scholarly

from scholarly import scholarly, ProxyGenerator import os # It is recommended to set up a proxy from the start of your application. # scholarly is designed to intelligently use proxies only when necessary. pg = ProxyGenerator() # For using free proxies (often less reliable for continuous scraping) # success = pg.FreeProxies() # if not success: print("Could not set up free proxies. Continuing without.") # Example for ScraperAPI (recommended for reliability, requires API key) # Set SCAPERAPI_API_KEY environment variable scraperapi_key = os.environ.get('SCAPERAPI_API_KEY', '') if scraperapi_key: print("Using ScraperAPI for proxies.") pg.ScraperAPI(scraperapi_key) scholarly.use_proxy(pg) else: print("SCAPERAPI_API_KEY not found. Using default connection (may hit limits). Consider setting up a proxy for robust scraping.") # Search for an author search_query = scholarly.search_author('Steven A Cholewiak') author = scholarly.fill(next(search_query)) print(f"Author Name: {author['name']}") print(f"Author Affiliation: {author['affiliation']}") print(f"Author Interests: {author['interests']}") # Print the titles of the author's publications publication_titles = [pub['bib']['title'] for pub in author['publications']] print(f"First 3 publication titles: {publication_titles[:3]}") # Take a closer look at the first publication if author['publications']: first_publication = scholarly.fill(author['publications'][0]) print(f"\nFirst Publication Title: {first_publication['bib']['title']}") print(f"First Publication Abstract: {first_publication['bib']['abstract'][:100]}...") # Which papers cited that publication? citations = [citation['bib']['title'] for citation in scholarly.citedby(first_publication)] print(f"First 3 papers citing this publication: {citations[:3]}")