Added the ronin-web xml command (closes #88).

README.md

@@ -57,6 +57,7 @@ Commands:
     spider
     user-agent
     wordlist
+    xml
 ```
 
 Open the `ronin-web` Ruby REPL:

gemspec.yml

@@ -37,6 +37,7 @@ generated_files:
   - man/ronin-web-session-cookie.1
   - man/ronin-web-user-agent.1
   - man/ronin-web-wordlist.1
+  - man/ronin-web-xml.1
 
 dependencies:
   nokogiri: ~> 1.4

lib/ronin/web/cli/commands/html.rb

@@ -18,7 +18,7 @@
 # along with ronin-web.  If not, see <https://www.gnu.org/licenses/>.
 #
 
-require 'ronin/web/cli/command'
+require 'ronin/web/cli/commands/xml'
 require 'ronin/support/network/http'
 
 require 'nokogiri'
@@ -55,19 +55,10 @@ module Commands
         #     URL | FILE                       The URL or FILE to search
         #     [XPATH | CSS-path]               The XPath or CSS-path query
         #
-        class Html < Command
+        class Html < Xml
 
           usage '[options] {URL | FILE} [XPATH | CSS-path]'
 
-          option :xpath, short: '-X',
-                         value: {
-                           type:  String,
-                           usage: 'XPATH'
-                         },
-                         desc:  'XPath query' do |xpath|
-                           @query = xpath
-                         end
-
           option :css_path, short: '-C',
                             value: {
                               type:  String,
@@ -77,9 +68,6 @@ class Html < Command
                               @query = css_path
                             end
 
-          option :text, short: '-t',
-                        desc:  'Prints the inner-text'
-
           option :meta_tags, short: '-M',
                              desc: 'Searches for all <meta ...> tags' do
                                @query = '//meta'
@@ -120,9 +108,6 @@ class Html < Command
                           @query = '//a/@href | //link/@href | //script/@src | //form/@action'
                         end
 
-          option :first, short: '-F',
-                         desc: 'Only print the first match'
-
           argument :source, required: true,
                             usage: 'URL | FILE',
                             desc:  'The URL or FILE to search'
@@ -155,34 +140,7 @@ def run(source,query=@query)
               exit(-1)
             end
 
-            doc   = parse(read(source))
-            nodes = if options[:first] then doc.at(query)
-                    else                    doc.search(query)
-                    end
-
-            if options[:text]
-              puts nodes.inner_text
-            else
-              puts nodes
-            end
-          end
-
-          #
-          # Reads a URI or file.
-          #
-          # @param [String] source
-          #   The URI or file path.
-          #
-          # @return [File, String]
-          #   The contents of the URI or file.
-          #
-          def read(source)
-            if source.start_with?('https://') ||
-               source.start_with?('http://')
-              Support::Network::HTTP.get_body(source)
-            else
-              File.new(source)
-            end
+            super(source,query)
           end
 
           #

lib/ronin/web/cli/commands/xml.rb

@@ -0,0 +1,149 @@
+# frozen_string_literal: true
+#
+# ronin-web - A collection of useful web helper methods and commands.
+#
+# Copyright (c) 2006-2023 Hal Brodigan (postmodern.mod3 at gmail.com)
+#
+# ronin-web is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# ronin-web is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with ronin-web.  If not, see <https://www.gnu.org/licenses/>.
+#
+
+require 'ronin/web/cli/command'
+require 'ronin/support/network/http'
+
+require 'nokogiri'
+
+module Ronin
+  module Web
+    class CLI
+      module Commands
+        #
+        # Performs XPath queries on a URL or XML file.
+        #
+        # ## Usage
+        #
+        #     ronin-web xml [options] {URL | FILE} [XPATH]
+        #
+        # ## Options
+        #
+        #     -X, --xpath XPATH                XPath query
+        #     -t, --text                       Prints the inner-text
+        #     -F, --first                      Only print the first match
+        #     -h, --help                       Print help information
+        #
+        # ## Arguments
+        #
+        #     URL | FILE                       The URL or FILE to search
+        #     XPATH                            The XPath query
+        #
+        # @since 2.0.0
+        #
+        class Xml < Command
+
+          usage '[options] {URL | FILE} [XPATH]'
+
+          option :xpath, short: '-X',
+                         value: {
+                           type:  String,
+                           usage: 'XPATH'
+                         },
+                         desc:  'XPath query' do |xpath|
+                           @query = xpath
+                         end
+
+          option :first, short: '-F',
+                         desc: 'Only print the first match'
+
+          option :text, short: '-t',
+                        desc:  'Prints the elements inner text'
+
+          argument :source, required: true,
+                            usage: 'URL | FILE',
+                            desc:  'The URL or FILE to search'
+
+          argument :query, required: false,
+                           usage: 'XPATH',
+                           desc: 'The XPath query'
+
+          description 'Performs XPath queries on a URL or HTML file'
+
+          man_page 'ronin-web-xml.1'
+
+          # The XPath expression.
