Bumped version

Prevent fetching off non RFC3968-compliant URLs

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**:

bin/wayback_machine_downloader

@@ -74,6 +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

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 = "2.3.10"
+  VERSION = "2.3.11"
   DEFAULT_TIMEOUT = 30
   MAX_RETRIES = 3
   RETRY_DELAY = 2
@@ -123,6 +125,7 @@ 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, :rewrite
@@ -153,6 +156,11 @@ class WaybackMachineDownloader
     @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
@@ -196,7 +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
@@ -209,7 +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
@@ -513,6 +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
@@ -740,6 +758,12 @@ class WaybackMachineDownloader
       # 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}"

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

@@ -1,6 +1,6 @@
 Gem::Specification.new do |s|
   s.name        = "wayback_machine_downloader_straw"
-  s.version     = "2.3.10"
+  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.)"