sitemaps_parsers 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 0dda6b2e07cbdbfde69a03ccd115184338819325da942d7551b5aaef037e3294
+  data.tar.gz: fc41c6b4b2af071ea02f407832234ccc7d362c35faa9910b6a0185d3dd838f3a
+SHA512:
+  metadata.gz: f8035d70ae575afa224181cfd46a7d87bd9f6f676b3ea32c46b283026c0c7937b238739b0db7449bc81a0a04dde8121899433b2a91b58f5800aaa19daa0b7ed8
+  data.tar.gz: 738103fb141ce1b224d9b9c36ae768d32dac1d0ed93f672e0c2425e910cf7cb16e0e0415397ee5fbb4bef95794ea62009690a6767c85f05d4cd595bf1f1dc595

data/.gitignore

@@ -0,0 +1,11 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+
+# rspec failure tracking
+.rspec_status

data/.rspec

@@ -0,0 +1,3 @@
+--format documentation
+--color
+--require spec_helper

data/.travis.yml

@@ -0,0 +1,7 @@
+---
+sudo: false
+language: ruby
+cache: bundler
+rvm:
+  - 2.5.3
+before_install: gem install bundler -v 1.17.3

data/Gemfile

@@ -0,0 +1,8 @@
+source "https://rubygems.org"
+
+git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+
+  gem 'nokogiri'
+  gem 'rspec'
+# Specify your gem's dependencies in sitemaps_parsers.gemspec
+gemspec

data/README.md

@@ -0,0 +1,42 @@
+# SitemapsParsers
+
+Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/sitemaps_parsers`. To experiment with that code, run `bin/console` for an interactive prompt.
+
+TODO: Delete this and the text above, and describe your gem
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'sitemaps_parsers'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install sitemaps_parsers
+
+## Usage
+Create a new instance of the Parser: sp = SitemapParser.new(domain name site), examples SitemapParser.new('test.com')
+
+Extract the URLs of the sitemap:
+
+sp.urls # => Array of urls from file sitemap.xml
+
+sp.sitemap_path # => Gets path to sitemap.xml
+
+sp.list_nested_sitemap #=> Gets list nested sitemaps
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/sitemaps_parsers.

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "sitemaps_parsers"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/lib/sitemaps_parsers.rb

@@ -0,0 +1,100 @@
+require 'nokogiri'
+require 'open-uri'
+require 'uri'
+require 'net/http'
+
+require 'sitemaps_parsers/version'
+
+class SitemapParser
+  attr_reader :domain, :robots_sitemap_path, :list_nested_sitemap
+
+  def initialize(domain)
+    @domain = domain
+    @url = URI.parse("http://#{@domain}")
+  end
+
+  def urls
+    return parse_sitemap(check_default_sitemap) if check_default_sitemap
+
+    parse_nested_sitemaps(robots_sitemap)
+  end
+
+  def sitemap_path
+    robots_sitemap
+    check_default_sitemap&.to_s || robots_sitemap_path&.join(',')
+  end
+
+  private
+
+  def check_default_sitemap
+    url_http_sitemap = URI.join(@url, 'sitemap.xml')
+    url_https_sitemap = URI.join(URI.parse("https://#{@domain}"), 'sitemap.xml')
+    url_http_www_sitemap = URI.join(URI.parse("http://www.#{@domain}"), 'sitemap.xml')
+    url_https_www_sitemap = URI.join(URI.parse("https://www.#{@domain}"), 'sitemap.xml')
+
+    return url_http_sitemap if Net::HTTP.get_response(url_http_sitemap).code == '200'
+    return url_https_sitemap if Net::HTTP.get_response(url_https_sitemap).code == '200'
+    return url_http_www_sitemap if Net::HTTP.get_response(url_http_www_sitemap).code == '200'
+    return url_https_www_sitemap if Net::HTTP.get_response(url_https_www_sitemap).code == '200'
+  rescue StandardError
+    nil
+  end
+
+  def robots_sitemap
+    @robots_sitemap_path ||= open(URI.join(@url, 'robots.txt')).read.scan(/\s*sitemap:\s*([^\r\n]+)\s*$/i).flatten!.uniq
+
+    @list_nested_sitemap ||= nested_sitemaps(@robots_sitemap_path)
+    @list_nested_sitemap
+  rescue StandardError
+    nil
+  end
+
+  def nested_sitemaps(sitemap_list = [])
+    sitemap_list.map do |path|
+      path_io = open(path)
+      Nokogiri::HTML(path_io).xpath('//sitemapindex/sitemap/loc').map(&:text)
+    end.flatten
+  end
+
+  def parse_nested_sitemaps(nested_sitemaps = [])
+    nested_sitemaps.map do |sitemap|
+      Nokogiri::XML(load_sitemap(sitemap))
+    end.compact.map do |sitemap_io|
+      filter_sitemap_urls(sitemap_io)
+    end.compact.flatten
+  end
+
+  def load_sitemap(url = nil)
+    sitemap_io = open(url)
+  rescue StandardError
+    nil
+  else
+    begin
+      return Zlib::GzipReader.new(sitemap_io)
+    rescue StandardError
+      return sitemap_io
+    end
+  end
+
+  def filter_sitemap_urls(sitemap_data)
+    sitemap_data.search('url').map { |url| url.at('loc').content.strip }
+  end
+
+  def parse_sitemap(url)
+    sitemap_data = Nokogiri::XML(open(url))
+
+    if !sitemap_data.at('urlset').nil?
+      return filter_sitemap_urls(sitemap_data.at('urlset'))
+
+    elsif !sitemap_data.at('sitemapindex').nil?
+      found_urls = []
+      nested_sitemaps = sitemap_data.at('sitemapindex').search('sitemap')
+
+      nested_sitemaps.each do |sitemap|
+        child_sitemap_location = sitemap.at('loc').content.strip
+        found_urls << filter_sitemap_urls(Nokogiri::XML(open(child_sitemap_location)))
+      end
+      return found_urls.flatten
+    end
+  end
+end

