logstash-input-crawler 1.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 25f7f64d83707e4bc2584693fafae5a741eb21b32dbfcec3ecd109f4d47bd0dc
+  data.tar.gz: a48c227043804fbc72336c4a2acf1a5893e4d6646d7df7fb73b56bdf1d002161
+SHA512:
+  metadata.gz: 3729fb3cb17afda7f9ca16fc20fe75d7ae3a4524f282927f40cb9284fdc399819e57d8887e49bf986e50c1977c97d38c6ad3c326bde02312a46c4cb4ac68e9ab
+  data.tar.gz: 0266a0c5c777c34885881eeda588aeab373a301f168faa92bf6e1e7771e84ae3d2aab52a3775bffc9e2f48d5edee3345caef58f2b1e651e045d37c0b3a79b302

data/CHANGELOG.md

@@ -0,0 +1,2 @@
+## 0.1.0
+  - Plugin created with the logstash plugin generator

data/CONTRIBUTORS

@@ -0,0 +1,10 @@
+The following is a list of people who have contributed ideas, code, bug
+reports, or in general have helped logstash along its way.
+
+Contributors:
+*  - 
+
+Note: If you've sent us patches, bug reports, or otherwise contributed to
+Logstash, and you aren't on the list above and want to be, please let us know
+and we'll make sure you're here. Contributions from folks like you are what make
+open source awesome.

data/DEVELOPER.md

@@ -0,0 +1,2 @@
+# logstash-input-crawler
+Example input plugin. This should help bootstrap your effort to write your own input plugin!

data/Gemfile

@@ -0,0 +1,6 @@
+source 'https://rubygems.org'
+
+gemspec
+
+gem 'mechanize'
+gem 'nokogiri'

data/LICENSE

@@ -0,0 +1,11 @@
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

data/README.md

@@ -0,0 +1,86 @@
+# Logstash Plugin
+
+This is a plugin for [Logstash](https://github.com/elastic/logstash).
+
+It is fully free and fully open source. The license is Apache 2.0, meaning you are pretty much free to use it however you want in whatever way.
+
+## Documentation
+
+Logstash provides infrastructure to automatically generate documentation for this plugin. We use the asciidoc format to write documentation so any comments in the source code will be first converted into asciidoc and then into html. All plugin documentation are placed under one [central location](http://www.elastic.co/guide/en/logstash/current/).
+
+- For formatting code or config example, you can use the asciidoc `[source,ruby]` directive
+- For more asciidoc formatting tips, see the excellent reference here https://github.com/elastic/docs#asciidoc-guide
+
+## Need Help?
+
+Need help? Try #logstash on freenode IRC or the https://discuss.elastic.co/c/logstash discussion forum.
+
+## Developing
+
+### 1. Plugin Developement and Testing
+
+#### Code
+- To get started, you'll need JRuby with the Bundler gem installed.
+
+- Create a new plugin or clone and existing from the GitHub [logstash-plugins](https://github.com/logstash-plugins) organization. We also provide [example plugins](https://github.com/logstash-plugins?query=example).
+
+- Install dependencies
+```sh
+bundle install
+```
+
+#### Test
+
+- Update your dependencies
+
+```sh
+bundle install
+```
+
+- Run tests
+
+```sh
+bundle exec rspec
+```
+
+### 2. Running your unpublished Plugin in Logstash
+
+#### 2.1 Run in a local Logstash clone
+
+- Edit Logstash `Gemfile` and add the local plugin path, for example:
+```ruby
+gem "logstash-filter-awesome", :path => "/your/local/logstash-filter-awesome"
+```
+- Install plugin
+```sh
+bin/logstash-plugin install --no-verify
+```
+- Run Logstash with your plugin
+```sh
+bin/logstash -e 'filter {awesome {}}'
+```
+At this point any modifications to the plugin code will be applied to this local Logstash setup. After modifying the plugin, simply rerun Logstash.
+
+#### 2.2 Run in an installed Logstash
+
+You can use the same **2.1** method to run your plugin in an installed Logstash by editing its `Gemfile` and pointing the `:path` to your local plugin development directory or you can build the gem and install it using:
+
+- Build your plugin gem
+```sh
+gem build logstash-filter-awesome.gemspec
+```
+- Install the plugin from the Logstash home
+```sh
+bin/logstash-plugin install /your/local/plugin/logstash-filter-awesome.gem
+```
+- Start Logstash and proceed to test the plugin
+
+## Contributing
+
+All contributions are welcome: ideas, patches, documentation, bug reports, complaints, and even something you drew up on a napkin.
+
+Programming is not a required skill. Whatever you've seen about open source and maintainers or community members  saying "send patches or die" - you will not see that here.
+
+It is more important to the community that you are able to contribute.
+
+For more information about contributing, see the [CONTRIBUTING](https://github.com/elastic/logstash/blob/master/CONTRIBUTING.md) file.

