Class: WaybackMachineDownloader

Inherits:
Object
  • Object
show all
Includes:
ArchiveAPI, SubdomainProcessor, URLRewrite
Defined in:
lib/wayback_machine_downloader.rb

Constant Summary collapse

VERSION = 
"2.4.8"
DEFAULT_TIMEOUT = 
30
MAX_RETRIES = 
3
RETRY_DELAY = 
2
RATE_LIMIT =

Delay between requests in seconds

0.25
CONNECTION_POOL_SIZE = 
10
MEMORY_BUFFER_SIZE =

16KB chunks

16384
STATE_CDX_FILENAME = 
".cdx.json"
STATE_DB_FILENAME = 
".downloaded.txt"
@@engine_printed = 
false

Constants included from URLRewrite

URLRewrite::SERVER_SIDE_EXTS

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods included from URLRewrite

#rewrite_css_urls, #rewrite_html_attr_urls, #rewrite_js_urls

Methods included from SubdomainProcessor

#process_subdomains

Methods included from ArchiveAPI

#get_raw_list_from_api, #parameters_for_api

Constructor Details

#initialize(params) ⇒ WaybackMachineDownloader

Returns a new instance of WaybackMachineDownloader.



178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
 
# File 'lib/wayback_machine_downloader.rb', line 178

def initialize params
  validate_params(params)
  @base_url = params[:base_url]&.tidy_bytes
  @exact_url = params[:exact_url]
  if params[:directory]
    sanitized_dir = params[:directory].tidy_bytes
    @directory = File.expand_path(sanitized_dir)
  else
    @directory = nil
  end
  @all_timestamps = params[:all_timestamps]
  @from_timestamp = params[:from_timestamp].to_i
  @to_timestamp = params[:to_timestamp].to_i
  @only_filter = params[:only_filter]
  @exclude_filter = params[:exclude_filter]
  @all = params[:all]
  @keep_duplicates = params[:keep_duplicates] || false
  @maximum_pages = params[:maximum_pages] ? params[:maximum_pages].to_i : 100
  default_threads = begin
    [Etc.nprocessors, 4].max
  rescue StandardError
    4
  end
  threads_param = params[:threads_count] ? params[:threads_count].to_i : 0
  threads_param = default_threads if threads_param <= 0
  @threads_count = [threads_param, 1].max
  @rewritten = params[:rewritten]
  @reset = params[:reset]
  @keep = params[:keep]
  @timeout = params[:timeout] || DEFAULT_TIMEOUT
  @logger = setup_logger
  @failed_downloads = Concurrent::Array.new
  @connection_pool = ConnectionPool.new(CONNECTION_POOL_SIZE)
  @db_mutex = Mutex.new
  @rewrite = params[:rewrite] || false
  @delay = params[:delay] ? params[:delay].to_f : 0.0
  @recursive_subdomains = params[:recursive_subdomains] || false
  @subdomain_depth = params[:subdomain_depth] || 1
  @snapshot_at = params[:snapshot_at] ? params[:snapshot_at].to_i : nil
  @max_retries = params[:max_retries] ? params[:max_retries].to_i : MAX_RETRIES
  @page_requisites = params[:page_requisites] || false
  @pending_jobs = Concurrent::AtomicFixnum.new(0)

  @db_buffer = []
  @db_buffer_mutex = Mutex.new
  @db_last_flush = Time.now
  @db_flush_threshold = 50  # flush to disk every 50 completed files
  @db_flush_interval = 5.0  # or flush every 5 seconds even if count isn't met

  # URL for rejecting invalid/unencoded wayback urls
  @url_regexp = /^(([A-Za-z][A-Za-z0-9+.-]*):((\/\/(((([A-Za-z0-9._~-])|(%[ABCDEFabcdef0-9][ABCDEFabcdef0-9])|([!$&'('')'*+,;=]))+)(:([0-9]*))?)(((\/((([A-Za-z0-9._~-])|(%[ABCDEFabcdef0-9][ABCDEFabcdef0-9])|([!$&'('')'*+,;=])|:|@)*))*)))|((\/(((([A-Za-z0-9._~-])|(%[ABCDEFabcdef0-9][ABCDEFabcdef0-9])|([!$&'('')'*+,;=])|:|@)+)(\/((([A-Za-z0-9._~-])|(%[ABCDEFabcdef0-9][ABCDEFabcdef0-9])|([!$&'('')'*+,;=])|:|@)*))*)?))|((((([A-Za-z0-9._~-])|(%[ABCDEFabcdef0-9][ABCDEFabcdef0-9])|([!$&'('')'*+,;=])|:|@)+)(\/((([A-Za-z0-9._~-])|(%[ABCDEFabcdef0-9][ABCDEFabcdef0-9])|([!$&'('')'*+,;=])|:|@)*))*)))(\?((([A-Za-z0-9._~-])|(%[ABCDEFabcdef0-9][ABCDEFabcdef0-9])|([!$&'('')'*+,;=])|:|@)|\/|\?)*)?(\#((([A-Za-z0-9._~-])|(%[ABCDEFabcdef0-9][ABCDEFabcdef0-9])|([!$&'('')'*+,;=])|:|@)|\/|\?)*)?)$/

  handle_reset
end

Instance Attribute Details

#all ⇒ Object

Returns the value of attribute all.



