govuk_mirrorer 1.3.2

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: d05df644e22f9aeb6bc503bc6d5c4df69c0dabb1
+  data.tar.gz: bd7337adf9cca849b5c3973c4f8ed009329fcee4
+SHA512:
+  metadata.gz: 5d42d4011e3b6767dfc71979b6883ad82fd73f098571dc2b3421e70068225dd618ed31d5defd05106d1d6370f272646acfb9e1db36d12d9c0031c943ad22a70c
+  data.tar.gz: 76850e16ad9b9956376f68500f1a2f1b98ad083873fbee9a45c71adc4bb213d3c0040fedf0a15b1869b40b71514460b88bc9ce8e674d1ff9de4447c467f2499c

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/.ruby-version

@@ -0,0 +1 @@
+2.2.2

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in govuk_mirrorer.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2013 Alex Tomlins
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,29 @@
+# GovukMirrorer
+
+TODO: Write a gem description
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'govuk_mirrorer'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install govuk_mirrorer
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,13 @@
+
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec
+
+require "gem_publisher"
+desc "Publish gem to RubyGems"
+task :publish_gem do |t|
+  gem = GemPublisher.publish_if_updated("govuk_mirrorer.gemspec", :rubygems)
+  puts "Published #{gem}" if gem
+end

data/bin/govuk_mirrorer

@@ -0,0 +1,9 @@
+#!/usr/bin/env ruby
+
+require 'govuk_mirrorer'
+
+begin
+  GovukMirrorer.run
+rescue GovukMirrorer::Configurer::NoRootUrlSpecifiedError
+  abort "No root url specified.\nEither specify the --site-root option or set the MIRRORER_SITE_ROOT env variable"
+end

data/govuk_mirrorer.gemspec

@@ -0,0 +1,32 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'govuk_mirrorer/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "govuk_mirrorer"
+  spec.version       = GovukMirrorer::VERSION
+  spec.authors       = ["Alex Tomlins"]
+  spec.email         = ["alex.tomlins@digital.cabinet-office.gov.uk"]
+  spec.summary       = %q{Tool to generate a static version of GOV.UK}
+  spec.description   = spec.summary
+  spec.homepage      = ""
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_dependency "spidey", "0.0.4"
+  spec.add_dependency "mechanize", "2.5.1"
+  spec.add_dependency "syslogger", "1.4.2"
+  spec.add_dependency "gds-api-adapters", "8.4.0"
+  spec.add_dependency "statsd-ruby", "1.2.1"
+
+  spec.add_development_dependency "bundler", "~> 1.1"
+  spec.add_development_dependency "rake"
+  spec.add_development_dependency "rspec"
+  spec.add_development_dependency "webmock"
+  spec.add_development_dependency "gem_publisher", "1.2.0"
+end

data/jenkins.sh

@@ -0,0 +1,6 @@
+#!/bin/bash -x
+set -e
+rm -f Gemfile.lock
+bundle install --path "${HOME}/bundles/${JOB_NAME}"
+bundle exec rake
+bundle exec rake publish_gem

data/lib/govuk_mirrorer.rb

@@ -0,0 +1,14 @@
+require 'govuk_mirrorer/net_http_sni_monkey_patch'
+require 'govuk_mirrorer/version'
+
+require 'govuk_mirrorer/configurer'
+require 'govuk_mirrorer/crawler'
+require 'govuk_mirrorer/indexer'
+require 'govuk_mirrorer/statsd'
+
+module GovukMirrorer
+  def self.run
+    crawler = Crawler.new(Configurer.run(ARGV))
+    crawler.crawl
+  end
+end

data/lib/govuk_mirrorer/configurer.rb

@@ -0,0 +1,44 @@
+module GovukMirrorer
+  class Configurer
+    class NoRootUrlSpecifiedError < Exception ; end
+
+    def self.run(args)
+      require 'optparse'
+      options = {
+        :site_root => ENV['MIRRORER_SITE_ROOT'],
+        :request_interval => 0.1,
+      }
+      OptionParser.new do |o|
+        o.banner = "Usage: govuk_mirrorer [options]"
+
+        o.on('--site-root URL',
+             "Base URL to mirror from",
+             "  falls back to MIRRORER_SITE_ROOT env variable") {|root| options[:site_root] = root }
+        o.on('--request-interval INTERVAL', Float,
+             "Specify the delay between requests in seconds",
+             "  defaults to 0.1") {|interval| options[:request_interval] = interval }
+
+        o.separator "Logging:"
+        o.on('--logfile FILE', "Enable logging to a file") { |file| options[:log_file] = file }
+        o.on('--syslog [FACILITY]',
+             "Enable logging to syslog",
+             "  optionally override the default facility (local3)") do |facility|
+          options[:syslog] = facility || "local3"
+        end
+        o.on('--loglevel LEVEL', 'DEBUG/INFO/WARN/ERROR, it defaults to INFO') do |level|
+          options[:log_level] = level
+        end
+        o.on('-v', '--verbose', 'sets loglevel to DEBUG') { |level| options[:log_level] = 'DEBUG' }
+
+        o.separator ""
+        o.on('-h', '--help') { puts o; exit }
+        o.parse!(args)
+      end
+
+      # Error if site_root nil or blank
+      raise NoRootUrlSpecifiedError if options[:site_root].nil? or options[:site_root].empty?
+
+      options
+    end
+  end
+end

