wayback_machine_downloader_straw 2.3.12 → 2.4.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 67f774a5476a54ad0224e11f0c9a24b8df6b0d418f5b3c8886277c286bbe3043
-  data.tar.gz: a881ccdac84cd8e4da13edd9fc8117bfdba8c7d432959ef81c85bc95072a0dd9
+  metadata.gz: f6650c4217f2630db6307bc50ae2d6cefcbc38afc18b5701cc90a956af5cf1cf
+  data.tar.gz: 0ad44d7daa4c69b75d319c3518c4b801810be071545d5eded4497073caab4667
 SHA512:
-  metadata.gz: 01bdc9142820719c1ab17a50067fc478975627f414a29bdca32ea5fedf23227f33fb331f9470bb002af80cc50a6a74c7c8361f214d162c537d100860bdb664bc
-  data.tar.gz: f47436ecd1d4b8a4062d8689dac0d9fc4d73c743d5f84bd96764aa2a186eaae607fcee6c7b9e72f9fd3befd1fadfe9006354a43bfd134c892fbf5dfdd736ee28
+  metadata.gz: 7a8cfd1cda19bc3ff2db8859e03877395eaf44092ffbe9f5334218fbd6293ff1aecc60e2bf272f875a67ecd086a209c56640db221f4d13739669a27eada1c826
+  data.tar.gz: 877436af63fa205add55ebeb55bafcd39fec0afa56707ee742871014dac48998e8028ef4616a0b611bee5f9a93ed0d8d136375d457503a3e34b9a37f87321787

data/lib/wayback_machine_downloader/archive_api.rb

@@ -25,7 +25,7 @@ module ArchiveAPI
       # Check if the response contains the header ["timestamp", "original"]
       json.shift if json.first == ["timestamp", "original"]
       json
-    rescue JSON::ParserError, StandardError => e
+    rescue JSON::ParserError => e
       warn "Failed to fetch data from API: #{e.message}"
       []
     end

