Bumped version

Prevent fetching off non RFC3968-compliant URLs

Dockerfile

@@ -1,11 +1,15 @@
-FROM ruby:3.1.6-alpine
+FROM ruby:3.4.4-alpine
 USER root
 WORKDIR /build
-COPY . /build
 
-RUN gem update \
+COPY Gemfile /build/
-    && gem install concurrent-ruby \
+COPY *.gemspec /build/
+
+RUN bundle config set jobs "$(nproc)" \
+    && bundle config set without 'development test' \
     && bundle install
 
+COPY . /build
+
 WORKDIR /
 ENTRYPOINT [ "/build/bin/wayback_machine_downloader" ]

README.md

@@ -27,6 +27,7 @@ To run most commands, just like in the original WMD, you can use:
 ```bash
 wayback_machine_downloader https://example.com
 ```
+**Note**: this gem may conflict with hartator's wayback_machine_downloader gem, and so you may have to uninstall it for this WMD fork to work. A good way to know is if a command fails; it will list the gem version as 2.3.1 or earlier, while this WMD fork uses 2.3.2 or above.
 
 ### Step-by-step setup
 1. **Install Ruby**:
@@ -62,6 +63,12 @@ docker build -t wayback_machine_downloader .
 docker run -it --rm wayback_machine_downloader [options] URL
 ```
 
+or the example without cloning the repo - fetching smallrockets.com until the year 2013:
+
+```bash
+docker run -v .:/websites ghcr.io/strawberrymaster/wayback-machine-downloader:master wayback_machine_downloader --to 20130101 smallrockets.com
+```
+
 ### 🐳 Using Docker Compose
 
 We can also use it with Docker Compose, which provides a lot of benefits for extending more functionalities (such as implementing storing previous downloads in a database):
@@ -74,21 +81,49 @@ services:
     tty: true
     image: wayback_machine_downloader:latest
     container_name: wayback_machine_downloader
+    environment:
+      - ENVIRONMENT=${ENVIRONMENT:-development}
+      - OPTIONS=${OPTIONS:-""}
+      - TARGET_URL=${TARGET_URL}
     volumes:
       - .:/build:rw
       - ./websites:/build/websites:rw
+    command: --directory /build/websites ${OPTIONS} ${TARGET_URL}
+```
+#### Usage:
+Now You can create a Docker image as named "wayback_machine_downloader" with the following command:
+```bash
+docker compose up -d --build
+```
+
+After that you must set TARGET_URL environment variable:
+```bash
+export TARGET_URL="https://example.com/"
+```
+
+The **OPTIONS** env. variable is optional this may include additional settings which are found in the "**Advanced usage**" section below.
+
+Example:
+```bash
+export OPTIONS="--list -f 20060121"
+```
+
+After that you can run the exists container with the following command:
+```bash
+docker compose run --rm wayback_machine_downloader https://example.com
 ```
 
 ## ⚙️ Configuration
 There are a few constants that can be edited in the `wayback_machine_downloader.rb` file for your convenience. The default values may be conservative, so you can adjust them to your needs. They are:
-
 ```ruby
 DEFAULT_TIMEOUT = 30        # HTTP timeout (in seconds)
-MAX_RETRIES = 3             # Failed request retries
+MAX_RETRIES = 3             # Number of times to retry failed requests
-RETRY_DELAY = 2             # Wait between retries
+RETRY_DELAY = 2             # Wait time between retries (seconds)
-RATE_LIMIT = 0.25           # Throttle between requests
+RATE_LIMIT = 0.25           # Throttle between requests (seconds)
-CONNECTION_POOL_SIZE = 10   # No. of simultaneous connections
+CONNECTION_POOL_SIZE = 10   # Maximum simultaneous connections
-MEMORY_BUFFER_SIZE = 16384  # Size of download buffer
+MEMORY_BUFFER_SIZE = 16384  # Download buffer size (bytes)
+STATE_CDX_FILENAME = '.cdx.json'       # Stores snapshot listing
+STATE_DB_FILENAME = '.downloaded.txt'  # Tracks completed downloads
 ```
 
 ## 🛠️ Advanced usage

bin/wayback_machine_downloader

@@ -62,6 +62,10 @@ option_parser = OptionParser.new do |opts|
     options[:rewritten] = true
   end
 
+  opts.on("--local", "Rewrite URLs to make them relative for local browsing") do |t|
+    options[:rewrite] = true
+  end
+
   opts.on("--reset", "Delete state files (.cdx.json, .downloaded.txt) and restart the download from scratch") do |t|
     options[:reset] = true
   end
@@ -70,6 +74,14 @@ option_parser = OptionParser.new do |opts|
     options[:keep] = true
   end
 
