wayback_machine_downloader_straw 2.3.8 → 2.3.10

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: df42d96c68c19fd39b6da3c9e9d51934197484ccb1ceb7a9387116622b0214a7
-  data.tar.gz: d6f04e3dc44c9f216b9d3dc631275fac5e48447ebd963a33818e82baf1ff79b3
+  metadata.gz: ef661bf573b09f79453cf6343d737c24715f343b6593cf313f2502ecd9a650cb
+  data.tar.gz: b80be4aaae7ab4ff695af6cc85273ac437fab1e6a68d3d8bdad67a9661be17e4
 SHA512:
-  metadata.gz: b9654877bb591082e1ef1c5dfdacff0bf887ed68f8ae1b2d995a99b87232523aa3350aede2d8cbb4045dbb15b380a1e93451004a45f881ad323615c0f66632c5
-  data.tar.gz: eb8753d3ceb689e9b8c3f3dbaeeac7c9dd818497f916882d5d3271f1901c099f8b7103e7b49bcef51d71aab86b2607174ac2eece768a092242b0d5e0dcec9b28
+  metadata.gz: 3dfb6477b142eebb45741e1b5a4552dd33feac34baa1eae5453baaa08a9a5be242ba46d4f1162e2dd2b68e8903e6de8402d6b6fa86128f312defac74f2e8da29
+  data.tar.gz: 39758aef4bda77babb81d479ef9f266e3fa328af163c7c3c053290796fda95ccb8ec8d3725a9dae5164b79debc6530919cd79df3f7421842f951b0ee6ef79e60

data/lib/wayback_machine_downloader/archive_api.rb

@@ -7,7 +7,8 @@ module ArchiveAPI
     # Automatically append /* if the URL doesn't contain a path after the domain
     # This is a workaround for an issue with the API and *some* domains.
     # See https://github.com/StrawberryMaster/wayback-machine-downloader/issues/6
-    if url && !url.match(/^https?:\/\/.*\//i)
+    # But don't do this when exact_url flag is set
+    if url && !url.match(/^https?:\/\/.*\//i) && !@exact_url
       url = "#{url}/*"
     end
 

data/lib/wayback_machine_downloader.rb

@@ -113,7 +113,7 @@ class WaybackMachineDownloader
 
   include ArchiveAPI
 
-  VERSION = "2.3.8"
+  VERSION = "2.3.10"
   DEFAULT_TIMEOUT = 30
   MAX_RETRIES = 3
   RETRY_DELAY = 2
@@ -131,7 +131,11 @@ class WaybackMachineDownloader
     validate_params(params)
     @base_url = params[:base_url]
     @exact_url = params[:exact_url]
-    @directory = params[:directory]
+    if params[:directory]
+      @directory = File.expand_path(params[:directory])
+    else
+      @directory = nil
+    end
     @all_timestamps = params[:all_timestamps]
     @from_timestamp = params[:from_timestamp].to_i
     @to_timestamp = params[:to_timestamp].to_i
@@ -165,13 +169,11 @@ class WaybackMachineDownloader
 
   def backup_path
     if @directory
-      if @directory[-1] == '/'
-        @directory
-      else
-        @directory + '/'
-      end
+      # because @directory is already an absolute path, we just ensure it exists
+      @directory
     else
-      'websites/' + backup_name + '/'
+      # ensure the default path is absolute and normalized
+      File.expand_path(File.join('websites', backup_name))
     end
   end
 
@@ -382,7 +384,7 @@ class WaybackMachineDownloader
       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 = 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]
@@ -638,21 +640,35 @@ class WaybackMachineDownloader
     file_url = file_remote_info[:file_url].encode(current_encoding)
     file_id = file_remote_info[:file_id]
     file_timestamp = file_remote_info[:timestamp]
-    file_path_elements = file_id.split('/')
+    
+    # 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 = backup_path
-      file_path = backup_path + 'index.html'
-    elsif file_url[-1] == '/' or not file_path_elements[-1].include? '.'
-      dir_path = backup_path + file_path_elements[0..-1].join('/')
-      file_path = backup_path + file_path_elements[0..-1].join('/') + '/index.html'
+      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
-      dir_path = backup_path + file_path_elements[0..-2].join('/')
-      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) }
+      # 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

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: wayback_machine_downloader_straw
 version: !ruby/object:Gem::Version
-  version: 2.3.8
+  version: 2.3.10
 platform: ruby
 authors:
 - strawberrymaster
 bindir: bin
 cert_chain: []
-date: 2025-06-05 00:00:00.000000000 Z
+date: 2025-06-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: concurrent-ruby