pep8

oneforall/modules/certificates/certdb_api.py

@@ -22,15 +22,19 @@ class CertDBAPI(Query):
             time.sleep(self.delay)
             self.header = self.get_header()
             self.proxy = self.get_proxy(self.source)
-            params = {'domain': self.domain, 'api_token': self.token, 'page': page_num}
+            params = {'domain': self.domain,
+                      'api_token': self.token,
+                      'page': page_num}
             resp = self.get(self.addr, params)
             if not resp:
                 return
-            resp_json = resp.json()
-            subdomains_find = utils.match_subdomain(self.domain, str(resp_json))
-            self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+            json = resp.json()
+            subdomains_find = utils.match_subdomain(self.domain, str(json))
+            # 合并搜索子域名搜索结果
+            self.subdomains = self.subdomains.union(subdomains_find)
             page_num += 1
-            if resp_json.get('count') < 30:  # 默认每次查询最多返回30条 当前条数小于30条说明已经查完
+            # 默认每次查询最多返回30条 当前条数小于30条说明已经查完
+            if json.get('count') < 30:
                 break
 
     def run(self):

oneforall/modules/certificates/certspotter.py

@@ -18,12 +18,14 @@ class CertSpotter(Query):
         time.sleep(self.delay)
         self.header = self.get_header()
         self.proxy = self.get_proxy(self.source)
-        params = {'domain': self.domain, 'include_subdomains': 'true', 'expand': 'dns_names'}
+        params = {'domain': self.domain, 'include_subdomains': 'true',
+                  'expand': 'dns_names'}
         resp = self.get(self.addr, params)
         if not resp:
             return
         subdomains_find = utils.match_subdomain(self.domain, str(resp.json()))
-        self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+        # 合并搜索子域名搜索结果
+        self.subdomains = self.subdomains.union(subdomains_find)
 
     def run(self):
         """
@@ -49,5 +51,4 @@ def do(domain):  # 统一入口名字 方便多线程调用
 
 
 if __name__ == '__main__':
-
     do('example.com')

oneforall/modules/certificates/entrust.py

@@ -18,7 +18,8 @@ class Entrust(Query):
         time.sleep(self.delay)
         self.header = self.get_header()
         self.proxy = self.get_proxy(self.source)
-        params = {'fields': 'subjectDN', 'domain': self.domain, 'includeExpired': 'true'}
+        params = {'fields': 'subjectDN', 'domain': self.domain,
+                  'includeExpired': 'true'}
         resp = self.get(self.addr, params)
         if not resp:
             return

oneforall/modules/certificates/google.py

@@ -9,7 +9,8 @@ class Google(Query):
         self.domain = self.register(domain)
         self.module = 'Certificate'
         self.source = 'GoogleQuery'
-        self.addr = 'https://transparencyreport.google.com/transparencyreport/api/v3/httpsreport/ct/certsearch'
+        self.addr = 'https://transparencyreport.google.com/' \
+                    'transparencyreport/api/v3/httpsreport/ct/certsearch'
 
     def query(self):
         """
@@ -18,12 +19,14 @@ class Google(Query):
         time.sleep(self.delay)
         self.header = self.get_header()
         self.proxy = self.get_proxy(self.source)
-        params = {'include_expired': 'true', 'include_subdomains': 'true', 'domain': self.domain}
+        params = {'include_expired': 'true', 'include_subdomains': 'true',
+                  'domain': self.domain}
         resp = self.get(self.addr, params)
         if not resp:
             return
         subdomains_find = utils.match_subdomain(self.domain, resp.text)
-        self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+        # 合并搜索子域名搜索结果
+        self.subdomains = self.subdomains.union(subdomains_find)
 
     def run(self):
         """

oneforall/modules/check/cdx.py

@@ -23,8 +23,10 @@ class CheckCDX(Module):
         检查crossdomain.xml收集子域名
         :return:
         """
-        urls = [f'http://{self.domain}/crossdomain.xml', f'https://{self.domain}/crossdomain.xml',
-                f'http://www.{self.domain}/crossdomain.xml', f'https://www.{self.domain}/crossdomain.xml']
+        urls = [f'http://{self.domain}/crossdomain.xml',
+                f'https://{self.domain}/crossdomain.xml',
+                f'http://www.{self.domain}/crossdomain.xml',
+                f'https://www.{self.domain}/crossdomain.xml']
         response = None
         for url in urls:
             self.header = self.get_header()
@@ -41,12 +43,12 @@ class CheckCDX(Module):
         类执行入口
         """
         self.begin()
-        logger.log('DEBUG', f'开始执行{self.source}检查{self.domain}域的crossdomain.xml')
+        logger.log('DEBUG', f'开始执行{self.source}检查{self.domain}域的跨域策略')
         self.check()
         self.save_json()
         self.gen_result()
         self.save_db()
-        logger.log('DEBUG', f'结束执行{self.source}检查{self.domain}域的crossdomain.xml')
+        logger.log('DEBUG', f'结束执行{self.source}检查{self.domain}域的跨域策略')
         self.finish()
 
