Diffbot Extract API

openapi: 3.1.0
info:
  title: Diffbot Crawl Extract API
  description: Diffbot's automatic web data extraction APIs. Includes the Extract family (Analyze, Article, Product, Image, Job, Video, Discussion, Event, List, Custom), Knowledge Graph (DQL Search, Enhance, Bulk Enhance), Crawl, and Natural Language Processing endpoints. All endpoints are authenticated via a token query parameter.
  version: '1.0'
servers:
- url: https://api.diffbot.com
  description: Diffbot API
- url: https://kg.diffbot.com
  description: Diffbot Knowledge Graph
- url: https://nl.diffbot.com
  description: Diffbot Natural Language
security:
- tokenAuth: []
tags:
- name: Extract
paths:
  /v3/analyze:
    get:
      tags:
      - Extract
      summary: Analyze a page and extract structured data
      operationId: analyze
      parameters:
      - $ref: '#/components/parameters/Url'
      - $ref: '#/components/parameters/Token'
      responses:
        '200':
          description: Extracted data
  /v3/article:
    get:
      tags:
      - Extract
      summary: Extract article content
      operationId: article
      parameters:
      - $ref: '#/components/parameters/Url'
      - $ref: '#/components/parameters/Token'
      responses:
        '200':
          description: Article data
  /v3/product:
    get:
      tags:
      - Extract
      summary: Extract product details
      operationId: product
      parameters:
      - $ref: '#/components/parameters/Url'
      - $ref: '#/components/parameters/Token'
      responses:
        '200':
          description: Product data
  /v3/image:
    get:
      tags:
      - Extract
      summary: Extract image metadata
      operationId: image
      parameters:
      - $ref: '#/components/parameters/Url'
      - $ref: '#/components/parameters/Token'
      responses:
        '200':
          description: Image data
  /v3/discussion:
    get:
      tags:
      - Extract
      summary: Extract reviews and discussion content
      operationId: discussion
      parameters:
      - $ref: '#/components/parameters/Url'
      - $ref: '#/components/parameters/Token'
      responses:
        '200':
          description: Discussion data
  /v3/video:
    get:
      tags:
      - Extract
      summary: Extract video metadata
      operationId: video
      parameters:
      - $ref: '#/components/parameters/Url'
      - $ref: '#/components/parameters/Token'
      responses:
        '200':
          description: Video data
  /v3/event:
    get:
      tags:
      - Extract
      summary: Extract event details
      operationId: event
      parameters:
      - $ref: '#/components/parameters/Url'
      - $ref: '#/components/parameters/Token'
      responses:
        '200':
          description: Event data
  /v3/job:
    get:
      tags:
      - Extract
      summary: Extract job posting details
      operationId: job
      parameters:
      - $ref: '#/components/parameters/Url'
      - $ref: '#/components/parameters/Token'
      responses:
        '200':
          description: Job data
  /v3/list:
    get:
      tags:
      - Extract
      summary: Extract list items
      operationId: list
      parameters:
      - $ref: '#/components/parameters/Url'
      - $ref: '#/components/parameters/Token'
      responses:
        '200':
          description: List data
components:
  parameters:
    Token:
      name: token
      in: query
      required: true
      schema:
        type: string
    Url:
      name: url
      in: query
      required: true
      schema:
        type: string
        format: uri
  securitySchemes:
    tokenAuth:
      type: apiKey
      in: query
      name: token