Created
July 11, 2025 13:20
-
-
Save hortongn/86bc6265fc58a0ab33569153162712a7 to your computer and use it in GitHub Desktop.
Export Scholar work information including count of files and file sizes
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| def get_file_size(file) | |
| @total_size = @total_size + file.file_size.first.to_i | |
| end | |
| def get_object(object_id) | |
| object = ActiveFedora::Base.find object_id | |
| if object.class == FileSet | |
| get_file_size(object) | |
| end | |
| end | |
| File.write('/tmp/export.csv', "\"Work Title\",\"PURL\",\"DOI\",\"File Count\",\"Size (GB)\"\n") | |
| total_size_by_type = {} | |
| work_types = [Dataset] | |
| work_types.each do |type| | |
| @total_size = 0 | |
| type.all.each do |work| | |
| @total_size = 0 | |
| @num_files = 0 | |
| work.ordered_member_ids.each do |object_id| | |
| get_object(object_id) | |
| @num_files = @num_files + 1 | |
| end | |
| @total_size = @total_size.to_f / 1000000000 | |
| collection = '' | |
| unless work.member_of_collections.first.nil? | |
| collection = work.member_of_collections.first.title.first | |
| end | |
| File.write('/tmp/export.csv', "\"#{work.title.first.to_s}\",\"https://scholar.uc.edu/show/#{work.id.to_s}\",\"#{work.doi.to_s}\",\"#{@num_files}\",\"#{@total_size.round(4)}\",\"#{collection}\"\n", mode: 'a') | |
| end | |
| total_size_by_type[type.to_s] = @total_size | |
| end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment