ICP备案信息查询API接口

Xidorn · 发表于 2023-10-14 23:17:24

胖虎发表于 2023-10-14 23:07
哈哈，我有时间的话，看看能不能把你的那个扩充一下，把其他几个查询都给列出来。 ...

好的，非常感谢！

Xidorn · 发表于 2023-10-20 08:31:58

胖虎发表于 2023-10-14 23:07
哈哈，我有时间的话，看看能不能把你的那个扩充一下，把其他几个查询都给列出来。 ...

大佬，请问这个接口是否可以查询备案站点名称？谢谢！

胖虎 · 发表于 2023-10-21 20:49:40

Xidorn 发表于 2023-10-20 08:31
大佬，请问这个接口是否可以查询备案站点名称？谢谢！

下面是查询结果json，你可以看看需要啥值，直接拿

{
"code": 200,
"msg": "操作成功",
"params": {
"endRow": 0,
"firstPage": 1,
"hasNextPage": false,
"hasPreviousPage": false,
"isFirstPage": true,
"isLastPage": true,
"lastPage": 1,
"list": [
{
"contentTypeName": "宗教、宗教、出版、新闻、出版、出版、新闻、宗教、文化、宗教",
"domain": "qq.com",
"domainId": 190000203203,
"leaderName": "",
"limitAccess": "否",
"mainId": 547280,
"mainLicence": "粤B2-20090059",
"natureName": "企业",
"serviceId": 4134047,
"serviceLicence": "粤B2-20090059-5",
"unitName": "深圳市腾讯计算机系统有限公司",
"updateRecordTime": "2023-10-18 10:27:25"
}
],
"navigatePages": 8,
"navigatepageNums": [
1
],
"nextPage": 1,
"pageNum": 1,
"pageSize": 10,
"pages": 1,
"prePage": 1,
"size": 1,
"startRow": 0,
"total": 1
},
"success": true
}

复制代码

胖虎 · 发表于 2023-10-21 20:52:00

可以参考baidu和qq的域名查询结果，应该可以猜出来各个字段的含义

{
"code": 200,
"msg": "操作成功",
"params": {
"endRow": 0,
"firstPage": 1,
"hasNextPage": false,
"hasPreviousPage": false,
"isFirstPage": true,
"isLastPage": true,
"lastPage": 1,
"list": [
{
"contentTypeName": "",
"domain": "baidu.com",
"domainId": 10000245113,
"leaderName": "",
"limitAccess": "否",
"mainId": 282751,
"mainLicence": "京ICP证030173号",
"natureName": "企业",
"serviceId": 282911,
"serviceLicence": "京ICP证030173号-1",
"unitName": "北京百度网讯科技有限公司",
"updateRecordTime": "2023-08-15 11:32:09"
}
],
"navigatePages": 8,
"navigatepageNums": [
1
],
"nextPage": 1,
"pageNum": 1,
"pageSize": 10,
"pages": 1,
"prePage": 1,
"size": 1,
"startRow": 0,
"total": 1
},
"success": true
}

复制代码

下面的这个是没有备案的，你可以参考，没有备案的域名怎么从返回值判断。

{
"code": 200,
"msg": "操作成功",
"params": {
"endRow": 0,
"firstPage": 1,
"hasNextPage": true,
"hasPreviousPage": false,
"isFirstPage": true,
"isLastPage": false,
"lastPage": 0,
"list": [],
"navigatePages": 8,
"navigatepageNums": [],
"nextPage": 1,
"pageNum": 1,
"pageSize": 10,
"pages": 0,
"prePage": 1,
"size": 0,
"startRow": 0,
"total": 0
},
"success": true
}

复制代码

胖虎 · 发表于 2023-10-21 20:53:42

total 这个字段应该是查询到的条数，你可以判断条数为0则没有备案，大于0就是有备案，因为他可以通过icp备案号查询域名，所以当用icp查询的时候，可能有多条数据

