usproxy.py 文件源码

def parse_page(self, response):
        pattern = re.compile(
                '<tr><td>(.*?)</td><td>(.*?)</td><td>(.*?)</td><td>(.*?)</td><td>(.*?)</td><td>(.*?)</td><td>('
                '.*?)</td><td>(.*?)</td></tr>',
                re.S)
        items = re.findall(pattern, response.body)

        if items is not None:
            for item in items:
                proxy = Proxy()
                proxy.set_value(
                        ip = item[0],
                        port = item[1],
                        country = item[3],
                        anonymity = item[4],
                        source = self.name,
                )

                self.add_proxy(proxy)