data/lib/logstash/inputs/crawler.rb

@@ -0,0 +1,103 @@
+# encoding: utf-8
+require "logstash/inputs/base"
+require "logstash/namespace"
+require "stud/interval"
+require "net/http"
+require "uri"
+require "mechanize"
+
+class LogStash::Inputs::Crawler < LogStash::Inputs::Base
+  config_name "crawler"
+
+  # If undefined, Logstash will complain, even if codec is unused.
+  default :codec, "plain"
+
+  # The message string to use in the event.
+  config :url, :validate => :string, :required => true
+
+  #Set de interval for stoppable_sleep
+  config :interval, :validate => :number, :default => 86400
+
+  #Set de max number of urls that go to sniff
+  config :url_max, :validate => :number, :default => 10
+
+  public
+   def register
+    @urls = []
+    @agent = Mechanize.new
+    @agent.agent.http.verify_mode = OpenSSL::SSL::VERIFY_NONE
+   end # def register
+
+
+   def run(queue)
+    # we can abort the loop if stop? becomes true
+    while !stop?
+      start_crawl(queue)      
+      Stud.stoppable_sleep(@interval) { stop? }
+    end # loop
+   end # def run
+
+
+   def stop
+    # nothing to do in this case so it is not necessary to define stop
+    # examples of common "stop" tasks:
+    #  * close sockets (unblocking blocking reads/accets)
+    #  * cleanup temporary files
+    #  * terminate spawned threads
+   end
+
+   def start_crawl(queue)
+	begin
+		get_urls_for_page(@url,queue)				
+	rescue Exception => e
+      		puts "FALLO DE CRAWL"
+	end
+   end
+  
+   def get_urls_for_page(url,queue)
+	page_content = get_page_content url	
+	# Regex to get all "links" in the page
+    	urlsa = page_content.scan(/\<a href\=(\"(http|https)\:.*?\")/)		
+	urlsa.each { |u| 
+		sanitized_url = u.first.gsub(/\"/, '').strip
+		if (@urls.include?(sanitized_url) == false) && (@urls.length <= @url_max)
+      			@urls.push(sanitized_url)
+        		pagina = @agent.get(sanitized_url)
+        		content = pagina.body
+        		evento = LogStash::Event.new("link" => sanitized_url , "contenido" => content)
+        		decorate(evento)
+        		queue << evento
+        		#puts "/*******************************************************************************/"
+        		#puts @urls.length
+        		#puts "/*******************************************************************************/"
+			# If Unexpected Error happens when trying to fetch URLs move on to the next URL
+			begin
+				get_urls_for_page(sanitized_url,queue)	
+        		rescue Exception => e
+          			#puts "/*******************************************************************************/"
+          			#puts "Problema al obtener el contenido de : " + sanitized_url
+          			#puts "/*******************************************************************************/"
+				next
+			end
+		end
+	}
+	return @urls
+  end
+
+  def get_page_content url
+	uri = URI(url)
+	request = Net::HTTP::Get.new(uri)
+	http = Net::HTTP.new(uri.host, uri.port)	
+	# Neet to enable use of SSL if the URL protocol is HTTPS
+	http.use_ssl = (uri.scheme == "https")
+	response = http.request(request)
+	# Check if URL needs to be forwarded because of redirect
+	case response
+		when Net::HTTPSuccess
+			return response.body
+		when Net::HTTPMovedPermanently || Net::HTTPRedirection
+			get_page_content response['location']
+	end
+  end
+
+end # class LogStash::Inputs::Crawler

