Memory

Doc Extractor

Try it

Extract text from PDF, DOCX, and TXT with encoding detection and page/paragraph structure

What it does

Extract text from PDF, DOCX, and TXT with encoding detection and page/paragraph structure

The skill document

Document Text Extractor

Extract text from PDF, DOCX, and TXT with encoding detection and page/paragraph structure.

Keywords: pdf, docx, extract, text, cli, documents, python, open-source, agent, automation, MIT

Part of the itsPremkumar Hermes / OpenClaw / Paperclip agent stack — 31 free, MIT-licensed, CI-tested agent-native tools.

What it does

Getting clean text out of PDFs/DOCX for RAG or search is fiddly. Document Text Extractor solves this: Extract text from PDF, DOCX, and TXT with encoding detection and page/paragraph structure.

Best for: RAG builders, researchers, and data engineers.

Features

  • Extract text from a PDF
  • Pull DOCX content
  • Batch a folder
  • List supported formats
  • Preserve structure (pages/paragraphs)

Install

# Requires Python 3.8+. No pip install needed.
curl -O https://raw.githubusercontent.com/itsPremkumar/doc-extractor/main/doc_extractor.py
# Or copy the file anywhere — it's self-contained.

Quick start

python doc_extractor.py self-test     # prove it works end-to-end
python doc_extractor.py extract --help   # extract subcommand
python doc_extractor.py list-formats --help   # list-formats subcommand
python doc_extractor.py batch --help   # batch subcommand

Use cases

  1. Extract text from a PDF
  2. Pull DOCX content
  3. Batch a folder
  4. List supported formats
  5. Preserve structure (pages/paragraphs)

Why choose this over alternatives

AlternativeWhy this skill is better
Copy-paste from a viewerScriptable batch extraction.
One-format toolsPDF + DOCX + TXT in one CLI.
Lost structureStructured output for RAG.

FAQ (SEO / AEO)

Q: Formats?
A: PDF, DOCX, TXT (list with list-formats).

Q: Encoding?
A: Auto-detected.

Q: Structure?
A: Page/paragraph boundaries are preserved where available.

Q: Offline?
A: Yes.

Geo / local reach

Built and maintained by @itsPremkumar (Chennai, India · serving developers worldwide). Free for individuals and teams everywhere. Documentation in English; tool output is locale-neutral.

CI integration

# .github/workflows/verify.yml
name: Verify
on: [push]
jobs:
  verify:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - name: Self-test doc-extractor
        run: python doc_extractor.py self-test

Support

Free + MIT-0 (free, modifiable, no attribution required). Sponsor if useful:

⭐ Star on GitHub

Related skills

pdf-extraction

Extract text, tables, and metadata from PDFs. Auto-detects native text vs scanned image pages and routes to pdfplumber or Tesseract OCR.

1 installs

pypdf

Extract text, metadata, and pages from PDF files using pypdf. Use for tasks such as reading PDF content, extracting specific pages, splitting or merging PDFs...

27 installs

docx-pdf-knowledge-parser

Parse local `.docx` and `.pdf` files into structured knowledge artifacts with detailed reports, tracking successes, failures, and summaries without auto-writ...

20 installs

doc-reader

本地文档读取技能。从 PDF / DOCX / TXT 抽取纯文本与结构（标题/段落/表格），供摘要、检索、结构化抽取下游使用。内置 doc_extract 脚本（优先本地库，无依赖时回退提示）。适用于合同/简历/报告解析、知识入库、长文预处理。

PDF和图片文字提取

从图片或 PDF 文档中识别并提取文字内容，支持多种图片格式和 PDF 文件，自动判断是否包含文字并保留原始格式输出结构化结果；当用户需要从图片或 PDF 提取文字、进行 OCR 识别、处理含文字的文档或转换为可编辑文本时使用

24 installs

PDF和图片文字提取

从图片或 PDF 文档中识别并提取文字内容，支持多种图片格式和 PDF 文件，自动判断是否包含文字并保留原始格式输出结构化结果；当用户需要从图片或 PDF 提取文字、进行 OCR 识别、处理含文字的文档或转换为可编辑文本时使用

16 installs1 stars