set使用update

brute.py

@@ -247,7 +247,7 @@ def collect_wildcard_record(domain, authoritative_ns):
             continue
         if ip is None:
             continue
-        ips = ips.union(ip)
+        ips.update(ip)
         # 统计每个泛解析IP出现次数
         for addr in ip:
             count = ips_stat.setdefault(addr, 0)

common/lookup.py

@@ -23,6 +23,6 @@ class Lookup(Module):
         for item in answer:
             record = item.to_text()
             subdomains = self.match_subdomains(record)
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             logger.log('DEBUG', record)
         return self.subdomains

common/module.py

@@ -220,7 +220,8 @@ class Module(object):
 
     def collect_subdomains(self, resp):
         subdomains = self.match_subdomains(resp)
-        return self.subdomains.union(subdomains)
+        self.subdomains.update(subdomains)
+        return self.subdomains
 
     def save_json(self):
         """

modules/certificates/censys_api.py

@@ -34,7 +34,7 @@ class CensysAPI(Query):
             logger.log('ALERT', f'{self.source} module {status}')
             return
         subdomains = self.match_subdomains(resp.text)
-        self.subdomains = self.subdomains.union(subdomains)
+        self.subdomains.update(subdomains)
         pages = json.get('metadata').get('pages')
         for page in range(2, pages + 1):
             data['page'] = page

modules/certificates/crtsh.py

@@ -21,7 +21,7 @@ class Crtsh(Query):
             return
         text = resp.text.replace(r'\n', ' ')
         subdomains = self.match_subdomains(text)
-        self.subdomains = self.subdomains.union(subdomains)
+        self.subdomains.update(subdomains)
 
     def run(self):
         """

modules/check/axfr.py

@@ -46,7 +46,7 @@ class CheckAXFR(Module):
         for name in names:
             full_domain = str(name) + '.' + self.domain
             subdomain = self.match_subdomains(full_domain)
-            self.subdomains = self.subdomains.union(subdomain)
+            self.subdomains.update(subdomain)
             record = zone[name].to_text(name)
             self.results.append(record)
         if self.results:

modules/check/cert.py

@@ -32,7 +32,7 @@ class CheckCert(Module):
             logger.log('DEBUG', e.args)
             return
         subdomains = self.match_subdomains(str(cert_dict))
-        self.subdomains = self.subdomains.union(subdomains)
+        self.subdomains.update(subdomains)
 
     def run(self):
         """

modules/check/nsec.py

@@ -23,7 +23,7 @@ class CheckNSEC(Module):
                 record = item.to_text()
                 subdomains = self.match_subdomains(record)
                 subdomain = ''.join(subdomains)  # 其实这里的subdomains的长度为1 也就是说只会有一个子域
-                self.subdomains = self.subdomains.union(subdomains)
+                self.subdomains.update(subdomains)
                 self.gen_record(subdomains, record)
             if subdomain == self.domain:  # 当查出子域为主域 说明完成了一个循环 不再继续查询
                 break

modules/crawl/archivecrawl.py

@@ -28,7 +28,7 @@ class ArchiveCrawl(Crawl):
                 url = resp.data.get('url')
                 subdomains = self.match_subdomains(self.get_maindomain(domain),
                                                    url + resp.text)
-                self.subdomains = self.subdomains.union(subdomains)
+                self.subdomains.update(subdomains)
 
     def run(self):
         """

modules/crawl/commoncrawl.py

@@ -27,7 +27,7 @@ class CommonCrawl(Crawl):
         for resp in tqdm(cdx.iter(url, limit=limit), total=limit):
             if resp.data.get('status') not in ['301', '302']:
                 subdomains = self.match_subdomains(self.get_maindomain(domain), resp.text)
-                self.subdomains = self.subdomains.union(subdomains)
+                self.subdomains.update(subdomains)
 
     def run(self):
         """

modules/datasets/cloudflare_api.py

@@ -81,7 +81,7 @@ class CloudFlareAPI(Query):
                        f'{list_dns_resp.status_code} {list_dns_resp.text}')
             return
         subdomains = self.match_subdomains(list_dns_resp.text)
-        self.subdomains = self.subdomains.union(subdomains)
+        self.subdomains.update(subdomains)
         if not self.subdomains:
             # waiting for cloudflare enumerate subdomains
             sleep(5)
@@ -96,7 +96,7 @@ class CloudFlareAPI(Query):
                     return
                 total_pages = list_dns_resp.json()['result_info']['total_pages']
                 subdomains = (self.match_subdomains(list_dns_resp.text))
-                self.subdomains = self.subdomains.union(subdomains)
+                self.subdomains.update(subdomains)
                 page += 1
                 if page > total_pages:
                     break

