Bump versions

I honestly don't recall if this was implemented in the original code, and I'm guessing this worked at *some point* during this fork. It seems to work correctly now, however. See #6 and #11

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 \
+RUN bundle config set jobs "$(nproc)" \
-    && 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 = "2.3.7"
   DEFAULT_TIMEOUT = 30
   MAX_RETRIES = 3
   RETRY_DELAY = 2
@@ -477,8 +477,8 @@ 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
@@ -659,11 +659,21 @@ 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)
-      if @rewrite && File.extname(file_path) =~ /\.(html?|css|js)$/i
+
-        rewrite_urls_to_relative(file_path)
+      case status
+      when :saved
+        if @rewrite && File.extname(file_path) =~ /\.(html?|css|js)$/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
@@ -714,8 +724,7 @@ 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?
@@ -725,26 +734,48 @@ 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

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     = "2.3.7"
   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.)"