article_authors.py 文件源码

def extract(text, paper=None, logger=logger):

    # try using pypdf2/pdfminer
    try:
        pdf = paper._read_document()
        pdfReader = PdfFileReader(pdf)
        author = pdfReader.getDocumentInfo().author
        value_text, value_result = author, author
        source_type = "extracted"
        source_detail = "pdf metadata"
        if author:
            return (value_text, value_result, source_type, source_detail)
        else:
            return None
    except:
        # search for author or return None
        # Though currently there is no search function
        return None