 

oneforall/modules/crawl/archivecrawl.py

@@ -27,7 +27,8 @@ class ArchiveCrawl(Crawl):
             if resp.data.get('status') not in ['301', '302']:
                 url = resp.data.get('url')
                 subdomains_find = self.match(self.register(domain), url + resp.text)
-                self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+                # 合并搜索子域名搜索结果
+                self.subdomains = self.subdomains.union(subdomains_find)
 
     def run(self):
         """
@@ -53,10 +54,7 @@ def do(domain):  # 统一入口名字 方便多线程调用
     """
     crawl = ArchiveCrawl(domain)
     crawl.run()
-    logger.log('INFOR', f'{crawl.source}模块耗时{crawl.elapsed}秒发现{crawl.domain}的子域{len(crawl.subdomains)}个')
-    logger.log('DEBUG', f'{crawl.source}模块发现{crawl.domain}的子域 {crawl.subdomains}')
 
 
 if __name__ == '__main__':
-
     do('example.com')

oneforall/modules/crawl/commoncrawl.py

@@ -28,7 +28,8 @@ class CommonCrawl(Crawl):
         for resp in tqdm(cdx.iter(url, limit=limit), total=limit):
             if resp.data.get('status') not in ['301', '302']:
                 subdomains_find = self.match(self.register(domain), resp.text)
-                self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+                # 合并搜索子域名搜索结果
+                self.subdomains = self.subdomains.union(subdomains_find)
 
     def run(self):
         """
@@ -54,10 +55,7 @@ def do(domain):  # 统一入口名字 方便多线程调用
     """
     crawl = CommonCrawl(domain)
     crawl.run()
-    logger.log('INFOR', f'{crawl.source}模块耗时{crawl.elapsed}秒发现{crawl.domain}的子域{len(crawl.subdomains)}个')
-    logger.log('DEBUG', f'{crawl.source}模块发现{crawl.domain}的子域 {crawl.subdomains}')
 
 
 if __name__ == '__main__':
-
     do('example.com')

oneforall/modules/datasets/binaryedge_api.py

@@ -52,5 +52,4 @@ def do(domain):  # 统一入口名字 方便多线程调用
 
 
 if __name__ == '__main__':
-
     do('example.com')

oneforall/modules/datasets/bufferover.py

@@ -22,7 +22,8 @@ class BufferOver(Query):
         if not resp:
             return
         subdomains_find = self.match(self.domain, resp.text)
-        self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+        # 合并搜索子域名搜索结果
+        self.subdomains = self.subdomains.union(subdomains_find)
 
     def run(self):
         """
@@ -41,12 +42,10 @@ def do(domain):  # 统一入口名字 方便多线程调用
     类统一调用入口
 
     :param str domain: 域名
-
     """
     query = BufferOver(domain)
     query.run()
 
 
 if __name__ == '__main__':
-
     do('example.com')

oneforall/modules/datasets/chinaz.py

@@ -48,5 +48,4 @@ def do(domain):  # 统一入口名字 方便多线程调用
 
 
 if __name__ == '__main__':
-
     do('example.com')

oneforall/modules/datasets/chinaz_api.py

@@ -24,7 +24,8 @@ class ChinazAPI(Query):
         if not resp:
             return
         subdomains_find = self.match(self.domain, str(resp.json()))
-        self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+        # 合并搜索子域名搜索结果
+        self.subdomains = self.subdomains.union(subdomains_find)
 
     def run(self):
         """
@@ -51,5 +52,4 @@ def do(domain):  # 统一入口名字 方便多线程调用
 
 
 if __name__ == '__main__':
-
     do('example.com')

oneforall/modules/datasets/circl_api.py

@@ -24,7 +24,8 @@ class CirclAPI(Query):
         if not resp:
             return
         subdomains_find = self.match(self.domain, str(resp.json()))
-        self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+        # 合并搜索子域名搜索结果
+        self.subdomains = self.subdomains.union(subdomains_find)
 
     def run(self):
         """
@@ -51,5 +52,4 @@ def do(domain):  # 统一入口名字 方便多线程调用
 
 
 if __name__ == '__main__':
-
     do('example.com')

oneforall/modules/datasets/dnsdb.py

@@ -28,16 +28,19 @@ class DNSdb(Query):
                 soup = BeautifulSoup(resp.text, features='lxml')
                 index_urls = set(map(lambda x: self.addr + self.domain + x.text, soup.find_all('a')))
                 for url in index_urls:
-                    self.delay = random.randint(2, 5)  # 休眠绕过CloudFlare的DDoS保护
+                    # 休眠绕过CloudFlare的DDoS保护
+                    self.delay = random.randint(2, 5)
                     time.sleep(self.delay)
                     resp = self.get(url)
                     if not resp:
                         return
                     subdomains_find = self.match(self.domain, resp.text)
-                    self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+                    # 合并搜索子域名搜索结果
+                    self.subdomains = self.subdomains.union(subdomains_find)
             else:
                 subdomains_find = self.match(self.domain, resp.text)
-                self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+                # 合并搜索子域名搜索结果
+                self.subdomains = self.subdomains.union(subdomains_find)
 
     def run(self):
         """

oneforall/modules/datasets/dnsdb_api.py

@@ -27,7 +27,8 @@ class DNSdbAPI(Query):
             return
         if resp.status_code == 200:
             subdomains_find = utils.match_subdomain(self.domain, resp.text)
-            self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+            # 合并搜索子域名搜索结果
+            self.subdomains = self.subdomains.union(subdomains_find)
 