+  opts.on("--recursive-subdomains", "Recursively download content from subdomains") do |t|
+    options[:recursive_subdomains] = true
+  end
+
+  opts.on("--subdomain-depth DEPTH", Integer, "Maximum depth for subdomain recursion (default: 1)") do |t|
+    options[:subdomain_depth] = t
+  end
+
   opts.on("-v", "--version", "Display version") do |t|
     options[:version] = t
   end

docker-compose.yml

@@ -6,8 +6,10 @@ services:
     image: wayback_machine_downloader:latest
     container_name: wayback_machine_downloader
     environment:
-      - ENVIRONMENT=${ENVIRONMENT}
+      - ENVIRONMENT=${DEVELOPMENT:-production}
+      - OPTIONS=${OPTIONS:-""}
+      - TARGET_URL=${TARGET_URL}
     volumes:
       - .:/build:rw
-      - ./websites:/build/websites:rw
+      - ./websites:/websites:rw
-    command: --directory /build/websites ${OPTIONS} ${TARGET_URL}
+    command: /build/bin/wayback_machine_downloader ${TARGET_URL} ${OPTIONS}

lib/wayback_machine_downloader.rb

@@ -14,6 +14,7 @@ require 'stringio'
 require_relative 'wayback_machine_downloader/tidy_bytes'
 require_relative 'wayback_machine_downloader/to_regex'
 require_relative 'wayback_machine_downloader/archive_api'
+require_relative 'wayback_machine_downloader/subdom_processor'
 
 class ConnectionPool
   MAX_AGE = 300
@@ -112,8 +113,9 @@ end
 class WaybackMachineDownloader
 
   include ArchiveAPI
+  include SubdomainProcessor
 
-  VERSION = "2.3.4"
+  VERSION = "2.3.11"
   DEFAULT_TIMEOUT = 30
   MAX_RETRIES = 3
   RETRY_DELAY = 2
@@ -123,15 +125,20 @@ class WaybackMachineDownloader
   STATE_CDX_FILENAME = ".cdx.json"
   STATE_DB_FILENAME = ".downloaded.txt"
 
+
   attr_accessor :base_url, :exact_url, :directory, :all_timestamps,
     :from_timestamp, :to_timestamp, :only_filter, :exclude_filter,
-    :all, :maximum_pages, :threads_count, :logger, :reset, :keep
+    :all, :maximum_pages, :threads_count, :logger, :reset, :keep, :rewrite
 
   def initialize params
     validate_params(params)
     @base_url = params[:base_url]
     @exact_url = params[:exact_url]
-    @directory = params[:directory]
+    if params[:directory]
+      @directory = File.expand_path(params[:directory])
+    else
+      @directory = nil
+    end
     @all_timestamps = params[:all_timestamps]
     @from_timestamp = params[:from_timestamp].to_i
     @to_timestamp = params[:to_timestamp].to_i
@@ -148,27 +155,33 @@ class WaybackMachineDownloader
     @failed_downloads = Concurrent::Array.new
     @connection_pool = ConnectionPool.new(CONNECTION_POOL_SIZE)
     @db_mutex = Mutex.new
+    @rewrite = params[:rewrite] || false
+    @recursive_subdomains = params[:recursive_subdomains] || false
+    @subdomain_depth = params[:subdomain_depth] || 1
+
+    # URL for rejecting invalid/unencoded wayback urls
+    @url_regexp = /^(([A-Za-z][A-Za-z0-9+.-]*):((\/\/(((([A-Za-z0-9._~-])|(%[ABCDEFabcdef0-9][ABCDEFabcdef0-9])|([!$&'('')'*+,;=]))+)(:([0-9]*))?)(((\/((([A-Za-z0-9._~-])|(%[ABCDEFabcdef0-9][ABCDEFabcdef0-9])|([!$&'('')'*+,;=])|:|@)*))*)))|((\/(((([A-Za-z0-9._~-])|(%[ABCDEFabcdef0-9][ABCDEFabcdef0-9])|([!$&'('')'*+,;=])|:|@)+)(\/((([A-Za-z0-9._~-])|(%[ABCDEFabcdef0-9][ABCDEFabcdef0-9])|([!$&'('')'*+,;=])|:|@)*))*)?))|((((([A-Za-z0-9._~-])|(%[ABCDEFabcdef0-9][ABCDEFabcdef0-9])|([!$&'('')'*+,;=])|:|@)+)(\/((([A-Za-z0-9._~-])|(%[ABCDEFabcdef0-9][ABCDEFabcdef0-9])|([!$&'('')'*+,;=])|:|@)*))*)))(\?((([A-Za-z0-9._~-])|(%[ABCDEFabcdef0-9][ABCDEFabcdef0-9])|([!$&'('')'*+,;=])|:|@)|\/|\?)*)?(\#((([A-Za-z0-9._~-])|(%[ABCDEFabcdef0-9][ABCDEFabcdef0-9])|([!$&'('')'*+,;=])|:|@)|\/|\?)*)?)$/
 