data/lib/wayback_machine_downloader/tidy_bytes.rb

@@ -1,74 +1,74 @@
 # frozen_string_literal: true
 
+# essentially, this is for converting a string with a potentially
+# broken or unknown encoding into a valid UTF-8 string
+# @todo: consider using charlock_holmes for this in the future
 module TidyBytes
-  # precomputing CP1252 to UTF-8 mappings for bytes 128-159
-  CP1252_MAP = (128..159).map do |byte|
-    case byte
-    when 128 then [226, 130, 172]  # EURO SIGN
-    when 130 then [226, 128, 154]  # SINGLE LOW-9 QUOTATION MARK
-    when 131 then [198, 146]       # LATIN SMALL LETTER F WITH HOOK
-    when 132 then [226, 128, 158]  # DOUBLE LOW-9 QUOTATION MARK
-    when 133 then [226, 128, 166]  # HORIZONTAL ELLIPSIS
-    when 134 then [226, 128, 160]  # DAGGER
-    when 135 then [226, 128, 161]  # DOUBLE DAGGER
-    when 136 then [203, 134]       # MODIFIER LETTER CIRCUMFLEX ACCENT
-    when 137 then [226, 128, 176]  # PER MILLE SIGN
-    when 138 then [197, 160]       # LATIN CAPITAL LETTER S WITH CARON
-    when 139 then [226, 128, 185]  # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
-    when 140 then [197, 146]       # LATIN CAPITAL LIGATURE OE
-    when 142 then [197, 189]       # LATIN CAPITAL LETTER Z WITH CARON
-    when 145 then [226, 128, 152]  # LEFT SINGLE QUOTATION MARK
-    when 146 then [226, 128, 153]  # RIGHT SINGLE QUOTATION MARK
-    when 147 then [226, 128, 156]  # LEFT DOUBLE QUOTATION MARK
-    when 148 then [226, 128, 157]  # RIGHT DOUBLE QUOTATION MARK
-    when 149 then [226, 128, 162]  # BULLET
-    when 150 then [226, 128, 147]  # EN DASH
-    when 151 then [226, 128, 148]  # EM DASH
-    when 152 then [203, 156]       # SMALL TILDE
-    when 153 then [226, 132, 162]  # TRADE MARK SIGN
-    when 154 then [197, 161]       # LATIN SMALL LETTER S WITH CARON
-    when 155 then [226, 128, 186]  # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
-    when 156 then [197, 147]       # LATIN SMALL LIGATURE OE
-    when 158 then [197, 190]       # LATIN SMALL LETTER Z WITH CARON
-    when 159 then [197, 184]       # LATIN SMALL LETTER Y WITH DIAERESIS
-    else nil                       # ANYTHING ELSE...
+  UNICODE_REPLACEMENT_CHARACTER = "�"
+
+  # common encodings to try for best multilingual compatibility
+  COMMON_ENCODINGS = [
+    Encoding::UTF_8,
+    Encoding::Windows_1251, # Cyrillic/Russian legacy
+    Encoding::GB18030,      # Simplified Chinese
+    Encoding::Shift_JIS,    # Japanese
+    Encoding::EUC_KR,       # Korean
+    Encoding::ISO_8859_1,   # Western European
+    Encoding::Windows_1252  # Western European/Latin1 superset
+  ].select { |enc| Encoding.name_list.include?(enc.name) }
+
+  # returns true if the string appears to be binary (has null bytes)
+  def binary_data?
+    self.include?("\x00".b)
+  end
+
+  # attempts to return a valid UTF-8 version of the string
+  def tidy_bytes
+    return self if self.encoding == Encoding::UTF_8 && self.valid_encoding?
+    return self.dup.force_encoding("BINARY") if binary_data?
+
+    str = self.dup
+    COMMON_ENCODINGS.each do |enc|
+      str.force_encoding(enc)
+      begin
+        utf8 = str.encode(Encoding::UTF_8, invalid: :replace, undef: :replace, replace: UNICODE_REPLACEMENT_CHARACTER)
+        return utf8 if utf8.valid_encoding? && !utf8.include?(UNICODE_REPLACEMENT_CHARACTER)
+      rescue Encoding::UndefinedConversionError, Encoding::InvalidByteSequenceError
+        # try next encoding
+      end
     end
-  end.freeze
 
-  # precomputing all possible byte conversions 
-  CP1252_TO_UTF8 = Array.new(256) do |b|
-    if (128..159).cover?(b)
-      CP1252_MAP[b - 128]&.pack('C*')
-    elsif b < 128
-      b.chr
-    else
-      b < 192 ? [194, b].pack('C*') : [195, b - 64].pack('C*')
+    # if no clean conversion found, try again but accept replacement characters
+    str = self.dup
+    COMMON_ENCODINGS.each do |enc|
+      str.force_encoding(enc)
+      begin
+        utf8 = str.encode(Encoding::UTF_8, invalid: :replace, undef: :replace, replace: UNICODE_REPLACEMENT_CHARACTER)
+        return utf8 if utf8.valid_encoding?
+      rescue Encoding::UndefinedConversionError, Encoding::InvalidByteSequenceError
+        # try next encoding
+      end
     end
-  end.freeze
+
+    # fallback: replace all invalid/undefined bytes
+    str.encode(Encoding::UTF_8, invalid: :replace, undef: :replace, replace: UNICODE_REPLACEMENT_CHARACTER)
+  end
+
+  def tidy_bytes!
+    replace(self.tidy_bytes)
+  end
 
   def self.included(base)
-    base.class_eval do
-      def tidy_bytes(force = false)
-        return nil if empty?
-        
-        if force
-          buffer = String.new(capacity: bytesize)
-          each_byte { |b| buffer << CP1252_TO_UTF8[b] }
-          return buffer.force_encoding(Encoding::UTF_8)
-        end
+    base.send(:include, InstanceMethods)
+  end
 
