proxylistplus.py 文件源码

def parse_page(self, response):
        self.write(response.body)

        sel = Selector(response)
        infos = sel.xpath('//tr[@class="cells"]').extract()
        for i, info in enumerate(infos):
            val = Selector(text = info)
            ip = val.xpath('//td[2]/text()').extract_first()
            port = val.xpath('//td[3]/text()').extract_first()
            country = val.xpath('//td[5]/text()').extract_first()
            anonymity = val.xpath('//td[4]/text()').extract_first()

            proxy = Proxy()
            proxy.set_value(
                    ip = ip,
                    port = port,
                    country = country,
                    anonymity = anonymity,
                    source = self.name,
            )

            self.add_proxy(proxy = proxy)