From 45f15236a85899bc1b63a639645b8e2cd84f087d Mon Sep 17 00:00:00 2001
From: aristotelis gkithkopoulos <aristogithk@gmail.com>
Date: Wed, 8 Jun 2022 16:51:06 +0300
Subject: [PATCH] add xlsx file option by using --xlsx parameter

---
 .gitignore           |  3 +++
 requirements.txt     |  1 +
 sherlock/sherlock.py | 41 +++++++++++++++++++++++++++++++++++++++--
 3 files changed, 43 insertions(+), 2 deletions(-)

diff --git a/.gitignore b/.gitignore
index 1f0eb5c..6326672 100644
--- a/.gitignore
+++ b/.gitignore
@@ -22,6 +22,9 @@ src/
 # Comma-Separated Values (CSV) Reports
 *.csv
 
+#XLSX Reports
+*.xlsx
+
 # Excluded sites list
 tests/.excluded_sites
 
diff --git a/requirements.txt b/requirements.txt
index 649ec7a..87ae820 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -5,3 +5,4 @@ requests>=2.22.0
 requests-futures>=1.0.0
 stem>=1.8.0 
 torrequest>=0.1.0
+pandas>=1.0.0
diff --git a/sherlock/sherlock.py b/sherlock/sherlock.py
index c69636d..e3c7442 100644
--- a/sherlock/sherlock.py
+++ b/sherlock/sherlock.py
@@ -8,6 +8,8 @@ networks.
 """
 
 import csv
+import xlsxwriter
+import pandas as pd
 import os
 import platform
 import re
@@ -376,7 +378,7 @@ def sherlock(username, site_data, query_notify,
 
         if error_text is not None:
             error_context = error_text
-    
+
         elif error_type == "message":
             # error_flag True denotes no error found in the HTML
             # error_flag False denotes error found in the HTML
@@ -506,6 +508,10 @@ def main():
                         action="store_true", dest="csv", default=False,
                         help="Create Comma-Separated Values (CSV) File."
                         )
+    parser.add_argument("--xlsx",
+                        action="store_true", dest="xlsx", default=False,
+                        help="Create the standard file for the modern Microsoft Excel spreadsheet (xslx)."
+                        )
     parser.add_argument("--site",
                         action="append", metavar="SITE_NAME",
                         dest="site_list", default=None,
@@ -579,7 +585,7 @@ def main():
 
     if args.tor or args.unique_tor:
         print("Using Tor to make requests")
-        
+
         print(
             "Warning: some websites might refuse connecting over Tor, so note that using this option might increase connection errors.")
 
@@ -647,6 +653,7 @@ def main():
                                     print_all=args.print_all)
 
     # Run report on all specified users.
+
     all_usernames = []
     for username in args.username:
         if(CheckForParameter(username)):
@@ -716,6 +723,36 @@ def main():
                                      response_time_s
                                      ]
                                     )
+        if args.xlsx:
+            usernames = []
+            names = []
+            url_main = []
+            url_user = []
+            exists = []
+            http_status = []
+            response_time_s = []
+
+            result_file = f"{username}.xlsx"
+            workbook = xlsxwriter.Workbook(f"{username}.xlsx")
+            sheet = workbook.add_worksheet()
+            for site in results:
+
+                if response_time_s is None:
+                    response_time_s.append("")
+                else:
+                    response_time_s.append(results[site]["status"].query_time)
+                usernames.append(username)
+                names.append(site)
+                url_main.append(results[site]["url_main"])
+                url_user.append(results[site]["url_user"])
+                exists.append(str(results[site]["status"].status))
+                http_status.append(results[site]["http_status"])
+            
+            DataFrame=pd.DataFrame({"username":usernames , "name":names , "url_main":url_main , "url_user":url_user , "exists" : exists , "http_status":http_status , "response_time_s":response_time_s})
+            DataFrame.to_excel(f'{username}.xlsx', sheet_name='sheet1', index=False)
+
+                                    
+
         print()
     query_notify.finish()