鹰图API

import base64
import time
import pandas as pd
import requests

# API 查询语句示例
API_PROMPT = """
    web.title="北京"         # 从网站标题中搜索“北京”
    ip.country="CN"        # 搜索IP对应主机所在国为”中国“的资产
    icp.web_name="奇安信"      # 搜索ICP备案网站名中含有“奇安信”的资产
    icp.name="奇安信"              # 搜索ICP备案单位名中含有“奇安信”的资产
    domain="qq.com"               # 搜索域名包含"qq.com"的网站
    domain.suffix="qq.com"      # 搜索主域为qq.com的网站
    app.vendor="PHP"NEW      # 查询包含组件厂商为"PHP"的资产
    app.version="1.8.1"NEW      # 查询包含组件版本为"1.8.1"的资产
    header="elastic"             # 搜索HTTP请求头中含有"elastic"的资产
    header.status_code="402"      # 搜索HTTP请求返回状态码为”402”的资产
    web.body="网络空间测绘"        # 搜索网站正文包含”网络空间测绘“的资产
    header.server=="Microsoft-IIS/10"      # 搜索server全名为“Microsoft-IIS/10”的服务器
    ip_address="1.1.1.1"          # 搜索IP为 ”1.1.1.1”的资产
    ip_range="220.181.111.1/24"        # 搜索起始IP为”220.181.111.1“的C段资产
    ip.port="6379"        # 搜索开放端口为”6379“的资产
    ip.os="Windows"    # 搜索操作系统标记为”Windows“的资产
    ip.isp="电信"         # 搜索运营商为”中国电信“的资产
"""

# 定义API URL和密钥
API_URL_BASE = "https://hunter.qianxin.com/openApi/search?api-key="
API_KEY = ""


def fetch_data(query, page_count):
    try:
        query_b64_encoded = base64.b64encode(query.encode('utf-8')).decode('utf-8')
        results_list = []
        page_size = 10
        for page in range(1, int(page_count) + 1):
            url = f"{API_URL_BASE}{API_KEY}&search={query_b64_encoded}&page={page}&page_size={page_size}&is_web=1&status_code=200"
            response_json = requests.get(url).json()
            print(url)
            if response_json['code'] != 200:
                print(f"请求失败，URL: {url}")
                print(response_json.text)
                exit()
            print(response_json['data']['rest_quota'])
            results_list.append(response_json)
            time.sleep(3)  # 遵守服务端请求间隔限制

        return results_list
    except:
        print('查询语法有问题')

def export_to_excel(json_response_list, search_query):
    data_rows = []

    for index, json_data in enumerate(json_response_list):
        def extract_and_add(data):
            # 检查 'arr' 是否存在且非空
            if 'data' in data and data['data'] is not None and 'arr' in data['data'] and data['data']['arr'] is not None:
                for item in data['data']['arr']:
                    data_rows.append(item)
            else:
                print(f"警告：数据 {index} 中不存在可迭代的资产数组")

        try:
            extract_and_add(json_data)
        except TypeError as te:
            print(f"在处理响应 {index} 时遇到错误: {te}")

    dataframe = pd.DataFrame(data_rows)

    # 使用查询字符串生成文件名，移除特殊字符
    file_name_safe = search_query.replace(" ", "_").replace('"', '') + ".xlsx"

    dataframe.to_excel(file_name_safe, index=False)


if __name__ == '__main__':
    print(API_PROMPT)
    search_query = input("请输入查询语句：")
    number_of_pages = input("输入获取的数量（页数）：")
    responses = fetch_data(search_query, number_of_pages)
    export_to_excel(responses, search_query)