超简单获取主域名加备案号脚本(通过获取icp网站爬取)

from urllib import request
import sys
from  urllib import  parse
import  re




base_url = "https://www.beianx.cn/search/"

real_url = base_url + parse.quote(sys.argv[1])

print(real_url)

s = request.urlopen(request.Request(real_url)).read().decode('utf-8')

alist = re.findall('<td\s+class="align-middle">\s+<div>\s+<a\shref=[^>]+>(.+)<\/a>',s)
blist = re.findall('<td\s+class="align-middle"\s+nowrap="nowrap">\s+(.+)\r\s+<\/td>',s)
print("主域名数量:",len(alist))
for a in alist:
    print(a)
for b in blist:
    print(b)




posted @ 2022-06-23 17:09  Azathoth_jk  阅读(383)  评论(0)    收藏  举报