data/lib/govuk_mirrorer/crawler.rb

@@ -0,0 +1,170 @@
+require 'spidey'
+require 'mechanize'
+require 'logger'
+require 'syslogger'
+
+module GovukMirrorer
+  class Crawler < Spidey::AbstractSpider
+    USER_AGENT = "GOV.UK Mirrorer/#{GovukMirrorer::VERSION}"
+    DEFAULT_SITE_ROOT = 'https://www.gov.uk'
+    RETRY_RESP_CODES = [429, (500..599).to_a].flatten
+
+    def initialize(attrs = {})
+      super
+      setup_agent
+      @http_errors = {}
+
+      setup_logger(attrs)
+
+      @site_root = attrs[:site_root] || DEFAULT_SITE_ROOT
+
+      @indexer = GovukMirrorer::Indexer.new(@site_root)
+      @indexer.all_start_urls.each do |url|
+        @logger.debug "Adding start url #{url}"
+        handle url, :process_govuk_page
+      end
+    end
+
+    def site_hostname
+      URI.parse(@site_root).host
+    end
+
+    attr_accessor :logger
+
+    def crawl(options = {})
+      GovukMirrorer.statsd.time("govuk.app.mirrorer.crawl_duration") do
+        each_url do |url, handler, default_data|
+          retried = false
+          begin
+            page = agent.get(url)
+            logger.debug "Handling #{url.inspect}"
+            send handler, page, default_data
+          rescue => ex
+            if ex.is_a?(Mechanize::ResponseCodeError) and RETRY_RESP_CODES.include?(ex.response_code.to_i) and ! retried
+              retried = true
+              sleep 1
+              retry
+            end
+            handle_error url: url, handler: handler, error: ex, data: default_data
+          end
+          sleep request_interval if request_interval > 0
+        end
+        logger.info "Completed crawling the site"
+      end
+    end
+
+    def process_govuk_page(page, data = {})
+      unless page.uri.host == site_hostname
+        msg = "Ended up on non #{site_hostname} page #{page.uri.to_s}"
+        msg << " from #{agent.history[-2].uri.to_s}" if agent.history[-2]
+        logger.warn msg
+        return
+      end
+      save_to_disk(page)
+      extract_and_handle_links(page)
+    end
+
+    def extract_and_handle_links(page)
+      if page.is_a?(Mechanize::Page)
+        page.search("//a[@href]").each do |elem|
+          process_link(page, elem["href"])
+        end
+        page.search("//img[@src]").each do |elem|
+          process_link(page, elem["src"])
+        end
+        page.search("//link[@href]").each do |elem|
+          process_link(page, elem["href"])
+        end
+        page.search("//script[@src]").each do |elem|
+          process_link(page, elem["src"])
+        end
+      end
+    end
+
+    def process_link(page, href)
+      uri = URI.parse(href)
+      if uri.scheme.nil? # relative link
+        uri = URI.join(page.uri.to_s, href)
+      elsif uri.host == site_hostname
+        logger.warn "Link to non https #{href} from #{page.uri.to_s}" unless uri.scheme == "https"
+        uri.scheme = 'https'
+      else
+        logger.debug "Ignoring non #{site_hostname} link #{href} on #{page.uri.to_s}"
+        return
+      end
+      uri.fragment = nil # prevent duplicate url's being missed
+      maybe_handle uri.to_s, :process_govuk_page, :referrer => page.uri.to_s
+    rescue URI::Error => ex
+      logger.warn "#{ex.class} parsing url #{href} on page #{page.uri.to_s}"
+    end
+
+    def maybe_handle(url, handler, data = {})
+      logger.debug "Evaluating link #{url}"
+      if @urls.include?(url)
+        logger.debug "Skipping seen url #{url}"
+        return
+      end
+      if @http_errors.has_key?(url)
+        logger.debug "Skipping previous erroring url #{url}"
+        return
+      end
+      if @indexer.blacklisted_url?(url)
+        logger.debug "Skipping blacklisted url #{url}"
+        return
+      end
+      if url.include? '?'
+        logger.debug "Skipping querystringed url #{url}"
+        return
+      end
+      logger.debug "Adding url #{url} from #{data[:referrer]}"
+      handle url, handler, data
+    end
+
+    private
+
+    def setup_logger(options)
+      if options[:syslog]
+        # Syslog settings
+        # programname: govuk_mirrorer
+        # options: Syslog::LOG_PID | Syslog::LOG_CONS
+        # facility: from options
+        # Syslog::LOG_PID - adds the process number to the message (just after the program name)
+        # Syslog::LOG_CONS - writes the message on the console if an error occurs when sending the message
+        facility = Syslog.const_get("LOG_#{options[:syslog].upcase}")
+        @logger = Syslogger.new('govuk_mirrorer', Syslog::LOG_PID | Syslog::LOG_CONS, facility)
+      else
+        @logger = Logger.new(options[:log_file] || STDOUT)
+      end
+      if options[:log_level]
+        @logger.level = Logger.const_get(options[:log_level].upcase)
+      else
+        @logger.level = Logger::INFO
+      end
+    end
+
+    def handle_error(attrs)
+      msg = "Error #{attrs[:error].inspect} for #{attrs[:url]}, data: #{attrs[:data].inspect}"
+      msg << "\n#{attrs[:error].backtrace.join("\n")}" unless attrs[:error].is_a?(Mechanize::Error)
+      logger.warn msg
+      @http_errors[attrs[:url]] = attrs[:error]
+    end
+
+    # Saves to a file in ./hostname/path
+    # adds .html for html files
+    def save_to_disk(page)
+      path = page.extract_filename(true)
+      logger.debug "Saving #{page.uri.to_s} to #{path}"
+      FileUtils.mkdir_p(File.dirname(path))
+      File.open(path, 'wb') do |f|
+        f.write page.body
+      end
+    end
+
+    def setup_agent
+      agent.user_agent = USER_AGENT
+      agent.request_headers["X-Govuk-Mirrorer"] = "1"
+      # Force Mechanize to use Net::HTTP which we've monkey-patched above
+      agent.agent.http.reuse_ssl_sessions = false
+    end
+  end
+end

