Skill 014

PPTX Data Extraction

Overview

Data embedded in PowerPoint presentations can provide valuable insights and facilitate analysis. This skill covers methods for extracting tables, charts, and other data elements from .pptx files.

Extracting Tables

To extract tables from a PowerPoint slide, use the following method:

from pptx import Presentation

# Load the presentation
prs = Presentation('path-to-file.pptx')

# Extract data from tables
for slide in prs.slides:
    for shape in slide.shapes:
        if shape.has_table:
            table = shape.table
            for row in range(len(table.rows)):
                for col in range(len(table.columns)):
                    cell = table.cell(row, col)
                    print(cell.text)

Extracting Charts

Charts can also be extracted for further data analysis. The following example demonstrates how to get chart data:

for slide in prs.slides:
    for shape in slide.shapes:
        if shape.has_chart:
            chart = shape.chart
            data = chart.plots[0].chart_data
            print(data)

Conclusion

The ability to extract data from PowerPoint presentations can enhance your analytical capabilities and enable better decision-making based on visual data representations.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: legendtkl
• Source: legendtkl/agentic-skill-router
• License: MIT
• Homepage: https://legendtkl.github.io/agentic-skill-router/

Install and usage instructions live in the source repository linked above.