data/lib/logstash/inputs/crawler.rb.BK

@@ -0,0 +1,93 @@
+# encoding: utf-8
+require "logstash/inputs/base"
+require "logstash/namespace"
+require "stud/interval"
+require "set"
+require "uri"
+require "nokogiri"
+require "open-uri"
+
+class LogStash::Inputs::Crawler < LogStash::Inputs::Base
+  config_name "crawler"
+
+  # If undefined, Logstash will complain, even if codec is unused.
+  default :codec, "plain"
+
+  # The message string to use in the event.
+  config :url, :validate => :string, :required => true
+
+  #Set de interval for stoppable_sleep 
+  config :interval, :validate => :number, :default => 86400
+
+  public
+  def register
+        @seen_pages = Set.new                      # Keep track of what we've seen
+  end # def register
+
+
+  def run(queue)
+    # we can abort the loop if stop? becomes true
+    while !stop?
+
+        crawl_site(@url) do |page,uri|
+          event = LogStash::Event.new("link" => uri.to_s)
+	        decorate(event)
+       		queue << event
+        end
+
+        evento = LogStash::Event.new("paginas_exploradas" => @seen_pages.length)
+	      decorate(evento)
+       	queue << evento
+
+      Stud.stoppable_sleep(@interval) { stop? }
+    end # loop
+  end # def run
+
+
+  def stop
+    # nothing to do in this case so it is not necessary to define stop
+    # examples of common "stop" tasks:
+    #  * close sockets (unblocking blocking reads/accets)
+    #  * cleanup temporary files
+    #  * terminate spawned threads
+  end
+
+  def crawl_site( starting_at, &each_page )
+        files = %w[png jpeg jpg gif svg txt js css zip gz asp PNG JPEG JPG GIF SVG TXT JS CSS ZIP GZ ASP]
+        starting_uri = URI.parse(starting_at)
+      
+        crawl_page = ->(page_uri) do              # A re-usable mini-function
+          unless @seen_pages.include?(page_uri)
+            @seen_pages << page_uri                # Record that we've seen this
+            begin
+              doc = Nokogiri.HTML(open(page_uri)) # Get the page
+              each_page.call(doc,page_uri)        # Yield page and URI to the block
+      
+              # Find all the links on the page
+              hrefs = doc.css('a[href]').map{ |a| a['href'] }
+
+              # Make these URIs, throwing out problem ones like mailto:
+              uris = hrefs.map{ |href| URI.join( page_uri, href ) rescue nil }.compact.uniq
+      
+              # Pare it down to only those pages that are on the same site
+              uris.select!{ |uri| uri.host == starting_uri.host }
+
+              # Throw out links to files (this could be more efficient with regex)
+              uris.reject!{ |uri| files.any?{ |ext| uri.path.end_with?(".#{ext}") } }
+      
+              # Remove #foo fragments so that sub-page links aren't differentiated
+              uris.each{ |uri| uri.fragment = nil }
+      
+              # Recursively crawl the child URIs
+              uris.each{ |uri| crawl_page.call(uri) }
+      
+            rescue OpenURI::HTTPError # Guard against 404s
+              warn "Skipping invalid link #{page_uri}"
+            end
+          end
+        end
+        crawl_page.call( starting_uri )   # Kick it all off!
+  end
+      
+
+end # class LogStash::Inputs::Crawler

data/lib/logstash/inputs/crawler.rb.bk

@@ -0,0 +1,91 @@
+# encoding: utf-8
+require "logstash/inputs/base"
+require "logstash/namespace"
+require "stud/interval"
+require "mechanize"
+
+class LogStash::Inputs::Crawler < LogStash::Inputs::Base
+  config_name "crawler"
+
+  # If undefined, Logstash will complain, even if codec is unused.
+  default :codec, "plain"
+
+  # The message string to use in the event.
+  config :url, :validate => :string, :required => true
+
+  # Set how depth should be explore.
+  config :deep, :validate => :number, :default => 3
+
+  #Set de interval for stoppable_sleep 
+  config :interval, :validate => :number, :default => 86400
+
+  public
+  def register
+	@prof = 1
+	@links = []
+	@cuenta = [1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
+	@agent = Mechanize.new
+	@agent.agent.http.verify_mode = OpenSSL::SSL::VERIFY_NONE
+	@agent.redirection_limit = 500
+	@cont = 0
+	@url_actual = @url
+	@cola = []
+	@cola << @url
+  end # def register
+
+
+  def run(queue)
+    # we can abort the loop if stop? becomes true
+    while !stop?
+
+	loop do
+                @url_actual = @cola.shift
+                if (!@links.include?(@url_actual))
+                        begin
+                                @page = @agent.get(@url_actual)
+                        rescue Mechanize::ResponseCodeError => exception
+                                if exception.response_code != '200'
+                                        @url_actual = @cola.shift
+                                end
+                                retry
+                        end
+                        @page.links_with(:href => /^https?/).each do |link|
+                                @cola << link.href
+                                @cuenta[@prof] = @cuenta[@prof] + 1
+                        end
+                        @links << @url_actual
+                end
+
+                if (@cuenta[@prof-1] == @links.length)
+                        @prof = @prof + 1
+                end
+
+                break if @prof >= @deep
+        end	
+
+	@links.each do |link|
+		pagina = @agent.get(link)
+		#content = pagina.body
+		event = LogStash::Event.new("link" => link)
+	        decorate(event)
+       		queue << event
+	end
+
+	event = LogStash::Event.new("numero_de_links" => @links.length)
+        decorate(event)
+        queue << event
+
+
+      Stud.stoppable_sleep(@interval) { stop? }
+    end # loop
+  end # def run
+
+
+  def stop
+    # nothing to do in this case so it is not necessary to define stop
+    # examples of common "stop" tasks:
+    #  * close sockets (unblocking blocking reads/accets)
+    #  * cleanup temporary files
+    #  * terminate spawned threads
+  end
+end # class LogStash::Inputs::Crawler

