1.fofa.py

import requests
from lxml import etree
import base64
import re
import time
import config
from urllib.parse import quote


def spider():
    searchbs64 = quote(str(base64.b64encode(config.SearchKEY.encode()), encoding='utf-8'))
    print("爬取页面为:https://fofa.so/result?&qbase64=" + searchbs64)
    html = requests.get(url="https://fofa.so/result?&qbase64=" + searchbs64, headers=config.headers).text
    tree = etree.HTML(html)
    pagenum = tree.xpath('//li[@class="number"]/text()')[5]
    # pagenum = re.findall('>(\d*)</a> <a class="next_page" rel="next"', html)
    print("该关键字存在页码: " + pagenum)
    config.StartPage = input("请输入开始页码:\n")
    config.StopPage = input("请输入终止页码: \n")
    doc = open("result.txt", "a+")
    for i in range(int(config.StartPage), int(pagenum)):
        print("Now write " + str(i) + " page")
        rep = requests.get(
            'https://api.fofa.so/v1/search?qbase64=' + searchbs64 + "&full=false&pn=" + str(i) + "&ps=10",
            headers=config.headers)
        pattern = re.compile('"link":"(.*?)",')
        urllist = re.findall(pattern, rep.text)
        print(urllist)
        for j in urllist:
            print(j)
            doc.write(j + "\n")
        if i == int(config.StopPage):
            break
        time.sleep(config.TimeSleep)
    doc.close()
    print("OK,Spider is End .")


if __name__ == '__main__':
    spider()

2.config.py

Authorization = ""

headers = {
        "Connection": "keep-alive",
        "Authorization": Authorization
    }

SearchKEY="title='天清汉马usg防火墙'"
StopPage=""
StartPage=""
TimeSleep=5

3.使用方法

config.py中 Authorization 填写参考以下图片位置

SearchKEY 为要搜索的关键字
执行python fofa.py 生成result.txt

参考github：https://github.com/Cl0udG0d/Fofa-script