PDF.co Find & Search API

openapi: 3.0.1
info:
  title: PDF.co Barcodes Find & Search API
  description: 'PDF.co Web API — programmatic PDF and document automation: AI invoice parsing, document parsing, PDF conversion (to/from PDF, Excel, CSV, JSON, XML, HTML, images), OCR, merging, splitting, compression, barcodes, e-signature workflows, and more. Authenticated via the x-api-key header.'
  version: '1.0'
  contact:
    name: PDF.co Support
    url: https://support.pdf.co/en
    email: support@pdf.co
  license:
    name: Proprietary
    url: https://pdf.co/terms
  termsOfService: https://pdf.co/terms
servers:
- url: https://api.pdf.co
security:
- ApiKeyAuth: []
tags:
- name: Find & Search
paths:
  /v1/pdf/find:
    post:
      tags:
      - Find & Search
      x-mint:
        href: /api-tester/pdf-find/basic
      operationId: post_v1_pdf_find
      requestBody:
        content:
          application/json:
            schema:
              required:
              - searchstring
              - url
              type: object
              properties:
                url:
                  allOf:
                  - $ref: '#/components/schemas/url'
                  default: pdfco-test-files.s3.us-west-2.amazonaws.compdf-to-text/sample.pdf
                file:
                  $ref: '#/components/schemas/file'
                searchstring:
                  allOf:
                  - $ref: '#/components/schemas/searchstring'
                  default: Invoice Date \d+/\d+/\d+
                regexsearch:
                  allOf:
                  - $ref: '#/components/schemas/regexsearch'
                  default: true
                wordmatchingmode:
                  type: string
                casesensitive:
                  $ref: '#/components/schemas/casesensitive'
                pages:
                  $ref: '#/components/schemas/pages0'
                  default: 0-
                name:
                  allOf:
                  - $ref: '#/components/schemas/name'
                  default: output
                inline:
                  allOf:
                  - $ref: '#/components/schemas/inline'
                  default: true
                async:
                  allOf:
                  - $ref: '#/components/schemas/async'
                  default: false
                password:
                  $ref: '#/components/schemas/password'
                timeout:
                  $ref: '#/components/schemas/timeout'
                expiration:
                  $ref: '#/components/schemas/expiration'
                profiles:
                  $ref: '#/components/schemas/profiles'
                httpusername:
                  $ref: '#/components/schemas/httpusername'
                httppassword:
                  $ref: '#/components/schemas/httppassword'
              additionalProperties: false
        required: false
      responses:
        '200':
          $ref: '#/components/responses/Success'
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '402':
          $ref: '#/components/responses/NotEnoughCredits'
        '403':
          $ref: '#/components/responses/Forbidden'
        '404':
          $ref: '#/components/responses/NotFound'
        '408':
          $ref: '#/components/responses/Timeout'
        '429':
          $ref: '#/components/responses/TooManyRequests'
        '441':
          $ref: '#/components/responses/InvalidPassword'
        '442':
          $ref: '#/components/responses/DamagedDocument'
        '443':
          $ref: '#/components/responses/PermissionsError'
        '444':
          $ref: '#/components/responses/ProfilesParsingError'
        '445':
          $ref: '#/components/responses/TimeoutError'
        '446':
          $ref: '#/components/responses/MissingFiles'
        '447':
          $ref: '#/components/responses/InvalidTemplate'
        '448':
          $ref: '#/components/responses/InvalidUrlOrHtml'
        '449':
          $ref: '#/components/responses/InvalidIndexRange'
        '450':
          $ref: '#/components/responses/InvalidPageRange'
        '452':
          $ref: '#/components/responses/InvalidUrl'
        '454':
          $ref: '#/components/responses/InvalidParameters'
        '500':
          $ref: '#/components/responses/InternalServerError'
      x-codegen-request-body-name: body
      summary: PDF Find Text
      description: Find text in PDF and get coordinates. Supports regular expressions.