modules/datasets/ipv4info_api.py

@@ -35,7 +35,7 @@ class IPv4InfoAPI(Query):
             subdomains = self.match_subdomains(str(json))
             if not subdomains:
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(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
             subdomains = json.get('Subdomains')
             if subdomains and len(subdomains) < 300:

modules/datasets/netcraft.py

@@ -50,7 +50,7 @@ class NetCraft(Query):
             subdomains = self.match_subdomains(resp)
             if not subdomains:  # 搜索没有发现子域名则停止搜索
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             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)

modules/datasets/qianxun.py

@@ -28,7 +28,7 @@ class QianXun(Query):
             subdomains = self.match_subdomains(resp)
             if not subdomains:  # 没有发现子域名则停止查询
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             if '<div id="page" class="pagelist">' not in resp.text:
                 break
             if '<li class="disabled"><span>&raquo;</span></li>' in resp.text:

modules/datasets/securitytrails_api.py

@@ -26,7 +26,7 @@ class SecurityTrailsAPI(Query):
         prefixs = resp.json()['subdomains']
         subdomains = [f'{prefix}.{self.domain}' for prefix in prefixs]
         if subdomains:
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
 
     def run(self):
         """

modules/datasets/sitedossier.py

@@ -25,7 +25,7 @@ class SiteDossier(Query):
             subdomains = self.match_subdomains(resp)
             if not subdomains:  # 没有发现子域名则停止查询
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             # 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

modules/datasets/spyse_api.py

@@ -29,7 +29,7 @@ class SpyseAPI(Query):
             subdomains = self.match_subdomains(str(json))
             if not subdomains:  # 没有发现子域名则停止查询
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             offset += limit
             if len(json.get('data').get('items')) < limit:
                 break

modules/datasets/threatcrowd.py

@@ -26,7 +26,7 @@ class ThreatCrowd(Query):
         if resp.status_code != 200:
             return
         subdomains = self.match_subdomains(resp.text)
-        self.subdomains = self.subdomains.union(subdomains)
+        self.subdomains.update(subdomains)
 
     def run(self):
         """

modules/datasets/wzpc.py

@@ -34,7 +34,7 @@ class WZPCQuery(Query):
             subdomains = self.match_subdomains(resp.text)
             if not subdomains:  # 没有发现子域名则停止查询
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             if not subdomains:
                 break
             if page_num > 10:

modules/dnsquery/srv.py

@@ -52,7 +52,7 @@ class BruteSRV(Module):
             for item in answer:
                 record = str(item)
                 subdomains = self.match_subdomains(record)
-                self.subdomains = self.subdomains.union(subdomains)
+                self.subdomains.update(subdomains)
                 self.gen_record(subdomains, record)
 
     def run(self):

modules/finder.py

@@ -163,7 +163,7 @@ def find_subdomains(domain, data):
         if not rsp_html:
             continue
         logger.log('DEBUG', f'matching subdomains from response of {req_url}')
-        subdomains = subdomains.union(match_subdomains(domain, rsp_html))
+        subdomains.update(match_subdomains(domain, rsp_html))
         urls = find_url(rsp_html)
         if not urls:
             continue
@@ -175,5 +175,5 @@ def find_subdomains(domain, data):
     for resp, text in resp_data:
         if text:
             logger.log('DEBUG', f'matching subdomains from response of {resp.url}')
-            subdomains = subdomains.union(match_subdomains(domain, text))
+            subdomains.update(match_subdomains(domain, text))
     return subdomains

modules/intelligence/virustotal.py

@@ -30,7 +30,7 @@ class VirusTotal(Query):
             subdomains = self.match_subdomains(resp)
             if not subdomains:
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             data = resp.json()
             next_cursor = data.get('meta').get('cursor')
 

modules/intelligence/virustotal_api.py

@@ -25,7 +25,7 @@ class VirusTotalAPI(Query):
             subdomains = self.match_subdomains(resp)
             if not subdomains:
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             data = resp.json()
             next_cursor = data.get('meta').get('cursor')
 

