Chronicling America

Chronicling America OCR API

Endpoints for retrieving OCR text from digitized newspaper pages.

Documentation GitHub OpenAPI

Operations 1

GET /titles/{lccn}/issues/{date}/ed-{edition}/seq-{sequence}/ocr.txt Get OCR text for a newspaper page #

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this

find_apisBrowse and filter every API in the catalog.
get_api_artifactsOne API's artifacts, grouped by type.
get_openapiThe primary OpenAPI for this API.
find_similar_apisAPIs that look like this one.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This API

curl "https://apis.io/api/v1/apis/chroniclingamerica-ocr-api"

All apis

curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

openapi: 3.2.0
info:
  title: Chronicling America Batches OCR API
  description: Chronicling America is a Library of Congress initiative providing free public access to a searchable database of historic American newspaper pages from 1770 to 1963. The platform hosts over 20 million digitized newspaper pages from hundreds of US newspapers contributed by institutions in the National Digital Newspaper Program (NDNP). The API exposes search, title, issue, batch, and OCR text endpoints with no authentication required, returning responses in JSON and Atom feed formats.
  version: 1.0.0
  contact:
    name: Library of Congress
    url: https://www.loc.gov/about/contact-us/
  termsOfService: https://www.loc.gov/legal/
  license:
    name: Public Domain
    url: https://www.loc.gov/legal/
servers:
- url: https://chroniclingamerica.loc.gov
  description: Chronicling America production server
tags:
- name: OCR
  description: Endpoints for retrieving OCR text from digitized newspaper pages.
paths:
  /titles/{lccn}/issues/{date}/ed-{edition}/seq-{sequence}/ocr.txt:
    get:
      operationId: getPageOcrText
      summary: Get OCR text for a newspaper page
      description: Retrieve the full plain-text OCR (Optical Character Recognition) content for a specific newspaper page. The text is extracted from digitized images and may contain recognition errors.
      tags:
      - OCR
      parameters:
      - name: lccn
        in: path
        required: true
        description: LCCN for the newspaper title.
        schema:
          type: string
        example: sn84026749
      - name: date
        in: path
        required: true
        description: Publication date in YYYY-MM-DD format.
        schema:
          type: string
          format: date
        example: '1900-01-01'
      - name: edition
        in: path
        required: true
        description: Edition number.
        schema:
          type: integer
        example: 1
      - name: sequence
        in: path
        required: true
        description: Page sequence number.
        schema:
          type: integer
        example: 1
      responses:
        '200':
          description: Plain text OCR content
          content:
            text/plain:
              schema:
                type: string
        '404':
          description: Page not found
externalDocs:
  description: Chronicling America API Documentation
  url: https://chroniclingamerica.loc.gov/about/api/