openapi: 3.0.2
info:
  title: Event Export API
  description: Export events as JSON.
  license:
    name: MIT
    url: https://opensource.org/licenses/MIT
  version: 1.0.0
  contact:
    url: https://mixpanel.com/get-support
servers:
  - $ref: ./common/export-api.yaml#/server
security:
  - ProjectSecret: []
tags:
  - name: Export
    description: Export events as JSON.
paths:
  /export:
    get:
      operationId: raw-event-export
      tags:
        - Export
      summary: Download Data
      description: >-
        Every data point sent to Mixpanel is stored as JSON in our data store.
        The raw export API allows you to download your event data as it is
        received and stored within Mixpanel, complete with all event properties
        (including distinct_id) and the exact timestamp the event was fired.

        The raw export API has a rate limit of 60 queries per hour, 3 queries per second, and a maximum of 100 concurrent queries. If you exceed the rate limit, a 429 error will be returned.
      parameters:
        - in: query
          name: project_id
          schema:
            type: integer
          description: >-
            Required if using service account to authenticate request.
        - in: query
          name: from_date
          schema:
            type: string
          description: >-
            The date in yyyy-mm-dd format to begin querying from. This date is inclusive and interpreted as UTC timezone for projects created after 1 January 2023 and current project timezone for projects created before 11 January 2023.
          required: true
        - in: query
          name: to_date
          schema:
            type: string
          description: >-
            The date in yyyy-mm-dd format to query to. This date is inclusive and interpreted as UTC timezone for projects created after 1 January 2023 and current project timezone for projects created before 11 January 2023.
          required: true
        - in: query
          name: limit
          schema:
            type: integer
          description: Use this parameter if you want to limit the max number of events to be returned. Value cannot be over 100000.
        - in: query
          name: event
          schema:
            type: string
          description: >-
            The event or events that you wish to get data for, encoded
            as a JSON array.
        - in: query
          name: where
          schema:
            type: string
          description: >-
            An expression to filter events by. More info on expression
            sequence structure can be found
            [here](ref:segmentation-expressions)
        - in: query
          name: time_in_ms
          schema:
            type: boolean
          description: >-
            Defaults to `false` which will export event timestamps with second-precision.
            
            Set to `true` to export event timestamps with millisecond-precision.
        - in: header
          name: Accept-Encoding
          description: If set to `gzip` and the response body is > 1400 bytes, the response will be compressed with gzip, and `Content-Encoding` will be set to `gzip`.
          schema:
            type: string
            enum:
              - "gzip"
      responses:
        "200":
          description: >-
            Success. The returned format is one event per line where each line is a valid JSON object, but the full return itself is JSONL.

          content:
            # We actually want this to be newline delimited json. More work is needed to figure out how to support it.
            # application/x-ndjson:
            # schema:
            #   type: string
            #   properties:
            #     event:
            #       type: string
            #       description: The name of the event
            #       example: Viewed report
            #       properties:
            #         type: object
            #         description: The properties of the event
            #         example:
            #           time: 1518393599
            #           distinct_id: test-email@mixpanel.com
            #           $browser: Chrome
            #           report_name: Funnels
            text/plain:
              schema:
                type: string
                example: |
                  {"event":"Signed up","properties":{"time":1602611311,"$insert_id":"hpuDqcvpltpCjBsebtxwadtEBDnFAdycabFb","mp_processing_time_ms":1602625711874}}
                  {"event":"Signed up","properties":{"time":1602787121,"$insert_id":"jajcebutltmvhbbholfhxtCcycwnBjDtndha","mp_processing_time_ms":1602801521561}}
                description: Newline delimited JSON ([JSONL](http://jsonlines.org))
  # TODO: Build "x-hidden: true" like pattern to hide endpoints
  # /export-upload:
  #   post:
  #     operationId: event-export-to-bucket
  #     tags:
  #       - Export
  #     summary: Upload Data to Bucket
  #     description: >-
  #       An alternative to `/export`. This endpoint allows you to specify where
  #       you would like the output to go, which can be especially helpful when
  #       you expect a lot of events to be returned.
  #     requestBody:
  #       content:
  #         application/x-www-form-urlencoded:
  #           examples:
  #             s3:
  #               summary: AWS S3
  #               value:
  #                 from_date: '2018-02-11'
  #                 to_date: '2018-02-11'
  #                 s3_bucket: mixpanel-events
  #                 s3_region: us-west-1
  #                 s3_prefix: /folder1/sub1/
  #                 where: 'properties["$os"]=="Linux"'
  #             gcs:
  #               summary: Google Cloud Storge
  #               value:
  #                 from_date: '2018-02-11'
  #                 to_date: '2018-02-11'
  #                 gcs_bucket: mixpanel-events
  #                 gcs_prefix: /folder1/sub1/
  #                 where: 'properties["$os"]=="Linux"'
  #           schema:
  #             oneOf:
  #               - $ref: '#/components/schemas/s3RequestProperties'
  #               - $ref: '#/components/schemas/gcsRequestProperties'
  #     responses:
  #       '200':
  #         description: Success.
  #         content:
  #           application/json:
  #             schema:
  #               type: object
  #               properties:
  #                 status:
  #                   type: string
  #                   example: ok
  #                 prefix:
  #                   type: string
  #                   example: folder1/sub1
components:
  securitySchemes:
    $ref: ./common/securitySchemes.yaml
  # schemas:
  #   s3RequestProperties:
  #     title: AWS S3
  #     required:
  #       - from_date
  #       - to_date
  #       - s3_bucket
  #       - s3_region
  #     properties:
  #       from_date:
  #         type: string
  #         description: >-
  #           The date in yyyy-mm-dd format from which to begin querying for the
  #           event from. This date is inclusive.
  #       to_date:
  #         type: string
  #         description: >-
  #           The date in yyyy-mm-dd format from which to stop querying for the
  #           event from. This date is inclusive.
  #       s3_bucket:
  #         type: string
  #         description: The name of your s3 bucket
  #       s3_region:
  #         type: string
  #         description: The region of your s3 bucket
  #       s3_prefix:
  #         type: string
  #         description: 'The string between a bucket name and an object name,'
  #       where:
  #         type: string
  #         description: >-
  #           An expression to filter events by. More info on expression sequence
  #           structure can be found
  #           [here](ref:segmentation-expressions)
  #   gcsRequestProperties:
  #     title: Google Cloud Storage
  #     required:
  #       - from_date
  #       - to_date
  #       - gcs_bucket
  #     properties:
  #       from_date:
  #         type: string
  #         description: >-
  #           The date in yyyy-mm-dd format from which to begin querying for the
  #           event from. This date is inclusive.
  #       to_date:
  #         type: string
  #         description: >-
  #           The date in yyyy-mm-dd format from which to stop querying for the
  #           event from. This date is inclusive.
  #       gcs_bucket:
  #         type: string
  #         description: The name of your GCS bucket
  #       gcs_prefix:
  #         type: string
  #         description: 'The string between a bucket name and an object name,'
  #       where:
  #         type: string
  #         description: >-
  #           An expression to filter events by. More info on expression sequence
  #           structure can be found
  #           [here](ref:segmentation-expressions)
x-explorer-enabled: true
x-proxy-enabled: true
x-samples-enabled: true
x-samples-languages:
  - curl
  - node
  - ruby
  - javascript
  - python