skills.rest
StianOby
StianObyCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

nbno

Download Norwegian Library items and convert them to searchable PDFs with OCR.

2|Updated May 8, 2026
Search Tags:#ocr#zotero#download#iiif#nb.no#nasjonalbiblioteket#bokhylla
One-click install
npx skills add https://github.com/StianOby/claude-legal-tools --skill nbno
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nbno
Source: https://github.com/StianOby/claude-legal-tools/tree/main/skills/nbno
Command: npx skills add https://github.com/StianOby/claude-legal-tools --skill nbno

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires nbno, playwright, ocrmypdf, pikepdf, Pillow, img2pdf, and includes scripts (resource) components.

What problem does it solve?

Researchers and legal professionals need to access Norwegian archival material from Nasjonalbiblioteket (nb.no), but the platform requires specific authentication for in-copyright content, uses IIIF APIs that silently downsample images, and produces output that is not immediately usable in reference managers like Zotero. This Skill automates the entire pipeline from ID resolution to searchable PDF delivery.

Core Features & Use Cases

  • Automated Download: Resolves URNs, canonical IDs, and nb.no item URLs to download books, newspapers, photos, journals, maps, and manuscripts via the IIIF API or the nbno CLI wrapper.
  • Authentication Handling: Supports open-content access, FEIDE/BankID/Vipps cookie capture via Playwright, and manual cookie files for Bokhylla in-copyright material.
  • Zotero Integration: Produces paired PDF and RDF files with full metadata, OCR text layers, and a direct web link attachment, ready for drag-and-drop import into Zotero.

Quick Start

Use the nbno skill to download the book identified by the URN URN:NBN:no-nb_digibok_2008051600041 as a searchable PDF and generate a Zotero-ready RDF file in your outputs directory.

Frequently Asked Questions about nbno

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
Do I need FEIDE authentication to download in-copyright material from nb.no?▼

Downloading in-copyright Bokhylla material from nb.no requires FEIDE, BankID, or Vipps authentication via Playwright cookie capture, or you can supply a manual cookie file to access restricted legal-deposit content.

What is the best way to automate IIIF manifest resolution for Norwegian archival material?▼

Yes, you can import nb.no books into Zotero because the process generates paired PDF and RDF files containing full bibliographic metadata, creator roles, and persistent web link attachments for drag-and-drop import.

Does the nb.no download pipeline handle newspapers and manuscripts or only digitized books?▼

Automating IIIF manifest resolution for Norwegian archival material involves resolving URNs and canonical IDs via the IIIF API or nbno CLI wrapper to fetch books, newspapers, and manuscripts without silent image downsampling.

Why does nb.no silently downsample images and how can I get full resolution?▼

The nb.no download pipeline handles newspapers, photos, journals, maps, and manuscripts in addition to digitized books, converting all fetched archival items into searchable PDFs with embedded OCR text layers.

How do I generate Zotero RDF files with bibliographic metadata for downloaded PDFs?▼

The nb.no IIIF API silently downsamples images, but using this Skill's pipeline resolves IIIF manifests directly to fetch full-resolution page images and batches page ranges to bypass downsampling limitations.

Related Skills

Explore More Legal & Compliance Skills→
DevMHOneDevMHOne

omni-webhooks

Register, list, test, and remove webhook endpoints with event subscriptions and retries.

Community
Intermediate
biomaps-infrabiomaps-infra

lib-pyzotero

Manage Zotero items, collections, tags, and attachments via the Web API v3.

Official
Intermediate
taracodlabstaracodlabs
779

ocr-and-documents

Extract readable text from PDFs, scanned images, and Word documents using Python libraries.

Official
Intermediate
flosrnflosrn

browser-download

Download files from authenticated web sessions using browser cookies with curl.

Community
Intermediate