-        begin
-          encode('UTF-8')
-        rescue Encoding::UndefinedConversionError, Encoding::InvalidByteSequenceError
-          buffer = String.new(capacity: bytesize)
-          scrub { |b| CP1252_TO_UTF8[b.ord] }
-        end
-      end
+  module InstanceMethods
+    def tidy_bytes
+      TidyBytes.instance_method(:tidy_bytes).bind(self).call
+    end
 
-      def tidy_bytes!(force = false)
-        result = tidy_bytes(force)
-        result ? replace(result) : self
-      end
+    def tidy_bytes!
+      TidyBytes.instance_method(:tidy_bytes!).bind(self).call
     end
   end
 end

data/lib/wayback_machine_downloader/url_rewrite.rb

@@ -0,0 +1,74 @@
+# frozen_string_literal: true
+
+# URLs in HTML attributes
+def rewrite_html_attr_urls(content)
+  
+  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
+  content
+end
+
+# URLs in CSS
+def rewrite_css_urls(content)
+
+  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
+  content
+end
+
+# URLs in JavaScript
+def rewrite_js_urls(content)
+  
+  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
+  
+  content
+end

data/lib/wayback_machine_downloader.rb

@@ -15,6 +15,7 @@ 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'
+require_relative 'wayback_machine_downloader/url_rewrite'
 
 class ConnectionPool
   MAX_AGE = 300
@@ -115,7 +116,7 @@ class WaybackMachineDownloader
   include ArchiveAPI
   include SubdomainProcessor
 
-  VERSION = "2.3.12"
+  VERSION = "2.4.1"
   DEFAULT_TIMEOUT = 30
   MAX_RETRIES = 3
   RETRY_DELAY = 2
@@ -133,10 +134,11 @@ class WaybackMachineDownloader
 