173
174
175
 
# File 'lib/wayback_machine_downloader.rb', line 173

def all
  @all
end

#all_timestamps ⇒ Object

Returns the value of attribute all_timestamps.



173
174
175
 
# File 'lib/wayback_machine_downloader.rb', line 173

def all_timestamps
  @all_timestamps
end

#base_url ⇒ Object

Returns the value of attribute base_url.



173
174
175
 
# File 'lib/wayback_machine_downloader.rb', line 173

def base_url
  @base_url
end

#directory ⇒ Object

Returns the value of attribute directory.



173
174
175
 
# File 'lib/wayback_machine_downloader.rb', line 173

def directory
  @directory
end

#exact_url ⇒ Object

Returns the value of attribute exact_url.



173
174
175
 
# File 'lib/wayback_machine_downloader.rb', line 173

def exact_url
  @exact_url
end

#exclude_filter ⇒ Object

Returns the value of attribute exclude_filter.



173
174
175
 
# File 'lib/wayback_machine_downloader.rb', line 173

def exclude_filter
  @exclude_filter
end

#from_timestamp ⇒ Object

Returns the value of attribute from_timestamp.



173
174
175
 
# File 'lib/wayback_machine_downloader.rb', line 173

def from_timestamp
  @from_timestamp
end

#keep ⇒ Object

Returns the value of attribute keep.



173
174
175
 
# File 'lib/wayback_machine_downloader.rb', line 173

def keep
  @keep
end

#keep_duplicates ⇒ Object

Returns the value of attribute keep_duplicates.



173
174
175
 
# File 'lib/wayback_machine_downloader.rb', line 173

def keep_duplicates
  @keep_duplicates
end

#logger ⇒ Object

Returns the value of attribute logger.



173
174
175
 
# File 'lib/wayback_machine_downloader.rb', line 173

def logger
  @logger
end

#maximum_pages ⇒ Object

Returns the value of attribute maximum_pages.



173
174
175
 
# File 'lib/wayback_machine_downloader.rb', line 173

def maximum_pages
  @maximum_pages
end

#only_filter ⇒ Object

Returns the value of attribute only_filter.



173
174
175
 
# File 'lib/wayback_machine_downloader.rb', line 173

def only_filter
  @only_filter
end

#page_requisites ⇒ Object

Returns the value of attribute page_requisites.



173
174
175
 
# File 'lib/wayback_machine_downloader.rb', line 173

def page_requisites
  @page_requisites
end

#reset ⇒ Object

Returns the value of attribute reset.



173
174
175
 
# File 'lib/wayback_machine_downloader.rb', line 173

def reset
  @reset
end

#rewrite ⇒ Object

Returns the value of attribute rewrite.



173
174
175
 
# File 'lib/wayback_machine_downloader.rb', line 173

def rewrite
  @rewrite
end

#snapshot_at ⇒ Object

Returns the value of attribute snapshot_at.



173
174
175
 
# File 'lib/wayback_machine_downloader.rb', line 173

def snapshot_at
  @snapshot_at
end

#threads_count ⇒ Object

Returns the value of attribute threads_count.



173
174
175
 
# File 'lib/wayback_machine_downloader.rb', line 173

def threads_count
  @threads_count
end

#to_timestamp ⇒ Object

Returns the value of attribute to_timestamp.



173
174
175
 
# File 'lib/wayback_machine_downloader.rb', line 173

def to_timestamp
  @to_timestamp
end

Instance Method Details

#append_to_db(file_id) ⇒ Object 



590
591
592
593
594
595
596
597
598
599
600
601
 
# File 'lib/wayback_machine_downloader.rb', line 590

def append_to_db(file_id)
  flush_needed = false

  @db_buffer_mutex.synchronize do
    @db_buffer << file_id
    if @db_buffer.size >= @db_flush_threshold || (Time.now - @db_last_flush) >= @db_flush_interval
      flush_needed = true
    end
  end

  flush_db if flush_needed
end

#backup_name ⇒ Object 



233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
 
# File 'lib/wayback_machine_downloader.rb', line 233

def backup_name
  url_to_process = @base_url
  url_to_process = url_to_process.chomp('/*') if url_to_process&.end_with?('/*')

  raw = if url_to_process.include?('//')
    url_to_process.split('/')[2]
  else
    url_to_process
  end

  # if it looks like a wildcard pattern, normalize to a safe host-ish name
  if raw&.start_with?('*.')
    raw = raw.sub(/\A\*\./, 'all-')
  end

