From 7819471a54e7a2f8470b4b3e22aea9914d59a7b0 Mon Sep 17 00:00:00 2001
From: gyani <gyani@e0a8ed71-7df4-0310-8962-fdc924857419>
Date: Fri, 14 Aug 2015 12:38:03 +0000
Subject: [PATCH] Removed http-email-harest and made changes to CHANGELOG and
 script.db to show the same.

The new http-grep comitted earlier does what http-email-harvest does
by default(no patterns given).
---
 CHANGELOG                      |  3 ++
 scripts/http-email-harvest.nse | 88 ----------------------------------
 scripts/script.db              |  1 -
 3 files changed, 3 insertions(+), 89 deletions(-)
 delete mode 100644 scripts/http-email-harvest.nse

diff --git a/CHANGELOG b/CHANGELOG
index a1b54c4d3..7ed7e07c0 100644
--- a/CHANGELOG
+++ b/CHANGELOG
@@ -1,5 +1,8 @@
 # Nmap Changelog ($Id$); -*-text-*-
 
+o [NSE] Removed http-email-harvest as the the new http-grep does email address
+  scraping by default. [Gyanendra Mishra]
+
 o [NSE] Added script http-fetch. This script can be used to fetch all files
   from the target, specific files from the target or files that match a  given
   pattern. [Gyanendra Mishra]
diff --git a/scripts/http-email-harvest.nse b/scripts/http-email-harvest.nse
deleted file mode 100644
index d978d4b8c..000000000
--- a/scripts/http-email-harvest.nse
+++ /dev/null
@@ -1,88 +0,0 @@
-local httpspider = require "httpspider"
-local shortport = require "shortport"
-local stdnse = require "stdnse"
-local table = require "table"
-
-description = [[
-Spiders a web site and collects e-mail addresses.
-]]
-
----
--- @usage
--- nmap --script=http-email-harvest <target>
---
--- @output
--- PORT   STATE SERVICE REASON
--- 80/tcp open  http    syn-ack
--- | http-email-harvest:
--- | Spidering limited to: maxdepth=3; maxpagecount=20
--- |   root@examplec.com
--- |_  postmaster@example.com
---
--- @args http-email-harvest.maxdepth the maximum amount of directories beneath
---       the initial url to spider. A negative value disables the limit.
---       (default: 3)
--- @args http-email-harvest.maxpagecount the maximum amount of pages to visit.
---       A negative value disables the limit (default: 20)
--- @args http-email-harvest.url the url to start spidering. This is a URL
---       relative to the scanned host eg. /default.html (default: /)
--- @args http-email-harvest.withinhost only spider URLs within the same host.
---       (default: true)
--- @args http-email-harvest.withindomain only spider URLs within the same
---       domain. This widens the scope from <code>withinhost</code> and can
---       not be used in combination. (default: false)
---
-
-author = "Patrik Karlsson"
-license = "Same as Nmap--See http://nmap.org/book/man-legal.html"
-categories = {"discovery", "safe"}
-
-
-portrule = shortport.http
-
-function action(host, port)
-  local EMAIL_PATTERN = "[A-Za-z0-9%.%%%+%-]+@[A-Za-z0-9%.%%%+%-]+%.%w%w%w?%w?"
-
-  local crawler = httpspider.Crawler:new(host, port, nil, {
-    scriptname = SCRIPT_NAME
-  }
-  )
-
-  if ( not(crawler) ) then
-    return
-  end
-  crawler:set_timeout(10000)
-
-  local emails = {}
-  while(true) do
-    local status, r = crawler:crawl()
-    -- if the crawler fails it can be due to a number of different reasons
-    -- most of them are "legitimate" and should not be reason to abort
-    if ( not(status) ) then
-      if ( r.err ) then
-        return stdnse.format_output(true, ("ERROR: %s"):format(r.reason))
-      else
-        break
-      end
-    end
-
-    -- Collect each e-mail address and build a unique index of them
-    if r.response.body then
-      for email in r.response.body:gmatch(EMAIL_PATTERN) do
-        emails[email] = true
-      end
-    end
-  end
-
-  -- if no email addresses were collected abort
-  if ( not(emails) ) then return end
-
-  local results = {}
-  for email, _ in pairs(emails) do
-    table.insert(results, email)
-  end
-
-  results.name = crawler:getLimitations()
-
-  return stdnse.format_output(true, results)
-end
diff --git a/scripts/script.db b/scripts/script.db
index 957476590..1d9aa111a 100644
--- a/scripts/script.db
+++ b/scripts/script.db
@@ -163,7 +163,6 @@ Entry { filename = "http-dombased-xss.nse", categories = { "exploit", "intrusive
 Entry { filename = "http-domino-enum-passwords.nse", categories = { "auth", "intrusive", } }
 Entry { filename = "http-drupal-enum.nse", categories = { "discovery", "intrusive", } }
 Entry { filename = "http-drupal-enum-users.nse", categories = { "discovery", "intrusive", } }
-Entry { filename = "http-email-harvest.nse", categories = { "discovery", "safe", } }
 Entry { filename = "http-enum.nse", categories = { "discovery", "intrusive", "vuln", } }
 Entry { filename = "http-errors.nse", categories = { "discovery", "intrusive", } }
 Entry { filename = "http-exif-spider.nse", categories = { "intrusive", } }