  /v1/pdf/find/table:
    post:
      tags:
      - Find & Search
      x-mint:
        href: /api-tester/pdf-find/table
      operationId: post_v1_pdf_find_table
      requestBody:
        content:
          application/json:
            schema:
              type: object
              properties:
                url:
                  allOf:
                  - $ref: '#/components/schemas/url'
                  default: pdfco-test-files.s3.us-west-2.amazonaws.compdf-to-text/sample.pdf
                pages:
                  $ref: '#/components/schemas/pages0'
                inline:
                  allOf:
                  - $ref: '#/components/schemas/inline'
                  default: true
                async:
                  allOf:
                  - $ref: '#/components/schemas/async'
                  default: false
                password:
                  $ref: '#/components/schemas/password'
                expiration:
                  $ref: '#/components/schemas/expiration'
                file:
                  $ref: '#/components/schemas/file'
                name:
                  $ref: '#/components/schemas/name'
                timeout:
                  $ref: '#/components/schemas/timeout'
                profiles:
                  allOf:
                  - $ref: '#/components/schemas/profiles'
                  default: '{ ''Mode'': ''Legacy'', ''ColumnDetectionMode'': ''BorderedTables'', ''DetectionMinNumberOfRows'': 1, ''DetectionMinNumberOfColumns'': 1, ''DetectionMaxNumberOfInvalidSubsequentRowsAllowed'': 0, ''DetectionMinNumberOfLineBreaksBetweenTables'': 0, ''EnhanceTableBorders'': false }'
                httpusername:
                  $ref: '#/components/schemas/httpusername'
                httppassword:
                  $ref: '#/components/schemas/httppassword'
              additionalProperties: false
              required:
              - url
        required: false
      responses:
        '200':
          $ref: '#/components/responses/Success'
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '402':
          $ref: '#/components/responses/NotEnoughCredits'
        '403':
          $ref: '#/components/responses/Forbidden'
        '404':
          $ref: '#/components/responses/NotFound'
        '408':
          $ref: '#/components/responses/Timeout'
        '429':
          $ref: '#/components/responses/TooManyRequests'
        '441':
          $ref: '#/components/responses/InvalidPassword'
        '442':
          $ref: '#/components/responses/DamagedDocument'
        '443':
          $ref: '#/components/responses/PermissionsError'
        '444':
          $ref: '#/components/responses/ProfilesParsingError'
        '445':
          $ref: '#/components/responses/TimeoutError'
        '446':
          $ref: '#/components/responses/MissingFiles'
        '447':
          $ref: '#/components/responses/InvalidTemplate'
        '448':
          $ref: '#/components/responses/InvalidUrlOrHtml'
        '449':
          $ref: '#/components/responses/InvalidIndexRange'
        '450':
          $ref: '#/components/responses/InvalidPageRange'
        '452':
          $ref: '#/components/responses/InvalidUrl'
        '454':
          $ref: '#/components/responses/InvalidParameters'
        '500':
          $ref: '#/components/responses/InternalServerError'
      x-codegen-request-body-name: body
      summary: Find Text in Table with AI
      description: AI powered document analysis can scan your document for tables and return the array of tables on pages with coordinates and information about columns detected in these tables.