  # sanitize for Windows (and safe cross-platform) to avoid ENOTDIR on mkdir (colon in host:port)
  if Gem.win_platform?
    raw = raw.gsub(/[:*?"<>|]/, '_')
    raw = raw.gsub(/[ .]+\z/, '')
  else
    # still good practice to strip path separators (and maybe '*' for POSIX too)
    raw = raw.gsub(/[\/:*?"<>|]/, '_')
  end

  raw = 'site' if raw.nil? || raw.empty?
  raw
end

#backup_path ⇒ Object 



261
262
263
264
265
266
267
268
269
270
 
# File 'lib/wayback_machine_downloader.rb', line 261

def backup_path
  if @directory
    # because @directory is already an absolute path, we just ensure it exists
    @directory
  else
    # ensure the default path is absolute and normalized
    cwd = Dir.pwd
    File.expand_path(File.join(cwd, 'websites', backup_name))
  end
end

#cdx_path ⇒ Object 



272
273
274
 
# File 'lib/wayback_machine_downloader.rb', line 272

def cdx_path
  File.join(backup_path, STATE_CDX_FILENAME)
end

#color(text, color_code) ⇒ Object 



1160
1161
1162
1163
1164
 
# File 'lib/wayback_machine_downloader.rb', line 1160

def color(text, color_code)
  return text if Gem.win_platform? && !ENV['ENABLE_ANSI']
  codes = { red: 31, green: 32, yellow: 33, blue: 34, magenta: 35, cyan: 36, white: 37 }
  "\e[#{codes[color_code]}m#{text}\e[0m"
end

#db_path ⇒ Object 



276
277
278
 
# File 'lib/wayback_machine_downloader.rb', line 276

def db_path
  File.join(backup_path, STATE_DB_FILENAME)
end

#download_file(file_remote_info, http) ⇒ Object 



1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
 
# File 'lib/wayback_machine_downloader.rb', line 1070

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]

  # 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 = 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
    # 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
  # this handles cases where a file was created manually or by a previous partial run without a .db entry
  if File.exist? file_path
     return ["#{color("[EXISTS]", :cyan)} #{file_url} (#{@processed_file_count + 1}/#{@total_to_download})", file_path]
  end

  begin
    structure_dir_path dir_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
      return ["#{color("[SAVED]", :green)}  #{file_url} (#{@processed_file_count + 1}/#{@total_to_download})", file_path]
    when :skipped_not_found
      return ["#{color("[NOT FOUND]", :yellow)} #{file_url} (#{@processed_file_count + 1}/#{@total_to_download})", nil]
    else
      # ideally, this case should not be reached if download_with_retry behaves as expected.
      # ideally, this case should not be reached if download_with_retry behaves as expected.
      return ["#{color("[UNKNOWN]", :magenta)} #{file_url} (#{@processed_file_count + 1}/#{@total_to_download})", nil]
    end
  rescue StandardError => e
    msg = "#{color("[FAILED]", :red)}  #{file_url} # #{e} (#{@processed_file_count + 1}/#{@total_to_download})"
    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
    return [msg, nil]
  end
end

#download_files ⇒ Object 



664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
 
# File 'lib/wayback_machine_downloader.rb', line 664

def download_files
  start_time = Time.now

  unless @@engine_printed
    engine_name = HTTPX_AVAILABLE ? "HTTPX" : "Net::HTTP"
    puts "Connection engine used: #{color(engine_name, :green)}"
    @@engine_printed = true
  end

  puts "Downloading #{@base_url} to #{backup_path} from Wayback Machine archives."

  FileUtils.mkdir_p(backup_path)

  # Load the list of files to potentially download
  files_to_download = file_list_by_timestamp

  if files_to_download.empty?
    puts "No files found matching criteria."
    cleanup
    return
  end

  total_files = files_to_download.count
  puts "#{total_files} files found matching criteria."

  # Load IDs of already downloaded files
  downloaded_ids = load_downloaded_ids

  # We use a thread-safe Set to track what we have queued/downloaded in this session
  # to avoid infinite loops with page requisites
  @session_downloaded_ids = Concurrent::Set.new
  downloaded_ids.each { |id| @session_downloaded_ids.add(id) }

  files_to_process = files_to_download.reject do |file_info|
    downloaded_ids.include?(file_info[:file_id])
  end

  remaining_count = files_to_process.count
  skipped_count = total_files - remaining_count

  if skipped_count > 0
    puts "Found #{skipped_count} previously downloaded files, skipping them."
  end

  if remaining_count == 0 && !@page_requisites
    puts "All matching files have already been downloaded."
    cleanup
    return
  end

  puts "#{remaining_count} files to download."

