{"id":81000,"library":"docsplit","title":"Docsplit","description":"A command-line utility and Ruby library for splitting documents into text, images, PDFs, and metadata.","status":"active","version":"0.7.6","language":"ruby","source_language":null,"source_url":"https://github.com/documentcloud/docsplit","tags":["document","pdf","text-extraction","cli"],"install":[{"cmd":"gem install docsplit","lang":"bash","label":"gem install"},{"cmd":"# Gemfile\ngem 'docsplit', '~> 0.7.6'","lang":"ruby","label":"Gemfile"}],"dependencies":[],"imports":[{"symbol":"Docsplit","correct":"require 'docsplit'"}],"quickstart":{"code":"require 'docsplit'\nDocsplit.extract_text('document.pdf')","lang":"ruby","description":"Extract text from a PDF document."},"warnings":[],"env_vars":null,"search_vec":"'cli':24 'command':4 'command-lin':3 'docsplit':1 'document':12,19 'extract':23 'imag':15 'librari':9 'line':5 'metadata':18 'pdf':20 'pdfs':16 'rubi':8 'split':11 'text':14,22 'text-extract':21 'util':6","created_at":"2026-06-18T05:41:18.143046+00:00","updated_at":"2026-06-18T05:41:18.143046+00:00","problems":[],"ecosystem":"rubygems","meta_description":null,"install_score":null,"quickstart_score":null,"quickstart_tag":null,"pypi_latest":null,"cli_name":null,"cli_version":null,"type":"library","homepage":"http://documentcloud.github.com/docsplit/","github":"https://github.com/documentcloud/docsplit","docs":"http://www.rubydoc.info/gems/docsplit/","changelog":null,"pypi":null,"npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"categories":["utility","cli"],"base_url":null,"auth_type":null,"provenance":{"verified_status":null,"verified_at":null,"last_verified":"2026-06-18","next_check":"2026-12-15","install_tag":null}}