     def run(self):
         """
@@ -55,5 +56,4 @@ def do(domain):  # 统一入口名字 方便多线程调用
 
 
 if __name__ == '__main__':
-
     do('example.com')

oneforall/modules/datasets/dnsdumpster.py

@@ -4,10 +4,6 @@ from common.query import Query
 
 
 class DNSdumpster(Query):
-    """
-
-    """
-
     def __init__(self, domain):
         Query.__init__(self)
         self.domain = self.register(domain)
@@ -33,7 +29,8 @@ class DNSdumpster(Query):
             return
         subdomains_find = utils.match_subdomain(self.domain, resp.text)
         if subdomains_find:
-            self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+            # 合并搜索子域名搜索结果
+            self.subdomains = self.subdomains.union(subdomains_find)
 
     def run(self):
         """
@@ -52,7 +49,6 @@ def do(domain):  # 统一入口名字 方便多线程调用
     类统一调用入口
 
     :param str domain: 域名
-
     """
     query = DNSdumpster(domain)
     query.run()

oneforall/modules/datasets/hackertarget.py

@@ -23,7 +23,8 @@ class HackerTarget(Query):
         if resp.status_code == 200:
             subdomains_find = utils.match_subdomain(self.domain, resp.text)
             if subdomains_find:
-                self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+                # 合并搜索子域名搜索结果
+                self.subdomains = self.subdomains.union(subdomains_find)
 
     def run(self):
         """
@@ -42,12 +43,10 @@ def do(domain):  # 统一入口名字 方便多线程调用
     类统一调用入口
 
     :param str domain: 域名
-
     """
     query = HackerTarget(domain)
     query.run()
 
 
 if __name__ == '__main__':
-
     do('example.com')

oneforall/modules/datasets/ipv4info.py

@@ -19,7 +19,8 @@ class IPv4InfoAPI(Query):
         while True:
             self.header = self.get_header()
             self.proxy = self.get_proxy(self.source)
-            params = {'type': 'SUBDOMAINS', 'key': self.api, 'value': self.domain, 'page': page}
+            params = {'type': 'SUBDOMAINS', 'key': self.api,
+                      'value': self.domain, 'page': page}
             resp = self.get(self.addr, params)
             if not resp:
                 return
@@ -29,9 +30,12 @@ class IPv4InfoAPI(Query):
             subdomains_find = self.match(self.domain, str(resp_json))
             if not subdomains_find:
                 break
-            self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
-            subdomains = resp_json.get('Subdomains')  # 不直接使用subdomains是因为可能里面会出现不符合标准的子域名
-            if len(subdomains) < 300:  # ipv4info子域查询接口每次最多返回300个 用来判断是否还有下一页
+            # 合并搜索子域名搜索结果
+            self.subdomains = self.subdomains.union(subdomains_find)
+            # 不直接使用subdomains是因为可能里面会出现不符合标准的子域名
+            subdomains = resp_json.get('Subdomains')
+            # ipv4info子域查询接口每次最多返回300个 用来判断是否还有下一页
+            if len(subdomains) < 300:
                 break
             page += 1
             if page >= 50:  # ipv4info子域查询接口最多允许查询50页
@@ -54,12 +58,10 @@ def do(domain):  # 统一入口名字 方便多线程调用
     类统一调用入口
 
     :param str domain: 域名
-
     """
     query = IPv4InfoAPI(domain)
     query.run()
 
 
 if __name__ == '__main__':
-
     do('example.com')

oneforall/modules/datasets/netcraft.py

@@ -27,7 +27,8 @@ class NetCraft(Query):
             return None
         self.cookie = self.get(self.init).cookies
         cookie_value = self.cookie['netcraft_js_verification_challenge']
-        verify_taken = hashlib.sha1(parse.unquote(cookie_value).encode('utf-8')).hexdigest()
+        cookie_encode = parse.unquote(cookie_value).encode('utf-8')
+        verify_taken = hashlib.sha1(cookie_encode).hexdigest()
         self.cookie['netcraft_js_verification_response'] = verify_taken
 
     def query(self):
@@ -48,7 +49,8 @@ class NetCraft(Query):
             subdomains_find = self.match(self.domain, resp.text)
             if not subdomains_find:  # 搜索没有发现子域名则停止搜索
                 break
-            self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+            # 合并搜索子域名搜索结果
+            self.subdomains = self.subdomains.union(subdomains_find)
             if 'Next page' not in resp.text:  # 搜索页面没有出现下一页时停止搜索
                 break
             last = re.search(r'&last=.*' + self.domain, resp.text).group(0)
@@ -71,12 +73,10 @@ def do(domain):  # 统一入口名字 方便多线程调用
     类统一调用入口
 