胖虎 · 发表于 2023-10-21 20:55:45

下面是通过百度的icp号查询到的备案域名有那些。你也可以扩展搜索。比如搜索一个域名，怎么去把他的同一个备案下所有域名查出。

{
"code": 200,
"msg": "操作成功",
"params": {
"endRow": 9,
"firstPage": 1,
"hasNextPage": true,
"hasPreviousPage": false,
"isFirstPage": true,
"isLastPage": false,
"lastPage": 27,
"list": [
{
"contentTypeName": "",
"domain": "baidu.com",
"domainId": 10000245113,
"leaderName": "",
"limitAccess": "否",
"mainId": 282751,
"mainLicence": "京ICP证030173号",
"natureName": "企业",
"serviceId": 282911,
"serviceLicence": "京ICP证030173号-1",
"unitName": "北京百度网讯科技有限公司",
"updateRecordTime": "2023-08-15 11:32:09"
},
{
"contentTypeName": "",
"domain": "yjs-cdn3.com",
"domainId": 10004879371,
"leaderName": "",
"limitAccess": "否",
"mainId": 282751,
"mainLicence": "京ICP证030173号",
"natureName": "企业",
"serviceId": 10001868696,
"serviceLicence": "京ICP证030173号-102",
"unitName": "北京百度网讯科技有限公司",
"updateRecordTime": "2023-08-15 11:32:09"
},
{
"contentTypeName": "",
"domain": "yunjiasu-cdn.net",
"domainId": 10005348493,
"leaderName": "",
"limitAccess": "否",
"mainId": 282751,
"mainLicence": "京ICP证030173号",
"natureName": "企业",
"serviceId": 10002200516,
"serviceLicence": "京ICP证030173号-120",
"unitName": "北京百度网讯科技有限公司",
"updateRecordTime": "2023-08-15 11:32:10"
},
{
"contentTypeName": "",
"domain": "yunjiasu.com",
"domainId": 10005348497,
"leaderName": "",
"limitAccess": "否",
"mainId": 282751,
"mainLicence": "京ICP证030173号",
"natureName": "企业",
"serviceId": 10002200520,
"serviceLicence": "京ICP证030173号-124",
"unitName": "北京百度网讯科技有限公司",
"updateRecordTime": "2023-08-15 11:32:10"
},
{
"contentTypeName": "",
"domain": "dushifen.com",
"domainId": 10005348485,
"leaderName": "",
"limitAccess": "否",
"mainId": 282751,
"mainLicence": "京ICP证030173号",
"natureName": "企业",
"serviceId": 10002200508,
"serviceLicence": "京ICP证030173号-131",
"unitName": "北京百度网讯科技有限公司",
"updateRecordTime": "2023-08-15 11:32:10"
},
{
"contentTypeName": "",
"domain": "videomind.net",
"domainId": 10005421452,
"leaderName": "",
"limitAccess": "否",
"mainId": 282751,
"mainLicence": "京ICP证030173号",
"natureName": "企业",
"serviceId": 10002273118,
"serviceLicence": "京ICP证030173号-139",
"unitName": "北京百度网讯科技有限公司",
"updateRecordTime": "2023-08-15 11:32:10"
},
{
"contentTypeName": "",
"domain": "yoojia.com",
"domainId": 990000676563,
"leaderName": "",
"limitAccess": "否",
"mainId": 282751,
"mainLicence": "京ICP证030173号",
"natureName": "企业",
"serviceId": 990000677061,
"serviceLicence": "京ICP证030173号-167",
"unitName": "北京百度网讯科技有限公司",
"updateRecordTime": "2023-08-15 11:32:11"
},
{
"contentTypeName": "",
"domain": "baidu.com.cn",
"domainId": 10000441535,
"leaderName": "",
"limitAccess": "否",
"mainId": 282751,
"mainLicence": "京ICP证030173号",
"natureName": "企业",
"serviceId": 10000264823,
"serviceLicence": "京ICP证030173号-17",
"unitName": "北京百度网讯科技有限公司",
"updateRecordTime": "2023-08-15 11:32:12"
},
{
"contentTypeName": "",
"domain": "17swan.com",
"domainId": 10002983984,
"leaderName": "",
"limitAccess": "否",
"mainId": 282751,
"mainLicence": "京ICP证030173号",
"natureName": "企业",
"serviceId": 10000512823,
"serviceLicence": "京ICP证030173号-26",
"unitName": "北京百度网讯科技有限公司",
"updateRecordTime": "2023-08-15 11:32:14"
},
{
"contentTypeName": "",
"domain": "eyoubaidu.com",
"domainId": 10003061407,
"leaderName": "",
"limitAccess": "否",
"mainId": 282751,
"mainLicence": "京ICP证030173号",
"natureName": "企业",
"serviceId": 10000567969,
"serviceLicence": "京ICP证030173号-28",
"unitName": "北京百度网讯科技有限公司",
"updateRecordTime": "2023-08-15 11:32:14"
}
],
"navigatePages": 8,
"navigatepageNums": [
1,
2,
3,
4,
5,
6,
7,
8
],
"nextPage": 2,
"pageNum": 1,
"pageSize": 10,
"pages": 27,
"prePage": 1,
"size": 10,
"startRow": 0,
"total": 264
},
"success": true
}