  @processed_file_count = 0
  @total_to_download = remaining_count
  @download_mutex = Mutex.new

  thread_count = [@threads_count, CONNECTION_POOL_SIZE].min
  @worker_pool = Concurrent::FixedThreadPool.new(thread_count)

  # initial batch
  files_to_process.each do |file_remote_info|
    @session_downloaded_ids.add(file_remote_info[:file_id])
    submit_download_job(file_remote_info)
  end

  # print a header for the download phase
  puts "\n#{color("Processing downloads:", :white)}"
  $stdout.flush

  # wait for all jobs to finish
  loop do
    sleep 0.5
    break if @pending_jobs.value == 0
  end

  @worker_pool.shutdown
  @worker_pool.wait_for_termination

  end_time = Time.now
  puts "\nDownload finished in #{(end_time - start_time).round(2)}s."

  # process subdomains if enabled
  if @recursive_subdomains
    subdomain_start_time = Time.now
    process_subdomains
    subdomain_end_time = Time.now
    subdomain_time = (subdomain_end_time - subdomain_start_time).round(2)
    puts "Subdomain processing finished in #{subdomain_time}s."
  end

  puts "Results saved in #{backup_path}"
  cleanup
end

#file_list_by_timestamp ⇒ Object 



1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
 
# File 'lib/wayback_machine_downloader.rb', line 1170

def file_list_by_timestamp
  if @snapshot_at
    @file_list_by_snapshot_at ||= get_composite_snapshot_file_list(@snapshot_at)
  elsif @all_timestamps
    file_list_curated = get_file_list_all_timestamps
    file_list_curated.map do |file_remote_info|
      file_remote_info[1][:file_id] = file_remote_info[0]
      file_remote_info[1]
    end
  else
    file_list_curated = get_file_list_curated
    file_list_curated = file_list_curated.sort_by { |_,v| v[:timestamp].to_s }.reverse
    file_list_curated.map do |file_remote_info|
      file_remote_info[1][:file_id] = file_remote_info[0]
      file_remote_info[1]
    end
  end
end

#file_queue ⇒ Object 



1166
1167
1168
 
# File 'lib/wayback_machine_downloader.rb', line 1166

def file_queue
  @file_queue ||= file_list_by_timestamp.each_with_object(Queue.new) { |file_info, q| q << file_info }
end

#flush_db ⇒ Object 



603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
 
# File 'lib/wayback_machine_downloader.rb', line 603

def flush_db
  lines_to_write = nil

  @db_buffer_mutex.synchronize do
    return if @db_buffer.empty?
    lines_to_write = @db_buffer.dup
    @db_buffer.clear
    @db_last_flush = Time.now
  end

  return if lines_to_write.nil? || lines_to_write.empty?

  begin
    FileUtils.mkdir_p(File.dirname(db_path))
    File.open(db_path, 'a') do |f|
      lines_to_write.each { |id| f.puts(id) }
    end
  rescue StandardError => e
    @logger.error("Failed to write batch to #{db_path}: #{e.message}")

    @db_buffer_mutex.synchronize do
      @db_buffer.unshift(*lines_to_write)
    end
  end
end

#get_all_snapshots_to_consider ⇒ Object 



315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
 
# File 'lib/wayback_machine_downloader.rb', line 315

def get_all_snapshots_to_consider
  if File.exist?(cdx_path) && !@reset
    puts "Loading snapshot list from #{cdx_path}"
    begin
      snapshot_list_to_consider = JSON.parse(File.read(cdx_path))
      puts "Loaded #{snapshot_list_to_consider.length} snapshots from cache."
      puts
      return Concurrent::Array.new(snapshot_list_to_consider)
    rescue JSON::ParserError => e
      puts "Error reading snapshot cache file #{cdx_path}: #{e.message}. Refetching..."
      FileUtils.rm_f(cdx_path)
    rescue => e
      puts "Error loading snapshot cache #{cdx_path}: #{e.message}. Refetching..."
      FileUtils.rm_f(cdx_path)
    end
  end

  snapshot_list_to_consider = Concurrent::Array.new
  mutex = Mutex.new

  # if snapshot_at is set, limit CDX queries to snapshots at or before that timestamp
  original_to = @to_timestamp
  if @snapshot_at
    @to_timestamp = @snapshot_at
  end

  puts "Getting snapshot pages from Wayback Machine API..."

  # Fetch the initial set of snapshots, sequentially
  @connection_pool.with_connection do |connection|
    initial_list = get_raw_list_from_api(@base_url, 0, connection)
    initial_list ||= []
    mutex.synchronize do
      snapshot_list_to_consider.concat(initial_list)
      print "."
      $stdout.flush
    end
  end

  # Fetch additional pages if the exact URL flag is not set and the first page wasn't empty
  unless @exact_url || snapshot_list_to_consider.empty?
    page_index = 1
    batch_size = [@threads_count, 5].min
    continue_fetching = true
    fetch_pool = Concurrent::FixedThreadPool.new([@threads_count, 1].max)
    begin
      while continue_fetching && page_index < @maximum_pages
        # Determine the range of pages to fetch in this batch
        end_index = [page_index + batch_size, @maximum_pages].min
        current_batch = (page_index...end_index).to_a