     :param str domain: 域名
-
     """
     query = NetCraft(domain)
     query.run()
 
 
 if __name__ == '__main__':
-
     do('example.com')

oneforall/modules/datasets/ptrarchive.py

@@ -18,7 +18,8 @@ class PTRArchive(Query):
         """
         self.header = self.get_header()
         self.proxy = self.get_proxy(self.source)
-        self.cookie = {'pa_id': str(random.randint(0, 1000000000))}  # 绕过主页前端JS验证
+        # 绕过主页前端JS验证
+        self.cookie = {'pa_id': str(random.randint(0, 1000000000))}
         params = {'label': self.domain, 'date': 'ALL'}
         resp = self.get(self.addr, params)
         if not resp:
@@ -26,7 +27,8 @@ class PTRArchive(Query):
         if resp.status_code == 200:
             subdomains_find = utils.match_subdomain(self.domain, resp.text)
             if subdomains_find:
-                self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+                # 合并搜索子域名搜索结果
+                self.subdomains = self.subdomains.union(subdomains_find)
 
     def run(self):
         """
@@ -51,5 +53,4 @@ def do(domain):  # 统一入口名字 方便多线程调用
 
 
 if __name__ == '__main__':
-
     do('example.com')

oneforall/modules/datasets/riddler.py

@@ -22,7 +22,8 @@ class Riddler(Query):
         if not resp:
             return
         subdomains_find = self.match(self.domain, resp.text)
-        self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+        # 合并搜索子域名搜索结果
+        self.subdomains = self.subdomains.union(subdomains_find)
 
     def run(self):
         """
@@ -47,5 +48,4 @@ def do(domain):  # 统一入口名字 方便多线程调用
 
 
 if __name__ == '__main__':
-
     do('example.com')

oneforall/modules/datasets/robtex.py

@@ -34,7 +34,8 @@ class Robtex(Query):
                     return
                 subdomains_find = self.match(self.domain, resp.text)
                 if subdomains_find:
-                    self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+                    # 合并搜索子域名搜索结果
+                    self.subdomains = self.subdomains.union(subdomains_find)
 
     def run(self):
         """

oneforall/modules/datasets/securitytrails_api.py

@@ -25,10 +25,11 @@ class SecurityTrailsAPI(Query):
         resp = self.get(url, params)
         if not resp:
             return
-        subdomains_prefix = resp.json()['subdomains']
-        subdomains_find = [f'{prefix}.{self.domain}' for prefix in subdomains_prefix]
+        prefixs = resp.json()['subdomains']
+        subdomains_find = [f'{prefix}.{self.domain}' for prefix in prefixs]
         if subdomains_find:
-            self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+            # 合并搜索子域名搜索结果
+            self.subdomains = self.subdomains.union(subdomains_find)
 
     def run(self):
         """
@@ -49,12 +50,10 @@ def do(domain):  # 统一入口名字 方便多线程调用
     类统一调用入口
 
     :param str domain: 域名
-
     """
     query = SecurityTrailsAPI(domain)
     query.run()
 
 
 if __name__ == '__main__':
-
     do('example.com')

oneforall/modules/datasets/sitedossier.py

@@ -29,8 +29,10 @@ class SiteDossier(Query):
             subdomains_find = self.match(self.domain, resp.text)
             if not subdomains_find:  # 搜索没有发现子域名则停止搜索
                 break
-            self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
-            if 'Show next 100 items' not in resp.text:  # 搜索页面没有出现下一页时停止搜索
+            # 合并搜索子域名搜索结果
+            self.subdomains = self.subdomains.union(subdomains_find)
+            # 搜索页面没有出现下一页时停止搜索
+            if 'Show next 100 items' not in resp.text:
                 break
             self.page_num += self.per_page_num
 
@@ -57,5 +59,4 @@ def do(domain):  # 统一入口名字 方便多线程调用
 
 
 if __name__ == '__main__':
-
     do('example.com')

oneforall/modules/intelligence/riskiq_api.py

@@ -46,12 +46,10 @@ def do(domain):  # 统一入口名字 方便多线程调用
     类统一调用入口
 
     :param str domain: 域名
-
     """
     query = RiskIQ(domain)
     query.run()
 
 
 if __name__ == '__main__':
-
     do('example.com')

oneforall/modules/intelligence/threatminer.py

@@ -18,12 +18,14 @@ class ThreatMiner(Query):
         time.sleep(self.delay)
         self.header = self.get_header()
         self.proxy = self.get_proxy(self.source)
-        params = {'e': 'subdomains_container', 'q': self.domain, 't': 0, 'rt': 10}
+        params = {'e': 'subdomains_container',
+                  'q': self.domain, 't': 0, 'rt': 10}
         resp = self.get(self.addr, params)
         if not resp:
             return
         subdomains_find = self.match(self.domain, resp.text)
-        self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+        # 合并搜索子域名搜索结果
+        self.subdomains = self.subdomains.union(subdomains_find)
 
     def run(self):
         """
@@ -48,5 +50,4 @@ def do(domain):  # 统一入口名字 方便多线程调用
 
 
 if __name__ == '__main__':
-
     do('example.com')

oneforall/modules/intelligence/virustotal.py

@@ -65,12 +65,10 @@ def do(domain):  # 统一入口名字 方便多线程调用
     类统一调用入口
 
     :param str domain: 域名
-
     """
     query = VirusTotal(domain)
     query.run()
 
 
 if __name__ == '__main__':
-
     do('example.com')

oneforall/modules/intelligence/virustotal_api.py

@@ -44,12 +44,10 @@ def do(domain):  # 统一入口名字 方便多线程调用
     类统一调用入口
 
     :param str domain: 域名
-
     """
     query = VirusTotalAPI(domain)
     query.run()
 
 
 if __name__ == '__main__':
-
     do('example.com')

oneforall/modules/search/ask.py

@@ -34,7 +34,8 @@ class Ask(Search):
             if not subdomain_find:
                 break
             if not full_search:
-                if subdomain_find.issubset(self.subdomains):  # 搜索中发现搜索出的结果有完全重复的结果就停止搜索
+                # 搜索中发现搜索出的结果有完全重复的结果就停止搜索
+                if subdomain_find.issubset(self.subdomains):
                     break
             self.subdomains = self.subdomains.union(subdomain_find)
             self.page_num += 1
@@ -53,9 +54,12 @@ class Ask(Search):
 