     handle_reset
   end
 
   def backup_name
-    if @base_url.include? '//'
+    url_to_process = @base_url.end_with?('/*') ? @base_url.chomp('/*') : @base_url
-      @base_url.split('/')[2]
+    
+    if url_to_process.include? '//'
+      url_to_process.split('/')[2]
     else
-      @base_url
+      url_to_process
     end
   end
 
   def backup_path
     if @directory
-      if @directory[-1] == '/'
+      # because @directory is already an absolute path, we just ensure it exists
-        @directory
+      @directory
-      else
-        @directory + '/'
-      end
     else
-      'websites/' + backup_name + '/'
+      # ensure the default path is absolute and normalized
+      File.expand_path(File.join('websites', backup_name))
     end
   end
 
@@ -191,7 +204,7 @@ class WaybackMachineDownloader
 
   def match_only_filter file_url
     if @only_filter
-      only_filter_regex = @only_filter.to_regex
+      only_filter_regex = @only_filter.to_regex(detect: true)
       if only_filter_regex
         only_filter_regex =~ file_url
       else
@@ -204,7 +217,7 @@ class WaybackMachineDownloader
 
   def match_exclude_filter file_url
     if @exclude_filter
-      exclude_filter_regex = @exclude_filter.to_regex
+      exclude_filter_regex = @exclude_filter.to_regex(detect: true)
       if exclude_filter_regex
         exclude_filter_regex =~ file_url
       else
@@ -240,6 +253,7 @@ class WaybackMachineDownloader
     # Fetch the initial set of snapshots, sequentially
     @connection_pool.with_connection do |connection|
       initial_list = get_raw_list_from_api(@base_url, nil, connection)
+      initial_list ||= []
       mutex.synchronize do
         snapshot_list_to_consider.concat(initial_list)
         print "."
@@ -264,6 +278,7 @@ class WaybackMachineDownloader
             @connection_pool.with_connection do |connection|
               result = get_raw_list_from_api("#{@base_url}/*", page, connection)
             end
+            result ||= []
             [page, result]
           end
         end
@@ -283,7 +298,7 @@ class WaybackMachineDownloader
 
         # Process results and check for empty pages
         results.each do |page, result|
-          if result.empty?
+          if result.nil? || result.empty?
             continue_fetching = false
             break
           else
@@ -377,7 +392,7 @@ class WaybackMachineDownloader
       end
     else
       file_list_curated = get_file_list_curated
-      file_list_curated = file_list_curated.sort_by { |k,v| v[:timestamp] }.reverse
+      file_list_curated = file_list_curated.sort_by { |_,v| v[:timestamp].to_s }.reverse
       file_list_curated.map do |file_remote_info|
         file_remote_info[1][:file_id] = file_remote_info[0]
         file_remote_info[1]
@@ -476,8 +491,8 @@ class WaybackMachineDownloader
         begin
           @connection_pool.with_connection do |connection|
             result_message = download_file(file_remote_info, connection)
-            # for now, assume success if no exception and message doesn't indicate error/skip
+            # assume download success if the result message contains ' -> '
-            if result_message && !result_message.downcase.include?('error') && !result_message.downcase.include?('failed') && !result_message.downcase.include?('skipping') && !result_message.downcase.include?('already exists')
+            if result_message && result_message.include?(' -> ')
                download_success = true
             end
             @download_mutex.synchronize do
@@ -506,6 +521,16 @@ class WaybackMachineDownloader
 
     end_time = Time.now
     puts "\nDownload finished in #{(end_time - start_time).round(2)}s."
+
+    # process subdomains if enabled
+    if @recursive_subdomains
+      subdomain_start_time = Time.now
+      process_subdomains
+      subdomain_end_time = Time.now
+      subdomain_time = (subdomain_end_time - subdomain_start_time).round(2)
+      puts "Subdomain processing finished in #{subdomain_time}s."
+    end
+
     puts "Results saved in #{backup_path}"
     cleanup
   end
@@ -533,27 +558,135 @@ class WaybackMachineDownloader
     end
   end
 