        # Create futures for concurrent API calls
        futures = current_batch.map do |page|
          Concurrent::Future.execute(executor: fetch_pool) do
            result = nil
            @connection_pool.with_connection do |connection|
              result = get_raw_list_from_api(@base_url, page, connection)
            end
            result ||= []
            [page, result]
          end
        end

        results = []

        futures.each do |future|
          begin
            val = future.value
            # only append if valid
            if val && val.is_a?(Array) && val.first.is_a?(Integer)
              results << val
            end
          rescue => e
            puts "\nError fetching page #{future}: #{e.message}"
          end
        end

        # Sort results by page number to maintain order
        results.sort_by! { |page, _| page }

        # Process results and check for empty pages
        results.each do |page, result|
          if result.nil? || result.empty?
            continue_fetching = false
            break
          else
            mutex.synchronize do
              snapshot_list_to_consider.concat(result)
              print "."
              $stdout.flush
            end
          end
        end

        page_index = end_index

        sleep(RATE_LIMIT) if continue_fetching
      end
    ensure
      fetch_pool.shutdown
      fetch_pool.wait_for_termination
    end
  end

  puts " found #{snapshot_list_to_consider.length} snapshots."

  # save the fetched list to the cache file
  begin
    FileUtils.mkdir_p(File.dirname(cdx_path))
    File.write(cdx_path, JSON.pretty_generate(snapshot_list_to_consider.to_a)) # Convert Concurrent::Array back to Array for JSON
    puts "Saved snapshot list to #{cdx_path}"
  rescue => e
    puts "Error saving snapshot cache to #{cdx_path}: #{e.message}"
  ensure
    # restore any previously set to-timestamp
    @to_timestamp = original_to
  end
  puts

  snapshot_list_to_consider
end

#get_composite_snapshot_file_list(target_timestamp) ⇒ Object

Get a composite snapshot file list for a specific timestamp



438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
 
# File 'lib/wayback_machine_downloader.rb', line 438

def get_composite_snapshot_file_list(target_timestamp)
  file_versions = {}
  get_all_snapshots_to_consider.each do |file_timestamp, file_url|
    next unless file_url.include?('/')
    next if file_timestamp.to_i > target_timestamp

    # allow empty path by treating missing tail as empty string
    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)

    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 }
    end
  end
  file_versions.values
end

#get_file_list_all_timestamps ⇒ Object 



496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
 
# File 'lib/wayback_machine_downloader.rb', line 496

def get_file_list_all_timestamps
  file_list_curated = Hash.new
  get_all_snapshots_to_consider.each do |file_timestamp, file_url|
    next unless file_url.include?('/')

    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 !match_only_filter(file_url)
        puts "File url doesn't match only filter, ignoring: #{file_url}"
      elsif file_list_curated[file_id_and_timestamp]
        # duplicate combo, ignore silently (verbose flag not shown here)
      else
        file_list_curated[file_id_and_timestamp] = { file_url: file_url, timestamp: file_timestamp }
      end
    end
  end
  puts "file_list_curated: " + file_list_curated.count.to_s
  file_list_curated
end

#get_file_list_by_timestamp ⇒ Object 



534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
 
# File 'lib/wayback_machine_downloader.rb', line 534

def get_file_list_by_timestamp
  if @snapshot_at
    @file_list_by_snapshot_at ||= get_composite_snapshot_file_list(@snapshot_at)
  elsif @all_timestamps
    file_list_curated = get_file_list_all_timestamps
    file_list_curated.map do |file_remote_info|
      file_remote_info[1][:file_id] = file_remote_info[0]
      file_remote_info[1]
    end
  else
    file_list_curated = get_file_list_curated
    file_list_curated = file_list_curated.sort_by { |_,v| v[:timestamp].to_s }.reverse
    file_list_curated.map do |file_remote_info|
      file_remote_info[1][:file_id] = file_remote_info[0]
      file_remote_info[1]
    end
  end
end

#get_file_list_composite_snapshot(target_timestamp) ⇒ Object

Returns a list of files for the composite snapshot



459
460
461
462
463
 
# File 'lib/wayback_machine_downloader.rb', line 459

def get_file_list_composite_snapshot(target_timestamp)
  file_list = get_composite_snapshot_file_list(target_timestamp)
  # return a list sorted newest->oldest by timestamp
  file_list.sort_by { |v| v[:timestamp].to_s }.reverse
end

#get_file_list_curated ⇒ Object 



465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
 
# File 'lib/wayback_machine_downloader.rb', line 465

def get_file_list_curated
  file_list_curated = Hash.new
  get_all_snapshots_to_consider.each do |file_timestamp, file_url|
    next unless file_url.include?('/')

    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 !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 }
        end
      else
        file_list_curated[file_id] = { file_url: file_url, timestamp: file_timestamp }
      end
    end
  end
  file_list_curated
end

#handle_reset ⇒ Object 



280
281
282
283
284
285
286
287
 
# File 'lib/wayback_machine_downloader.rb', line 280

def handle_reset
  if @reset
    puts "Resetting download state..."
    FileUtils.rm_f(cdx_path)
    FileUtils.rm_f(db_path)
    puts "Removed state files: #{cdx_path}, #{db_path}"
  end
end