         # 递归搜索下一层的子域
         if self.recursive_search:
-            for layer_num in range(1, self.recursive_times):  # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            for layer_num in range(1, self.recursive_times):
                 for subdomain in self.subdomains:
-                    if subdomain.count('.') - self.domain.count('.') == layer_num:  # 进行下一层子域搜索的限制条件
+                    # 进行下一层子域搜索的限制条件
+                    count = subdomain.count('.') - self.domain.count('.')
+                    if count == layer_num:
                         self.search(subdomain)
         self.save_json()
         self.gen_result()

oneforall/modules/search/baidu.py

@@ -22,7 +22,8 @@ class Baidu(Search):
         """
         bs = BeautifulSoup(html, features='lxml')
         subdomains_all = set()
-        for find_res in bs.find_all('a', {'class': 'c-showurl'}):  # 获取搜索结果中所有的跳转URL地址
+        # 获取搜索结果中所有的跳转URL地址
+        for find_res in bs.find_all('a', {'class': 'c-showurl'}):
             url = find_res.get('href')
             subdomain = self.match_location(domain, url)
             subdomains_all = subdomains_all.union(subdomain)
@@ -42,22 +43,27 @@ class Baidu(Search):
             self.header = self.get_header()
             self.proxy = self.get_proxy(self.source)
             query = 'site:' + domain + filtered_subdomain
-            params = {'wd': query, 'pn': self.page_num, 'rn': self.per_page_num}
+            params = {'wd': query, 'pn': self.page_num,
+                      'rn': self.per_page_num}
             resp = self.get(self.addr, params)
             if not resp:
                 return
             if len(domain) > 12:  # 解决百度搜索结果中域名过长会显示不全的问题
-                subdomains_find = self.redirect_match(domain, resp.text)  # 获取百度跳转URL响应头的Location字段获取直链
+                # 获取百度跳转URL响应头的Location字段获取直链
+                subdomains_find = self.redirect_match(domain, resp.text)
             else:
                 subdomains_find = self.match(domain, resp.text)
             if not subdomains_find:  # 搜索没有发现子域名则停止搜索
                 break
             if not full_search:
-                if subdomains_find.issubset(self.subdomains):  # 搜索中发现搜索出的结果有完全重复的结果就停止搜索
+                # 搜索中发现搜索出的结果有完全重复的结果就停止搜索
+                if subdomains_find.issubset(self.subdomains):
                     break
-            self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+            # 合并搜索子域名搜索结果
+            self.subdomains = self.subdomains.union(subdomains_find)
             self.page_num += self.per_page_num
-            if '&pn={next_pn}&'.format(next_pn=self.page_num) not in resp.text:  # 搜索页面没有出现下一页时停止搜索
+            # 搜索页面没有出现下一页时停止搜索
+            if '&pn={next_pn}&'.format(next_pn=self.page_num) not in resp.text:
                 break
             if self.page_num >= self.limit_num:  # 搜索条数限制
                 break
@@ -76,9 +82,12 @@ class Baidu(Search):
 
         # 递归搜索下一层的子域
         if self.recursive_search:
-            for layer_num in range(1, self.recursive_times):  # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            for layer_num in range(1, self.recursive_times):
                 for subdomain in self.subdomains:
-                    if subdomain.count('.') - self.domain.count('.') == layer_num:  # 进行下一层子域搜索的限制条件
+                    # 进行下一层子域搜索的限制条件
+                    count = subdomain.count('.') - self.domain.count('.')
+                    if count == layer_num:
                         self.search(subdomain)
 
         self.save_json()

oneforall/modules/search/bing.py

@@ -31,7 +31,8 @@ class Bing(Search):
             time.sleep(self.delay)
             self.proxy = self.get_proxy(self.source)
             query = 'site:' + domain + filtered_subdomain
-            params = {'q': query, 'first': self.page_num, 'count': self.per_page_num}
+            params = {'q': query, 'first': self.page_num,
+                      'count': self.per_page_num}
             resp = self.get(self.addr, params)
             if not resp:
                 return
@@ -39,10 +40,13 @@ class Bing(Search):
             if not subdomains_find:  # 搜索没有发现子域名则停止搜索
                 break
             if not full_search:
-                if subdomains_find.issubset(self.subdomains):  # 搜索中发现搜索出的结果有完全重复的结果就停止搜索
+                # 搜索中发现搜索出的结果有完全重复的结果就停止搜索
+                if subdomains_find.issubset(self.subdomains):
                     break
-            self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
-            if '<div class="sw_next>' not in resp.text:  # 搜索页面没有出现下一页时停止搜索
+            # 合并搜索子域名搜索结果
+            self.subdomains = self.subdomains.union(subdomains_find)
+            # 搜索页面没有出现下一页时停止搜索
+            if '<div class="sw_next>' not in resp.text:
                 break
             self.page_num += self.per_page_num
             if self.page_num >= self.limit_num:  # 搜索条数限制
@@ -53,7 +57,6 @@ class Bing(Search):
         类执行入口
         """
         self.begin()
-
         self.search(self.domain, full_search=True)
 
