2

我需要自动化 PubMed 文章收集。我只找到了通过术语查询下载 PubMed 文章和通过pmid下载 PubMed 文章的示例。（一篇文章）但我正在考虑的是按日期（从到）或全部下载 PubMed ID 的列表，就像在 OAI 中一样。

4

1 回答 1

3

您可以将BioPython用于此类目的。以下代码片段将为您提供特定日期范围内所有 PubMed 文章的链接。PMC 文章可以直接下载，其他文章提供 DOI，但 PDF 的位置是特定于出版商的，无法预测所有文章的位置。

def article_links(start_date, end_date = '3000'):
    """
    start_date, end_date = 'YYYY/MM/DD'
    returns a list of PubMedCentral links and a 2nd list of DOI links
    """
    from Bio import Entrez

    Entrez.email = "Your.Name.Here@example.org"

    #get all articles in certain date range, in this case 5 articles which will be published in the future
    handle = Entrez.esearch(db="pubmed", term='("%s"[Date - Publication] : "%s"[Date - Publication]) ' %(start_date, end_date))
    records = Entrez.read(handle)

    #get a list of Pubmed IDs for all articles
    idlist = ','.join(records['IdList'])
    handle = Entrez.efetch("pubmed", id=idlist, retmode="xml")
    records = Entrez.parse(handle)

    pmc_articles = []
    doi = []
    for record in records:
        #get all PMC articles
        if record.get('MedlineCitation'):
            if record['MedlineCitation'].get('OtherID'):
               for other_id in record['MedlineCitation']['OtherID']:
                   if other_id.title().startswith('Pmc'):
                       pmc_articles.append('http://www.ncbi.nlm.nih.gov/pmc/articles/%s/pdf/' % (other_id.title().upper()))
        #get all DOIs
        if record.get('PubmedData'):
            if record['PubmedData'].get('ArticleIdList'):
                for other_id in record['PubmedData']['ArticleIdList']:
                    if 'doi' in other_id.attributes.values():
                        doi.append('http://dx.doi.org/' + other_id.title())


    return pmc_articles, doi

if __name__ == '__main__':
    print (article_links('2016/12/20'))
于 2016-06-16T13:05:20.837 回答