Feature | 更新部分功能,详情见CHANGELOG

Feature | 更新部分功能,详情见CHANGELOG

config.py

@@ -5,14 +5,8 @@
 # @File    : config.py
 # @Github: https://github.com/Cl0udG0d
 
-
-SearchKEY = ""
-TimeSleep = 5
-
-
-
 # Fofa-hack 版本号
-VERSION_NUM="2.0.0"
+VERSION_NUM="2.0.1"
 # 登录最大重试次数
 MAX_LOGIN_RETRY_NUM=3
 # 页面URL获取最大重试次数

docs/CHANGELOG.md

@@ -1,5 +1,10 @@
 # CHANGELOG 代码变更记录
 
+### 2.0.1
++ 修改filename,timeSleep等为类内部变量
++ 新增logoutInitMsg方法输出初始化信息
++ 新增fofa_fuzz_spider方法
+
 ### 2.0.0
 
 + 返璞归真,去除账号登录,直接使用时间戳来在第一页进行爬取

fofa.py

@@ -10,37 +10,25 @@
 import time
 from urllib.parse import quote_plus
 import config
-
 from tookit import unit, fofa_useragent
 import argparse
-
 from tookit.levelData import LevelData
 from tookit.outputData import OutputData
-
-filename=""
-
-
-
-
-
-
-
 import re, requests
-
 from lxml import etree
 
 
 
 class Fofa:
-
-
     def __init__(self):
         self.headers_use = ""
         self.level = 0
         self.host_set = set()
         self.timestamp_set = set()
         self.oldLength = -1
         self.endcount=0
+        self.filename = ""
+
         print('''
          ____  ____  ____  ____      
         | ===|/ () \| ===|/ () \     
@@ -50,8 +38,6 @@ def __init__(self):
             |_| |_|/__/\__\\\\____)|__|\__\\ V{}
         '''.format(config.VERSION_NUM))
 
-
-
     def headers(self,cookie):
         headers_use = {
             'User-Agent': fofa_useragent.getFakeUserAgent(),
@@ -60,6 +46,16 @@ def headers(self,cookie):
         }
         return headers_use
 
+    def logoutInitMsg(self):
+        print('''[*] LEVEL = {} , 初始化成功
+[*] 爬取延时: {}s
+[*] 爬取关键字: {}
+[*] 爬取结束数量: {}
+[*] 是否FUZZ: {}
+[*] 输出格式为: {}
+[*] 存储文件名: {}'''.format(self.level,self.timeSleep,self.searchKey,self.endcount,self.fuzz,self.output,self.filename)
+        )
+        return
 
     def init(self):
         parser = argparse.ArgumentParser(description='Fofa-hack v{} 使用说明'.format(config.VERSION_NUM))
@@ -68,29 +64,21 @@ def init(self):
         parser.add_argument('--endcount', '-e', help='爬取结束数量')
         parser.add_argument('--level', '-l', help='爬取等级: 1-3 ,数字越大内容越详细,默认为 1')
         parser.add_argument('--output', '-o', help='输出格式:txt、json、csv,默认为txt')
+        parser.add_argument('--fuzz', '-f', help='关键字fuzz参数,增加内容获取粒度',action='store_true')
         args = parser.parse_args()
-        config.TimeSleep = int(args.timesleep)
-        print("[*] 爬取延时: {}s".format(config.TimeSleep))
-        config.SearchKEY = args.keyword
-        print("[*] 爬取关键字: {}".format(config.SearchKEY))
+        self.timeSleep= int(args.timesleep)
+        self.searchKey= args.keyword
         if args.endcount:
             self.endcount=int(args.endcount)
-            print("[*] 爬取结束数量: {}".format(self.endcount))
         else:
             self.endcount=100
         self.level=args.level if args.level else "1"
         self.levelData=LevelData(self.level)
-
-
+        self.fuzz=args.fuzz
         self.output = args.output if args.output else "txt"
-        print("[*] 输出格式为: {}".format(self.output))
-
-
-        global filename
-        filename = "{}_{}.{}".format(unit.md5(config.SearchKEY), int(time.time()),self.output)
-        print("[*] 存储文件名: {}".format(filename))
-        self.outputData = OutputData(filename, pattern=self.output)
-        return
+        self.filename = "{}_{}.{}".format(unit.md5(self.searchKey), int(time.time()),self.output)
+        self.outputData = OutputData(self.filename, pattern=self.output)
+        self.logoutInitMsg()
 
     def get_count_num(self, search_key):
         """
@@ -109,7 +97,6 @@ def get_count_num(self, search_key):
         except Exception as e:
             print("[-] error:{}".format(e))
             countnum = '0'
-            standaloneIpNum = '0'
             pass
         print("[*] 存在数量:" + countnum)
         # print("[*] 独立IP数量:" + standaloneIpNum)
@@ -148,13 +135,13 @@ def fofa_spider_page(self, searchbs64):
                 print("[*] 已爬取条数 [{}]: ".format(len(self.host_set))+str(self.levelData.formatData))
 
                 for i in self.levelData.formatData:
-                    with open(filename, 'a+', encoding="utf-8") as f:
+                    with open(self.filename, 'a+', encoding="utf-8") as f:
                         f.write(str(i) + "\n")
                 for url in self.levelData.formatData:
                     self.host_set.add(url)
                 for temptime in timelist:
                     self.timestamp_set.add(temptime)
-                time.sleep(config.TimeSleep)
+                time.sleep(self.timeSleep)
                 return
             except Exception as e:
                 print("[-] error:{}".format(e))
@@ -167,20 +154,40 @@ def fofa_spider_page(self, searchbs64):
         exit(0)
 
