skills.rest
xjtulyc
xjtulycCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

digital-archives

Harvest historical documents and metadata from digital archive platforms into tabular outputs.

33|6|Updated Mar 17, 2026
Search Tags:#api integration#historical research#corpus building#oai-pmh#digital archives#metadata harvesting#ocr extraction
One-click install
npx skills add https://github.com/xjtulyc/awesome-rosetta-skills --skill digital-archives
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: digital-archives
Source: https://github.com/xjtulyc/awesome-rosetta-skills/tree/main/skills/13-history/digital-archives
Command: npx skills add https://github.com/xjtulyc/awesome-rosetta-skills --skill digital-archives

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, pandas, beautifulsoup4, lxml, tqdm, internetarchive.

What problem does it solve?

This Skill solves the problem of manually searching and gathering historical documents scattered across different digital archive platforms.

Core Features & Use Cases

  • Multi-archive access: Query and retrieve records from Europeana, Chronicling America, Internet Archive, HathiTrust, DPLA, and generic OAI-PMH providers for cross-source research.
  • Bulk harvesting + corpus building: Normalize metadata into analysis-ready tables and optionally download OCR text (e.g., Chronicling America) to support large-scale historical corpus construction.
  • Key security & automation: Reads archive API keys strictly from environment variables (never hardcoded) while using consistent request patterns, pagination, and output structuring.

Quick Start

Use the digital-archives skill to search Chronicling America for WWI pages, download OCR text, and export a structured corpus dataset.

Frequently Asked Questions about digital-archives

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

FAQPage Schema
How do I harvest historical documents from multiple digital archives for research corpus building?▼

You can harvest historical documents by querying Europeana, Chronicling America, Internet Archive, HathiTrust, DPLA, and OAI-PMH endpoints using paginated REST requests, then normalize the metadata into tabular outputs for analysis.

Can I download OCR text from Chronicling America newspaper pages in bulk?▼

Yes, bulk downloading and OCR extraction for Chronicling America newspaper pages is supported, allowing you to retrieve full-text OCR data to construct a large-scale historical research corpus.

Do I need API keys to access HathiTrust and DPLA metadata via OAI-PMH?▼

You need API keys for certain platforms, which must be provided strictly through environment variables rather than hardcoded, ensuring secure access when harvesting metadata via OAI-PMH and REST endpoints.

What is the best way to normalize metadata across different digital archive platforms?▼

Cross-archive normalization is achieved by parsing harvested metadata from diverse platforms into consistent, analysis-ready tables using Python dependencies like pandas and beautifulsoup4.

Does this Skill support full-text search across Europeana and Internet Archive?▼

Yes, full-text search and structured metadata retrieval are supported across major platforms including Europeana and Internet Archive, enabling targeted querying before bulk harvesting and corpus construction.

Related Skills

Explore More Education & Research Skills→
gruckiongruckion

skill-creator

Create and package Claude Skills with SKILL.md scaffolds and ZIP archives.

Community
Intermediate
iOfficeAIiOfficeAI
31.8k

xlsx

Create, edit, and analyze Excel spreadsheets with pandas and openpyxl.

Official
Advanced
Gimpy666Gimpy666
1

scraped_docs

Convert Tribot JavaDoc HTML pages into per-class Markdown files and a consolidated reference.

Community
Intermediate
SimHackerSimHacker
49

honest-forget

Compress and archive content with metadata pointers for traceable recall.

Community
Intermediate