import pandas as pd
import requests

def import_data(pages, start_year, end_year, search_terms):
    
    """
    This function is used to use the OpenAlex API, conduct a search on works, a return a dataframe with associated works.
    
    Inputs: 
        - pages: int, number of pages to loop through
        - search_terms: str, keywords to search for (must be formatted according to OpenAlex standards)
        - start_year and end_year: int, years to set as a range for filtering works
    """
    
    #create an empty dataframe
    search_results = pd.DataFrame()
    
    for page in range(1, pages):
        
        #use paramters to conduct request and format to a dataframe
        response = requests.get(f'https://api.openalex.org/works?page={page}&per-page=200&filter=publication_year:{start_year}-{end_year},type:article&search={search_terms}')
        data = pd.DataFrame(response.json()['results'])
        
        #append to empty dataframe
        search_results = pd.concat([search_results, data])
    
    #subset to relevant features
    search_results = search_results[["id", "title", "display_name", "publication_year", "publication_date",
                                        "type", "countries_distinct_count","institutions_distinct_count",
                                        "has_fulltext", "cited_by_count", "keywords", "referenced_works_count", "abstract_inverted_index"]]
    
    return(search_results)

#search for AI-related research
ai_search = import_data(30, 2018, 2025, "'artificial intelligence' OR 'deep learn' OR 'neural net' OR 'natural language processing' OR 'machine learn' OR 'large language models' OR 'small language models'")