 
-
-
-    def fofa_spider(self, search_key, searchbs64):
-
+    def fofa_common_spider(self, search_key, searchbs64):
         while len(self.host_set) < self.endcount and self.oldLength !=len(self.host_set):
             self.oldLength=len(self.host_set)
             self.timestamp_set.clear()
             self.fofa_spider_page(searchbs64)
-            search_key_modify, searchbs64_modify = self.modify_search_url(search_key)
+            search_key_modify= self.modify_search_time_url(search_key)
+            searchbs64_modify = quote_plus(base64.b64encode(search_key_modify.encode()))
             search_key = search_key_modify
             searchbs64 = searchbs64_modify
+        if len(self.host_set) >= self.endcount:
+            print("[*] 数据爬取结束")
+            return
+        if self.oldLength == len(self.host_set):
+            print("[-] 数据无新增,退出爬取")
+            return
+
+    def fofa_fuzz_spider(self, search_key, searchbs64):
+        while len(self.host_set) < self.endcount and self.oldLength !=len(self.host_set):
+            self.oldLength=len(self.host_set)
+            self.timestamp_set.clear()
+            self.fofa_spider_page(searchbs64)
+            search_key_modify = self.modify_search_time_url(search_key)
 
-
-    def modify_search_url(self, search_key):
+            searchbs64_modify = quote_plus(base64.b64encode(search_key_modify.encode()))
+            search_key = search_key_modify
+            searchbs64 = searchbs64_modify
+        if len(self.host_set) >= self.endcount:
+            print("[*] 数据爬取结束")
+            return
+        if self.oldLength == len(self.host_set):
+            print("[-] 数据无新增,退出爬取")
+            return
+
+    def modify_search_time_url(self, search_key):
         """
         根据时间修订搜索值
         :param search_key:
@@ -206,24 +213,24 @@ def modify_search_url(self, search_key):
             search_key = search_key + ' && ' + 'before="' + str(time_before) + '"'
         search_key_modify = search_key
 
-        searchbs64_modify = quote_plus(base64.b64encode(search_key_modify.encode()))
-        # print('[*] 搜索词： ' + search_key_modify)
 
-        return search_key_modify, searchbs64_modify
+        # print('[*] 搜索词： ' + search_key_modify)
 
+        return search_key_modify
 
     def run(self):
-        searchbs64 = self.get_count_num(config.SearchKEY)
-        self.fofa_spider(config.SearchKEY, searchbs64)
+        searchbs64 = self.get_count_num(self.searchKey)
+        if not self.fuzz:
+            self.fofa_common_spider(self.searchKey, searchbs64)
+        else:
+            self.fofa_fuzz_spider(self.searchKey, searchbs64)
         print('[*] 抓取结束，共抓取数据 ' + str(len(self.host_set)) + ' 条\n')
 
     def main(self):
         self.init()
         print('[*] 开始运行')
         self.run()
 
-
-
 if __name__ == '__main__':
     fofa = Fofa()
     fofa.main()

test.py

@@ -11,16 +11,27 @@
 import requests
 from lxml import etree
 
-def cleanData(urllist):
-    newlist=list()
-    for url in urllist:
-        newlist.append(url.strip())
-    return newlist
+data=[1,2,3,4,5,6,7,8,9]
+result=[]
 
-resp = requests.get(url='https://fofa.info/result?qbase64=MQ==&page_size=10')
-tree = etree.HTML(resp.text)
-urllist1 = tree.xpath('//span[@class="hsxa-host"]/text()')
 
-urllist2 = tree.xpath('//span[@class="hsxa-host"]/a/@href')
 
-print(cleanData(urllist1)+urllist2)
+for i in data:
+
+    for j in data:
+        for k in data:
+            for l in data:
+                for m in data:
+                    for n in data:
+                        num1=i*10+j
+                        num2=k
+                        num3=l*10+m
+                        num4=n
+                        if num1-num2==num3-num4:
+                            templist=[i,j,k,l,m,n]
+                            if templist.count(2)<2 and templist.count(3)<2 and templist.count(4)<2 and templist.count(5)<2 and templist.count(6)<2 and templist.count(7)<2 and templist.count(8)<2 and templist.count(9)<2:
+
+                                print("{}-{}={}-{}".format(num1,num2,num3,num4))
+                                result.append([num1,num2,num3,num4])
+
+print(len(result))

tookit/levelData.py

@@ -38,11 +38,7 @@ class LevelData:
     formatData = []
 
     def __init__(self, level="1"):
-
         self.level = level if self.checkLevelStandard(level) else "1"
-        print("[*] LEVEL = {} , 初始化成功".format(self.level))
-
-        return
 
     def checkLevelStandard(self, level):
         """