DOI2PAPER

#从DOI获取文章的详细信息
import csv
import requests
import time

CROSSREF_BASE_URL = "https://api.crossref.org/works"

def get_paper_details_from_doi(doi):
    """从DOI获取文章的详细信息"""
    url = f"{CROSSREF_BASE_URL}/{doi}"
    response = requests.get(url)
    # 初始化默认值
    details = {
        "DOI": doi,
        "Authors": "error",
        "Abstract": "error",
        "Publication Year": "error",
        "Title": "error"
    }

    try:
        data = response.json()
        item = data['message']
        authors = ", ".join([author.get('given', '') + ' ' + author.get('family', '') for author in item.get('author', [])])
        abstract = item.get('abstract', "error")
        publication_year = item.get('published-print', {}).get('date-parts', [])[0][0] if item.get('published-print') else "error"
        title = item.get('title', ["error"])[0]

        details["Authors"] = authors
        details["Abstract"] = abstract
        details["Publication Year"] = publication_year
        details["Title"] = title
    except Exception as e:
        print(f"Error processing DOI {doi}: {e}")

    time.sleep(0.1)  # 延迟0.1秒
    return details

def main(input_csv, output_csv):
    with open(input_csv, 'r') as infile, open(output_csv, 'w', newline='') as outfile:
        reader = csv.reader(infile)
        writer = csv.writer(outfile)

        # 写入表头
        writer.writerow(["DOI", "Authors", "Abstract", "Publication Year", "Title"])

        for row in reader:
            doi = row[0]  # 假设DOI是CSV文件的第一列
            details = get_paper_details_from_doi(doi)
            writer.writerow([details["DOI"], details["Authors"], details["Abstract"], details["Publication Year"], details["Title"]])


if __name__ == "__main__":
    input_csv = "/PATH/in.csv"  # 输入文件名
    output_csv = "/PATH/out.csv"  # 输出文件名
    main(input_csv, output_csv)