Find duplicates in bibtex file based on publication title

find_duplicates_in_bib.py

import bibtexparser
from collections import defaultdict

# Replace 'yourfile.bib' with the path to your BibTeX file
bibtex_filename = 'root.bib'

# Load the BibTeX file
with open(bibtex_filename, encoding='utf-8') as bibtex_file:
    bib_database = bibtexparser.load(bibtex_file)

# Initialize a dictionary to map normalized titles to entry IDs
title_to_ids = defaultdict(list)

# Process each entry in the BibTeX database
for entry in bib_database.entries:
    title = entry.get('title', '').strip()
    entry_id = entry.get('ID', '').strip()

    # Normalize the title
    normalized_title = title.replace('{', '').replace('}', '').lower().strip()

    # Add the entry ID to the list for this normalized title
    if normalized_title:
        title_to_ids[normalized_title].append(entry_id)

# Identify and print duplicate titles
duplicates_found = False
for title, ids in title_to_ids.items():
    if len(ids) > 1:
        duplicates_found = True
        print(f'Duplicate title: "{title}"')
        print(f'Entry IDs: {", ".join(ids)}\n')

if not duplicates_found:
    print("No duplicate titles found.")