pdf-dft-extractor | skill guide | OpenClaw Study

PDF DFT Extractor automates extraction of DFT molecular coordinates from PDFs (especially supplementary materials) and generates ready-to-run Gaussian.gjf…

PDF DFT Extractor automates extraction of DFT molecular coordinates from PDFs (especially supplementary materials) and generates ready-to-run Gaussian.gjf input files. It converts PDFs to structured Markdown via the MinerU API, automatically identifies coordinate blocks, and supports single-file and batch processing with a dedicated output folder per PDF. Accessible through a CLI or Python API, it provides configurable CPU, memory, method, solvent, charge, multiplicity, and Gaussian keywords, plus optional preservation of temporary files. The tool enforces correct Gaussian dispersion formatting (e.g., em=d3bj) and outputs per-paper structured files to eliminate manual transcription, accelerate computational setup, and improve reproducibility when collecting literature-derived geometries for DFT calculations.

This page belongs to the OpenClaw Skills learning hub with install guides, category navigation, and practical links.

简体中文 繁體中文 日本語 Español Português