data/lib/sitemaps_parsers/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module SitemapsParsers
+  VERSION = '0.1.0'
+end

data/sitemaps_parsers.gemspec

@@ -0,0 +1,26 @@
+lib = File.expand_path('lib', __dir__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'sitemaps_parsers/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'sitemaps_parsers'
+  spec.version       = SitemapsParsers::VERSION
+  spec.authors       = ['Maksimov Konstantin']
+  spec.email         = ['kmakimovv@gmail.com']
+  spec.license       = 'MIT'
+  spec.summary       = 'SitemapsParsers - gem for parsing file sitemap.xml and gets all urls from sitemap.xml '
+  spec.description   = 'SitemapsParsers - parser for XML sitemaps which respects sitemaps listed in robots.txt and handles gziped and nested sitemaps as well'
+  spec.homepage      = 'https://github.com/kmaksimovv/sitemaps_parsers'
+
+  spec.files = Dir.chdir(File.expand_path(__dir__)) do
+    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  end
+  spec.bindir        = 'exe'
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ['lib']
+
+  spec.add_development_dependency 'bundler', '~> 1.17'
+  spec.add_development_dependency 'nokogiri', '~> 1.10', '>= 1.10.3'
+  spec.add_development_dependency 'rake', '~> 10.0'
+  spec.add_development_dependency 'rspec', '~> 3.0'
+end

metadata

@@ -0,0 +1,118 @@
+--- !ruby/object:Gem::Specification
+name: sitemaps_parsers
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Maksimov Konstantin
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2019-07-03 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.17'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.17'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.10'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.10.3
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.10'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 1.10.3
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+description: SitemapsParsers - parser for XML sitemaps which respects sitemaps listed
+  in robots.txt and handles gziped and nested sitemaps as well
+email:
+- kmakimovv@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- Gemfile
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- lib/sitemaps_parsers.rb
+- lib/sitemaps_parsers/version.rb
+- sitemaps_parsers.gemspec
+homepage: https://github.com/kmaksimovv/sitemaps_parsers
+licenses:
+- MIT
+metadata: {}
+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: []
+rubygems_version: 3.0.3
+signing_key: 
+specification_version: 4
+summary: SitemapsParsers - gem for parsing file sitemap.xml and gets all urls from
+  sitemap.xml
+test_files: []