abstract-api/openapi/abstract-api-web-scraping.yaml at main · api-evangelist/abstract-api · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
openapi: 3.0.3
info:
  title: Abstract API - Web Scraping API
  description: Extract data from any website by providing the target URL. Handles JavaScript rendering and returns the full HTML content of any web page.
  version: 1.0.0
  contact:
    url: https://www.abstractapi.com/
  x-generated-from: documentation
servers:
  - url: https://scrape.abstractapi.com/v1
    description: Web Scraping API v1
security:
  - apiKey: []
tags:
  - name: Web Scraping
    description: Web content extraction operations
paths:
  /:
    get:
      operationId: scrapeWebPage
      summary: Abstract API Scrape Web Page
      description: Extract the full HTML content of any website URL, with support for JavaScript-rendered pages.
      tags:
        - Web Scraping
      parameters:
        - name: api_key
          in: query
          required: true
          description: Your unique API key for the Web Scraping API.
          schema:
            type: string
          example: abc123def456
        - name: url
          in: query
          required: true
          description: The URL of the webpage to scrape.
          schema:
            type: string
            format: uri
          example: https://www.example.com
        - name: render_js
          in: query
          required: false
          description: Whether to render JavaScript before returning HTML. Defaults to false.
          schema:
            type: boolean
          example: false
      responses:
        '200':
          description: Scraped HTML content
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/WebScrapingResponse'
              examples:
                scrapeWebPage200Example:
                  summary: Default scrapeWebPage 200 response
                  x-microcks-default: true
                  value:
                    body: '<html><head><title>Example Domain</title></head><body>...</body></html>'
                    url: https://www.example.com
                    status_code: 200
        '400':
          description: Bad request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
components:
  securitySchemes:
    apiKey:
      type: apiKey
      in: query
      name: api_key
  schemas:
    WebScrapingResponse:
      type: object
      description: Web scraping result
      properties:
        body:
          type: string
          description: Full HTML content of the page
          example: '<html><head><title>Example Domain</title></head><body>...</body></html>'
        url:
          type: string
          format: uri
          description: Final URL after redirects
          example: https://www.example.com
        status_code:
          type: integer
          description: HTTP status code of the scraped page
          example: 200
    ErrorResponse:
      type: object
      properties:
        message:
          type: string
          example: The provided API key is invalid
        error:
          type: string
          example: invalid_api_key