Bumping version

don’t append /* when using —exact-url

Dockerfile

@@ -1,15 +1,15 @@
-FROM ruby:3.4.3-alpine
+FROM ruby:3.4.4-alpine
 USER root
 WORKDIR /build
 
 COPY Gemfile /build/
 COPY *.gemspec /build/
 
-RUN gem update \
-    && bundle config set jobs $(nproc) \
+RUN bundle config set jobs "$(nproc)" \
+    && bundle config set without 'development test' \
     && bundle install
 
 COPY . /build
 
 WORKDIR /
-ENTRYPOINT [ "/build/bin/wayback_machine_downloader" ]
+ENTRYPOINT [ "/build/bin/wayback_machine_downloader" ]

lib/wayback_machine_downloader.rb

@@ -113,7 +113,7 @@ class WaybackMachineDownloader
 
   include ArchiveAPI
 
-  VERSION = "2.3.6"
+  VERSION = "2.3.9"
   DEFAULT_TIMEOUT = 30
   MAX_RETRIES = 3
   RETRY_DELAY = 2
@@ -131,7 +131,11 @@ class WaybackMachineDownloader
     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
@@ -154,22 +158,22 @@ class WaybackMachineDownloader
   end
 
   def backup_name
-    if @base_url.include? '//'
-      @base_url.split('/')[2]
+    url_to_process = @base_url.end_with?('/*') ? @base_url.chomp('/*') : @base_url
+    
+    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] == '/'
-        @directory
-      else
-        @directory + '/'
-      end
+      # because @directory is already an absolute path, we just ensure it exists
+      @directory
     else
-      'websites/' + backup_name + '/'
+      # ensure the default path is absolute and normalized
+      File.expand_path(File.join('websites', backup_name))
     end
   end
 
@@ -241,6 +245,7 @@ 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 "."
@@ -265,6 +270,7 @@ class WaybackMachineDownloader
             @connection_pool.with_connection do |connection|
               result = get_raw_list_from_api("#{@base_url}/*", page, connection)
             end
+            result ||= []
             [page, result]
           end
         end
@@ -284,7 +290,7 @@ 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
@@ -477,8 +483,8 @@ 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
-            if result_message && !result_message.downcase.include?('error') && !result_message.downcase.include?('failed') && !result_message.downcase.include?('skipping') && !result_message.downcase.include?('already exists')
+            # assume download success if the result message contains ' -> '
+            if result_message && result_message.include?(' -> ')
                download_success = true
             end
             @download_mutex.synchronize do
@@ -634,21 +640,35 @@ class WaybackMachineDownloader
     file_url = file_remote_info[:file_url].encode(current_encoding)
     file_id = file_remote_info[:file_id]
     file_timestamp = file_remote_info[:timestamp]
-    file_path_elements = file_id.split('/')
+    
+    # sanitize file_id to ensure it is a valid path component
+    raw_path_elements = file_id.split('/')
+
+    sanitized_path_elements = raw_path_elements.map do |element|
+      if Gem.win_platform?
+        # for Windows, we need to sanitize path components to avoid invalid characters
+        # this prevents issues with file names that contain characters not allowed in
+        # Windows file systems. See # https://docs.microsoft.com/en-us/windows/win32/fileio/naming-a-file#naming-conventions
+        element.gsub(/[:\*?"<>\|\&\=\/\\]/, ->(match) { '%' + match.ord.to_s(16).upcase })
+      else
+        element
+      end
+    end
+    
+    current_backup_path = backup_path
 
     if file_id == ""
-      dir_path = backup_path
-      file_path = backup_path + 'index.html'
-    elsif file_url[-1] == '/' or not file_path_elements[-1].include? '.'
-      dir_path = backup_path + file_path_elements[0..-1].join('/')
-      file_path = backup_path + file_path_elements[0..-1].join('/') + '/index.html'
+      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
-      dir_path = backup_path + file_path_elements[0..-2].join('/')
-      file_path = backup_path + file_path_elements[0..-1].join('/')
-    end
-    if Gem.win_platform?
-      dir_path = dir_path.gsub(/[:*?&=<>\\|]/) {|s| '%' + s.ord.to_s(16) }
-      file_path = file_path.gsub(/[:*?&=<>\\|]/) {|s| '%' + s.ord.to_s(16) }
+      # 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
@@ -659,11 +679,21 @@ class WaybackMachineDownloader
 
     begin
       structure_dir_path dir_path
-      download_with_retry(file_path, file_url, file_timestamp, http)
-      if @rewrite && File.extname(file_path) =~ /\.(html?|css|js)$/i
-        rewrite_urls_to_relative(file_path)
+      status = download_with_retry(file_path, file_url, file_timestamp, http)
+
+      case status
+      when :saved
+        if @rewrite && File.extname(file_path) =~ /\.(html?|css|js)$/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
-      "#{file_url} -> #{file_path} (#{@processed_file_count + 1}/#{@total_to_download})"
     rescue StandardError => e
       msg = "Failed: #{file_url} # #{e} (#{@processed_file_count + 1}/#{@total_to_download})"
       if File.exist?(file_path) and File.size(file_path) == 0
@@ -707,6 +737,9 @@ 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')
+
       request = Net::HTTP::Get.new(URI(wayback_url))
       request["Connection"] = "keep-alive"
       request["User-Agent"] = "WaybackMachineDownloader/#{VERSION}"
@@ -714,8 +747,7 @@ class WaybackMachineDownloader
 
       response = connection.request(request)
 
-      case response
-      when Net::HTTPSuccess
+      save_response_body = lambda do
         File.open(file_path, "wb") do |file|
           body = response.body
           if response['content-encoding'] == 'gzip' && body && !body.empty?
@@ -725,26 +757,48 @@ 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
-        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
-      else
-        raise "HTTP Error: #{response.code} #{response.message}"
+      end
+
+      if @all
+        case response
+        when Net::HTTPSuccess, Net::HTTPRedirection, Net::HTTPClientError, Net::HTTPServerError
+          save_response_body.call
+          if response.is_a?(Net::HTTPRedirection)
+            @logger.info("Saved redirect page for #{file_url} (status #{response.code}).")
+          elsif response.is_a?(Net::HTTPClientError) || response.is_a?(Net::HTTPServerError)
+            @logger.info("Saved error page for #{file_url} (status #{response.code}).")
+          end
+          return :saved
+        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)

wayback_machine_downloader.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |s|
   s.name        = "wayback_machine_downloader_straw"
-  s.version     = "2.3.6"
+  s.version     = "2.3.9"
   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.)"