+  def rewrite_urls_to_relative(file_path)
+    return unless File.exist?(file_path)
+    
+    file_ext = File.extname(file_path).downcase
+    
+    begin
+      content = File.binread(file_path)
+
+      if file_ext == '.html' || file_ext == '.htm'
+        encoding = content.match(/<meta\s+charset=["']?([^"'>]+)/i)&.captures&.first || 'UTF-8'
+        content.force_encoding(encoding) rescue content.force_encoding('UTF-8')
+      else
+        content.force_encoding('UTF-8')
+      end
+
+      # URLs in HTML attributes
+      content.gsub!(/(\s(?:href|src|action|data-src|data-url)=["'])https?:\/\/web\.archive\.org\/web\/[0-9]+(?:id_)?\/([^"']+)(["'])/i) do
+        prefix, url, suffix = $1, $2, $3
+        
+        if url.start_with?('http')
+          begin
+            uri = URI.parse(url)
+            path = uri.path
+            path = path[1..-1] if path.start_with?('/')
+            "#{prefix}#{path}#{suffix}"
+          rescue
+            "#{prefix}#{url}#{suffix}"
+          end
+        elsif url.start_with?('/')
+          "#{prefix}./#{url[1..-1]}#{suffix}"
+        else
+          "#{prefix}#{url}#{suffix}"
+        end
+      end
+      
+      # URLs in CSS
+      content.gsub!(/url\(\s*["']?https?:\/\/web\.archive\.org\/web\/[0-9]+(?:id_)?\/([^"'\)]+)["']?\s*\)/i) do
+        url = $1
+        
+        if url.start_with?('http')
+          begin
+            uri = URI.parse(url)
+            path = uri.path
+            path = path[1..-1] if path.start_with?('/')
+            "url(\"#{path}\")"
+          rescue
+            "url(\"#{url}\")"
+          end
+        elsif url.start_with?('/')
+          "url(\"./#{url[1..-1]}\")"
+        else
+          "url(\"#{url}\")"
+        end
+      end
+      
+      # URLs in JavaScript
+      content.gsub!(/(["'])https?:\/\/web\.archive\.org\/web\/[0-9]+(?:id_)?\/([^"']+)(["'])/i) do
+        quote_start, url, quote_end = $1, $2, $3
+        
+        if url.start_with?('http')
+          begin
+            uri = URI.parse(url)
+            path = uri.path
+            path = path[1..-1] if path.start_with?('/')
+            "#{quote_start}#{path}#{quote_end}"
+          rescue
+            "#{quote_start}#{url}#{quote_end}"
+          end
+        elsif url.start_with?('/')
+          "#{quote_start}./#{url[1..-1]}#{quote_end}"
+        else
+          "#{quote_start}#{url}#{quote_end}"
+        end
+      end
+      
+      # for URLs in HTML attributes that start with a single slash
+      content.gsub!(/(\s(?:href|src|action|data-src|data-url)=["'])\/([^"'\/][^"']*)(["'])/i) do
+        prefix, path, suffix = $1, $2, $3
+        "#{prefix}./#{path}#{suffix}"
+      end
+      
+      # for URLs in CSS that start with a single slash
+      content.gsub!(/url\(\s*["']?\/([^"'\)\/][^"'\)]*?)["']?\s*\)/i) do
+        path = $1
+        "url(\"./#{path}\")"
+      end
+
+      # save the modified content back to the file
+      File.binwrite(file_path, content)
+      puts "Rewrote URLs in #{file_path} to be relative."
+    rescue Errno::ENOENT => e
+      @logger.warn("Error reading file #{file_path}: #{e.message}")
+    end
+  end
+
   def download_file (file_remote_info, http)
     current_encoding = "".encoding
     file_url = file_remote_info[:file_url].encode(current_encoding)
     file_id = file_remote_info[:file_id]
     file_timestamp = file_remote_info[:timestamp]
-    original_file_id = @all_timestamps ? file_id.split('/', 2)[1] : file_id
-    file_path_elements = original_file_id.split('/')
     
