Chronicling America OCR API

openapi: 3.0.3
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/