modules/search/ask.py

@@ -30,7 +30,7 @@ class Ask(Search):
             subdomains = self.match_subdomains(resp, fuzzy=False)
             if not self.check_subdomains(subdomains):
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             self.page_num += 1
             if '>Next<' not in resp.text:
                 break

modules/search/baidu.py

@@ -25,7 +25,7 @@ class Baidu(Search):
         for find_res in bs.find_all('a', {'class': 'c-showurl'}):
             url = find_res.get('href')
             subdomains = self.match_location(url)
-            subdomains_all = subdomains_all.union(subdomains)
+            subdomains_all.update(subdomains)
         return subdomains_all
 
     def search(self, domain, filtered_subdomain=''):
@@ -54,7 +54,7 @@ class Baidu(Search):
                 subdomains = self.match_subdomains(resp, fuzzy=False)
             if not self.check_subdomains(subdomains):
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             self.page_num += self.per_page_num
             # 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:

modules/search/bing.py

@@ -36,7 +36,7 @@ class Bing(Search):
             subdomains = self.match_subdomains(resp, fuzzy=False)
             if not self.check_subdomains(subdomains):
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             # 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

modules/search/bing_api.py

@@ -36,7 +36,7 @@ class BingAPI(Search):
             subdomains = self.match_subdomains(resp)
             if not self.check_subdomains(subdomains):
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             self.page_num += self.per_page_num
             if self.page_num >= self.limit_num:  # 搜索条数限制
                 break

modules/search/fofa_api.py

@@ -40,7 +40,7 @@ class FoFa(Search):
             subdomains = self.match_subdomains(resp)
             if not subdomains:  # 搜索没有发现子域名则停止搜索
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             size = resp_json.get('size')
             if size < 10000:
                 break

modules/search/gitee.py

@@ -37,7 +37,7 @@ class Gitee(Search):
             subdomains = self.match_subdomains(soup, fuzzy=False)
             if not self.check_subdomains(subdomains):
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             if '<li class="disabled"><a href="###">' in resp.text:
                 break
             page_num += 1

modules/search/github_api.py

@@ -63,7 +63,7 @@ class GithubAPI(Search):
             subdomains = self.match_subdomains(resp)
             if not subdomains:
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             page += 1
             try:
                 resp_json = resp.json()

modules/search/google.py

@@ -40,7 +40,7 @@ class Google(Search):
             subdomains = self.match_subdomains(resp, fuzzy=False)
             if not self.check_subdomains(subdomains):
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             page_num += per_page_num
             if 'start=' + str(page_num) not in resp.text:
                 break

modules/search/google_api.py

@@ -35,7 +35,7 @@ class GoogleAPI(Search):
             subdomains = self.match_subdomains(resp)
             if not self.check_subdomains(subdomains):
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             self.page_num += self.per_page_num
             if self.page_num > 100:  # 免费的API只能查询前100条结果
                 break

modules/search/shodan_api.py

@@ -26,7 +26,7 @@ class ShodanAPI(Search):
             subdomains = self.match_subdomains(resp)
             if not subdomains:  # 搜索没有发现子域名则停止搜索
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             page += 1
 
     def run(self):

modules/search/so.py

@@ -31,7 +31,7 @@ class So(Search):
             subdomains = self.match_subdomains(resp, fuzzy=False)
             if not self.check_subdomains(subdomains):
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             page_num += 1
             # 搜索页面没有出现下一页时停止搜索
             if '<a id="snext"' not in resp.text:

modules/search/sogou.py

@@ -28,7 +28,7 @@ class Sogou(Search):
             subdomains = self.match_subdomains(resp, fuzzy=False)
             if not self.check_subdomains(subdomains):
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             self.page_num += 1
             # 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:

modules/search/yahoo.py

@@ -38,7 +38,7 @@ class Yahoo(Search):
             subdomains = self.match_subdomains(text, fuzzy=False)
             if not self.check_subdomains(subdomains):
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             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

modules/search/yandex.py

@@ -36,7 +36,7 @@ class Yandex(Search):
             subdomains = self.match_subdomains(resp, fuzzy=False)
             if not self.check_subdomains(subdomains):
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             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

modules/search/zoomeye_api.py

@@ -50,7 +50,7 @@ class ZoomEyeAPI(Search):
             subdomains = self.match_subdomains(resp)
             if not subdomains:  # 搜索没有发现子域名则停止搜索
                 break
-            self.subdomains = self.subdomains.union(subdomains)
+            self.subdomains.update(subdomains)
             page_num += 1
             if page_num > 500:
                 break