         # 排除同一子域搜索结果过多的子域以发现新的子域
@@ -62,15 +65,17 @@ class Bing(Search):
 
         # 递归搜索下一层的子域
         if self.recursive_search:
-            for layer_num in range(1, self.recursive_times):  # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            for layer_num in range(1, self.recursive_times):
                 for subdomain in self.subdomains:
-                    if subdomain.count('.') - self.domain.count('.') == layer_num:  # 进行下一层子域搜索的限制条件
+                    # 进行下一层子域搜索的限制条件
+                    count = subdomain.count('.') - self.domain.count('.')
+                    if count == layer_num:
                         self.search(subdomain)
 
         self.save_json()
         self.gen_result()
         self.save_db()
-
         self.finish()
 
 

oneforall/modules/search/bing_api.py

@@ -39,9 +39,11 @@ class BingAPI(Search):
             if not subdomains_find:  # 搜索没有发现子域名则停止搜索
                 break
             if not full_search:
-                if subdomains_find.issubset(self.subdomains):  # 搜索中发现搜索出的结果有完全重复的结果就停止搜索
+                # 搜索中发现搜索出的结果有完全重复的结果就停止搜索
+                if subdomains_find.issubset(self.subdomains):
                     break
-            self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+            # 合并搜索子域名搜索结果
+            self.subdomains = self.subdomains.union(subdomains_find)
             self.page_num += self.per_page_num
             if self.page_num >= self.limit_num:  # 搜索条数限制
                 break
@@ -61,9 +63,12 @@ class BingAPI(Search):
 
         # 递归搜索下一层的子域
         if self.recursive_search:
-            for layer_num in range(1, self.recursive_times):  # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            for layer_num in range(1, self.recursive_times):
                 for subdomain in self.subdomains:
-                    if subdomain.count('.') - self.domain.count('.') == layer_num:  # 进行下一层子域搜索的限制条件
+                    # 进行下一层子域搜索的限制条件
+                    count = subdomain.count('.') - self.domain.count('.')
+                    if count == layer_num:
                         self.search(subdomain)
 
         self.save_json()

oneforall/modules/search/duckduckgo.py

@@ -34,7 +34,8 @@ class DuckDuckGO(Search):
             if not subdomain_find:
                 break
             if not full_search:
-                if subdomain_find.issubset(self.subdomains):  # 搜索中发现搜索出的结果有完全重复的结果就停止搜索
+                # 搜索中发现搜索出的结果有完全重复的结果就停止搜索
+                if subdomain_find.issubset(self.subdomains):
                     break
             self.subdomains = self.subdomains.union(subdomain_find)
             try:
@@ -43,7 +44,8 @@ class DuckDuckGO(Search):
             except Exception as e:
                 logger.error(e)
                 break
-            data.update({'s': s, 'nextParams': '', 'o': 'json', 'dc': dc, 'api': '/d.js'})
+            data.update({'s': s, 'nextParams': '', 'o': 'json',
+                         'dc': dc, 'api': '/d.js'})
 
     def run(self):
         """
@@ -59,9 +61,12 @@ class DuckDuckGO(Search):
 
         # 递归搜索下一层的子域
         if self.recursive_search:
-            for layer_num in range(1, self.recursive_times):  # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            for layer_num in range(1, self.recursive_times):
                 for subdomain in self.subdomains:
-                    if subdomain.count('.') - self.domain.count('.') == layer_num:  # 进行下一层子域搜索的限制条件
+                    # 进行下一层子域搜索的限制条件
+                    count = subdomain.count('.') - self.domain.count('.')
+                    if count == layer_num:
                         self.search(subdomain)
 
         self.save_json()

oneforall/modules/search/exalead.py

@@ -27,7 +27,8 @@ class Exalead(Search):
             self.header = self.get_header()
             self.proxy = self.get_proxy(self.source)
             query = 'site:' + domain + filtered_subdomain
-            params = {'q': query, 'elements_per_page': '30', "start_index": self.page_num}
+            params = {'q': query, 'elements_per_page': '30',
+                      "start_index": self.page_num}
             resp = self.get(url=self.addr, params=params)
             if not resp:
                 return
@@ -59,15 +60,17 @@ class Exalead(Search):
 
         # 递归搜索下一层的子域
         if self.recursive_search:
-            for layer_num in range(1, self.recursive_times):  # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            for layer_num in range(1, self.recursive_times):
                 for subdomain in self.subdomains:
-                    if subdomain.count('.') - self.domain.count('.') == layer_num:  # 进行下一层子域搜索的限制条件
+                    # 进行下一层子域搜索的限制条件
+                    count = subdomain.count('.') - self.domain.count('.')
+                    if count == layer_num:
                         self.search(subdomain)
 
         self.save_json()
         self.gen_result()
         self.save_db()
-
         self.finish()
 
