Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 10 additions & 1 deletion lib/wayback_machine_downloader.rb
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,8 @@
require 'fileutils'
require 'cgi'
require 'json'
require 'zlib'
require 'stringio'
require_relative 'wayback_machine_downloader/tidy_bytes'
require_relative 'wayback_machine_downloader/to_regex'
require_relative 'wayback_machine_downloader/archive_api'
Expand Down Expand Up @@ -269,7 +271,14 @@ def download_file file_remote_info
open(file_path, "wb") do |file|
begin
URI("https://web.archive.org/web/#{file_timestamp}id_/#{file_url}").open("Accept-Encoding" => "plain") do |uri|
file.write(uri.read)
content = uri.read

if uri.content_encoding.include? 'gzip'
gz = Zlib::GzipReader.new(StringIO.new(content))
content = gz.read
end

file.write(content)
end
rescue OpenURI::HTTPError => e
puts "#{file_url} # #{e}"
Expand Down