+          #
+          # @return [String, nil]
+          attr_reader :query
+
+          #
+          # Runs the `ronin-web xml` command.
+          #
+          # @param [String] source
+          #   The `URL` or `FILE` argument.
+          #
+          # @param [String, nil] query
+          #   The optional XPath argument.
+          #
+          def run(source,query=@query)
+            unless query
+              print_error "must specify --xpath or an XPath argument"
+              exit(-1)
+            end
+
+            doc   = parse(read(source))
+            nodes = if options[:first] then doc.at(query)
+                    else                    doc.search(query)
+                    end
+
+            if options[:text]
+              puts nodes.inner_text
+            else
+              puts nodes
+            end
+          end
+
+          #
+          # Reads a URI or file.
+          #
+          # @param [String] source
+          #   The URI or file path.
+          #
+          # @return [File, String]
+          #   The contents of the URI or file.
+          #
+          def read(source)
+            if source.start_with?('https://') ||
+               source.start_with?('http://')
+              Support::Network::HTTP.get_body(source)
+            else
+              File.new(source)
+            end
+          end
+
+          #
+          # Parses the HTML source code.
+          #
+          # @param [String] html
+          #   The raw unparsed XML.
+          #
+          # @return [Nokogiri::XML::Document]
+          #   The parsed XML document.
+          #
+          def parse(html)
+            Nokogiri::XML(html)
+          end
+
+        end
+      end
+    end
+  end
+end

man/ronin-web-html.1.md

@@ -34,6 +34,9 @@ Performs XPath/CSS-path queries on a URL or HTML file.
 `-C`, `--css-path` *CSS-path*
 : The CSS-path query to perform.
 
+`-F`, `--first`
+: Only print the first match.
+
 `-t`, `--text`
 : Prints the inner-text of the matching elements.
 
@@ -61,13 +64,13 @@ Performs XPath/CSS-path queries on a URL or HTML file.
 `-u`, `--urls`
 : Dumps all URLs in the page.
 
-`-F`, `--first`
-: Only print the first match.
-
 `-h`, `--help`
 : Print help information.
 
 ## AUTHOR
 
 Postmodern <[email protected]>
 
+## SEE ALSO
+
+[ronin-web-xml](ronin-web-xml.1.md)

man/ronin-web-xml.1.md

@@ -0,0 +1,46 @@
+# ronin-web-xml 1 "2022-01-01" Ronin "User Manuals"
+
+## NAME
+
+ronin-web-xml - Performs XPath queries on a URL or XML file
+
+## SYNOPSIS
+
+`ronin-web xml` [*options*] {*URL* \| *FILE*} [*XPATH*]
+
+## DESCRIPTION
+
+Performs XPath queries on a URL or HTML file.
+
+## ARGUMENTS
+
+*URL*
+: The `http://` or `https://` URL to fetch and parse.
+
+*FILE*
+: The local XML file to parse.
+
+*XPATH*
+: The XPath query expression.
+
+## OPTIONS
+
+`-X`, `--xpath` *XPATH*
+: The XPath query to perform.
+
+`-F`, `--first`
+: Only print the first match.
+
+`-t`, `--text`
+: Prints the inner-text of the matching elements.
+
+`-h`, `--help`
+: Print help information.
+
+## AUTHOR
+
+Postmodern <[email protected]>
+
+## SEE ALSO
+
+[ronin-web-html](ronin-web-html.1.md)

man/ronin-web.1.md

@@ -31,4 +31,4 @@ Postmodern <[email protected]>
 
 ## SEE ALSO
 
-[ronin-web-diff](ronin-web-diff.1.md) [ronin-web-html](ronin-web-html.1.md) [ronin-web-server](ronin-web-server.1.md) [ronin-web-spider](ronin-web-spider.1.md) [ronin-web-proxy](ronin-web-proxy.1.md)
+[ronin-web-diff](ronin-web-diff.1.md) [ronin-web-html](ronin-web-html.1.md) [ronin-web-server](ronin-web-server.1.md) [ronin-web-spider](ronin-web-spider.1.md) [ronin-web-proxy](ronin-web-proxy.1.md) [ronin-web-xml](ronin-web-xml.1.md)