  /v1/pdf/makesearchable:
    post:
      tags:
      - Find & Search
      x-mint:
        href: /api-tester/pdf-change-text-searchable/searchable
      summary: Make Text Searchable
      operationId: post_v1_pdf_makesearchable
      requestBody:
        content:
          application/json:
            schema:
              type: object
              properties:
                file:
                  $ref: '#/components/schemas/file'
                url:
                  allOf:
                  - $ref: '#/components/schemas/url'
                  default: https://pdfco-test-files.s3.us-west-2.amazonaws.com/image-to-pdf/image2.jpg
                lang:
                  allOf:
                  - $ref: '#/components/schemas/lang'
                  default: eng
                pages:
                  $ref: '#/components/schemas/pages0'
                name:
                  allOf:
                  - $ref: '#/components/schemas/name'
                  default: result.pdf
                async:
                  allOf:
                  - $ref: '#/components/schemas/async'
                  default: false
                password:
                  $ref: '#/components/schemas/password'
                expiration:
                  $ref: '#/components/schemas/expiration'
                rect:
                  $ref: '#/components/schemas/rect'
                timeout:
                  $ref: '#/components/schemas/timeout'
                profiles:
                  $ref: '#/components/schemas/profiles'
                httpusername:
                  $ref: '#/components/schemas/httpusername'
                httppassword:
                  $ref: '#/components/schemas/httppassword'
              additionalProperties: false
              required:
              - url
        required: false
      responses:
        '200':
          $ref: '#/components/responses/Success'
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '402':
          $ref: '#/components/responses/NotEnoughCredits'
        '403':
          $ref: '#/components/responses/Forbidden'
        '404':
          $ref: '#/components/responses/NotFound'
        '408':
          $ref: '#/components/responses/Timeout'
        '429':
          $ref: '#/components/responses/TooManyRequests'
        '441':
          $ref: '#/components/responses/InvalidPassword'
        '442':
          $ref: '#/components/responses/DamagedDocument'
        '443':
          $ref: '#/components/responses/PermissionsError'
        '444':
          $ref: '#/components/responses/ProfilesParsingError'
        '445':
          $ref: '#/components/responses/TimeoutError'
        '446':
          $ref: '#/components/responses/MissingFiles'
        '447':
          $ref: '#/components/responses/InvalidTemplate'
        '448':
          $ref: '#/components/responses/InvalidUrlOrHtml'
        '449':
          $ref: '#/components/responses/InvalidIndexRange'
        '450':
          $ref: '#/components/responses/InvalidPageRange'
        '452':
          $ref: '#/components/responses/InvalidUrl'
        '454':
          $ref: '#/components/responses/InvalidParameters'
        '500':
          $ref: '#/components/responses/InternalServerError'
      x-codegen-request-body-name: body
      description: This method converts scanned PDF documents (where pages are fully or partially made from scanned images) or image files into a text-searchable PDF. It runs OCR and adds an invisible text layer on top of your document that can be used for text search, text indexing, etc.
  /v1/pdf/makeunsearchable:
    post:
      tags:
      - Find & Search
      x-mint:
        href: /api-tester/pdf-change-text-searchable/unsearchable
      operationId: post_v1_pdf_makeunsearchable
      requestBody:
        content:
          application/json:
            schema:
              type: object
              properties:
                file:
                  $ref: '#/components/schemas/file'
                url:
                  allOf:
                  - $ref: '#/components/schemas/url'
                  default: pdfco-test-files.s3.us-west-2.amazonaws.compdf-to-text/sample.pdf
                pages:
                  $ref: '#/components/schemas/pages0'
                name:
                  allOf:
                  - $ref: '#/components/schemas/name'
                  default: result.pdf
                async:
                  allOf:
                  - $ref: '#/components/schemas/async'
                  default: false
                password:
                  $ref: '#/components/schemas/password'
                timeout:
                  $ref: '#/components/schemas/timeout'
                expiration:
                  $ref: '#/components/schemas/expiration'
                profiles:
                  $ref: '#/components/schemas/profiles'
                httpusername:
                  $ref: '#/components/schemas/httpusername'
                httppassword:
                  $ref: '#/components/schemas/httppassword'
              additionalProperties: false
              required:
              - url
        required: false
      responses:
        '200':
          $ref: '#/components/responses/Success'
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '402':
          $ref: '#/components/responses/NotEnoughCredits'
        '403':
          $ref: '#/components/responses/Forbidden'
        '404':
          $ref: '#/components/responses/NotFound'
        '408':
          $ref: '#/components/responses/Timeout'
        '429':
          $ref: '#/components/responses/TooManyRequests'
        '441':
          $ref: '#/components/responses/InvalidPassword'
        '442':
          $ref: '#/components/responses/DamagedDocument'
        '443':
          $ref: '#/components/responses/PermissionsError'
        '444':
          $ref: '#/components/responses/ProfilesParsingError'
        '445':
          $ref: '#/components/responses/TimeoutError'
        '446':
          $ref: '#/components/responses/MissingFiles'
        '447':
          $ref: '#/components/responses/InvalidTemplate'
        '448':
          $ref: '#/components/responses/InvalidUrlOrHtml'
        '449':
          $ref: '#/components/responses/InvalidIndexRange'
        '450':
          $ref: '#/components/responses/InvalidPageRange'
        '452':
          $ref: '#/components/responses/InvalidUrl'
        '454':
          $ref: '#/components/responses/InvalidParameters'
        '500':
          $ref: '#/components/responses/InternalServerError'
      x-codegen-request-body-name: body
      summary: Make Text Unsearchable
      description: This method converts PDF files into a "text unsearchable" version by converting your PDF into a "scanned" PDF file which is effectively a flat image.