   def initialize params
     validate_params(params)
-    @base_url = params[:base_url]
+    @base_url = params[:base_url]&.tidy_bytes
     @exact_url = params[:exact_url]
     if params[:directory]
-      @directory = File.expand_path(params[:directory])
+      sanitized_dir = params[:directory].tidy_bytes
+      @directory = File.expand_path(sanitized_dir)
     else
       @directory = nil
     end
@@ -338,15 +340,15 @@ class WaybackMachineDownloader
     get_all_snapshots_to_consider.each do |file_timestamp, file_url|
       next unless file_url.include?('/')
       next if file_timestamp.to_i > target_timestamp
-      file_id = file_url.split('/')[3..-1].join('/')
-      file_id = CGI::unescape file_id
-      file_id = file_id.tidy_bytes unless file_id == ""
+
+      raw_tail = file_url.split('/')[3..-1]&.join('/')
+      file_id = sanitize_and_prepare_id(raw_tail, file_url)
       next if file_id.nil?
       next if match_exclude_filter(file_url)
       next unless match_only_filter(file_url)
-      # Select the most recent version <= target_timestamp
+
       if !file_versions[file_id] || file_versions[file_id][:timestamp].to_i < file_timestamp.to_i
-        file_versions[file_id] = {file_url: file_url, timestamp: file_timestamp, file_id: file_id}
+        file_versions[file_id] = { file_url: file_url, timestamp: file_timestamp, file_id: file_id }
       end
     end
     file_versions.values
@@ -366,22 +368,27 @@ class WaybackMachineDownloader
     file_list_curated = Hash.new
     get_all_snapshots_to_consider.each do |file_timestamp, file_url|
       next unless file_url.include?('/')
-      file_id = file_url.split('/')[3..-1].join('/')
-      file_id = CGI::unescape file_id
-      file_id = file_id.tidy_bytes unless file_id == ""
+
+      raw_tail = file_url.split('/')[3..-1]&.join('/')
+      file_id = sanitize_and_prepare_id(raw_tail, file_url)
       if file_id.nil?
         puts "Malformed file url, ignoring: #{file_url}"
+        next
+      end
+
+      if file_id.include?('<') || file_id.include?('>')
+        puts "Invalid characters in file_id after sanitization, ignoring: #{file_url}"
       else
         if match_exclude_filter(file_url)
           puts "File url matches exclude filter, ignoring: #{file_url}"
-        elsif not match_only_filter(file_url)
+        elsif !match_only_filter(file_url)
           puts "File url doesn't match only filter, ignoring: #{file_url}"
         elsif file_list_curated[file_id]
           unless file_list_curated[file_id][:timestamp] > file_timestamp
-            file_list_curated[file_id] = {file_url: file_url, timestamp: file_timestamp}
+            file_list_curated[file_id] = { file_url: file_url, timestamp: file_timestamp }
           end
         else
-          file_list_curated[file_id] = {file_url: file_url, timestamp: file_timestamp}
+          file_list_curated[file_id] = { file_url: file_url, timestamp: file_timestamp }
         end
       end
     end
@@ -392,21 +399,32 @@ class WaybackMachineDownloader
     file_list_curated = Hash.new
     get_all_snapshots_to_consider.each do |file_timestamp, file_url|
       next unless file_url.include?('/')
-      file_id = file_url.split('/')[3..-1].join('/')
-      file_id_and_timestamp = [file_timestamp, file_id].join('/')
-      file_id_and_timestamp = CGI::unescape file_id_and_timestamp
-      file_id_and_timestamp = file_id_and_timestamp.tidy_bytes unless file_id_and_timestamp == ""
+
+      raw_tail = file_url.split('/')[3..-1]&.join('/')
+      file_id = sanitize_and_prepare_id(raw_tail, file_url)
       if file_id.nil?
         puts "Malformed file url, ignoring: #{file_url}"
+        next
+      end
+
+      file_id_and_timestamp_raw = [file_timestamp, file_id].join('/')
+      file_id_and_timestamp = sanitize_and_prepare_id(file_id_and_timestamp_raw, file_url)
+      if file_id_and_timestamp.nil?
+        puts "Malformed file id/timestamp combo, ignoring: #{file_url}"
+        next
+      end
+
+      if file_id_and_timestamp.include?('<') || file_id_and_timestamp.include?('>')
+        puts "Invalid characters in file_id after sanitization, ignoring: #{file_url}"
       else
         if match_exclude_filter(file_url)
           puts "File url matches exclude filter, ignoring: #{file_url}"
-        elsif not match_only_filter(file_url)
+        elsif !match_only_filter(file_url)
           puts "File url doesn't match only filter, ignoring: #{file_url}"
         elsif file_list_curated[file_id_and_timestamp]
-          puts "Duplicate file and timestamp combo, ignoring: #{file_id}" if @verbose
+          # duplicate combo, ignore silently (verbose flag not shown here)
         else
-          file_list_curated[file_id_and_timestamp] = {file_url: file_url, timestamp: file_timestamp}
+          file_list_curated[file_id_and_timestamp] = { file_url: file_url, timestamp: file_timestamp }
         end
       end
     end
@@ -473,6 +491,39 @@ class WaybackMachineDownloader
     end
   end
 
