From baf6f8e20b0187125c4900149c55c0ed62089c48 Mon Sep 17 00:00:00 2001
From: Jing Ling <shmilylty@gmail.com>
Date: Sat, 9 May 2020 17:09:19 +0800
Subject: [PATCH] =?UTF-8?q?exalead.com=E5=8A=A0=E4=BA=86=E8=B0=B7=E6=AD=8C?=
 =?UTF-8?q?=E4=BA=BA=E6=9C=BA=E9=AA=8C=E8=AF=81=20=E6=9A=82=E6=97=B6?=
 =?UTF-8?q?=E7=A7=BB=E9=99=A4=E8=BF=99=E4=B8=AA=E6=A8=A1=E5=9D=97?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 modules/search/exalead.py | 87 ---------------------------------------
 1 file changed, 87 deletions(-)
 delete mode 100644 modules/search/exalead.py

diff --git a/modules/search/exalead.py b/modules/search/exalead.py
deleted file mode 100644
index 71a4fc3..0000000
--- a/modules/search/exalead.py
+++ /dev/null
@@ -1,87 +0,0 @@
-import random
-import time
-from common.search import Search
-
-
-class Exalead(Search):
-    def __init__(self, domain):
-        Search.__init__(self)
-        self.domain = domain
-        self.module = 'Search'
-        self.source = "ExaleadSearch"
-        self.addr = "http://www.exalead.com/search/web/results/"
-        self.per_page_num = 30
-
-    def search(self, domain, filtered_subdomain='', full_search=False):
-        """
-        发送搜索请求并做子域匹配
-
-        :param str domain: 域名
-        :param str filtered_subdomain: 过滤的子域
-        :param bool full_search: 全量搜索
-        """
-        self.page_num = 0
-        while True:
-            self.delay = random.randint(1, 5)
-            time.sleep(self.delay)
-            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}
-            resp = self.get(url=self.addr, params=params)
-            if not resp:
-                return
-            subdomains = self.match(domain, resp.text)
-            if not subdomains:
-                break
-            if not full_search:
-                if subdomains.issubset(self.subdomains):
-                    break
-            self.subdomains = self.subdomains.union(subdomains)
-            self.page_num += self.per_page_num
-            if self.page_num > 1999:
-                break
-            if 'title="Go to the next page"' not in resp.text:
-                break
-
-    def run(self):
-        """
-        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
-        for statement in self.filter(self.domain, self.subdomains):
-            statement = statement.replace('-site', 'and -site')
-            self.search(self.domain, filtered_subdomain=statement)
-
-        # 递归搜索下一层的子域
-        if self.recursive_search:
-            # 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:
-                    # 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.finish()
-        self.save_json()
-        self.gen_result()
-        self.save_db()
-
-
-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
-    """
-    search = Exalead(domain)
-    search.run()
-
-
-if __name__ == '__main__':
-    do('example.com')