 

oneforall/modules/search/fofa_api.py

@@ -22,12 +22,13 @@ class FoFa(Search):
         发送搜索请求并做子域匹配
         """
         self.page_num = 1
-        query_base64 = base64.b64encode(f'domain={self.domain}'.encode('utf-8'))
+        query_data = base64.b64encode(f'domain={self.domain}'.encode('utf-8'))
         while True:
             time.sleep(self.delay)
             self.header = self.get_header()
             self.proxy = self.get_proxy(self.source)
-            query = {'email': self.email, 'key': self.key, 'qbase64': query_base64, 'page': self.page_num}
+            query = {'email': self.email, 'key': self.key,
+                     'qbase64': query_data, 'page': self.page_num}
             resp = self.get(self.addr, query)
             if not resp:
                 return
@@ -39,7 +40,6 @@ class FoFa(Search):
         """
         类执行入口
         """
-
         if not self.check(self.email, self.key):
             return
         self.begin()

oneforall/modules/search/google.py

@@ -67,9 +67,12 @@ class Google(Search):
 
         # 递归搜索下一层的子域
         if self.recursive_search:
-            for layer_num in range(1, self.recursive_times):  # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            for layer_num in range(1, self.recursive_times):
                 for subdomain in self.subdomains:
-                    if subdomain.count('.') - self.domain.count('.') == layer_num:  # 进行下一层子域搜索的限制条件
+                    # 进行下一层子域搜索的限制条件
+                    count = subdomain.count('.') - self.domain.count('.')
+                    if count == layer_num:
                         self.search(subdomain)
 
         self.save_json()

oneforall/modules/search/google_api.py

@@ -29,7 +29,8 @@ class GoogleAPI(Search):
             time.sleep(self.delay)
             self.header = self.get_header()
             self.proxy = self.get_proxy(self.source)
-            params = {'key': self.key, 'cx': self.cx, 'q': word, 'fields': 'items/link',
+            params = {'key': self.key, 'cx': self.cx,
+                      'q': word, 'fields': 'items/link',
                       'start': self.page_num, 'num': self.per_page_num}
             resp = self.get(self.addr, params)
             if not resp:
@@ -60,9 +61,12 @@ class GoogleAPI(Search):
 
         # 递归搜索下一层的子域
         if self.recursive_search:
-            for layer_num in range(1, self.recursive_times):  # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            for layer_num in range(1, self.recursive_times):
                 for subdomain in self.subdomains:
-                    if subdomain.count('.') - self.domain.count('.') == layer_num:  # 进行下一层子域搜索的限制条件
+                    # 进行下一层子域搜索的限制条件
+                    count = subdomain.count('.') - self.domain.count('.')
+                    if count == layer_num:
                         self.search(subdomain)
 
         self.save_json()

oneforall/modules/search/shodan_api.py

@@ -20,7 +20,8 @@ class ShodanAPI(Search):
         query = 'hostname:.' + self.domain
         page = 1
         while True:
-            params = {'key': self.key, 'page': page, 'query': query, 'minify': True, 'facets': {'hostnames'}}
+            params = {'key': self.key, 'page': page, 'query': query,
+                      'minify': True, 'facets': {'hostnames'}}
             resp = self.get(self.addr, params)
             if not resp:
                 return

oneforall/modules/search/so.py

@@ -35,13 +35,16 @@ class So(Search):
             if not subdomain_find:
                 break
             if not full_search:
-                if subdomain_find.issubset(self.subdomains):  # 搜索中发现搜索出的结果有完全重复的结果就停止搜索
+                # 搜索中发现搜索出的结果有完全重复的结果就停止搜索
+                if subdomain_find.issubset(self.subdomains):
                     break
             self.subdomains = self.subdomains.union(subdomain_find)
             page_num += 1
-            if '<a id="snext"' not in resp.text:  # 搜索页面没有出现下一页时停止搜索
+            # 搜索页面没有出现下一页时停止搜索
+            if '<a id="snext"' not in resp.text:
                 break
-            if self.page_num * self.per_page_num >= self.limit_num:  # 搜索条数限制
+            # 搜索条数限制
+            if self.page_num * self.per_page_num >= self.limit_num:
                 break
 
     def run(self):
@@ -49,7 +52,6 @@ class So(Search):
         类执行入口
         """
         self.begin()
-
         self.search(self.domain, full_search=True)
 
         # 排除同一子域搜索结果过多的子域以发现新的子域
@@ -58,9 +60,12 @@ class So(Search):
 
         # 递归搜索下一层的子域
         if self.recursive_search:
-            for layer_num in range(1, self.recursive_times):  # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            for layer_num in range(1, self.recursive_times):
                 for subdomain in self.subdomains:
-                    if subdomain.count('.') - self.domain.count('.') == layer_num:  # 进行下一层子域搜索的限制条件
+                    # 进行下一层子域搜索的限制条件
+                    count = subdomain.count('.') - self.domain.count('.')
+                    if count == layer_num:
                         self.search(subdomain)
 
         self.save_json()