components:
  responses:
    Forbidden:
      description: Access forbidden for input URL.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 403
              message:
                type: string
                example: Access forbidden for input URL.
    InvalidUrlOrHtml:
      description: Invalid URL or HTML. Ensure the provided URL is valid and accessible.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 448
              message:
                type: string
                example: Invalid URL or HTML. Ensure the provided URL is valid and accessible.
    InvalidTemplate:
      description: Invalid template.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 447
              message:
                type: string
                example: Invalid template.
    InvalidPageRange:
      description: Invalid page range specified.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 450
              message:
                type: string
                example: Invalid page range specified.
    DamagedDocument:
      description: Input document is damaged or of incorrect type.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 442
              message:
                type: string
                example: Input document is damaged or of incorrect type.
    Timeout:
      description: The server timed out waiting for the request.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 408
              message:
                type: string
                example: The server timed out waiting for the request.
    InvalidIndexRange:
      description: Invalid index range. Page index is out of range. Use `/pdf/info` to get page count. First page is `0`.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 449
              message:
                type: string
                example: Invalid index range. Page index is out of range.
    TooManyRequests:
      description: Too many requests in a given time period.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 429
              message:
                type: string
                example: Too many requests in a given time period.
    ProfilesParsingError:
      description: Profiles parsing error. Please ensure that the configuration is supported. See `/profiles` samples.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 444
              message:
                type: string
                example: Profiles parsing error. Please ensure that the configuration is supported.
    MissingFiles:
      description: Some files required for conversion are missing.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 446
              message:
                type: string
                example: Some files required for conversion are missing.
    NotFound:
      description: The requested resource could not be found.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 404
              message:
                type: string
                example: The requested resource could not be found.
    Unauthorized:
      description: Unauthorized. Authentication is required and has failed or has not yet been provided.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 401
              message:
                type: string
                example: Unauthorized. Authentication is required and has failed or has not yet been provided.
    PermissionsError:
      description: 'Permissions. The operation is prohibited by document security settings. You can turn off this check by setting the `profiles` param to `{CheckPermissions: false}`. Important: only use this if you are the owner or have legal permission.'
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 443
              message:
                type: string
                example: Permissions. The operation is prohibited by document security settings.
    Success:
      description: Success.
      content:
        application/json:
          schema:
            type: object
            properties:
              status:
                type: string
                example: success
                description: Status of the API response.
              message:
                type: string
                example: Success
                description: Descriptive message for the response status.
              url:
                type: string
                format: uri
                example: https://pdf-temp-files.s3.us-west-2.amazonaws.com/output.pdf
                description: URL to the output file.
              jobId:
                type: string
                example: 6YSZD3U872ZYYFEDMQCQSGEEO8YSF5WA
                description: Unique identifier for the job.
              credits:
                type: integer
                example: 2
                description: Credits used for this operation.
              remainingCredits:
                type: integer
                example: 1480582
                description: Credits remaining after this operation.
              duration:
                type: integer
                example: 33
                description: Time taken to complete the request, in milliseconds.
    BadRequest:
      description: Bad request. Typically due to bad input parameters or unreachable input URLs (e.g., access restrictions like login or password).
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 400
              message:
                type: string
                example: Bad request. Typically due to bad input parameters or unreachable input URLs (e.g., access restrictions like login or password).
    InvalidParameters:
      description: Invalid parameters.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 454
              message:
                type: string
                example: Invalid parameters.
