wayback_machine_downloader 2.2.1 → 2.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: d037bdcdc516a9366f9d6181d63e61970f3a2ec1
-  data.tar.gz: 03eef551fbb7be1d6dfb29f05c380e517b2870f8
+SHA256:
+  metadata.gz: 57cbbb04b38525f6dd9c1a8f4022ee28ce45c76d1d26acc90076a4b8b6014b44
+  data.tar.gz: 4128b3ab753e91bea93ddebdafba133091663617e0c247c022076a8c11dfa5c2
 SHA512:
-  metadata.gz: ee25c7e833907143a08d9b6438482d1c9bc76219eb62b4ac179ef770c323b60c3956bb7c1c1bd33ce0e7f5b3cda620fda4c06258837066762541b4404fd4d2cc
-  data.tar.gz: cffca8734ae0ee449b35aae26f77032cd27bd749bbc34e925a64ea51f52a8a55c9b7fe85c5a3c2a8787715fba15f5c4138a04d4499ab170a0404d4fb0c2624d2
+  metadata.gz: bb08b6f6e9fa930b025fbf0c783476bd965e364ef46ccd2fecc8e5d0954be062b67b801acf4d168556f7d90f1d5c836a16184e371a5e5d47da7e804278d893ab
+  data.tar.gz: e750e04ab4e1f795e061f0fe91581abb60baecc7d5427d9ec8e724f931d1afba207512731f350eee7c04ceacf12b4a90823e9b3c750e3799810944430279c330

data/bin/wayback_machine_downloader

@@ -46,7 +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.rb

@@ -14,7 +14,7 @@ class WaybackMachineDownloader
 
   include ArchiveAPI
 
-  VERSION = "2.2.1"
+  VERSION = "2.3.0"
 
   attr_accessor :base_url, :exact_url, :directory, :all_timestamps,
     :from_timestamp, :to_timestamp, :only_filter, :exclude_filter, 
@@ -84,7 +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
@@ -95,17 +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 == ""
@@ -130,10 +128,8 @@ class WaybackMachineDownloader
 
   def get_file_list_all_timestamps
     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_and_timestamp = [file_timestamp, file_id].join('/')
       file_id_and_timestamp = CGI::unescape file_id_and_timestamp 
@@ -176,11 +172,15 @@ class WaybackMachineDownloader
 
   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
 
@@ -268,7 +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.open("https://web.archive.org/web/#{file_timestamp}id_/#{file_url}", "Accept-Encoding" => "plain") do |uri|
               file.write(uri.read)
             end
           rescue OpenURI::HTTPError => e

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

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: wayback_machine_downloader
 version: !ruby/object:Gem::Version
-  version: 2.2.1
+  version: 2.3.0
 platform: ruby
 authors:
 - hartator
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2017-10-27 00:00:00.000000000 Z
+date: 2021-06-07 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: []