Chronicling America Batches API

openapi: 3.2.0
info:
  title: Chronicling America Batches 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: Batches
  description: Endpoints for retrieving digitization batch information.
paths:
  /batches.json:
    get:
      operationId: listBatches
      summary: List all digitization batches
      description: Retrieve a list of all digitization batches contributed to Chronicling America by participating institutions in the National Digital Newspaper Program. Each batch represents a set of newspaper pages submitted by a single institution.
      tags:
      - Batches
      responses:
        '200':
          description: List of all digitization batches
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BatchesListResponse'
  /batches/{batch_name}.json:
    get:
      operationId: getBatch
      summary: Get a specific digitization batch
      description: Retrieve metadata for a specific digitization batch including the contributing institution, ingestion date, number of pages, and links to included titles.
      tags:
      - Batches
      parameters:
      - name: batch_name
        in: path
        required: true
        description: Name of the batch (e.g., batch_dlc_jamaica_ver01).
        schema:
          type: string
        example: batch_dlc_jamaica_ver01
      responses:
        '200':
          description: Batch metadata
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/BatchDetail'
        '404':
          description: Batch not found
components:
  schemas:
    BatchSummary:
      type: object
      description: Summary record for a digitization batch.
      properties:
        name:
          type: string
          description: Name of the batch.
          example: batch_dlc_jamaica_ver01
        url:
          type: string
          description: URL to the batch JSON record.
        awardee:
          $ref: '#/components/schemas/Awardee'
        ingested:
          type: string
          description: Date and time the batch was ingested (ISO 8601).
          example: '2007-04-10T00:00:00+00:00'
        page_count:
          type: integer
          description: Number of pages in this batch.
    Awardee:
      type: object
      description: Institution awarded the NDNP grant that contributed this batch.
      properties:
        url:
          type: string
          description: URL to the awardee record.
        name:
          type: string
          description: Name of the contributing institution.
          example: Library of Congress
    BatchesListResponse:
      type: object
      description: List of all digitization batches.
      properties:
        batches:
          type: array
          description: Array of batch records.
          items:
            $ref: '#/components/schemas/BatchSummary'
    BatchDetail:
      type: object
      description: Detailed metadata for a digitization batch.
      properties:
        name:
          type: string
          description: Name of the batch.
          example: batch_dlc_jamaica_ver01
        url:
          type: string
          description: URL to this batch record.
        awardee:
          $ref: '#/components/schemas/Awardee'
        ingested:
          type: string
          description: Date and time the batch was ingested (ISO 8601).
          example: '2007-04-10T00:00:00+00:00'
        page_count:
          type: integer
          description: Total number of pages in this batch.
        lccns:
          type: array
          description: List of LCCNs (newspaper titles) included in this batch.
          items:
            type: string
externalDocs:
  description: Chronicling America API Documentation
  url: https://chroniclingamerica.loc.gov/about/api/