wayback_machine_downloader_straw 2.3.4 → 2.3.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 220999514eb0c1dd5bce948a2ac028e4527eb07f089b9f6b437f02a6a00860be
-  data.tar.gz: '03780351285ee37d38ba04652725ffa33f6112837e01e68469c8be3cda13eb45'
+  metadata.gz: 04ac6f9f045b4f92a7481ad8544f2f9138454b9eabdcf6f47b28195c1dd1cdaf
+  data.tar.gz: '09a16685d1299afb338d86495d1c58825482a6785e7e1a596bb02eb2da1fc7f1'
 SHA512:
-  metadata.gz: 3b05448a6271b8e45d5655b5ee415851f6e8e2daaec5f9bb12b0681e58292c06fe4ab91ab4f2ca1530edb0632755808dc8a465165c5e73fea2673481dddad610
-  data.tar.gz: 95440ee51316da6f2e48c3ec1d54f9fc391b2d59447625f07052222ecfeacf6fc26d430ac64ede6da589c0115fddc7a71fc7eb2fa45ff403491f1b3dc51b66ec
+  metadata.gz: fd157e047c8631ff5cdfd4ca540840a7d49196131dc4de9f9725c3989164151e4c05dda0dae0dc884bfb9bbb51483f061378ef7a1e737b36d1d11882719bcf60
+  data.tar.gz: e9b814bbbed6caef69972b9e94891f7af9be61674cf50bdd3bb1bf4a60c3622156e93b07de8a3761dba87a852bd67aa10439481c4ca72bffe564019f04451ed5

data/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

data/lib/wayback_machine_downloader.rb

@@ -113,7 +113,7 @@ class WaybackMachineDownloader
 
   include ArchiveAPI
 
-  VERSION = "2.3.4"
+  VERSION = "2.3.6"
   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)
@@ -148,6 +148,7 @@ 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
@@ -533,15 +534,109 @@ 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? '.'
@@ -565,10 +660,13 @@ 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)
+      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 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

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: wayback_machine_downloader_straw
 version: !ruby/object:Gem::Version
-  version: 2.3.4
+  version: 2.3.6
 platform: ruby
 authors:
 - strawberrymaster
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2025-04-19 00:00:00.000000000 Z
+date: 2025-05-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: concurrent-ruby
@@ -86,7 +86,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 1.9.2
+      version: 3.4.3
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="