diff --git a/lib/wayback_machine_downloader.rb b/lib/wayback_machine_downloader.rb index bdc721f..c8fe3e2 100644 --- a/lib/wayback_machine_downloader.rb +++ b/lib/wayback_machine_downloader.rb @@ -78,11 +78,11 @@ class WaybackMachineDownloader file_list_curated = Hash.new [index_file_list_raw, all_file_list_raw].each do |file| file.each_line do |line| - line = line.tidy_bytes.split(' ') - file_timestamp = line[0].to_i - file_url = line[1] + file_timestamp = line[0..13].to_i + file_url = line[15..-2] file_id = file_url.split('/')[3..-1].join('/') file_id = CGI::unescape file_id + file_id = file_id.tidy_bytes unless file_id == "" if file_id.nil? puts "Malformed file url, ignoring: #{file_url}" else