-    if original_file_id == ""
+    # sanitize file_id to ensure it is a valid path component
-      dir_path = backup_path
+    raw_path_elements = file_id.split('/')
-      file_path = backup_path + 'index.html'
+
-    elsif file_url[-1] == '/' or not file_path_elements[-1].include? '.'
+    sanitized_path_elements = raw_path_elements.map do |element|
-      dir_path = backup_path + file_path_elements[0..-1].join('/')
+      if Gem.win_platform?
-      file_path = backup_path + file_path_elements[0..-1].join('/') + '/index.html'
+        # for Windows, we need to sanitize path components to avoid invalid characters
-    else
+        # this prevents issues with file names that contain characters not allowed in
-      dir_path = backup_path + file_path_elements[0..-2].join('/')
+        # Windows file systems. See # https://docs.microsoft.com/en-us/windows/win32/fileio/naming-a-file#naming-conventions
-      file_path = backup_path + file_path_elements[0..-1].join('/')
+        element.gsub(/[:\*?"<>\|\&\=\/\\]/) { |match| '%' + match.ord.to_s(16).upcase }
+      else
+        element
+      end
     end
-    if Gem.win_platform?
+    
-      dir_path = dir_path.gsub(/[:*?&=<>\\|]/) {|s| '%' + s.ord.to_s(16) }
+    current_backup_path = backup_path
-      file_path = file_path.gsub(/[:*?&=<>\\|]/) {|s| '%' + s.ord.to_s(16) }
+
+    if file_id == ""
+      dir_path = current_backup_path
+      file_path = File.join(dir_path, 'index.html')
+    elsif file_url[-1] == '/' || (sanitized_path_elements.last && !sanitized_path_elements.last.include?('.'))
+      # if file_id is a directory, we treat it as such
+      dir_path = File.join(current_backup_path, *sanitized_path_elements)
+      file_path = File.join(dir_path, 'index.html')
+    else
+      # if file_id is a file, we treat it as such
+      filename = sanitized_path_elements.pop
+      dir_path = File.join(current_backup_path, *sanitized_path_elements)
+      file_path = File.join(dir_path, filename)
     end
 
     # check existence *before* download attempt
@@ -564,11 +697,24 @@ class WaybackMachineDownloader
 
     begin
       structure_dir_path dir_path
-      download_with_retry(file_path, file_url, file_timestamp, http)
+      status = download_with_retry(file_path, file_url, file_timestamp, http)
-      "#{file_url} -> #{file_path} (#{@processed_file_count + 1}/#{@total_to_download})"
+
+      case status
+      when :saved
+        if @rewrite && File.extname(file_path) =~ /\.(html?|css|js)$/i
+          rewrite_urls_to_relative(file_path)
+        end
+        "#{file_url} -> #{file_path} (#{@processed_file_count + 1}/#{@total_to_download})"
+      when :skipped_not_found
+        "Skipped (not found): #{file_url} (#{@processed_file_count + 1}/#{@total_to_download})"
+      else
+        # ideally, this case should not be reached if download_with_retry behaves as expected.
+        @logger.warn("Unknown status from download_with_retry for #{file_url}: #{status}")
+        "Unknown status for #{file_url}: #{status} (#{@processed_file_count + 1}/#{@total_to_download})"
+      end
     rescue StandardError => e
       msg = "Failed: #{file_url} # #{e} (#{@processed_file_count + 1}/#{@total_to_download})"
-      if not @all and File.exist?(file_path) and File.size(file_path) == 0
+      if File.exist?(file_path) and File.size(file_path) == 0
         File.delete(file_path)
         msg += "\n#{file_path} was empty and was removed."
       end
@@ -609,6 +755,15 @@ class WaybackMachineDownloader
         "https://web.archive.org/web/#{file_timestamp}id_/#{file_url}"
       end
 
+      # Escape square brackets because they are not valid in URI()
+      wayback_url = wayback_url.gsub('[', '%5B').gsub(']', '%5D')
+
+      # reject invalid/unencoded wayback_url, behaving as if the resource weren't found
+      if not @url_regexp.match?(wayback_url)
+          @logger.warn("Skipped #{file_url}: invalid URL")
+          return :skipped_not_found
+      end
+
       request = Net::HTTP::Get.new(URI(wayback_url))
       request["Connection"] = "keep-alive"
       request["User-Agent"] = "WaybackMachineDownloader/#{VERSION}"
@@ -616,8 +771,7 @@ class WaybackMachineDownloader
 
       response = connection.request(request)
 
