Bump version

Fix bug with archive urls containing square brackets

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 \
-    && gem install concurrent-ruby \
+COPY Gemfile /build/
+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" ]
+ENTRYPOINT [ "/build/bin/wayback_machine_downloader" ]

README.md

@@ -62,6 +62,12 @@ 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 +80,49 @@ 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
-RETRY_DELAY = 2             # Wait between retries
-RATE_LIMIT = 0.25           # Throttle between requests
-CONNECTION_POOL_SIZE = 10   # No. of simultaneous connections
-MEMORY_BUFFER_SIZE = 16384  # Size of download buffer
+MAX_RETRIES = 3             # Number of times to retry failed requests
+RETRY_DELAY = 2             # Wait time between retries (seconds)
+RATE_LIMIT = 0.25           # Throttle between requests (seconds)
+CONNECTION_POOL_SIZE = 10   # Maximum simultaneous connections
+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

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
-    command: --directory /build/websites ${OPTIONS} ${TARGET_URL}
+      - ./websites:/websites:rw
+    command: /build/bin/wayback_machine_downloader ${TARGET_URL} ${OPTIONS}

lib/wayback_machine_downloader.rb

@@ -113,7 +113,7 @@ class WaybackMachineDownloader
 
   include ArchiveAPI
 
-  VERSION = "2.3.4"
+  VERSION = "2.3.8"
   DEFAULT_TIMEOUT = 30
   MAX_RETRIES = 3
   RETRY_DELAY = 2
@@ -125,7 +125,7 @@ class WaybackMachineDownloader
 
   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)
@@ -148,15 +148,18 @@ class WaybackMachineDownloader
     @failed_downloads = Concurrent::Array.new
     @connection_pool = ConnectionPool.new(CONNECTION_POOL_SIZE)
     @db_mutex = Mutex.new
+    @rewrite = params[:rewrite] || false
 
     handle_reset
   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
 
@@ -240,6 +243,7 @@ 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 +268,7 @@ 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 +288,7 @@ 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
@@ -476,8 +481,8 @@ 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
@@ -533,15 +538,109 @@ 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('/')
+    file_path_elements = file_id.split('/')
 
-    if original_file_id == ""
+    if file_id == ""
       dir_path = backup_path
       file_path = backup_path + 'index.html'
     elsif file_url[-1] == '/' or not file_path_elements[-1].include? '.'
@@ -564,11 +663,24 @@ class WaybackMachineDownloader
 
     begin
       structure_dir_path dir_path
-      download_with_retry(file_path, file_url, file_timestamp, http)
-      "#{file_url} -> #{file_path} (#{@processed_file_count + 1}/#{@total_to_download})"
+      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
     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 +721,9 @@ 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}"
@@ -616,8 +731,7 @@ 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?
@@ -627,26 +741,48 @@ 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 +4,13 @@ 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
+    if url && !url.match(/^https?:\/\/.*\//i)
+      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

@@ -1,8 +1,6 @@
-require './lib/wayback_machine_downloader'
-
 Gem::Specification.new do |s|
   s.name        = "wayback_machine_downloader_straw"
-  s.version     = WaybackMachineDownloader::VERSION
+  s.version     = "2.3.8"
   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"