    InternalServerError:
      description: Something went wrong. Please try again or contact support.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 500
              message:
                type: string
                example: Something went wrong. Please try again or contact support.
    InvalidUrl:
      description: Invalid URL.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 452
              message:
                type: string
                example: Invalid URL.
    TimeoutError:
      description: Timeout error. For large documents, use asynchronous mode (`async=true`) and check status via `/job/check`. For many-page files, use the `pages` parameter.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 445
              message:
                type: string
                example: Timeout error. For large documents, use asynchronous mode (async=true) and check status via /job/check.
    InvalidPassword:
      description: Invalid Password. Password protected document.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 441
              message:
                type: string
                example: Invalid Password. Password protected document.
    NotEnoughCredits:
      description: Not enough credits.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 402
              message:
                type: string
                example: Not enough credits.
  schemas:
    url:
      type: string
      format: uri
      description: URL to the source file [`url` attribute](/api-reference/url-input-and-request-limits).
    name:
      type: string
      description: File name for generated output.
    timeout:
      type: number
      description: Timeout for output links in seconds
      readOnly: true
    inline:
      default: false
      type: boolean
      description: Set to true to return results inside the response. Otherwise, the endpoint will return a URL to the output file generated.
    rect:
      type: string
      format: '{x} {y} {width} {height}'
      description: Defines coordinates for extraction. Use[PDF Edit Add Helper](https://app.pdf.co/pdf-edit-add-helper) to get or measure PDF coordinates. The format is `{x} {y} {width} {height}`.
      example: 10 20 300 400
    async:
      type: boolean
      default: false
      description: Set `async` to `true` for long processes to run in the background, API will then return a `jobId` which you can use with the [Background Job Check endpoint](/api-reference/job-check). Also see [Webhooks & Callbacks](/api-reference/webhooks)
    httppassword:
      type: string
      description: HTTP auth password if required to access source URL.
    lang:
      type: string
      description: 'Set the language for OCR (text from image) to use for scanned PDF, PNG, and JPG documents input when extracting text. see [Language Support](/api-reference/language-support). You can also use 2 languages simultaneously like this: `eng+deu` (any combination).'
      pattern: ^[a-z]{3}(\+[a-z]{3})*$
      default: eng
      example: eng+deu
    password:
      type: string
      description: Password for the PDF file.
    searchstring:
      type: string
      description: The string to search.
    file:
      type: string
      format: path to a local file
      description: The path to the local file to be uploaded.
      readOnly: true
    casesensitive:
      type: boolean
      default: true
      description: Set to `false` to don't use case-sensitive search.
    profiles:
      type: string
      description: Profiles are used configure extra options for specific API endpoints and may be unique to an API. For more information, see [Profiles](/api-reference/profiles) and the documentation of each endpoint for profiles specific to it.
    regexsearch:
      type: boolean
      default: false
      description: Set to true to enable regular expression search for the `searchString(s)` parameter.
    pages0:
      type: string
      description: 'Page indices/ranges (0-based). Items are comma-separated. Each item is one of: N (e.g., 0), N-M (e.g., 3-7), N- (open-ended, e.g., 10-), or !N (reverse index; !0 is last page, !1 is second-to-last). Whitespace is allowed. If not specified, the default configuration processes all pages.'
      pattern: ^\s*(?:!?\d+\s*-\s*!?\d+|!?\d+\s*-\s*|!?\d+)\s*(?:,\s*(?:!?\d+\s*-\s*!?\d+|!?\d+\s*-\s*|!?\d+)\s*)*$
      example: 0,2,5-10, !0, !5-!2
    httpusername:
      type: string
      description: HTTP auth user name if required to access source URL.
    expiration:
      type: number
      default: 60
      description: Sets the expiration time for the output link, in minutes. After this period, generated output file(s) are automatically deleted from [PDF.co Temporary Files Storage](/api-reference/file-upload/overview). The maximum allowed duration depends on your subscription plan. For permanent storage of input files (e.g., reusable images, PDF templates, documents), use `PDF.co Built‑In Files Storage`.
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: x-api-key
x-original-swagger-version: '2.0'