复制代码

胖虎 · 发表于 2023-10-21 20:59:03

请求的参数中，可以把下面的两个参数带值，第一个参数是第几页，正常1，第二个参数是一次返回的数据有多少行（个）可以写多点，把同一个icp备案下的所有备案域名都查出来。

pageNum: 1
pageSize: 40

复制代码

Xidorn · 发表于 2023-10-21 22:48:33

胖虎发表于 2023-10-21 20:59
请求的参数中，可以把下面的两个参数带值，第一个参数是第几页，正常1，第二个参数是一次返回的数据有多少 ...

好的，感谢大佬。

rocky · 发表于 2023-10-23 15:18:10

用python改写了个版本
from flask import Flask, jsonify, request
import requests
import json
import random
import hashlib
from urllib.parse import urlparse
import urllib3

urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)

app = Flask(__name__)

def curl_post(url, data, content_type, token=None):
ip = f"101.{random.randint(1, 255)}.{random.randint(1, 255)}.{random.randint(1, 255)}"
headers = {
      "Content-Type": content_type,
      "Origin": "https://beian.miit.gov.cn/",
      "Referer": "https://beian.miit.gov.cn/",
      "User-Agent": ("Mozilla/5.0 (Windows NT 10.0; WOW64) "
                  "AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.87 Safari/537.36"),
      "CLIENT-IP": ip,
      "X-FORWARDED-FOR": ip
}

if token:
      headers["token"] = token

response = requests.post(
      f"https://hlwicpfwc.miit.gov.cn/icpproject_query/api/{url}",
      data=data,
      headers=headers,
      verify=False,
      timeout=10
)

return response.content

def get_top_host(url):
if "http" not in url:
      url = "http://" + url

url = url.lower()
parsed_url = urlparse(url)
host = parsed_url.netloc
data = host.split('.')
n = len(data)

domain_cn_patterns = ['com.cn', 'net.cn', 'org.cn', 'gov.cn', 'edu.cn']
ip_pattern = (r'((2(5[0-5]|[0-4]\d))|[0-1]?\d{1,2})(\.((2(5[0-5]|[0-4]\d))|[0-1]?\d{1,2})){3}')

if n > 2 and any(pattern in host for pattern in domain_cn_patterns):
      host = f"{data[n-3]}.{data[n-2]}.{data[n-1]}"
elif any(pattern in host for pattern in [ip_pattern]):
      pass
else:
      host = f"{data[n-2]}.{data[n-1]}"

return host

@app.route('/get-domain-info', methods=['GET'])
def get_domain_info():
domain = request.args.get('domain')
if not domain:
      return jsonify({"error": "缺少参数"}), 400

domain = get_top_host(domain)
time_stamp = str(int(requests.get('https://api.ipify.org?format=json').json()['ip'].split('.')[0]))
auth_key = hashlib.md5(("testtest" + time_stamp).encode()).hexdigest()

token_response = json.loads(curl_post(
      "auth", f"authKey={auth_key}&timeStamp={time_stamp}", "application/x-www-form-urlencoded;charset=UTF-8"))

token = token_response["params"]["bussiness"]

query_response = json.loads(curl_post(
      "icpAbbreviateInfo/queryByCondition",
      json.dumps({"pageNum": "", "pageSize": "", "serviceType": "1", "unitName": domain}),
      "application/json;charset=UTF-8",
      token
))

query = query_response["params"]["list"][0]

icp = query["serviceLicence"]
unit_name = query["unitName"]
nature_name = query["natureName"]

if not token:
      icp = "服务器请求频率过高，请稍后再试"
      msg = "查询失败"
      code = "0"
elif not icp:
      icp = "未备案"
      msg = "查询成功"
      code = "1"
else:
      msg = "查询成功"
      code = "1"

result = {
      'icp': icp,
      'unitName': unit_name,
      'natureName': nature_name,
      'msg': msg,
      'result': code
}

return app.response_class(
      response=json.dumps(result, ensure_ascii=False),
      status=200,
      mimetype='application/json'
)

if __name__ == '__main__':
app.run(debug=True)