data/lib/govuk_mirrorer/indexer.rb

@@ -0,0 +1,94 @@
+require 'gds_api/content_api'
+
+module GovukMirrorer
+  class Indexer
+    FORMATS_TO_503 = %w(
+      local_transaction
+      smart-answer
+      custom-application
+      place
+      licence
+    ).freeze
+
+    ADDITIONAL_START_PATHS = %w(
+      /
+      /designprinciples
+      /designprinciples/styleguide
+      /designprinciples/performanceframework
+      /service-manual
+    ).freeze
+
+    # Calendars currently register as custom-application
+    WHITELIST_PATHS = %w(
+      /bank-holidays
+      /gwyliau-banc
+      /when-do-the-clocks-change
+    ).freeze
+
+    ADDITIONAL_BLACKLIST_PATHS = %w(
+      /trade-tariff
+      /licence-finder
+      /business-finance-support-finder
+      /government/uploads
+      /apply-for-a-licence
+      /search
+    ).freeze
+
+    BLACKLISTED_ATOM_FEEDS_USED_FOR_EMAIL_ALERTS = %w(
+      /government/announcements.atom
+      /government/publications.atom
+    ).freeze
+
+    def initialize(root)
+      @root = root
+      @api_endpoint = @root + '/api/artefacts.json'
+      @all_start_urls = ADDITIONAL_START_PATHS.map{ |x| @root + x}
+      @blacklist_paths = ADDITIONAL_BLACKLIST_PATHS.dup + BLACKLISTED_ATOM_FEEDS_USED_FOR_EMAIL_ALERTS.dup
+      process_artefacts
+    end
+
+    attr_reader :all_start_urls, :blacklist_paths
+
+    def blacklisted_url?(url)
+      path = URI.parse(url).path
+      return false if path.nil? # e.g. mailto: links...
+      url_segments = path.sub(%r{\A/}, '').split('/')
+      @blacklist_paths.any? do |blacklist_path|
+        bl_segments = blacklist_path.sub(%r{\A/}, '').split('/')
+        url_segments[0..(bl_segments.length - 1)] == bl_segments
+      end
+    end
+
+    private
+
+    def process_artefacts
+      artefacts.each do |artefact|
+        uri = URI.parse(artefact.web_url)
+        if WHITELIST_PATHS.include?(uri.path)
+          @all_start_urls << artefact.web_url
+        elsif FORMATS_TO_503.include?(artefact.format)
+          @blacklist_paths << uri.path
+        else
+          @all_start_urls << artefact.web_url
+        end
+      end
+    end
+
+    def artefacts
+      retried = false
+      @artefacts ||= begin
+        content_api = GdsApi::ContentApi.new("#{@root}/api", :timeout => 10)
+        GovukMirrorer.statsd.time("govuk.app.mirrorer.artefacts_duration") do
+          content_api.artefacts.with_subsequent_pages.to_a
+        end
+      rescue GdsApi::HTTPErrorResponse, GdsApi::TimedOutException
+        if ! retried
+          retried = true
+          sleep 1
+          retry
+        end
+        raise
+      end
+    end
+  end
+end