pdf.py

import scipdf


def parse_pdf_to_artcile_dict(pdf_path):
    return scipdf.parse_pdf_to_dict(pdf_path)


if __name__ == "__main__":
    article_dict = scipdf.parse_pdf_to_dict(
        "/Users/jp/Documents/papers/demo-test/EMNLP23_Influence_NLP_Citation_Analysis.pdf"
    )  # return dictionary
    print(article_dict.keys())
    print(article_dict["title"])
    print(article_dict["references"][0].keys())