A script to detect possibly non-DBLP entries in a BibTeX file

detect_non_dblp_bibtex.py

####################################################################################
# Name
#  detect_non_dblp_bibtex.py
# Description
#  This script reads a BibTeX file and detectes possibly non-DBLP entries.
#  More precisely, it checks each entry for the presence of a 'biburl' field.
#  If the 'biburl' field is missing or does not contain 'dblp', it considers the entry
#  as possibly non-DBLP and prints the citation key of that entry.
# Usage
#  python detect_non_dblp_bibtex.py /path/to/bibtex.bib
# Requirements
#  - bibtexparser: install by running `pip install bibtexparser`
# Author
#  Masaki Waga
# License
#  This script is released under the MIT License.
# Note
#  This script can be processed by pandoc with ScrDoc template (https://github.com/maswag/scrdoc).
####################################################################################

import sys
import bibtexparser

def bib_entries(filepath):
    with open(filepath, encoding='utf-8') as bibtex_file:
        bib_database = bibtexparser.load(bibtex_file)
    return bib_database.entries  # each entry is a dict

if __name__ == "__main__":
    # Get the target BibTeX file from command line arguments
    if len(sys.argv) < 2:
        print("Usage: python detect_non_dblp_bibtex.py /path/to/bibtex.bib")
        sys.exit(1)
    bibtex_file = sys.argv[1]
    
    for entry in bib_entries(bibtex_file):
        biburl = entry.get('biburl')
        # the citation key is stored under 'ID'
        key = entry.get('ID')
        if biburl is None or 'dblp' not in biburl:
            print(key)