增加报表下载功能

README.md

@@ -6,7 +6,7 @@ w11scan是一款分布式的WEB指纹识别系统（包括CMS识别、js框架
 
 ## 安装
 软件本身安装非常简单，比较复杂的是一些框架、数据库的安装。  
-[安装](./docs/install.md)  
+- [安装](./docs/install.md)  
 - docker在筹划中...
 
 ## 使用的技术和思路
@@ -21,6 +21,7 @@ w11scan是一款分布式的WEB指纹识别系统（包括CMS识别、js框架
 2. 优先使用命中率最高的指纹，其次，将指纹按照访问路径分类排序，再优先使用访问路径次数最多的指纹。
 3. 一个指纹识别成功后，会停止识别该URL的其他指纹，开始下一个任务
 4. 搜索功能支持多种语法，全文搜索(mongodb特性)
+5. 支持将内容下载为报表
 
 ## show 
 Preview [https://x.hacking8.com/?tag=w11scan](https://x.hacking8.com/?tag=w11scan)

app/Common.py

@@ -0,0 +1,27 @@
+from io import BytesIO
+import xlwt
+
+# 将数据保存成excel
+def write_data(data, tname):
+    file = xlwt.Workbook(encoding='utf-8')
+    table = file.add_sheet(tname, cell_overwrite_ok=True)
+    l = 0
+    for line in data:
+        c = 0
+        for _ in line:
+            table.write(l, c, line[c])
+            c += 1
+        l += 1
+    sio = BytesIO()
+    file.save(sio)
+    return sio
+
+
+# excel业务逻辑处理
+def CreateTable(cursor, id):
+    item = []
+    item.append(['任务状态', '域名', '网站标题', 'CMS识别结果', '其他信息'])
+    for i in cursor:
+        item.append(i)
+    file = write_data(item, id)
+    return file.getvalue()

app/views.py

@@ -9,6 +9,7 @@
 import time
 from cms.tasks import buildPayload
 from urllib.parse import urlparse
+from app.Common import CreateTable
 import re
 
 # Create your views here.
@@ -330,4 +331,37 @@ def detail(request,slug = ""):
 
     data = db.coll["result"].find({"taskid":ObjectId(slug)})
 
-    return render(request, "task_detail.html", {"cursor":data,"tasks":tasks,"len":data.count()})
+    return render(request, "task_detail.html", {"cursor":data,"tasks":tasks,"len":data.count()})
+
+def download(request,slug = ""):
+
+    if not request.session.get('is_login',None):
+        return redirect(login)
+
+    db = Conn.MongDB(database="w11scan_config")
+
+    tasks = db.coll["tasks"].find_one({"_id":ObjectId(slug)})
+    colname = tasks.get("name",None)
+    taskdate = tasks.get("time",None)
+    if taskdate is None:
+        return HttpResponse("faild,taskid invalid")
+    taskdate = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(taskdate))
+    data = db.coll["result"].find({"taskid":ObjectId(slug)})
+    # { "_id" : ObjectId("5b6696d78598849b135dd44e"), "url" : "http://okoko.cn", "status" : "finish", "taskid" : ObjectId("5b6696d78598849b135dd448"), "other" : { "web-servers" : [ "Tengine" ], "other" : [ "Langeuage:php", "Server:Tengine/1.4.2", "X-Powered-By:PHP/5.3.10" ] }, "title" : "okoko.cn-您正在访问的网站可以合作！" }
+    # ['任务状态', '域名', '网站标题', 'CMS识别结果', '其他信息']
+    show = []
+    for i in data:
+        cms = i.get("webdna","")
+        if cms != "":
+            cms = cms.get("cmsname","")
+        _ = [i.get("status",""),i.get("url",""),i.get("title",""),cms,repr(i.get("other",""))]
+        show.append(_)
+    siov = CreateTable(show,colname)
+
+    response = HttpResponse(siov, content_type='application/vnd.ms-excel')
+    response['Content-Disposition'] = 'attachment; filename={}.xls'.format(taskdate)
+    response.write(siov)
+
+    return response
+
+

requirements.txt

@@ -15,3 +15,4 @@ requests==2.19.1
 six==1.11.0
 urllib3==1.23
 vine==1.1.4
+xlwt==1.3.0

templates/task_detail.html

@@ -1,4 +1,5 @@
 {% extends "layout.html" %}
+{% load appname_tags %}
 {% load staticfiles %}
 {% block css %}
     <link href="{% static 'buss/css/task.css' %}" rel="stylesheet" type="text/css"/>
@@ -12,8 +13,8 @@
         <div class="row">
             <div class="col-sm-12">
                 <div class="btn-group pull-right m-t-15">
-                    <a type="button" class="btn btn-tag dropdown-toggle waves-effect waves-light"
-                       href="/downloadxls" style="color: white">下载
+                    <a type="button" target="_blank" class="btn btn-tag dropdown-toggle waves-effect waves-light"
+                       href="{% url 'download' tasks|mongo2id:'_id' %}" style="color: white">下载
                     </a>
 
                 </div>

xun/urls.py

@@ -33,5 +33,6 @@
     path(r'logout',views.logout),
     path(r'task_add',views.task_add),
     path(r'task_del',views.task_del),
-    path(r'task/<str:slug>',views.detail,name="task_detail")
+    path(r'task/<str:slug>',views.detail,name="task_detail"),
+    path(r'download/<str:slug>',views.download,name="download")
 ]