termux-pdf-analysis

Extract text, tables, and chart data from local PDFs on Android Termux.

1|Updated Jul 22, 2026
One-click install
npx skills add https://github.com/IceHeartGitH/Hermes-Agent-Android-Termux --skill termux-pdf-analysis-iceheartgith
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: termux-pdf-analysis
Source: https://github.com/IceHeartGitH/Hermes-Agent-Android-Termux/tree/main/custom-skills/productivity/termux-pdf-analysis
Command: npx skills add https://github.com/IceHeartGitH/Hermes-Agent-Android-Termux --skill termux-pdf-analysis-iceheartgith

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pypdfium2, pdfplumber, pytesseract, and includes references (resource) components.

What problem does it solve? Reading and analyzing PDF documents on an Android phone is difficult, especially when key data lives in charts, scanned pages, or complex tables. This Skill provides a complete Termux-based workflow to extract grounded values from local PDFs without needing a laptop or desktop tools. ## Core Features & Use Cases - Text and Table Extraction: Uses poppler tools (pdfinfo, pdftotext, pdftoppm) plus Python libraries (pypdf, pypdfium2, pdfplumber) to pull text, metadata, and tables from PDFs stored in Android shared storage. - Chart Rendering and OCR: Renders chart-heavy pages to PNG for visual analysis and runs Tesseract OCR on scanned or image-only PDFs when text extraction fails. - PageSpeed and CrUX Reports: Includes a dedicated pattern for analyzing PageSpeed Insights and CrUX Vis PDFs, extracting performance scores, Core Web Vitals metrics, and trend interpretations with correct rolling-window reasoning. - Use Case: A user downloads a CrUX Vis PDF to their phone and asks when site performance started degrading. The Skill locates the file in Downloads, renders the chart pages, reads the trend visually, and reports the first deterioration period while noting CrUX's 28-day rolling window caveat. ## Quick Start Analyze the PDF file in my Downloads folder and extract its text, tables, and chart values with a grounded report.

Frequently Asked Questions about termux-pdf-analysis

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract text from a PDF in Termux on Android?▼

Install poppler with pkg install poppler, then run pdftotext -layout on the PDF to extract text while preserving layout. If poppler is unavailable, use the pypdf Python library to iterate pages and call extract_text on each one.

How to analyze PDF charts that have no text layer?▼

Render the chart pages to PNG images using pdftoppm -png -r 180 or pypdfium2's page.render method, then inspect the images visually. For exact values, query a structured source like the CrUX History API instead of estimating from charts.

What tools extract tables from PDF files in Python?▼

pdfplumber extracts tables by detecting cell boundaries and returns them as structured lists per page. It works alongside pdftotext for plain text and pypdf for metadata and page splitting.

Can I OCR scanned PDFs on Android Termux?▼

Yes, install tesseract and imagemagick via pkg, plus pytesseract via pip, then render pages to images and OCR them. For Bulgarian documents, verify the Tesseract language data is installed before expecting accurate results.

Why does CrUX PDF data not match a specific deploy date?▼

CrUX is a 28-day rolling dataset, so each visible date marks the end of a collection period, not an exact event date. A deterioration visible in one period may have started anytime inside that window, so confirm causes with deployment and server logs.

When should I avoid heavy PDF tools like marker or docling on Termux?▼

Avoid heavyweight OCR and document-understanding stacks until the light poppler and pypdf path has failed. Tools like marker, docling, and unstructured have large dependencies that may exceed phone storage and memory limits.