)
            for proxy in proxies:
                yield ":".join(proxy)

    @staticmethod
    def freeProxyTwelve(page_count=2):
        """
        http://ip.jiangxianli.com/?page=
        免费代理库
        超多量
        :return:
        """
        for i in range(1, page_count + 1):
            url = 'http://ip.jiangxianli.com/?page={}'.format(i)
            html_tree = getHtmlTree(url)
            tr_list = html_tree.xpath("/html/body/div[1]/div/div[1]/div[2]/table/tbody/tr")
            if len(tr_list) == 0:
                continue
            for tr in tr_list:
                yield tr.xpath("./td[2]/text()")[0] + ":" + tr.xpath("./td[3]/text()")[0]

    @staticmethod
    def freeProxyWallFirst():
        """
        墙外网站 cn-proxy
        :return:
        """
        urls = ['http://cn-proxy.com/', 'http://cn-proxy.com/archives/218']
        request = WebRequest()
        for url in urls:
            r = request.get(url, timeout=10)
            proxies = re.findall(r'<td>(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})</td>[\w\W]<td>(\d+)</td>', r.text)
            for proxy in proxies:
                yield ':'.join(proxy)

    @staticmethod
    def freeProxyWallSecond():
        """
        https://proxy-list.org/english/index.php
        :return:
        """
        urls = ['https://proxy-list.org/english/index.php?p=%s' % n for n in range(1, 10)]
        request = WebRequest()
        import base64
        for url in urls:
            r = request.get(url, timeout=10)
            proxies = re.findall(r"Proxy\('(.*?)'\)", r.text)
            for proxy in proxies:
                yield base64.b64decode(proxy).decode()

    @staticmethod
    def freeProxyWallThird():
        urls = ['https://list.proxylistplus.com/Fresh-HTTP-Proxy-List-1']
        request = WebRequest()
        for url in urls:
            r = request.get(url, timeout=10)
            proxies = re.findall(r'<td>(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})</td>[\s\S]*?<td>(\d+)</td>', r.text)
            for proxy in proxies:
                yield ':'.join(proxy)


if __name__ == '__main__':
    from CheckProxy import CheckProxy

    # CheckProxy.checkGetProxyFunc(GetFreeProxy.freeProxy01())
    # CheckProxy.checkGetProxyFunc(GetFreeProxy.freeProxy02)
    # CheckProxy.checkGetProxyFunc(GetFreeProxy.freeProxy03)
    # CheckProxy.checkGetProxyFunc(GetFreeProxy.freeProxy04)
    CheckProxy.checkGetProxyFunc(GetFreeProxy.freeProxySixth)
    # CheckProxy.checkGetProxyFunc(GetFreeProxy.freeProxySeventh)
    # CheckProxy.checkGetProxyFunc(GetFreeProxy.freeProxyEight)
    # CheckProxy.checkGetProxyFunc(GetFreeProxy.freeProxyNinth)
    # CheckProxy.checkGetProxyFunc(GetFreeProxy.freeProxyTen)
    # CheckProxy.checkGetProxyFunc(GetFreeProxy.freeProxyEleven)
    # CheckProxy.checkGetProxyFunc(GetFreeProxy.freeProxyTwelve)

    # CheckProxy.checkAllGetProxyFunc()