问用于匹配学术论文in的Python

EN

import pandas as pd
from scholarly import scholarly

AuthorList = ['Zoe Pikramenou', 'James H. R. Tucker', 'Alison Rodger', 'Timothy Dafforn']
frames = []

for Author in AuthorList:
    search_query = scholarly.search_author(Author)
    author = next(search_query).fill()
    # creating DataFrame with authors
    df = pd.DataFrame([x.__dict__ for x in author.publications])
    df['author'] = Author
    frames.append(df.copy())

# joining all author DataFrames
df = pd.concat(frames, axis=0)

# taking bib dict into separate columns
df[['title', 'cites', 'year']] = pd.DataFrame(df.bib.to_list())

# counting unique authors attached to each title
n_authors = df.groupby('title').author.nunique()
# locating the unique titles for all publications with n_authors >= 2
output = n_authors[n_authors >= 2].index

Index(['1, 1′-Homodisubstituted ferrocenes containing adenine and thymine nucleobases: synthesis, electrochemistry, and formation of H-bonded arrays',
       '722: Iron chelation by biopolymers for an anti-cancer therapy; binding up the'ferrotoxicity'in the colon',
       'A Luminescent One-Dimensional Copper (I) Polymer',
       'A Unidirectional Energy Transfer Cascade Process in a Ruthenium Junction Self-Assembled by r-and-Cyclodextrins',
       'A Zinc(II)-Cyclen Complex Attached to an Anthraquinone Moiety that Acts as a Redox-Active Nucleobase Receptor in Aqueous Solution',
       'A ditopic ferrocene receptor for anions and cations that functions as a chromogenic molecular switch',
       'A ferrocene nucleic acid oligomer as an organometallic structural mimic of DNA',
       'A heterodifunctionalised ferrocene derivative that self-assembles in solution through complementary hydrogen-bonding interactions',
       'A locking X-ray window shutter and collimator coupling to comply with the new Health and Safety at Work Act',
       'A luminescent europium hairpin for DNA photosensing in the visible, based on trimetallic bis-intercalators',
       ...
       'Up-Conversion Device Based on Quantum Dots With High-Conversion Efficiency Over 6%',
       'Vectorial Control of Energy‐Transfer Processes in Metallocyclodextrin Heterometallic Assemblies',
       'Verteporfin selectively kills hypoxic glioma cells through iron-binding and increased production of reactive oxygen species',
       'Vibrational Absorption from Oxygen-Hydrogen (Oi-H2) Complexes in Hydrogenated CZ Silicon',
       'Virginia review of sociology',
       'Wildlife use of log landings in the White Mountain National Forest',
       'Yttrium 1995',
       'ZUSCHRIFTEN-Redox-Switched Control of Binding Strength in Hydrogen-Bonded Metallocene Complexes Stichworter: Carbonsauren. Elektrochemie. Metallocene. Redoxchemie …',
       '[2] Rotaxanes comprising a macrocylic Hamilton receptor obtained using active template synthesis: synthesis and guest complexation',
       'pH-controlled delivery of luminescent europium coated nanoparticles into platelets'],
      dtype='object', name='title', length=202)

author_list = ['Zoe Pikramenou', 'James H. R. Tucker', 'Alison Rodger', 'Timothy Dafforn']
bibs = {}
for author_name in author_list:
    search_query = scholarly.search_author(author_name)
    for bib in search_query:
        bib = bib.fill()
        bibs.setdefault(bib['id_citations'], []).append((bib, author_name))

most_cited = sorted(bibs.items(), key=lambda k: len(k[1]))
# most_cited is now a list of tuples (key, value)
# which maps to (id_citation, [(bib1, author1), (bib2, author2), ...])

cited_enough = [tup[1][0][0] for tup in most_cited if len(tup[1]) >= 3]
# using key [0] in the middle is arbitrary. It can be anything in the 
# list, provided the bib objects are identical, but index 0 is guaranteed
# to be there.
# otherwise, the first index is to grab the list rather than the id_citation,
# and the last index is to grab the bib, rather than the author_name

paper_titles = [bib['bib']['title'] for bib in cited_enough]