{"id":546,"date":"2020-09-07T03:59:01","date_gmt":"2020-09-06T19:59:01","guid":{"rendered":"https:\/\/byy3.com\/?p=546"},"modified":"2021-01-09T10:10:09","modified_gmt":"2021-01-09T02:10:09","slug":"python%e7%94%a8%e4%ba%8e%e7%88%ac%e5%8f%96ip%e4%bb%a3%e7%90%86%e5%9c%b0%e5%9d%80","status":"publish","type":"post","link":"https:\/\/byy3.com\/?p=546","title":{"rendered":"python\u7528\u4e8e\u722c\u53d6ip\u4ee3\u7406\u5730\u5740\u5b58\u50a8txt"},"content":{"rendered":"

#\u6cd3\u6e90\u89c6\u91ce-\u535a\u5f08\u6e90\u00a0\u00a0<\/a><\/p>\n

#python3\u7528\u4e8e\u722c\u53d6ip\u4ee3\u7406\u5730\u5740\uff0c\u7a0b\u5e8f\u6682\u672a\u5b8c\u5584\uff0c\u6ca1\u6709\u6709\u505a\u81ea\u52a8\u7ffb\u9875<\/p>\n

import requests
\nimport parsel
\nimport time<\/p>\n

def check_ip(proxies_list):
\n\"\"\"\u68c0\u6d4bip\u7684\u65b9\u6cd5\"\"\"
\nheaders = {'User-Agent': 'Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/79.0.3945.79 Safari\/537.36'}<\/p>\n

can_use = []
\nfor proxy in proxies_list:
\ntry:
\nresponse = requests.get('http:\/\/www.baidu.com', headers=headers, proxies=proxy, timeout=0.1) # \u8d85\u65f6\u62a5\u9519
\nif response.status_code == 200:
\ncan_use.append(proxy)
\nexcept Exception as error:
\nprint(error)
\nreturn can_use
\nimport requests
\nimport parsel<\/p>\n

# 1\u3001\u786e\u5b9a\u722c\u53d6\u7684url\u8def\u5f84\uff0cheaders\u53c2\u6570
\nbase_url = 'https:\/\/www.kuaidaili.com\/free\/intr'
\nheaders = {'User-Agent': 'Mozilla\/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit\/537.36 (KHTML, like Gecko) Chrome\/79.0.3945.79 Safari\/537.36'}<\/p>\n

# 2\u3001\u53d1\u9001\u8bf7\u6c42 -- requests \u6a21\u62df\u6d4f\u89c8\u5668\u53d1\u9001\u8bf7\u6c42\uff0c\u83b7\u53d6\u54cd\u5e94\u6570\u636e
\nresponse = requests.get(base_url, headers=headers)
\ndata = response.text
\n# print(data)
\n#\u6253\u5f00\u4e00\u4e2aip.txt\u6587\u4ef6\u7528\u4e8e\u8bb0\u5f55
\nfile = open('ip.txt', 'a+', encoding='utf-8')\u00a0 #'a+'\u8868\u793a\uff08\u53ef\u8ffd\u52a0\u53ef\u5199\uff0c\u6587\u4ef6\u82e5\u4e0d\u5b58\u5728\u5c31\u521b\u5efa\uff09<\/p>\n

for j in range(1,10):
\nprint(\"\u6b63\u5728\u722c\u53d6\u7b2c\"+str(j)+\"\u9875IP\")<\/p>\n

# 3\u3001\u89e3\u6790\u6570\u636e -- parsel \u8f6c\u5316\u4e3aSelector\u5bf9\u8c61\uff0cSelector\u5bf9\u8c61\u5177\u6709xpath\u7684\u65b9\u6cd5\uff0c\u80fd\u591f\u5bf9\u8f6c\u5316\u7684\u6570\u636e\u8fdb\u884c\u5904\u7406
\n# 3\u30011 \u8f6c\u6362python\u53ef\u4ea4\u4e92\u7684\u6570\u636e\u7c7b\u578b
\nhtml_data = parsel.Selector(data)
\n# 3\u30012 \u89e3\u6790\u6570\u636e
\nparse_list = html_data.xpath('\/\/table[@class=\"table table-bordered table-striped\"]\/tbody\/tr') # \u8fd4\u56deSelector\u5bf9\u8c61
\n# print(parse_list)<\/p>\n

# \u514d\u8d39 IP {\"\u534f\u8bae\":\"IP:port\"}
\n# \u5faa\u73af\u904d\u5386\uff0c\u4e8c\u6b21\u63d0\u53d6
\nproxies_list = []
\nfor tr in parse_list:
\nproxies_dict = {}
\nhttp_type = tr.xpath('.\/td[4]\/text()').extract_first()
\nip_num = tr.xpath('.\/td[1]\/text()').extract_first()
\nport_num = tr.xpath('.\/td[2]\/text()').extract_first()
\n# print(http_type, ip_num, port_num)
\n#\u5199\u5165txt\u6587\u4ef6
\nfile.write(ip_num)
\nfile.write(' ')
\nfile.write(port_num)
\nfile.write('\\n')<\/p>\n

# \u6784\u5efa\u4ee3\u7406ip\u5b57\u5178
\nproxies_dict[http_type] = ip_num + ':' + port_num
\n# print(proxies_dict)
\nproxies_list.append(proxies_dict)<\/p>\n

print(proxies_list)
\nprint(\"\u83b7\u53d6\u5230\u7684\u4ee3\u7406ip\u6570\u91cf\uff1a\", len(proxies_list), '\u4e2a')<\/p>\n

file.close()<\/p>\n","protected":false},"excerpt":{"rendered":"