wayback_machine_downloader 2.1.1 → 2.3.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 48f524cedc0e9f66c7b0acca132a71557a327ea2
-  data.tar.gz: 1d70bb2a76cd07c82c08674fdc96b543caec48c0
+SHA256:
+  metadata.gz: 54752c73ebfac815e91ef6bba40547a36282e5ec9c3ef2792370c13352fce0b6
+  data.tar.gz: df2f5d94981eeb2d1e55d2b4a9dd8fe57a24e8b29cf79a700ca520b7c3bc1a21
 SHA512:
-  metadata.gz: 26eb05cbeebd911502bd01513535c7cc2d4ad0fe3850adc0205ca4f649351e56855af66915d86c501fb8be64963fe1d409d013d8afcd24064cc15673b2cc0854
-  data.tar.gz: 0dbbd54b4b4ab231adcae908bbf6cd3865768590263e767fe5e45fb3a9d70676c337f79aba576378272ddc14647ecd06fc26820fc1dec8cb52704aa6740582b7
+  metadata.gz: 108d33cf57b738ba69ccf960f503ab5ea44b296ba043716fb2e83e9fa5bebcaec9a488bc4a5ab64dad55c1f23434c2b71005a86389e9b26fd07b38372f96b6d4
+  data.tar.gz: 62afad1698415e0c80b85599da7aba1e19574ec571862f8d69c56d1fe718f8c65cae3e3be2293d8418ecc7dd09803b4d9908186e93f3062ccd85b363a5e7dde4

data/bin/wayback_machine_downloader

@@ -18,6 +18,10 @@ option_parser = OptionParser.new do |opts|
     options[:directory] = t
   end
 
+  opts.on("-s", "--all-timestamps", "Download all snapshots/timestamps for a given website") do |t|
+    options[:all_timestamps] = true
+  end
+  
   opts.on("-f", "--from TIMESTAMP", Integer, "Only files on or after timestamp supplied (ie. 20060716231334)") do |t|
     options[:from_timestamp] = t
   end
@@ -42,7 +46,7 @@ option_parser = OptionParser.new do |opts|
     options[:all] = true
   end
 
-  opts.on("-c", "--concurrency NUMBER", Integer, "Number of multiple files to dowload at a time", "Default is one file at a time (ie. 20)") do |t|
+  opts.on("-c", "--concurrency NUMBER", Integer, "Number of multiple files to download at a time", "Default is one file at a time (ie. 20)") do |t|
     options[:threads_count] = t
   end
 

data/lib/wayback_machine_downloader/archive_api.rb

@@ -1,28 +1,38 @@
+require 'json'
+require 'uri'
+
 module ArchiveAPI
 
   def get_raw_list_from_api url, page_index
-    request_url = "http://web.archive.org/cdx/search/xd?url="
-    request_url += url
-    request_url += parameters_for_api page_index
+    request_url = URI("https://web.archive.org/cdx/search/xd")
+    params = [["output", "json"], ["url", url]]
+    params += parameters_for_api page_index
+    request_url.query = URI.encode_www_form(params)
 
-    open(request_url).read
+    begin
+      json = JSON.parse(URI(request_url).open.read)
+      if (json[0] <=> ["timestamp","original"]) == 0
+        json.shift
+      end
+      json
+    rescue JSON::ParserError
+      []
+    end
   end
 
   def parameters_for_api page_index
-    parameters = "&fl=timestamp,original&collapse=digest&gzip=false"
-    if @all
-      parameters += ""
-    else
-      parameters += "&filter=statuscode:200"
+    parameters = [["fl", "timestamp,original"], ["collapse", "digest"], ["gzip", "false"]]
+    if !@all
+      parameters.push(["filter", "statuscode:200"])
     end
     if @from_timestamp and @from_timestamp != 0
-      parameters += "&from=" + @from_timestamp.to_s
+      parameters.push(["from", @from_timestamp.to_s])
     end
     if @to_timestamp and @to_timestamp != 0
-      parameters += "&to=" + @to_timestamp.to_s
+      parameters.push(["to", @to_timestamp.to_s])
     end
     if page_index
-      parameters += "&page=#{page_index}"
+      parameters.push(["page", page_index])
     end
     parameters
   end

data/lib/wayback_machine_downloader/tidy_bytes.rb

@@ -70,7 +70,7 @@ module TibyBytes
         if is_unused || is_restricted
           bytes[i] = tidy_byte(byte)
         elsif is_cont
-          # Not expecting contination byte? Clean up. Otherwise, now expect one less.
+          # Not expecting continuation byte? Clean up. Otherwise, now expect one less.
           conts_expected == 0 ? bytes[i] = tidy_byte(byte) : conts_expected -= 1
         else
           if conts_expected > 0

data/lib/wayback_machine_downloader.rb

@@ -14,9 +14,9 @@ class WaybackMachineDownloader
 
   include ArchiveAPI
 
-  VERSION = "2.1.1"
+  VERSION = "2.3.1"
 