#list_files ⇒ Object 



553
554
555
556
557
558
559
560
561
562
563
564
565
 
# File 'lib/wayback_machine_downloader.rb', line 553

def list_files
  # retrieval produces its own output
  @orig_stdout = $stdout
  $stdout = $stderr
  files = get_file_list_by_timestamp
  $stdout = @orig_stdout
  puts "["
  files[0...-1].each do |file|
    puts file.to_json + ","
  end
  puts files[-1].to_json
  puts "]"
end

#load_downloaded_ids ⇒ Object 



567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
 
# File 'lib/wayback_machine_downloader.rb', line 567

def load_downloaded_ids
  downloaded_ids = Set.new
  if File.exist?(db_path) && !@reset
    puts "Loading list of already downloaded files from #{db_path}"
    begin
      File.foreach(db_path) do |line|
        id = line.strip
        # only trust DB entries that actually exist on disk; this helps when resuming
        path = local_path_for_file_id(id)
        if path && File.exist?(path)
          downloaded_ids.add(id)
        else
          puts "Found DB entry but file missing, will requeue: #{id}" if @logger && @logger.level == Logger::DEBUG
        end
      end
    rescue => e
      puts "Error reading downloaded files list #{db_path}: #{e.message}. Assuming no files downloaded."
      downloaded_ids.clear
    end
  end
  downloaded_ids
end

#local_path_for_file_id(file_id) ⇒ Object

derive the local filesystem path for a sanitized file_id stored in the DB



1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
 
# File 'lib/wayback_machine_downloader.rb', line 1140

def local_path_for_file_id(file_id)
  return nil if file_id.nil?
  current_backup_path = backup_path

  # file_id coming from DB is expected to already be sanitized
  raw_path_elements = file_id.split('/')

  if file_id == ""
    dir_path = current_backup_path
    return File.join(dir_path, 'index.html')
  elsif file_id[-1] == '/' || (raw_path_elements.last && !raw_path_elements.last.include?('.'))
    dir_path = File.join(current_backup_path, *raw_path_elements)
    return File.join(dir_path, 'index.html')
  else
    filename = raw_path_elements.pop
    dir_path = File.join(current_backup_path, *raw_path_elements)
    return File.join(dir_path, filename)
  end
end

#match_exclude_filter(file_url) ⇒ Object 



302
303
304
305
306
307
308
309
310
311
312
313
 
# File 'lib/wayback_machine_downloader.rb', line 302

def match_exclude_filter file_url
  if @exclude_filter
    exclude_filter_regex = @exclude_filter.to_regex(detect: true)
    if exclude_filter_regex
      exclude_filter_regex =~ file_url
    else
      file_url.downcase.include? @exclude_filter.downcase
    end
  else
    false
  end
end

#match_only_filter(file_url) ⇒ Object 



289
290
291
292
293
294
295
296
297
298
299
300
 
# File 'lib/wayback_machine_downloader.rb', line 289

def match_only_filter file_url
  if @only_filter
    only_filter_regex = @only_filter.to_regex(detect: true)
    if only_filter_regex
      only_filter_regex =~ file_url
    else
      file_url.downcase.include? @only_filter.downcase
    end
  else
    true
  end
end

#process_page_requisites(file_path, parent_remote_info) ⇒ Object 



819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
 
# File 'lib/wayback_machine_downloader.rb', line 819

def process_page_requisites(file_path, parent_remote_info)
  return unless File.exist?(file_path)

  content = File.read(file_path)
  content = content.force_encoding('UTF-8').scrub

  assets = PageRequisites.extract(content)

  # prepare base URI for resolving relative paths
  parent_raw = parent_remote_info[:file_url]
  parent_raw = "http://#{parent_raw}" unless parent_raw.match?(/^https?:\/\//)

  begin
    base_uri = URI(parent_raw)
    # calculate the "root" host of the site we are downloading to compare later
    current_project_host = URI("http://" + @base_url.gsub(%r{^https?://}, '')).host
  rescue URI::InvalidURIError
    return
  end

  parent_timestamp = parent_remote_info[:timestamp]

  assets.each do |asset_rel_url|
    begin
      # resolve full URL (handles relative paths like "../img/logo.png")
      resolved_uri = base_uri + asset_rel_url

      # detect if the asset URL is already a Wayback "web/<timestamp>/.../https://..." embed
      asset_timestamp = parent_timestamp
      if resolved_uri.path =~ %r{\A/web/([0-9]{4,})[^/]*/(https?://.+)\z}
        embedded_ts = $1
        begin
          orig_uri = URI($2)
          resolved_uri = orig_uri
          asset_timestamp = embedded_ts.to_i
        rescue URI::InvalidURIError
          # fall back to original resolved_uri and parent timestamp
        end
      end

