mirror of
https://codeberg.org/readeck/readeck.git
synced 2025-12-22 13:17:10 +00:00
Added documentation for the /api/cookbook/extract route
This commit is contained in:
Olivier Meunier
@@ -45,7 +45,7 @@ info:
|
||||
On this documentation, you can test every route.
|
||||
|
||||
If you don't provide an API token in [Authentication](#auth), you can still test all the routes
|
||||
but note that the given curl example only work with an API token.
|
||||
but note that the given curl examples only work with an API token.
|
||||
|
||||
|
||||
servers:
|
||||
@@ -69,9 +69,12 @@ tags:
|
||||
- name: bookmarks
|
||||
description: Bookmarks
|
||||
|
||||
- name: bookmarks-export
|
||||
- name: bookmark export
|
||||
description: Bookmark Export
|
||||
|
||||
- name: dev tools
|
||||
description: Routes used for testing or development
|
||||
|
||||
paths:
|
||||
/bookmarks:
|
||||
get:
|
||||
@@ -110,7 +113,7 @@ paths:
|
||||
- "bookmarks/routes.yaml#.withBookmark"
|
||||
|
||||
get:
|
||||
tags: [bookmarks-export]
|
||||
tags: [bookmark export]
|
||||
$merge:
|
||||
- "traits.yaml#.authenticated"
|
||||
- "bookmarks/routes.yaml#.article"
|
||||
@@ -120,7 +123,14 @@ paths:
|
||||
- "bookmarks/routes.yaml#.withBookmark"
|
||||
|
||||
get:
|
||||
tags: [bookmarks-export]
|
||||
tags: [bookmark export]
|
||||
$merge:
|
||||
- "traits.yaml#.authenticated"
|
||||
- "bookmarks/routes.yaml#.export"
|
||||
|
||||
/cookbook/extract:
|
||||
get:
|
||||
tags: [dev tools]
|
||||
$merge:
|
||||
- "traits.yaml#.authenticated"
|
||||
- "cookbook/routes.yaml#.extract"
|
||||
|
||||
143
docs/api/cookbook/routes.yaml
Normal file
143
docs/api/cookbook/routes.yaml
Normal file
@@ -0,0 +1,143 @@
|
||||
---
|
||||
# SPDX-FileCopyrightText: © 2023 Olivier Meunier <olivier@neokraft.net>
|
||||
#
|
||||
# SPDX-License-Identifier: AGPL-3.0-only
|
||||
|
||||
# GET /cookbook/extrack
|
||||
extract:
|
||||
summary: Extract Link
|
||||
description: |
|
||||
This route extracts a link and returns the extraction result.
|
||||
|
||||
You can pass an `Accept` header to the request, with one of the following values:
|
||||
|
||||
- `application/json` (default) returns a JSON response
|
||||
- `text/html` returns an HTML response with all the media included as base64 encoded
|
||||
URLs.
|
||||
|
||||
parameters:
|
||||
- name: url
|
||||
in: query
|
||||
required: true
|
||||
schema:
|
||||
type: string
|
||||
format: uri
|
||||
description: URL to extract
|
||||
|
||||
responses:
|
||||
"200":
|
||||
description: |
|
||||
Extraction result.
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
properties:
|
||||
url:
|
||||
type: string
|
||||
format: uri
|
||||
description: The extracted URL
|
||||
logs:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
description: Extraction log
|
||||
errors:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
description: Extraction errors, if any
|
||||
meta:
|
||||
type: object
|
||||
additionalProperties:
|
||||
type: array
|
||||
items:
|
||||
type: string
|
||||
description: |
|
||||
Contains the meta tags extracted from the page.
|
||||
properties:
|
||||
properties:
|
||||
json-ld:
|
||||
type: array
|
||||
items:
|
||||
type: object
|
||||
description: A list of JSON-LD documents retrieved during the extraction
|
||||
link:
|
||||
type: array
|
||||
items:
|
||||
type: object
|
||||
patternProperties:
|
||||
"^@.+":
|
||||
type: string
|
||||
description: Link attribute, always starting with `@`
|
||||
description: A list of all `link` tags retrieved during the extraction
|
||||
meta:
|
||||
type: array
|
||||
items:
|
||||
type: object
|
||||
patternProperties:
|
||||
"^@.+":
|
||||
type: string
|
||||
description: Meta attribute, always starting with `@`
|
||||
description: A list of all `meta` tags retrieved during the extraction
|
||||
domain:
|
||||
type: string
|
||||
format: hostname
|
||||
description: Page's domain name
|
||||
title:
|
||||
type: string
|
||||
description: Page's title
|
||||
authors:
|
||||
type: "[string]"
|
||||
description: Page's author list
|
||||
site:
|
||||
type: string
|
||||
format: hostname
|
||||
description: Page's site
|
||||
site_name:
|
||||
type: string
|
||||
description: Page's site name
|
||||
lang:
|
||||
type: string
|
||||
description: Language Code
|
||||
text_direction:
|
||||
type: string
|
||||
enum: [rtl, ltr]
|
||||
description: |
|
||||
Direction of the article's text. It can be empty when it's unknown.
|
||||
date:
|
||||
type: [string]
|
||||
format: date-time
|
||||
nullable: true
|
||||
description: Publication date. Can be `null` when unknown.
|
||||
document_type:
|
||||
type: string
|
||||
description: |
|
||||
The detected document type. The value is usualy `article`, `photo` or `video`
|
||||
but can vary, based on the extraction process.
|
||||
description:
|
||||
type: string
|
||||
description: |
|
||||
Page's short description, when it exists. It's always an unformatted text.
|
||||
html:
|
||||
type: string
|
||||
description: |
|
||||
The HTML content after processing.
|
||||
embed:
|
||||
type: string
|
||||
description: |
|
||||
The oembed HTML fragment, when it exists. It usualy contains an iframe when
|
||||
extracting videos.
|
||||
images:
|
||||
properties:
|
||||
additionalProperties:
|
||||
properties:
|
||||
size:
|
||||
type: "[integer]"
|
||||
description: The image size in pixels
|
||||
encoded:
|
||||
type: string
|
||||
description: The base64 URI encoded image
|
||||
|
||||
text/html:
|
||||
schema:
|
||||
type: string
|
||||
@@ -1,4 +1,8 @@
|
||||
---
|
||||
# SPDX-FileCopyrightText: © 2023 Olivier Meunier <olivier@neokraft.net>
|
||||
#
|
||||
# SPDX-License-Identifier: AGPL-3.0-only
|
||||
|
||||
schemas:
|
||||
message:
|
||||
properties:
|
||||
|
||||
Reference in New Issue
Block a user