scholarly.py

from habanero import counts
from habanero import Crossref
import pdb
from fuzzywuzzy import fuzz

def get_citation_count(doi):
    try:
        cit = counts.citation_count(doi = doi)
        return str(cit)
    except Exception as e:
        # print(f"Error fetching data for DOI {doi}: {e}")
        return None
    
def get_doi_from_title(title):
    try:
        cr = Crossref()
        result = cr.works(query = title)
        for item in result['message']['items']:
            retrieved_title = item.get('title', [''])[0].lower()  # Convert retrieved title to lowercase
            similarity_score = fuzz.ratio(title.lower(), retrieved_title) / 100  # Calcola il punteggio di similarità
            # soglia di similarità desiderata (75%)
            similarity_threshold = 0.75
            # print(retrieved_title, similarity_score)
            if similarity_score >= similarity_threshold:
                # pdb.set_trace()
                return item.get('DOI', None)
             
    except Exception as e:
        return None