      # filter out navigation links (pages) vs assets
      # skip if extension is empty or looks like an HTML page
      path = resolved_uri.path
      ext = File.extname(path).downcase
      if ext.empty? || ['.html', '.htm', '.php', '.asp', '.aspx'].include?(ext)
         next
      end

      # construct the original URL to query the Wayback API
      asset_wbm_url = if resolved_uri.scheme
                        "#{resolved_uri.scheme}://#{resolved_uri.host}#{resolved_uri.path}"
                      else
                        "#{resolved_uri.host}#{resolved_uri.path}"
                      end
      asset_wbm_url += "?#{resolved_uri.query}" if resolved_uri.query

      # attempt to find the best snapshot timestamp for this asset to increase hit rate
      begin
        @connection_pool.with_connection do |connection|
          snapshots = get_raw_list_from_api(asset_wbm_url, 0, connection)
          if snapshots && snapshots.any?
            # choose the most recent snapshot at or before the
            # parent page timestamp, else the latest available
            chosen = snapshots.select { |ts, _| ts.to_i <= parent_timestamp.to_i }.max_by { |s| s[0].to_i } || snapshots.max_by { |s| s[0].to_i }
            asset_timestamp = chosen[0].to_i if chosen
          end
        end
      rescue => e
        @logger.warn("Failed to query CDX for #{asset_wbm_url}: #{e.message}") if @logger
      end

      # construct the local file ID
      #  if the asset is on the SAME domain, strip the domain from the folder path
      #  if it's on a DIFFERENT domain (e.g. cdn.jquery.com), keep the domain folder
      if resolved_uri.host == current_project_host
         # e.g. /static/css/style.css
         asset_file_id = resolved_uri.path
         asset_file_id = asset_file_id[1..-1] if asset_file_id.start_with?('/')
      else
         # e.g. cdn.google.com/jquery.js
         asset_file_id = asset_wbm_url
      end

    rescue URI::InvalidURIError, StandardError
      next
    end

    # sanitize and queue
    asset_id = sanitize_and_prepare_id(asset_file_id, asset_wbm_url)

    unless @session_downloaded_ids.include?(asset_id)
      @session_downloaded_ids.add(asset_id)

      new_file_info = {
        file_url: asset_wbm_url,
        timestamp: asset_timestamp,
        file_id: asset_id
      }

      @download_mutex.synchronize do
        @total_to_download += 1
        puts "Queued requisite: #{asset_file_id} (#{asset_wbm_url} @ #{asset_timestamp})"
      end

      submit_download_job(new_file_info)
    end
  end
end

#process_single_file(file_remote_info) ⇒ Object 



770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
 
# File 'lib/wayback_machine_downloader.rb', line 770

def process_single_file(file_remote_info)
  download_success = false
  downloaded_path = nil

  # if delay was set by the user
  sleep(@delay) if @delay > 0

  # fast-path for resumed runs: if file already exists locally, avoid HTTP work entirely
  existing_path = local_path_for_file_id(file_remote_info[:file_id])
  if existing_path && File.exist?(existing_path)
    result_message = "#{color("[EXISTS]", :cyan)} #{file_remote_info[:file_url]} (#{@processed_file_count + 1}/#{@total_to_download})"
    @download_mutex.synchronize do
      @processed_file_count += 1 if @processed_file_count < @total_to_download
      puts result_message
    end

    append_to_db(file_remote_info[:file_id])

    if @page_requisites && File.extname(existing_path) =~ /\.(html?|php|asp|aspx|jsp)$/i
      process_page_requisites(existing_path, file_remote_info)
    end
    return
  end

  @connection_pool.with_connection do |connection|
    result_message, downloaded_path = download_file(file_remote_info, connection)

    if downloaded_path && File.exist?(downloaded_path)
       download_success = true
    end

    @download_mutex.synchronize do
      @processed_file_count += 1 if @processed_file_count < @total_to_download
      # only print if it's a "User" file or a requisite we found
      puts result_message if result_message
    end
  end

  if download_success
    append_to_db(file_remote_info[:file_id])

    if @page_requisites && downloaded_path && File.extname(downloaded_path) =~ /\.(html?|php|asp|aspx|jsp)$/i
      process_page_requisites(downloaded_path, file_remote_info)
    end
  end
rescue => e
  @logger.error("Error processing file #{file_remote_info[:file_url]}: #{e.message}")
end

#processing_files(pool, files_to_process) ⇒ Object 



629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
 
# File 'lib/wayback_machine_downloader.rb', line 629

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, downloaded_path = download_file(file_remote_info, connection)
          # consider the download successful if we have a downloaded path present
          if downloaded_path && File.exist?(downloaded_path)
             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

#rewrite_local_files ⇒ Object 



964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
 
# File 'lib/wayback_machine_downloader.rb', line 964

def rewrite_local_files
  puts "Scanning #{backup_path} for files to rewrite..."
  files = Dir.glob(File.join(backup_path, "**/*.{html,htm,css,js,php,asp,aspx,jsp}"))

  puts "Found #{files.size} files. Rewriting links for local browsing..."

