From 953b7a4e9ba1f1d76897c7901bdb6e1f4e41de1f Mon Sep 17 00:00:00 2001
From: shmilylty <admin@hackfun.org>
Date: Fri, 18 Oct 2019 00:33:31 +0800
Subject: [PATCH] =?UTF-8?q?=E6=B7=BB=E5=8A=A0=E7=99=BE=E5=BA=A6=E4=BA=91?=
 =?UTF-8?q?=E8=A7=82=E6=B5=8B=E6=8E=A5=E5=8F=A3=E6=9F=A5=E8=AF=A2?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 oneforall/modules/datasets/cebaidu.py | 52 +++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)
 create mode 100644 oneforall/modules/datasets/cebaidu.py

diff --git a/oneforall/modules/datasets/cebaidu.py b/oneforall/modules/datasets/cebaidu.py
new file mode 100644
index 0000000..c19e7c1
--- /dev/null
+++ b/oneforall/modules/datasets/cebaidu.py
@@ -0,0 +1,52 @@
+import time
+from common.query import Query
+
+
+class CeBaidu(Query):
+    def __init__(self, domain):
+        Query.__init__(self)
+        self.domain = self.register(domain)
+        self.module = 'Dataset'
+        self.source = 'CeBaiduQuery'
+        self.addr = 'http://ce.baidu.com/index/getRelatedSites'
+
+    def query(self):
+        """
+        向接口查询子域并做子域匹配
+        """
+        time.sleep(self.delay)
+        self.header = self.get_header()
+        self.proxy = self.get_proxy(self.source)
+        params = {'site_address': self.domain}
+        resp = self.get(self.addr, params)
+        if not resp:
+            return
+        subdomains = self.match(self.domain, str(resp.json()))
+        # 合并搜索子域名搜索结果
+        self.subdomains = self.subdomains.union(subdomains)
+        print(self.subdomains)
+
+    def run(self):
+        """
+        类执行入口
+        """
+        self.begin()
+        self.query()
+        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
+    """
+    query = CeBaidu(domain)
+    query.run()
+
+
+if __name__ == '__main__':
+    do('example.com')