Extract a table from an image or screenshot into a spreadsheet
Turn a photo, screenshot, or scanned list into clean tab-separated rows you can paste straight into Excel or Google Sheets.
The prompt
Extract the data from the image I've attached into a spreadsheet-ready table.
What the image shows: [e.g. "a list of companies", "a receipt", "a printed price list", "a table in a slide"]
Columns I want: [e.g. "Name, Ticker, Exchange" or "keep the columns as shown"]
Formatting rules: [e.g. dates as YYYY-MM-DD, numbers without currency symbols, lowercase codes]
Extra columns to add (optional): [e.g. "a category for each item", "the country for each city" - information not shown in the image]
Rules:
- Copy text exactly as it appears. Do not correct spellings or guess at blurry characters - mark unreadable cells as [UNCLEAR].
- Keep one row per item, in the order shown.
- Split combined values into separate columns only if I asked.
- If I asked for extra columns with information that is not in the image, put them in a separate column and mark any you are not certain of with [CHECK]. Never present a guess as fact.
Return:
1. The table as tab-separated values inside a code block, with a header row, so it pastes into separate columns.
2. The same data as a Markdown table for a quick visual check.
3. A short list of cells marked [UNCLEAR] or [CHECK] so I can verify them against the original.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Data & Analysis prompts
What to fill in
- e.g. "Name, Ticker, Exchange" or "keep the columns as shown"
- UNCLEAR
- CHECK
How this prompt is built
This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.
Related prompts
- Speed up a slow Power BI or Tableau dashboardDiagnoses why a BI report loads slowly and gives a ranked list of fixes across data model, queries, calculations, and visuals.
- Explain a dataset or report in plain business languageExplains what a dataset or report contains, what each column or metric means, and what it shows, in words anyone can follow.
- Find what my dashboard is not telling meReviews a dashboard for blind spots, missing comparisons, vanity metrics, and misleading views, and suggests what to add.
- Flag impossible or suspicious values in my dataChecks your data against logic and business rules for impossible, placeholder, and implausible values, and gives reusable validation rules.