Research software supporting the publication “Leveraging Large Language Models to Classify and Inspect Defects in Reinforced Autoclaved Aerated Concrete (RAAC)”

1292 18 7104 3 39446 document 7104 UnpaywallPDFDownloader_Package.zip application/zip cd5fb7686f915b8b26eb54c6d79157c1 MD5 6183 2025-05-20 22:04:55 http://edata.bham.ac.uk/1292/1/UnpaywallPDFDownloader_Package.zip 1292 1 1 application/zip archive public cc_by_4

UnpaywallPDFDownloader_Package.zip

full_archive archive 654 disk0/00/00/12/92 2025-05-29 12:54:16 2025-05-29 14:21:09 2025-05-29 12:54:16 data_collection show duplicate_title_1300 duplicate_title Duplicate title to <a href="http://edata.bham.ac.uk/view/creators/Liu=3ALixu=3A=3A.html"><span class="person_name">Liu, Lixu</span></a> (2025). <a href="http://edata.bham.ac.uk/cgi/users/home?screen=EPrint::View&eprintid=1300"><xhtml:em xmlns:xhtml="http://www.w3.org/1999/xhtml">Research software supporting the publication “Leveraging Large Language Models to Classify and Inspect Defects in Reinforced Autoclaved Aerated Concrete (RAAC)”.</xhtml:em></a> University of Birmingham. DataSet. <a href="https://doi.org/10.25500/edata.bham.00001300" target="_blank">https://doi.org/10.25500/edata.bham.00001300</a>. 2025-06-03 01:30:06 discovered 1 Liu Lixu l.liu.9@bham.ac.uk; lixu@verdemetrix.com 0009-0008-8011-496X Research software supporting the publication “Leveraging Large Language Models to Classify and Inspect Defects in Reinforced Autoclaved Aerated Concrete (RAAC)” 10col_ephy Python, PDF Downloader, Unpaywall API, Open Access, Research Tools, DOI, Academic Software, Scholarly Communication, Python, Automation The script requires the user to specify their own email address for Unpaywall API access and to adjust file paths for CSV input and download output. It is intended for research use only and should be run with care to avoid excessive requests to external servers. The tool does not circumvent paywalls and only downloads content legally available via Unpaywall. Audio notification may not work in all server environments. Source code reviewed on 2025-05-20. The script contains no personal or sensitive data and complies with the Unpaywall API usage policy. Repository link included for version tracking. This dataset contains a Python-based tool to automate the download of open access full-text PDFs using the Unpaywall API. It accepts a CSV of DOIs and retrieves available PDFs into a structured directory. The project includes source code, a requirements file, and documentation. It was developed to support open science workflows by simplifying access to freely available scholarly publications. 2025-05-29 published University of Birmingham https://doi.org/10.25500/edata.bham.00001292 Software research-data@contacts.bham.ac.uk School of Engineering, Department of Civil Engineering other Research England Imfuna Ltd C-DICE Industrial Secondment en yes yes yes TRUE Liu Lixu l.liu.9@bham.ac.uk; lixu@verdemetrix.com UnpaywallPDFDownloader web https://github.com/lixuliu/UnpaywallPDFDownloader.git IsIdenticalTo The script was developed using Python 3.10 and tested in a local environment. Dependencies were managed using pip and listed in requirements.txt. The code reads DOIs from a CSV file, queries the Unpaywall API, and downloads open-access PDFs to a local directory. Logging and error handling were implemented to track failed downloads, which are saved separately in rest_articles.csv. A notification sound was added to indicate completion using librosa and sounddevice. en