  pool = Concurrent::FixedThreadPool.new(@threads_count)
  progress = Concurrent::AtomicFixnum.new(0)

  files.each do |file_path|
    pool.post do
      rewrite_urls_to_relative(file_path)
      current = progress.increment
      print "\rProgress: #{current}/#{files.size}" if current % 100 == 0
    end
  end

  pool.shutdown
  pool.wait_for_termination
  puts "\nFinished rewriting all files."
end

#rewrite_urls_to_relative(file_path) ⇒ Object 



986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
 
# File 'lib/wayback_machine_downloader.rb', line 986

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)

    # detect encoding for HTML files
    if file_ext == '.html' || file_ext == '.htm' || file_ext == '.php' || file_ext == '.asp'
      encoding_match = content.match(/<meta.*?charset=["'\s]?([^"'\s>;]+)/i)
      encoding_name = encoding_match ? encoding_match.captures.first : 'UTF-8'

      begin
        encoding = Encoding.find(encoding_name)
      rescue ArgumentError
        encoding = Encoding::UTF_8
      end

      content.force_encoding(encoding)
    else
      content.force_encoding('UTF-8')
    end

    # convert the content to valid UTF-8
    if !content.valid_encoding? || content.encoding != Encoding::UTF_8
      begin
        content = content.encode(Encoding::UTF_8, invalid: :replace, undef: :replace, replace: '')
      rescue Encoding::UndefinedConversionError, Encoding::InvalidByteSequenceError, ArgumentError
        content = content.tidy_bytes
      end
    end

    # URLs in HTML attributes
    content = rewrite_html_attr_urls(content)

    # URLs in CSS
    content = rewrite_css_urls(content)

    # URLs in JavaScript
    content = rewrite_js_urls(content)

    root_prefix = site_root_relative_prefix(file_path)

    # rewrite root-absolute links to paths relative to the downloaded site root
    content.gsub!(/(\s(?:href|src|action|data-src|data-url)=["'])\/([^"'\/][^"']*)(["'])/i) do
      prefix, path, suffix = $1, $2, $3
      "#{prefix}#{root_prefix}#{path}#{suffix}"
    end

    # apply the same root-relative conversion to CSS url(...) references
    content.gsub!(/url\(\s*["']?\/([^"'\)\/][^"'\)]*?)["']?\s*\)/i) do
      path = $1
      "url(\"#{root_prefix}#{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}")
  rescue StandardError => e
    @logger.error("Failed to rewrite URLs in #{file_path}: #{e.message}")
  end
end

#site_root_relative_prefix(file_path) ⇒ Object 



1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
 
# File 'lib/wayback_machine_downloader.rb', line 1052

def site_root_relative_prefix(file_path)
  file_dir = File.dirname(File.expand_path(file_path))
  root_dir = File.expand_path(backup_path)

  begin
    relative_dir = Pathname.new(file_dir).relative_path_from(Pathname.new(root_dir)).to_s
  rescue ArgumentError
    return './'
  end

  return './' if relative_dir == '.' || relative_dir.empty?

  depth = relative_dir.split(/[\\\/]+/).reject(&:empty?).length
  return './' if depth <= 0

  '../' * depth
end

#structure_dir_path(dir_path) ⇒ Object 



928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
 
# File 'lib/wayback_machine_downloader.rb', line 928

def structure_dir_path dir_path
  begin
    # check if it's already a directory; if not, try to create it
    FileUtils::mkdir_p dir_path unless File.directory? dir_path
  rescue Errno::EEXIST, Errno::ENOTDIR => e
    file_already_existing = nil
    check_path = dir_path

    # walk up the path to find the specific file that is blocking directory creation
    while check_path != "." && check_path != "/"
      if File.exist?(check_path) && !File.directory?(check_path)
        file_already_existing = check_path
        break
      end
      parent = File.dirname(check_path)
      break if parent == check_path
      check_path = parent
    end

    if file_already_existing
      file_already_existing_temporary = file_already_existing + '.temp'
      file_already_existing_permanent = file_already_existing + '/index.html'

      FileUtils::mv file_already_existing, file_already_existing_temporary
      FileUtils::mkdir_p file_already_existing
      FileUtils::mv file_already_existing_temporary, file_already_existing_permanent

      puts "#{file_already_existing} -> #{file_already_existing_permanent}"
      # retry the directory creation now that the path is clear
      structure_dir_path dir_path
    else
      raise "Unhandled directory restructure error: #{e.message}"
    end
  end
end

#submit_download_job(file_remote_info) ⇒ Object

helper to submit jobs and increment the counter



759
760
761
762
763
764
765
766
767
768
 
# File 'lib/wayback_machine_downloader.rb', line 759

def submit_download_job(file_remote_info)
  @pending_jobs.increment
  @worker_pool.post do
    begin
      process_single_file(file_remote_info)
    ensure
      @pending_jobs.decrement
    end
  end
end