data/logstash-input-crawler.gemspec

@@ -0,0 +1,27 @@
+Gem::Specification.new do |s|
+  s.name          = 'logstash-input-crawler'
+  s.version       = '1.0.0'
+  s.licenses      = ['Apache-2.0']
+  s.summary       = 'This plugin get the links and the html content from a initial page .'
+  s.description   = 'This plugin need set the initial url.'
+  s.homepage      = 'https://github.com/felixramirezgarcia/logstash-input-crawler'
+  s.authors       = ['Felix R G']
+  s.email         = 'felixramirezgarcia@correo.ugr.es'
+  s.require_paths = ['lib']
+
+  # Files
+  s.files = Dir['lib/**/*','spec/**/*','vendor/**/*','*.gemspec','*.md','CONTRIBUTORS','Gemfile','LICENSE','NOTICE.TXT']
+   # Tests
+  s.test_files = s.files.grep(%r{^(test|spec|features)/})
+
+  # Special flag to let us know this is actually a logstash plugin
+  s.metadata = { "logstash_plugin" => "true", "logstash_group" => "input" }
+
+  # Gem dependencies
+  s.add_runtime_dependency "logstash-core"
+  s.add_runtime_dependency 'logstash-codec-plain'
+  s.add_runtime_dependency 'stud', '>= 0.0.22'
+  s.add_development_dependency 'logstash-devutils', '>= 0.0.16'
+  s.add_runtime_dependency "mechanize"
+  s.add_runtime_dependency "nokogiri"
+end

data/spec/inputs/crawler_spec.rb

@@ -0,0 +1,11 @@
+# encoding: utf-8
+require "logstash/devutils/rspec/spec_helper"
+require "logstash/inputs/crawler"
+
+describe LogStash::Inputs::Crawler do
+
+  it_behaves_like "an interruptible input plugin" do
+    let(:config) { { "interval" => 100 } }
+  end
+
+end

metadata

@@ -0,0 +1,141 @@
+--- !ruby/object:Gem::Specification
+name: logstash-input-crawler
+version: !ruby/object:Gem::Version
+  version: 1.0.0
+platform: ruby
+authors:
+- Felix R G
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2018-07-24 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  name: logstash-core
+  prerelease: false
+  type: :runtime
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  name: logstash-codec-plain
+  prerelease: false
+  type: :runtime
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.0.22
+  name: stud
+  prerelease: false
+  type: :runtime
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.0.22
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.0.16
+  name: logstash-devutils
+  prerelease: false
+  type: :development
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.0.16
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  name: mechanize
+  prerelease: false
+  type: :runtime
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  name: nokogiri
+  prerelease: false
+  type: :runtime
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: This plugin need set the initial url.
+email: felixramirezgarcia@correo.ugr.es
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- CHANGELOG.md
+- CONTRIBUTORS
+- DEVELOPER.md
+- Gemfile
+- LICENSE
+- README.md
+- lib/logstash/inputs/crawler.rb
+- lib/logstash/inputs/crawler.rb.BK
+- lib/logstash/inputs/crawler.rb.bk
+- logstash-input-crawler.gemspec
+- spec/inputs/crawler_spec.rb
+homepage: https://github.com/felixramirezgarcia/logstash-input-crawler
+licenses:
+- Apache-2.0
+metadata:
+  logstash_plugin: 'true'
+  logstash_group: input
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project:
+rubygems_version: 2.6.13
+signing_key:
+specification_version: 4
+summary: This plugin get the links and the html content from a initial page .
+test_files:
+- spec/inputs/crawler_spec.rb