extract_html Leave feedback

extract_html opens a document for editing: it converts the whole document — or one worksheet (worksheet), one slide (slide), or a PDF page range (pages) — into an HTML file in the output folder, keeping fonts, styles, tables and images. The agent edits that file, then calls save_from_html. Example prompt: “Open the Q3 worksheet of budget.xlsx for editing.”

Tool description (as the AI agent sees it):

Opens a document for editing: converts it — or one worksheet, one slide, or a PDF page range — into editable HTML and saves the .html file to storage, keeping fonts, styles, tables and images. Edit that file, then call save_from_html to turn it back into DOCX, XLSX, PPTX, PDF or another format. For a simple find-and-replace use replace_text instead. Supports DOCX, DOC, RTF, ODT, XLSX, XLS, ODS, CSV, PPTX, PPT, ODP, PDF, TXT, HTML, XML, Markdown, EPUB, MOBI, EML and more. Do NOT pre-check whether files exist — just pass the filename the user provided; a missing file returns the list of available files. By default the HTML is self-contained (images, CSS and fonts embedded); set embedResources=false to get .html plus a _resources folder. Returns the saved path (‘Saved to: …’), which part was extracted (e.g. ‘worksheet 2 of 3’), and a plain-text preview of the content. On failure isError is set and the text starts with ‘HTML extraction failed for’; a file that cannot be found returns the list of available files instead.

{
  "name": "extract_html",
  "arguments": {
    "file": {
      "filePath": "budget.xlsx"
    },
    "worksheet": 2
  }
}

Plain text — captured from server 26.10.0:

Evaluation mode: outputs start with an evaluation banner, saved workbooks gain
an extra worksheet, and only the first 2 PDF pages, worksheets and slides can
be edited. Set GROUPDOCS_LICENSE_PATH, or the metered keys, to remove these
limits.

Extracted worksheet 2 of 3 of 'budget.xlsx' as editable HTML
Saved to: …/budget_worksheet2.html

Next: edit the saved .html and call save_from_html to write it back as DOCX,
XLSX, PPTX, PDF or another format.

Preview (plain text):
Created with evaluation version of GroupDocs.Editor © Aspose Pty Ltd 2001-2026.
All Rights Reserved. Cost centre Planned (EUR) Owner Hosting 57600 IT Support
14400 IT Travel 9000 Sales Training 6000 HR

(Wrapped for width.) The HTML file is named after the part: <name>_worksheet2.html, <name>_slide2.html, <name>_pages1-2.html, or <name>.html for a whole document. embedResources (default true) keeps images, CSS and fonts inside the one file; pagination: true keeps page boundaries for Word and PDF.

In evaluation mode the server refuses a worksheet or slide past the second, and says why:

HTML extraction failed for 'budget.xlsx': Evaluation mode edits only the first
2 visible worksheets of a workbook; worksheet 3 is beyond them. Set
GROUPDOCS_LICENSE_PATH, or the metered keys, to edit every worksheet.

A PDF extraction holds at most two pages per call in evaluation mode: pages: "1-3" returned pages 1 and 2 and stopped at the first line of page 3, with no error beyond the evaluation line; pages: "3" on its own extracted page 3.

• “Open the Q3 worksheet of budget.xlsx for editing.”
• “Give me slide 2 of the review deck as HTML.”
• “Turn pages 1-2 of travel-policy.pdf into something I can edit.”

See it used end-to-end: Edit one worksheet or slide and put it back.