Ignore urls with particularly long file name #4

This commit is contained in:
hartator 2015-08-21 20:43:31 -05:00
parent 919210fe64
commit 47ff4bed13

View File

@ -80,17 +80,21 @@ class WaybackMachineDownloader
end
unless File.exists? file_path
structure_dir_path dir_path
open(file_path, "wb") do |file|
begin
open("http://web.archive.org/web/#{timestamp}id_/#{file_url}") do |uri|
file.write(uri.read)
begin
open(file_path, "wb") do |file|
begin
open("http://web.archive.org/web/#{timestamp}id_/#{file_url}") do |uri|
file.write(uri.read)
end
rescue OpenURI::HTTPError => e
puts "#{file_url} # #{e}"
file.write(e.io.read)
rescue StandardError => e
puts "#{file_url} # #{e}"
end
rescue OpenURI::HTTPError => e
puts "#{file_url} # #{e}"
file.write(e.io.read)
rescue StandardError => e
puts "#{file_url} # #{e}"
end
rescue Errno::ENAMETOOLONG => e
puts "#{file_url} # #{e}"
end
puts "#{file_url} -> #{file_path} (#{count}/#{file_list_curated.size})"
else