from abc import ABC, abstractmethod
from typing import List
import requests
import bs4
from .model import ProxyModel


class AbsFreeProxyBase(ABC):
    # 请求
    http = requests

    # 初始化
    def __init__(self, url, code, **kwargs):
        """
        :param url: 请求地址
        :param code: 页面编码
        :param kw: 附加信息
        """
        self.url = url
        self.code = code
        self.kwargs = kwargs
        self.beautifulsoup = bs4.BeautifulSoup

    # 模板方法模式
    # 第一步 获取页面内容  第二步 解析内容  第二步 格式化数据
    def run(self) -> List[ProxyModel]:
        text = self.get_page_text()
        soup = self.beautifulsoup(text, \'lxml\')
        data = self.parse_text(soup)
        return self.to_proxy(data)

    # 获取页面内容
    def get_page_text(self):
        res = AbsFreeProxyBase.http.get(self.url, **self.kwargs)
        if not res.ok:
            res.raise_for_status()
        return res.content.decode(self.code)

    # 解析内容
    @abstractmethod
    def parse_text(self, soup: bs4.BeautifulSoup) -> List[list]:
        pass

    # 格式转换
    @abstractmethod
    def to_proxy(self, data:List[list]) -> List[ProxyModel]:
        pass

from .base import AbsFreeProxyBase
from typing import List
from .model import ProxyModel
import re

\'\'\'
快代理
https://www.kuaidaili.com/free
\'\'\'


class WWW_KUAIDAILI_COM(AbsFreeProxyBase):

    # 初始化
    def __init__(self, url, code=\'utf-8\', **kwargs):
        super().__init__(url, code, **kwargs)

    # 解析内容
    def parse_text(self, soup) -> List[list]:
        """
        格式如下：
        IP     port(端口)     匿名度     类型(HTTP/https)     位置     响应速度     最后验证时间
        """
        regex = re.compile(r\'<td[^>]*>([^<>]+)</td>\')
        rows = soup.select(\'.table-bordered tr\')
        result = []
        for row in [str(n) for n in rows]:
            item = regex.findall(row)
            item and result.append(item)
        return result

    # 格式转换
    def to_proxy(self, data: List[list]) -> List[ProxyModel]:
        result = []
        for item in data:
            result.append(ProxyModel(item[3], item[0], item[1], item[2]))
        return result

from website import ProxyFactory
from browser.agent import useragent

factory = ProxyFactory()
headers = {
    \'user-agent\': useragent.random()
}
\'\'\'
66免费代理网
www = factory.create(\'http://www.66ip.cn/mo.php?sxb=&tqsl=100&port=&export=&ktip=&sxa=&submit=%CC%E1++%C8%A1&textarea=\',
                     \'gbk\',
                     headers=headers)
\'\'\'

\'\'\'
小幻HTTP代理 
www = factory.create(\'https://ip.ihuan.me/\',headers = headers)
\'\'\'

\'\'\'
89免费代理 http://www.89ip.cn/
www = factory.create(\'http://www.89ip.cn/\',headers = headers)
\'\'\'

\'\'\'
无忧代理 http://www.data5u.com/
www = factory.create(\'http://www.data5u.com/\',headers = headers)
\'\'\'


\'\'\'
http://www.goubanjia.com/
全网代理IP 
www = factory.create(\'http://www.goubanjia.com/\',headers = headers)
\'\'\'


\'\'\'
云代理 http://www.ip3366.net/
www = factory.create(\'http://www.ip3366.net/\',\'gbk\',headers = headers)
\'\'\'

\'\'\'
快代理
https://www.kuaidaili.com/free
\'\'\'
www = factory.create(\'https://www.kuaidaili.com/free\',headers = headers)
data = www.run()

print(data)