def ipc_record(simple_url):
ipc_url = "https://icp.aizhan.com/" + simple_url
print(current_time("yellow").format("站长工具备案查询中..."))
print(current_time("sep_prefix"))
result = get_req(ipc_url)
if result:
result_text = result.text
url_error = re.findall("未找到", result_text, re.S)
unit_name = re.findall("主办单位名称.*?<td>(.*?)</td>", result_text, re.S)
unit_nature = re.findall("主办单位性质.*?<td>(.*?)</td>", result_text, re.S)
website_filing = re.findall("网站备案/许可证号.*?<span>(.*?)</span>",
result_text, re.S)
website_name = re.findall("网站名称.*?<td>(.*?)</td>", result_text, re.S)
Website_owner = re.findall("网站负责人.*?<td>(.*?)</td>", result_text, re.S)
Legal_representative = re.findall("法定代表人.*?<span>(.*?)</span>",
result_text, re.S)
Company_address = re.findall("公司地址.*?title=\"(.*?)\">", result_text,
re.S)
industry = re.findall("行业.*?<span>(.*?)</span>", result_text, re.S)
found_time = re.findall("成立时间.*?<span>(.*?)</span>", result_text, re.S)
if url_error:
print(current_time("red").format("url有误，请重试：" + ipc_url))
print(current_time("sep_suffix"))
return
if unit_name:
print(
current_time("green").format("主办单位名称：{}").format(unit_name[0]))
if industry:
print(current_time("green").format("行业：{}").format(industry[0]))
if found_time:
print(
current_time("green").format("成立时间：{}").format(found_time[0]))
if unit_nature:
print(
current_time("green").format("主办单位性质：{}").format(
unit_nature[0]))
if website_filing:
print(
current_time("green").format("网站备案/许可证号：{}").format(
website_filing[0]))
if website_name:
print(
current_time("green").format("网站名称：{}").format(
website_name[0]))
if Website_owner:
if not Website_owner[0][0] == "\'":
print(
current_time("green").format("网站负责人：{}").format(
Website_owner[0]))
if Legal_representative:
print(
current_time("green").format("法定代表人：{}").format(
Legal_representative[0]))
if Company_address:
print(
current_time("green").format("公司地址：{}").format(
Company_address[0]))
print(current_time("sep_suffix"))
def ssl_domain(simple_url):
query_url = "https://crt.sh/?q={}".format(simple_url)
content = get_req(query_url).text
pattern = re.compile(
"<TD>(\w{0,100}\.\w{0,100}\.?\w{0,100}\.?\w{0,100}\.?\w{0,100}\.?\w{0,100}\.?\w{0,100}\.?\w{0,100})</TD>",
re.S)
if content:
reg_match(content, pattern)
def searchdns_netcraft_com(simple_url):
query_url = "https://searchdns.netcraft.com/?restriction=site+contains&host={}&position=limited".format(
simple_url)
cookie = "netcraft_js_verification_challenge=djF8RUlTNmw3d3c3M2c1WlNOOWZ0UHBMOTNPZ3YzWmVjY0tXWDBnUm9xSEFid1c4dEtOcjNoTHRp%0AaTRUWTBxUTBZOHo2NkFUbEtGdlpnSQovanQ5eStTditRPT0KfDE1ODI4MTU5Mzc%3D%0A%7Cab7e7165c79edb9371c422b504bf4cdd28713046; netcraft_js_verification_response=957f5bb05b956dbd8a1790ae4529e9ad0e0b6eb2"
cookie_dict = {
i.split("=")[0]: i.split("=")[-1]
for i in cookie.split("; ")
}
content = get_req(query_url, cookies=cookie_dict).text
pattern = re.compile("""rel="nofollow">.*?(\w{0,100}\..*?<b>.*?)</b>""",
re.S)
if content:
reg_match(content, pattern)
def get_url_result(html_file):
while True:
if queue.empty():
break
else:
url = queue.get()
ip_list.append(url)
result = get_req(url)
if result == None:
continue
response_code = result.status_code
result_encode = get_encode(result)
result.encoding = result_encode
response_title = get_title(result.text)
write_file(
"""<a href="{}">{}</a>  {}  {}<br>""".
format(url, url, response_code, response_title), html_file)
def aizhan_whois(simple_url):
query_url = "https://whois.aizhan.com/{}".format(simple_url) + "/"
print(current_time("yellow").format("爱站whois查询中..."))
print(current_time("sep_prefix"))
result = get_req(query_url)
if result:
try:
result_text = result.text
domain = re.findall("""<td class="thead">域名</td>.*?<td>(.*?)<""", result_text, re.S)[0]
if domain.strip()[0] == "\'":
print(current_time("red").format("url有误，请重试：" + query_url))
print(current_time("sep_suffix"))
return
except:
print(current_time("red").format("url有误，请重试：" + query_url))
return
registrar = re.findall("""<td class="thead">注册商</td>.*?<td>(.*?)<""", result_text, re.S)[0]
domain_name = re.findall("""<td class="thead">域名持有人/机构名称</td>.*?<td>(.*?)<""", result_text, re.S)[0]
create_time = re.findall("""<td class="thead">创建时间</td>.*?<span>(.*?)<""", result_text, re.S)[0]
re_time = re.findall("""<td class="thead">更新时间</td>.*?<td>.*?<span>(.*?)<""", result_text, re.S)[0]
expiration_date = re.findall("""<td class="thead">过期时间</td>.*?<span>(.*?)<""", result_text, re.S)[0]
domain_server = re.findall("""<td class="thead">域名服务器</td>.*?<td>(\w.*?)<""", result_text, re.S)
dns_server = re.findall("""<td class="thead">DNS服务器</td>.*?<td>(\w.*?)<""", result_text, re.S)
try:
email = re.findall("Tech Email.*?>(.*?)<", result_text, re.S)[0]
except:
email = []
try:
Tech_City = re.findall("Tech City.*?>(.*?)<", result_text, re.S)[0]
except:
Tech_City = []
try:
Tech_Street = re.findall("Tech Street.*?>(.*?)<", result_text, re.S)[0]
except:
Tech_Street = []
if domain.strip() and domain.strip() != "-":
print(current_time("green").format("域名：" + domain))
if registrar.strip() and registrar.strip() != "-":
print(current_time("green").format("注册商：" + registrar))
if domain_name.strip() and domain_name.strip() != "-":
print(current_time("green").format("域名持有人/机构名称：" + domain_name))
if create_time.strip() and create_time.strip() != "-":
print(current_time("green").format("创建时间：" + create_time))
if re_time.strip() and re_time.strip() != "-":
print(current_time("green").format("更新时间：" + re_time))
if expiration_date.strip() and expiration_date.strip() != "-":
print(current_time("green").format("过期时间：" + expiration_date))
if domain_server:
print(current_time("green").format("域名服务器：" + str(domain_server)))
if dns_server:
print(current_time("green").format("dns服务器：" + str(dns_server)))
if email:
print(current_time("green").format("注册人邮箱：" + str(email)))
if Tech_City:
print(current_time("green").format("城市：" + str(Tech_City)))
if Tech_Street:
print(current_time("green").format("街道：" + str(Tech_Street)))
else:
print(current_time("red").format(" 请求错误..."))
print(current_time("sep_suffix"))