-      case response
+      save_response_body = lambda do
-      when Net::HTTPSuccess
         File.open(file_path, "wb") do |file|
           body = response.body
           if response['content-encoding'] == 'gzip' && body && !body.empty?
@@ -627,26 +781,48 @@ class WaybackMachineDownloader
               gz.close
               file.write(decompressed_body)
             rescue Zlib::GzipFile::Error => e
-              @logger.warn("Failure decompressing gzip file #{file_url}: #{e.message}")
+              @logger.warn("Failure decompressing gzip file #{file_url}: #{e.message}. Writing raw body.")
               file.write(body)
             end
           else
             file.write(body) if body
           end
         end
-      when Net::HTTPRedirection
+      end
-        raise "Too many redirects for #{file_url}" if redirect_count >= 2
+
-        location = response['location']
+      if @all
-        @logger.warn("Redirect found for #{file_url} -> #{location}")
+        case response
-        return download_with_retry(file_path, location, file_timestamp, connection, redirect_count + 1)
+        when Net::HTTPSuccess, Net::HTTPRedirection, Net::HTTPClientError, Net::HTTPServerError
-      when Net::HTTPTooManyRequests
+          save_response_body.call
-        sleep(RATE_LIMIT * 2)
+          if response.is_a?(Net::HTTPRedirection)
-        raise "Rate limited, retrying..."
+            @logger.info("Saved redirect page for #{file_url} (status #{response.code}).")
-      when Net::HTTPNotFound
+          elsif response.is_a?(Net::HTTPClientError) || response.is_a?(Net::HTTPServerError)
-        @logger.warn("File not found, skipping: #{file_url}")
+            @logger.info("Saved error page for #{file_url} (status #{response.code}).")
-        return
+          end
-      else
+          return :saved
-        raise "HTTP Error: #{response.code} #{response.message}"
+        else
+          # for any other response type when --all is true, treat as an error to be retried or failed
+          raise "Unhandled HTTP response: #{response.code} #{response.message}"
+        end
+      else # not @all (our default behavior)
+        case response
+        when Net::HTTPSuccess
+          save_response_body.call
+          return :saved
+        when Net::HTTPRedirection
+          raise "Too many redirects for #{file_url}" if redirect_count >= 2
+          location = response['location']
+          @logger.warn("Redirect found for #{file_url} -> #{location}")
+          return download_with_retry(file_path, location, file_timestamp, connection, redirect_count + 1)
+        when Net::HTTPTooManyRequests
+          sleep(RATE_LIMIT * 2)
+          raise "Rate limited, retrying..."
+        when Net::HTTPNotFound
+          @logger.warn("File not found, skipping: #{file_url}")
+          return :skipped_not_found
+        else
+          raise "HTTP Error: #{response.code} #{response.message}"
+        end
       end
 
     rescue StandardError => e

lib/wayback_machine_downloader/archive_api.rb

@@ -4,6 +4,14 @@ require 'uri'
 module ArchiveAPI
 
   def get_raw_list_from_api(url, page_index, http)
+    # Automatically append /* if the URL doesn't contain a path after the domain
+    # This is a workaround for an issue with the API and *some* domains.
+    # See https://github.com/StrawberryMaster/wayback-machine-downloader/issues/6
+    # But don't do this when exact_url flag is set
+    if url && !url.match(/^https?:\/\/.*\//i) && !@exact_url
+      url = "#{url}/*"
+    end
+
     request_url = URI("https://web.archive.org/cdx/search/cdx")
     params = [["output", "json"], ["url", url]] + parameters_for_api(page_index)
     request_url.query = URI.encode_www_form(params)

