sitemap_gen 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 9806fa1dd6d1946761e6e877cda97887632fcb6a
+  data.tar.gz: 54441447f5e85f4980b365058d9b94658db7c774
+SHA512:
+  metadata.gz: 14025eb1aae87595b4828d0964f801e59bf485c8bbb1526d2f1b41be8b2abad98a816c5f170e53fd5d526a00af8429abd1783a87e4350c4e4f20adca20290455
+  data.tar.gz: 55eaa213439a2378052724f2ba5d5767d51ff14379284f10fb129436569c520d6ab565629a1d59eb961ad051b8c0588cda68831edf00a2e17c927b8114d35f39

data/bin/sitemap-gen

@@ -0,0 +1,41 @@
+#!/usr/bin/env ruby
+
+require 'sitemap_gen'
+require 'optparse'
+
+options = {}
+
+OptionParser.new do |opts|
+  opts.banner = <<-EOS
+
+A sitemap generator use directory structure input
+Usage: sitemap-gen [OPTION] PATH
+
+Options:
+  EOS
+
+  opts.on('-i', '--input [PATH]', 'Input directory that need to generate csv') do |path|
+    options[:input] = path
+  end
+
+  opts.on('-u', '--base_url [PATH]', 'Base url of website') do |path|
+    options[:base_url] = path
+  end
+
+  opts.on('-o', '--output [PATH]', 'Path to save output csv') do |path|
+    options[:output] = path
+  end
+
+  opts.on('-h', '--help', 'Display information') do |help|
+    puts opts
+    exit
+  end
+end.parse!
+
+if options.key?(:input) && options.key?(:base_url)
+  if options.key?(:output)
+    SitemapGen.run(options[:input], options[:base_url], options[:output])
+    exit
+  end
+  SitemapGen.run(options[:input], options[:base_url])
+end

data/lib/sitemap_gen/version.rb

@@ -0,0 +1,3 @@
+module SitemapGen
+  VERSION = '0.1.0'
+end

data/lib/sitemap_gen.rb

@@ -0,0 +1,62 @@
+require 'nokogiri'
+require 'csv'
+
+module SitemapGen
+  IGNORE_DIRS_REGEX = /img|cgi-bin|images|css|js/i
+
+  class << self
+    def run(dir_path, base_url, save_path = nil)
+      generate_csv(csv_data(dir_path, base_url), save_path)
+    end
+
+    def generate_csv(data, save_path)
+      header = data.inject([]) { |max, row| max.size < row.keys.size ? row.keys : max }
+      save_path ||= Dir.pwd
+      CSV.open("#{save_path}/sitemap.csv", 'wb') do |csv|
+        csv << header
+        data.each do |row|
+          csv << row.values
+        end
+      end
+    end
+
+    def csv_data(dir_path, base_url)
+      # If there is a foward slash at the end of dir path then remove it
+      #dir_path = dir_path[0..-2] if dir_path[-1] =~ /\//
+
+      # Exit if there is no html files
+      html_files = Dir.glob("#{dir_path}/**/*.html")
+      exit if html_files.empty?
+
+      data = []
+      html_files.each_with_index do |file_path, i|
+        next if file_path =~ IGNORE_DIRS_REGEX
+        server_pathname = file_path.sub(dir_path, '')
+        base_path = File.dirname(server_pathname)
+        last_slash = base_path == '/' ? '' : '/'
+        data.push({
+          id: i + 1,
+          #page_title: page_title(file_path),
+          url: base_url + base_path + last_slash
+        }.merge(dir_levels(server_pathname)))
+      end
+      data
+    end
+
+    def page_title(file_path)
+      html_doc = Nokogiri::HTML(File.read(file_path))
+      html_doc.css('head title').first.content
+    end
+
+    def dir_levels(server_pathname)
+      levels = {}
+      dirs = server_pathname.split('/')
+
+      # Drop first and last element of dirs array, because they are a empty string and a filename
+      dirs[1..-2].each_with_index do |dir, i|
+        levels.merge!({"level_#{i + 1}": dir})
+      end
+      levels
+    end
+  end
+end

metadata

@@ -0,0 +1,105 @@
+--- !ruby/object:Gem::Specification
+name: sitemap_gen
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Minh Phan
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2017-07-05 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.8'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.8'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.13'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.13'
+- !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: 
+email:
+- wofi.minh@1pac.vn
+executables:
+- sitemap-gen
+extensions: []
+extra_rdoc_files: []
+files:
+- bin/sitemap-gen
+- lib/sitemap_gen.rb
+- lib/sitemap_gen/version.rb
+homepage: https://github.com/1PACVietnam/sitemap-gen
+licenses:
+- MIT
+metadata:
+  allowed_push_host: https://rubygems.org
+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: 2.6.10
+signing_key: 
+specification_version: 4
+summary: A generator sitemap based on directory structure
+test_files: []