bohrium-pdf-parser

Extract text, tables, charts, formulas, and molecules from PDF documents.

11|8|Updated Mar 30, 2026

Search Tags:#data extraction #api #text extraction #pdf parsing #bohrium

Ready to run

npx skills add https://github.com/dptech-corp/bohrium-skills --skill bohrium-pdf-parser

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: bohrium-pdf-parser
Source: https://github.com/dptech-corp/bohrium-skills/tree/main/zh/bohrium-pdf-parser
Command: npx skills add https://github.com/dptech-corp/bohrium-skills --skill bohrium-pdf-parser

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) components.

What problem does it solve?

This Skill addresses the challenge of manually extracting text, tables, charts, formulas, and molecules from PDF documents, offering an efficient solution to automate these processes.

Core Features & Use Cases

PDF Parsing: Extract text, tables, charts, formulas, and molecules from PDFs using Bohrium's Uni-Parser.
URL or File Upload: Submit PDFs via URL or file upload for processing.
Async or Sync: Supports both asynchronous and synchronous parsing methods.
Use Case: For a researcher looking to analyze data extracted from research papers or scientific articles.

Quick Start

Upload the PDF you wish to parse by providing the URL or the file, and let the skill process the document for you.

Frequently Asked Questions about bohrium-pdf-parser

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

FAQPage Schema

How do I extract text and tables from PDF documents?▼

To extract text and tables from PDF documents, you can use this Skill to parse structured content via URL or file upload. It leverages Bohrium's Uni-Parser API to automate the extraction of text, tables, charts, formulas, and molecules.

Can I parse PDFs asynchronously or do I need to wait for synchronous processing?▼

You can parse PDFs using either asynchronous or synchronous methods. This flexibility allows you to submit documents via URL or file upload and choose the processing mode that best fits your workflow and latency requirements.

What do I need to authenticate and start extracting data from PDFs?▼

To authenticate and start extracting data from PDFs, you need a valid API key for the Bohrium open API. Once configured, you can submit your PDF documents for parsing directly.

Does this PDF parsing method support extracting molecules and formulas from research papers?▼

Yes, this PDF parsing method supports extracting molecules, formulas, and charts from research papers. It is specifically designed to automate the extraction of essential scientific data from PDF documents.

What is the best way to automate PDF text extraction for scientific articles?▼

The best way to automate PDF text extraction for scientific articles is by submitting the document URL or file to this Skill. It processes the PDF and returns extracted text, tables, and structured content efficiently.

Are there limitations when using asynchronous PDF parsing for large documents?▼

While the Skill supports asynchronous PDF parsing to handle large documents without blocking, specific file size limitations are not detailed. It requires the requests library and a valid API key for successful operation.