lib/wayback_machine_downloader/subdom_processor.rb

@@ -0,0 +1,238 @@
+# frozen_string_literal: true
+
+module SubdomainProcessor
+  def process_subdomains
+    return unless @recursive_subdomains
+    
+    puts "Starting subdomain processing..."
+    
+    # extract base domain from the URL for comparison
+    base_domain = extract_base_domain(@base_url)
+    @processed_domains = Set.new([base_domain])
+    @subdomain_queue = Queue.new
+    
+    # scan downloaded files for subdomain links
+    initial_files = Dir.glob(File.join(backup_path, "**/*.{html,htm,css,js}"))
+    puts "Scanning #{initial_files.size} downloaded files for subdomain links..."
+    
+    subdomains_found = scan_files_for_subdomains(initial_files, base_domain)
+    
+    if subdomains_found.empty?
+      puts "No subdomains found in downloaded content."
+      return
+    end
+    
+    puts "Found #{subdomains_found.size} subdomains to process: #{subdomains_found.join(', ')}"
+    
+    # add found subdomains to the queue
+    subdomains_found.each do |subdomain|
+      full_domain = "#{subdomain}.#{base_domain}"
+      @subdomain_queue << "https://#{full_domain}/"
+    end
+    
+    # process the subdomain queue
+    download_subdomains(base_domain)
+    
+    # after all downloads, rewrite all URLs to make local references
+    rewrite_subdomain_links(base_domain) if @rewrite
+  end
+  
+  private
+  
+  def extract_base_domain(url)
+    uri = URI.parse(url.gsub(/^https?:\/\//, '').split('/').first) rescue nil
+    return nil unless uri
+    
+    host = uri.host || uri.path.split('/').first
+    host = host.downcase
+    
+    # extract the base domain (e.g., "example.com" from "sub.example.com")
+    parts = host.split('.')
+    return host if parts.size <= 2
+    
+    # for domains like co.uk, we want to keep the last 3 parts
+    if parts[-2].length <= 3 && parts[-1].length <= 3 && parts.size > 2
+      parts.last(3).join('.')
+    else
+      parts.last(2).join('.')
+    end
+  end
+  
+  def scan_files_for_subdomains(files, base_domain)
+    return [] unless base_domain
+    
+    subdomains = Set.new
+    
+    files.each do |file_path|
+      next unless File.exist?(file_path)
+      
+      begin
+        content = File.read(file_path)
+        
+        # extract URLs from HTML href/src attributes
+        content.scan(/(?:href|src|action|data-src)=["']https?:\/\/([^\/."']+)\.#{Regexp.escape(base_domain)}[\/"]/) do |match|
+          subdomain = match[0].downcase
+          next if subdomain == 'www' # skip www subdomain
+          subdomains.add(subdomain)
+        end
+        
+        # extract URLs from CSS
+        content.scan(/url\(["']?https?:\/\/([^\/."']+)\.#{Regexp.escape(base_domain)}[\/"]/) do |match|
+          subdomain = match[0].downcase
+          next if subdomain == 'www' # skip www subdomain
+          subdomains.add(subdomain)
+        end
+        
+        # extract URLs from JavaScript strings
+        content.scan(/["']https?:\/\/([^\/."']+)\.#{Regexp.escape(base_domain)}[\/"]/) do |match|
+          subdomain = match[0].downcase
+          next if subdomain == 'www' # skip www subdomain
+          subdomains.add(subdomain)
+        end
+      rescue => e
+        puts "Error scanning file #{file_path}: #{e.message}"
+      end
+    end
+    
+    subdomains.to_a
+  end
+  
+  def download_subdomains(base_domain)
+    puts "Starting subdomain downloads..."
+    depth = 0
+    max_depth = @subdomain_depth || 1
+    
+    while depth < max_depth && !@subdomain_queue.empty?
+      current_batch = []
+      
+      # get all subdomains at current depth
+      while !@subdomain_queue.empty?
+        current_batch << @subdomain_queue.pop
+      end
+      
+      puts "Processing #{current_batch.size} subdomains at depth #{depth + 1}..."
+      
+      # download each subdomain
+      current_batch.each do |subdomain_url|
+        download_subdomain(subdomain_url, base_domain)
+      end
+      
+      # if we need to go deeper, scan the newly downloaded files
+      if depth + 1 < max_depth
+        # get all files in the subdomains directory
+        new_files = Dir.glob(File.join(backup_path, "subdomains", "**/*.{html,htm,css,js}"))
+        new_subdomains = scan_files_for_subdomains(new_files, base_domain)
+        
+        # filter out already processed subdomains
+        new_subdomains.each do |subdomain|
+          full_domain = "#{subdomain}.#{base_domain}"
+          unless @processed_domains.include?(full_domain)
+            @processed_domains.add(full_domain)
+            @subdomain_queue << "https://#{full_domain}/"
+          end
+        end
+        
+        puts "Found #{@subdomain_queue.size} new subdomains at depth #{depth + 1}" if !@subdomain_queue.empty?
+      end
+      
+      depth += 1
+    end
+  end
+  
+  def download_subdomain(subdomain_url, base_domain)
+    begin
+      uri = URI.parse(subdomain_url)
+      subdomain_host = uri.host
+      
+      # skip if already processed
+      if @processed_domains.include?(subdomain_host)
+        puts "Skipping already processed subdomain: #{subdomain_host}"
+        return
+      end
+      
+      @processed_domains.add(subdomain_host)
+      puts "Downloading subdomain: #{subdomain_url}"
+      
+      # create the directory for this subdomain
+      subdomain_dir = File.join(backup_path, "subdomains", subdomain_host)
+      FileUtils.mkdir_p(subdomain_dir)
+      
+      # create subdomain downloader with appropriate options
+      subdomain_options = {
+        base_url: subdomain_url,
+        directory: subdomain_dir,
+        from_timestamp: @from_timestamp,
+        to_timestamp: @to_timestamp,
+        all: @all,
+        threads_count: @threads_count,
+        maximum_pages: [@maximum_pages / 2, 10].max,
+        rewrite: @rewrite,
+        # don't recursively process subdomains from here
+        recursive_subdomains: false
+      }
+      
+      # download the subdomain content
+      subdomain_downloader = WaybackMachineDownloader.new(subdomain_options)
+      subdomain_downloader.download_files
+      
+      puts "Completed download of subdomain: #{subdomain_host}"
+    rescue => e
+      puts "Error downloading subdomain #{subdomain_url}: #{e.message}"
+    end
+  end
+  
+  def rewrite_subdomain_links(base_domain)
+    puts "Rewriting all files to use local subdomain references..."
+    
+    all_files = Dir.glob(File.join(backup_path, "**/*.{html,htm,css,js}"))
+    subdomains = @processed_domains.reject { |domain| domain == base_domain }
+    
+    puts "Found #{all_files.size} files to check for rewriting"
+    puts "Will rewrite links for subdomains: #{subdomains.join(', ')}"
+    
+    rewritten_count = 0
+    
+    all_files.each do |file_path|
+      next unless File.exist?(file_path)
+      
+      begin
+        content = File.read(file_path)
+        original_content = content.dup
+        
+        # replace subdomain URLs with local paths
+        subdomains.each do |subdomain_host|
+          # for HTML attributes (href, src, etc.)
+          content.gsub!(/(\s(?:href|src|action|data-src|data-url)=["'])https?:\/\/#{Regexp.escape(subdomain_host)}([^"']*)(["'])/i) do
+            prefix, path, suffix = $1, $2, $3
+            path = "/index.html" if path.empty? || path == "/"
+            "#{prefix}../subdomains/#{subdomain_host}#{path}#{suffix}"
+          end
+          
+          # for CSS url()
+          content.gsub!(/url\(\s*["']?https?:\/\/#{Regexp.escape(subdomain_host)}([^"'\)]*?)["']?\s*\)/i) do
+            path = $1
+            path = "/index.html" if path.empty? || path == "/"
+            "url(\"../subdomains/#{subdomain_host}#{path}\")"
+          end
+          
+          # for JavaScript strings
+          content.gsub!(/(["'])https?:\/\/#{Regexp.escape(subdomain_host)}([^"']*)(["'])/i) do
+            quote_start, path, quote_end = $1, $2, $3
+            path = "/index.html" if path.empty? || path == "/"
+            "#{quote_start}../subdomains/#{subdomain_host}#{path}#{quote_end}"
+          end
+        end
+        
+        # save if modified
+        if content != original_content
+          File.write(file_path, content)
+          rewritten_count += 1
+        end
+      rescue => e
+        puts "Error rewriting file #{file_path}: #{e.message}"
+      end
+    end
+    
+    puts "Rewrote links in #{rewritten_count} files"
+  end
+end

