skills.rest
tusosos
tusososCOMMUNITY
Explore all skills by this author →
GitHub

pdf-analyzer

Extract text, tables, and metadata from PDFs into JSON or CSV.

Updated Apr 3, 2026
Search Tags:#pdf#json#metadata#extraction#text#tables#scanned-pdfs
One-click install
npx skills add https://github.com/tusosos/manus-knowledge-base --skill pdf-analyzer-tusosos
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pdf-analyzer
Source: https://github.com/tusosos/manus-knowledge-base/tree/main/skills/pdf-analyzer
Command: npx skills add https://github.com/tusosos/manus-knowledge-base --skill pdf-analyzer-tusosos

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extract text, tables, and metadata from PDF files and convert them into usable, structured data formats, reducing manual copy-paste and reformatting.

Core Features & Use Cases

  • Text extraction: pull readable content from pages of a PDF.
  • Table and data extraction: detect and export tables to JSON or CSV, preserving structure.
  • Metadata capture: read title, author, creation date, and page count for indexing and archival.
  • Use Case: convert a batch of invoices into a clean JSON dataset for downstream accounting workflows.

Quick Start

Upload a PDF or provide a file path and ask to extract its text, tables, and metadata into JSON or CSV.

Frequently Asked Questions about pdf-analyzer

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

FAQPage Schema
How do I extract tables from a PDF and export them as JSON?▼

To extract tables from a PDF and export as JSON, you upload your file or provide a file path. The Skill detects tabular structures and preserves the layout, converting the extracted data into a clean JSON or CSV dataset.

Can I extract text from scanned PDFs that are image-based?▼

Yes, you can extract text from scanned PDFs. The Skill uses an optional OCR fallback mechanism to process image-based pages, ensuring readable content is pulled from scanned documents into structured formats.

What is the best way to capture PDF metadata like author and creation date?▼

The best way to capture PDF metadata is to let the Skill automatically read the document properties. It extracts the title, author, creation date, and page count for indexing and archival into structured data.

Does this tool work for multi-page PDF extraction?▼

Yes, this tool handles multi-page PDF extraction. It applies to both single and multi-page documents, pulling readable text, tables, and metadata across the entire file into structured JSON or CSV formats.

Do I need pdfplumber or PyMuPDF to extract PDF tables?▼

You need either pdfplumber or PyMuPDF to extract PDF tables. The Skill requires one of these libraries to parse document structures, while an optional OCR fallback handles image-based pages.

Why does my PDF table extraction return misaligned data?▼

PDF table extraction may return misaligned data if the document is scanned or image-based. In these cases, standard text parsing fails, requiring the OCR fallback to accurately detect structural boundaries and preserve table formatting.

Related Skills

Explore More Data & Analytics Skills→
mindmorassmindmorass
2

pdf-harvester

Extract text, tables, and metadata from PDFs for RAG pipelines.

Community
Advanced
Pans0020Pans0020

markdown-exporter

Convert Markdown content into DOCX, PPTX, XLSX, PDF, HTML, IPYNB, MD, CSV, JSON/JSONL, XML, and extracted code files.

Community
Advanced
junchenghuojunchenghuo
3

image-ocr

Extracts printed and handwritten text from images and PDFs using multiple OCR engines and preprocessing techniques.

Community
Advanced
yashs33244yashs33244
1

hackernews-frontpage

Scrapes the Hacker News front page into structured JSON with ordered stories and count.

Community
Basic