From a1e47b80a35f1d3ae4b5fcac1a5cf49d89c5a29e Mon Sep 17 00:00:00 2001
From: Jing Ling <shmilylty@gmail.com>
Date: Fri, 19 Feb 2021 18:32:22 +0800
Subject: [PATCH] =?UTF-8?q?=E8=A7=A3=E5=86=B3=E4=BB=A3=E7=90=86=E9=85=8D?=
 =?UTF-8?q?=E7=BD=AE=E6=97=A0=E6=95=88=E9=97=AE=E9=A2=98?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 modules/datasets/netcraft.py | 4 ++--
 modules/search/bing.py       | 2 +-
 modules/search/gitee.py      | 3 ++-
 modules/search/yahoo.py      | 3 ++-
 modules/search/yandex.py     | 3 ++-
 5 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/modules/datasets/netcraft.py b/modules/datasets/netcraft.py
index 0970d97..c729737 100644
--- a/modules/datasets/netcraft.py
+++ b/modules/datasets/netcraft.py
@@ -21,7 +21,6 @@ class NetCraft(Query):
         """
         绕过NetCraft的JS验证
         """
-        self.header = self.get_header()  # Netcraft会检查User-Agent
         resp = self.get(self.init)
         if not resp:
             return False
@@ -36,12 +35,13 @@ class NetCraft(Query):
         """
         向接口查询子域并做子域匹配
         """
+        self.header = self.get_header()  # NetCraft会检查User-Agent
+        self.proxy = self.get_proxy(self.source)
         if not self.bypass_verification():
             return
         last = ''
         while True:
             time.sleep(self.delay)
-            self.header = self.get_header()
             self.proxy = self.get_proxy(self.source)
             params = {'restriction': 'site ends with',
                       'host': '.' + self.domain,
diff --git a/modules/search/bing.py b/modules/search/bing.py
index 52dc448..21c4d9b 100644
--- a/modules/search/bing.py
+++ b/modules/search/bing.py
@@ -19,9 +19,9 @@ class Bing(Search):
         :param str domain: 域名
         :param str filtered_subdomain: 过滤的子域
         """
-        self.page_num = 0  # 二次搜索重新置0
         self.header = self.get_header()
         self.proxy = self.get_proxy(self.source)
+        self.page_num = 0  # 二次搜索重新置0
         resp = self.get(self.init)
         if not resp:
             return
diff --git a/modules/search/gitee.py b/modules/search/gitee.py
index b97bd3b..2265cda 100644
--- a/modules/search/gitee.py
+++ b/modules/search/gitee.py
@@ -11,7 +11,6 @@ class Gitee(Search):
         self.module = 'Search'
         self.addr = 'https://search.gitee.com/'
         self.domain = domain
-        self.header = self.get_header()
 
     def search(self):
         """
@@ -20,6 +19,8 @@ class Gitee(Search):
         page_num = 1
         while True:
             time.sleep(self.delay)
+            self.header = self.get_header()
+            self.proxy = self.get_proxy(self.source)
             params = {'pageno': page_num, 'q': self.domain, 'type': 'code'}
             try:
                 resp = self.get(self.addr, params=params)
diff --git a/modules/search/yahoo.py b/modules/search/yahoo.py
index 296bf57..16727e3 100644
--- a/modules/search/yahoo.py
+++ b/modules/search/yahoo.py
@@ -21,13 +21,14 @@ class Yahoo(Search):
         :param str domain: 域名
         :param str filtered_subdomain: 过滤的子域
         """
+        self.header = self.get_header()
+        self.proxy = self.get_proxy(self.source)
         resp = self.get(self.init)
         if not resp:
             return
         self.cookie = resp.cookies  # 获取cookie Yahoo在搜索时需要带上cookie
         while True:
             time.sleep(self.delay)
-            self.header = self.get_header()
             self.proxy = self.get_proxy(self.source)
             query = 'site:.' + domain + filtered_subdomain
             params = {'p': query, 'b': self.page_num, 'pz': self.per_page_num}
diff --git a/modules/search/yandex.py b/modules/search/yandex.py
index 6e5f1ea..2128241 100644
--- a/modules/search/yandex.py
+++ b/modules/search/yandex.py
@@ -20,6 +20,8 @@ class Yandex(Search):
         :param str domain: 域名
         :param str filtered_subdomain: 过滤的子域
         """
+        self.header = self.get_header()
+        self.proxy = self.get_proxy(self.source)
         self.page_num = 0  # 二次搜索重新置0
         resp = self.get(self.init)
         if not resp:
@@ -27,7 +29,6 @@ class Yandex(Search):
         self.cookie = resp.cookies  # 获取cookie
         while True:
             time.sleep(self.delay)
-            self.header = self.get_header()
             self.proxy = self.get_proxy(self.source)
             query = 'site:.' + domain + filtered_subdomain
             params = {'text': query, 'p': self.page_num,