xiladaili crawler, http://www.xiladaili.com/
| 7 | |
| 8 | |
| 9 | class XiladailiCrawler(BaseCrawler): |
| 10 | """ |
| 11 | xiladaili crawler, http://www.xiladaili.com/ |
| 12 | """ |
| 13 | urls = ["http://www.xiladaili.com/"] |
| 14 | |
| 15 | def parse(self, html): |
| 16 | """ |
| 17 | parse html file to get proxies |
| 18 | :return: |
| 19 | """ |
| 20 | etree_html = etree.HTML(html) |
| 21 | ip_ports = etree_html.xpath("//tbody/tr/td[1]/text()") |
| 22 | |
| 23 | for ip_port in ip_ports: |
| 24 | host = ip_port.partition(":")[0] |
| 25 | port = ip_port.partition(":")[2] |
| 26 | yield Proxy(host=host, port=port) |
| 27 | |
| 28 | |
| 29 | if __name__ == '__main__': |