-  attr_accessor :base_url, :exact_url, :directory,
+  attr_accessor :base_url, :exact_url, :directory, :all_timestamps,
     :from_timestamp, :to_timestamp, :only_filter, :exclude_filter, 
     :all, :maximum_pages, :threads_count
 
@@ -24,6 +24,7 @@ class WaybackMachineDownloader
     @base_url = params[:base_url]
     @exact_url = params[:exact_url]
     @directory = params[:directory]
+    @all_timestamps = params[:all_timestamps]
     @from_timestamp = params[:from_timestamp].to_i
     @to_timestamp = params[:to_timestamp].to_i
     @only_filter = params[:only_filter]
@@ -83,7 +84,7 @@ class WaybackMachineDownloader
     # Note: Passing a page index parameter allow us to get more snapshots,
     # but from a less fresh index
     print "Getting snapshot pages"
-    snapshot_list_to_consider = ""
+    snapshot_list_to_consider = []
     snapshot_list_to_consider += get_raw_list_from_api(@base_url, nil)
     print "."
     unless @exact_url
@@ -94,17 +95,15 @@ class WaybackMachineDownloader
         print "."
       end
     end
-    puts " found #{snapshot_list_to_consider.lines.count} snaphots to consider."
+    puts " found #{snapshot_list_to_consider.length} snaphots to consider."
     puts
     snapshot_list_to_consider
   end
 
   def get_file_list_curated
     file_list_curated = Hash.new
-    get_all_snapshots_to_consider.each_line do |line|
-      next unless line.include?('/')
-      file_timestamp = line[0..13].to_i
-      file_url = line[15..-2]
+    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 == ""
@@ -127,22 +126,61 @@ class WaybackMachineDownloader
     file_list_curated
   end
 
+  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?('/')
+      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 == ""
+      if file_id.nil?
+        puts "Malformed file url, 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)
+          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
+        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
+
+
   def get_file_list_by_timestamp
-    file_list_curated = get_file_list_curated
-    file_list_curated = file_list_curated.sort_by { |k,v| v[:timestamp] }.reverse
-    file_list_curated.map do |file_remote_info|
-      file_remote_info[1][:file_id] = file_remote_info[0]
-      file_remote_info[1]
+    if @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 { |k,v| v[:timestamp] }.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
 
   def list_files
     # retrieval produces its own output
+    @orig_stdout = $stdout
+    $stdout = $stderr
     files = get_file_list_by_timestamp
+    $stdout = @orig_stdout
     puts "["
-    files.each do |file|
+    files[0...-1].each do |file|
       puts file.to_json + ","
     end
+    puts files[-1].to_json
     puts "]"
   end
 
@@ -222,6 +260,7 @@ class WaybackMachineDownloader
       file_path = backup_path + file_path_elements[0..-1].join('/')
     end
     if Gem.win_platform?
+      dir_path = dir_path.gsub(/[:*?&=<>\\|]/) {|s| '%' + s.ord.to_s(16) }
       file_path = file_path.gsub(/[:*?&=<>\\|]/) {|s| '%' + s.ord.to_s(16) }
     end
     unless File.exist? file_path
@@ -229,7 +268,7 @@ class WaybackMachineDownloader
         structure_dir_path dir_path
         open(file_path, "wb") do |file|
           begin
-            open("http://web.archive.org/web/#{file_timestamp}id_/#{file_url}", "Accept-Encoding" => "plain") do |uri|
+            URI("https://web.archive.org/web/#{file_timestamp}id_/#{file_url}").open("Accept-Encoding" => "plain") do |uri|
               file.write(uri.read)
             end
           rescue OpenURI::HTTPError => e

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: wayback_machine_downloader
 version: !ruby/object:Gem::Version
-  version: 2.1.1
+  version: 2.3.1
 platform: ruby
 authors:
 - hartator
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2017-06-12 00:00:00.000000000 Z
+date: 2021-09-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rake
@@ -57,7 +57,7 @@ homepage: https://github.com/hartator/wayback-machine-downloader
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -72,9 +72,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.5.2
-signing_key: 
+rubygems_version: 3.1.4
+signing_key:
 specification_version: 4
 summary: Download an entire website from the Wayback Machine.
 test_files: []