+  def processing_files(pool, files_to_process)
+    files_to_process.each do |file_remote_info|
+      pool.post do
+        download_success = false
+        begin
+          @connection_pool.with_connection do |connection|
+            result_message = download_file(file_remote_info, connection)
+            # assume download success if the result message contains ' -> '
+            if result_message && result_message.include?(' -> ')
+               download_success = true
+            end
+            @download_mutex.synchronize do
+              @processed_file_count += 1
+              # adjust progress message to reflect remaining files
+              progress_message = result_message.sub(/\(#{@processed_file_count}\/\d+\)/, "(#{@processed_file_count}/#{@total_to_download})") if result_message
+              puts progress_message if progress_message
+            end
+          end
+          # sppend to DB only after successful download outside the connection block
+          if download_success
+            append_to_db(file_remote_info[:file_id])
+          end
+        rescue => e
+          @logger.error("Error processing file #{file_remote_info[:file_url]}: #{e.message}")
+           @download_mutex.synchronize do
+              @processed_file_count += 1
+           end
+        end
+        sleep(RATE_LIMIT)
+      end
+    end
+  end
+
   def download_files
     start_time = Time.now
     puts "Downloading #{@base_url} to #{backup_path} from Wayback Machine archives."
@@ -519,36 +570,7 @@ class WaybackMachineDownloader
     thread_count = [@threads_count, CONNECTION_POOL_SIZE].min
     pool = Concurrent::FixedThreadPool.new(thread_count)
 
-    files_to_process.each do |file_remote_info|
-      pool.post do
-        download_success = false
-        begin
-          @connection_pool.with_connection do |connection|
-            result_message = download_file(file_remote_info, connection)
-            # assume download success if the result message contains ' -> '
-            if result_message && result_message.include?(' -> ')
-               download_success = true
-            end
-            @download_mutex.synchronize do
-              @processed_file_count += 1
-              # adjust progress message to reflect remaining files
-              progress_message = result_message.sub(/\(#{@processed_file_count}\/\d+\)/, "(#{@processed_file_count}/#{@total_to_download})") if result_message
-              puts progress_message if progress_message
-            end
-          end
-          # sppend to DB only after successful download outside the connection block
-          if download_success
-            append_to_db(file_remote_info[:file_id])
-          end
-        rescue => e
-          @logger.error("Error processing file #{file_remote_info[:file_url]}: #{e.message}")
-           @download_mutex.synchronize do
-              @processed_file_count += 1
-           end
-        end
-        sleep(RATE_LIMIT)
-      end
-    end
+    processing_files(pool, files_to_process)
 
     pool.shutdown
     pool.wait_for_termination
@@ -608,64 +630,13 @@ class WaybackMachineDownloader
       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
+      rewrite_html_attr_urls(content)
       
       # 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
+      rewrite_css_urls(content)
       
       # 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
+      rewrite_js_urls(content)
       
       # for URLs in HTML attributes that start with a single slash
       content.gsub!(/(\s(?:href|src|action|data-src|data-url)=["'])\/([^"'\/][^"']*)(["'])/i) do
@@ -794,6 +765,20 @@ class WaybackMachineDownloader
     end
     logger
   end
+    
+  # safely sanitize a file id (or id+timestamp)
+  def sanitize_and_prepare_id(raw, file_url)
+    return nil if raw.nil?
+    begin
+      raw = CGI.unescape(raw) rescue raw
+      raw.gsub!(/<[^>]*>/, '')
+      raw = raw.tidy_bytes unless raw.empty?
+      raw
+    rescue => e
+      @logger&.warn("Failed to sanitize file id from #{file_url}: #{e.message}")
+      nil
+    end
+  end
 
   def download_with_retry(file_path, file_url, file_timestamp, connection, redirect_count = 0)
     retries = 0

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: wayback_machine_downloader_straw
 version: !ruby/object:Gem::Version
-  version: 2.3.12
+  version: 2.4.1
 platform: ruby
 authors:
 - strawberrymaster
 bindir: bin
 cert_chain: []
-date: 2025-07-22 00:00:00.000000000 Z
+date: 2025-08-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: concurrent-ruby
@@ -74,6 +74,7 @@ files:
 - lib/wayback_machine_downloader/subdom_processor.rb
 - lib/wayback_machine_downloader/tidy_bytes.rb
 - lib/wayback_machine_downloader/to_regex.rb
+- lib/wayback_machine_downloader/url_rewrite.rb
 homepage: https://github.com/StrawberryMaster/wayback-machine-downloader
 licenses:
 - MIT