parse html file to get proxies :return:
(self, html)
| 15 | ignore = False |
| 16 | |
| 17 | def parse(self, html): |
| 18 | """ |
| 19 | parse html file to get proxies |
| 20 | :return: |
| 21 | """ |
| 22 | # doc = pq(html)('.text-left') |
| 23 | ip_address = re.compile('([\d:\.]*).*?<br>') |
| 24 | hosts_ports = ip_address.findall(html) |
| 25 | for addr in hosts_ports: |
| 26 | addr_split = addr.split(':') |
| 27 | if(len(addr_split) == 2): |
| 28 | host = addr_split[0] |
| 29 | port = addr_split[1] |
| 30 | yield Proxy(host=host, port=port) |
| 31 | |
| 32 | |
| 33 | if __name__ == '__main__': |