wayback_machine_downloader.gemspec

@@ -1,8 +1,6 @@
-require './lib/wayback_machine_downloader'
-
 Gem::Specification.new do |s|
   s.name        = "wayback_machine_downloader_straw"
-  s.version     = WaybackMachineDownloader::VERSION
+  s.version     = "2.3.11"
   s.executables << "wayback_machine_downloader"
   s.summary     = "Download an entire website from the Wayback Machine."
   s.description = "Download complete websites from the Internet Archive's Wayback Machine. While the Wayback Machine (archive.org) excellently preserves web history, it lacks a built-in export functionality; this gem does just that, allowing you to download entire archived websites. (This is a significant rewrite of the original wayback_machine_downloader gem by hartator, with enhanced features and performance improvements.)"
@@ -11,7 +9,7 @@ Gem::Specification.new do |s|
   s.files       = ["lib/wayback_machine_downloader.rb", "lib/wayback_machine_downloader/tidy_bytes.rb", "lib/wayback_machine_downloader/to_regex.rb", "lib/wayback_machine_downloader/archive_api.rb"]
   s.homepage    = "https://github.com/StrawberryMaster/wayback-machine-downloader"
   s.license     = "MIT"
-  s.required_ruby_version = ">= 1.9.2"
+  s.required_ruby_version = ">= 3.4.3"
   s.add_runtime_dependency "concurrent-ruby", "~> 1.3", ">= 1.3.4"
   s.add_development_dependency "rake", "~> 12.2"
   s.add_development_dependency "minitest", "~> 5.2"