Chronicling America Pages API

openapi: 3.2.0
info:
  title: Chronicling America Batches Pages 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: Pages
  description: Endpoints for retrieving individual newspaper page metadata and content.
paths:
  /titles/{lccn}/issues/{date}/ed-{edition}/seq-{sequence}.json:
    get:
      operationId: getPage
      summary: Get a specific newspaper page
      description: Retrieve metadata for a specific page within a newspaper issue. Returns OCR text URL, image service URLs (IIIF), PDF download URL, JP2 image URL, and TIFF URL. Page sequence numbering starts at 1.
      tags:
      - Pages
      parameters:
      - name: lccn
        in: path
        required: true
        description: Library of Congress Control Number (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 within the issue (1-based).
        schema:
          type: integer
        example: 1
      responses:
        '200':
          description: Page metadata including image and OCR URLs
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/PageDetail'
        '404':
          description: Page not found
  /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:
      - Pages
      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
components:
  schemas:
    IssueSummary:
      type: object
      description: Summary of a single newspaper issue.
      properties:
        url:
          type: string
          description: URL to the issue JSON record.
        date_issued:
          type: string
          description: Date the issue was published (YYYY-MM-DD).
          example: '1900-01-01'
    PageDetail:
      type: object
      description: Detailed metadata for a single newspaper page.
      properties:
        url:
          type: string
          description: URL to this page record.
        sequence:
          type: integer
          description: Page sequence number within the issue (1-based).
          example: 1
        title:
          $ref: '#/components/schemas/TitleSummary'
        issue:
          $ref: '#/components/schemas/IssueSummary'
        edition:
          type: integer
          description: Edition number.
        section_label:
          type: string
          description: Section label for this page.
        edition_label:
          type: string
          description: Human-readable edition label.
        pdf:
          type: string
          description: URL to the PDF download for this page.
          example: https://chroniclingamerica.loc.gov/lccn/sn84026749/1900-01-01/ed-1/seq-1.pdf
        jp2:
          type: string
          description: URL to the JPEG 2000 image of this page.
          example: https://chroniclingamerica.loc.gov/lccn/sn84026749/1900-01-01/ed-1/seq-1.jp2
        tif:
          type: string
          description: URL to the TIFF image of this page.
        text:
          type: string
          description: URL to the plain text OCR for this page.
          example: https://chroniclingamerica.loc.gov/lccn/sn84026749/1900-01-01/ed-1/seq-1/ocr.txt
        ocr_eng:
          type: string
          description: URL to the word coordinate XML for English OCR.
    TitleSummary:
      type: object
      description: Summary record for a newspaper title.
      properties:
        lccn:
          type: string
          description: Library of Congress Control Number.
          example: sn84026749
        title:
          type: string
          description: Name of the newspaper.
          example: Chicago Tribune
        url:
          type: string
          description: URL to the full title JSON record.
          example: https://chroniclingamerica.loc.gov/lccn/sn84026749.json
        state:
          type: array
          items:
            type: string
          description: State(s) where the newspaper was published.
        county:
          type: array
          items:
            type: string
          description: County or counties of publication.
        city:
          type: array
          items:
            type: string
          description: City or cities of publication.
        start_year:
          type: string
          description: First year of publication.
          example: '1849'
        end_year:
          type: string
          description: Last year of publication (or "present" if ongoing).
          example: '1920'
externalDocs:
  description: Chronicling America API Documentation
  url: https://chroniclingamerica.loc.gov/about/api/