oneforall/modules/search/sogou.py

@@ -23,7 +23,8 @@ class Sogou(Search):
             self.header = self.get_header()
             self.proxy = self.get_proxy(self.source)
             word = 'site:' + domain + filtered_subdomain
-            payload = {'query': word, 'page': self.page_num, "num": self.per_page_num}
+            payload = {'query': word, 'page': self.page_num,
+                       "num": self.per_page_num}
             resp = self.get(self.addr, payload)
             if not resp:
                 return
@@ -31,13 +32,16 @@ class Sogou(Search):
             if not subdomain_find:
                 break
             if not full_search:
-                if subdomain_find.issubset(self.subdomains):  # 搜索中发现搜索出的结果有完全重复的结果就停止搜索
+                # 搜索中发现搜索出的结果有完全重复的结果就停止搜索
+                if subdomain_find.issubset(self.subdomains):
                     break
             self.subdomains = self.subdomains.union(subdomain_find)
             self.page_num += 1
-            if '<a id="sogou_next"' not in resp.text:  # 搜索页面没有出现下一页时停止搜索
+            # 搜索页面没有出现下一页时停止搜索
+            if '<a id="sogou_next"' not in resp.text:
                 break
-            if self.page_num * self.per_page_num >= self.limit_num:  # 搜索条数限制
+            # 搜索条数限制
+            if self.page_num * self.per_page_num >= self.limit_num:
                 break
 
     def run(self):
@@ -54,9 +58,12 @@ class Sogou(Search):
 
         # 递归搜索下一层的子域
         if self.recursive_search:
-            for layer_num in range(1, self.recursive_times):  # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            for layer_num in range(1, self.recursive_times):
                 for subdomain in self.subdomains:
-                    if subdomain.count('.') - self.domain.count('.') == layer_num:  # 进行下一层子域搜索的限制条件
+                    # 进行下一层子域搜索的限制条件
+                    count = subdomain.count('.') - self.domain.count('.')
+                    if count == layer_num:
                         self.search(subdomain)
 
         self.save_json()

oneforall/modules/search/yahoo.py

@@ -40,9 +40,11 @@ class Yahoo(Search):
             if not subdomains_find:  # 搜索没有发现子域名则停止搜索
                 break
             if not full_search:
-                if subdomains_find.issubset(self.subdomains):  # 搜索中发现搜索出的结果有完全重复的结果就停止搜索
+                # 搜索中发现搜索出的结果有完全重复的结果就停止搜索
+                if subdomains_find.issubset(self.subdomains):
                     break
-            self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+            # 合并搜索子域名搜索结果
+            self.subdomains = self.subdomains.union(subdomains_find)
             if '>Next</a>' not in resp.text:  # 搜索页面没有出现下一页时停止搜索
                 break
             self.page_num += self.per_page_num
@@ -63,9 +65,12 @@ class Yahoo(Search):
 
         # 递归搜索下一层的子域
         if self.recursive_search:
-            for layer_num in range(1, self.recursive_times):  # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            for layer_num in range(1, self.recursive_times):
                 for subdomain in self.subdomains:
-                    if subdomain.count('.') - self.domain.count('.') == layer_num:  # 进行下一层子域搜索的限制条件
+                    # 进行下一层子域搜索的限制条件
+                    count = subdomain.count('.') - self.domain.count('.')
+                    if count == layer_num:
                         self.search(subdomain)
 
         self.save_json()

oneforall/modules/search/yandex.py

@@ -31,7 +31,8 @@ class Yandex(Search):
             self.header = self.get_header()
             self.proxy = self.get_proxy(self.source)
             query = 'site:' + domain + filtered_subdomain
-            params = {'text': query, 'p': self.page_num, 'numdoc': self.per_page_num}
+            params = {'text': query, 'p': self.page_num,
+                      'numdoc': self.per_page_num}
             resp = self.get(self.addr, params)
             if not resp:
                 return
@@ -39,9 +40,11 @@ class Yandex(Search):
             if not subdomains_find:  # 搜索没有发现子域名则停止搜索
                 break
             if not full_search:
-                if subdomains_find.issubset(self.subdomains):  # 搜索中发现搜索出的结果有完全重复的结果就停止搜索
+                # 搜索中发现搜索出的结果有完全重复的结果就停止搜索
+                if subdomains_find.issubset(self.subdomains):
                     break
-            self.subdomains = self.subdomains.union(subdomains_find)  # 合并搜索子域名搜索结果
+            # 合并搜索子域名搜索结果
+            self.subdomains = self.subdomains.union(subdomains_find)
             if '>next</a>' not in resp.text:  # 搜索页面没有出现下一页时停止搜索
                 break
             self.page_num += 1
@@ -62,9 +65,12 @@ class Yandex(Search):
 
         # 递归搜索下一层的子域
         if self.recursive_search:
-            for layer_num in range(1, self.recursive_times):  # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            # 从1开始是之前已经做过1层子域搜索了,当前实际递归层数是layer+1
+            for layer_num in range(1, self.recursive_times):
                 for subdomain in self.subdomains:
-                    if subdomain.count('.') - self.domain.count('.') == layer_num:  # 进行下一层子域搜索的限制条件
+                    # 进行下一层子域搜索的限制条件
+                    count = subdomain.count('.') - self.domain.count('.')
+                    if count == layer_num:
                         self.search(subdomain)
 
         self.save_json()