Question

我从以下查询中获取摘要时遇到问题

Entrez.email = "anonymous@gmail.com"
esearch_query = Entrez.esearch(db="pubmed", term="cancer AND food", retmode="xml")
esearch_result = Entrez.read(esearch_query)

# Now we need to get all papers from our search using the IDList
for iden in esearch_result['IdList'][-1]:
    pubmed_entry = Entrez.efetch(db="pubmed", id=iden, retmode="xml")
    result = Entrez.read(pubmed_entry)
    print result

输出如下（仅作为示例中的一个条目）。

{u＆＃39; PubmedArticle＆＃39;：[{u＆＃39; MedlineCitation＆＃39;： DictElement（{u＆＃39; DateCompleted＆＃39 ;: {u＆＃39; Month＆＃39;：＆＃39; 01＆＃39;，u＆＃39; Day＆＃39;：＆＃39; 10＆＃39;，u＆＃39;年＆＃39 ;: ＆＃39; 1976＆＃39;}，你＆＃39; OtherID＆＃39;：[]，你＆＃39; DateRevised＆＃39;：{u＆＃39;月＆＃39;：＆＃39; 03＆＃39;， U＆＃39;日＆＃39 ;: ＆＃39; 22＆＃39;，u＆＃39;年＆＃39;：＆＃39; 2017＆＃39;}，u＆＃39; MeshHeadingList＆＃39;：[{u＆＃39; QualifierName＆＃39;：[] ， u＆＃39; DescriptorName＆＃39 ;: StringElement（＆＃39;绑定网站＆＃39;，attributes = {u＆＃39; UI＆＃39;：你＆＃39; D001665＆＃39;，你＆＃39; MajorTopicYN＆＃39;：你＆＃39; N＆＃39;}}}，{u＆＃39; QualifierName＆＃39;： [StringElement（＆＃39; blood＆＃39;，attributes = {u＆＃39; UI＆＃39;：u＆＃39; Q000097＆＃39;，你是主要的专家＆＃39;：你＆＃39; N＆＃39;}），你＆＃39; DescriptorName＆＃39;：StringElement（＆＃39; Cobalt＆＃39;， attributes = {u＆＃39; UI＆＃39;：你＆＃39; D003035＆＃39;，你＆＃39; MajorTopicYN＆＃39;：你＆＃39; N＆＃39;}）}， {u＆＃39; QualifierName＆＃39;：[]，u＆＃39; DescriptorName＆＃39 ;: StringElement（＆＃39; Hemoglobins＆＃39;， attributes = {u＆＃39; UI＆＃39 ;: u＆＃39; D006454＆＃39;，u＆＃39; MajorTopicYN＆＃39;：u＆＃39; Y＆＃39;}）}， {u＆＃39; QualifierName＆＃39;：[]，u＆＃39; DescriptorName＆＃39 ;: StringElement（＆＃39; Humans＆＃39;， attributes = {u＆＃39; UI＆＃39;：你＆＃39; D006801＆＃39;，你＆＃39; MajorTopicYN＆＃39;：你＆＃39; N＆＃39;}）}， {u＆＃39; QualifierName＆＃39;：[]，u＆＃39; DescriptorName＆＃39 ;: StringElement（＆＃39; Hydrogen-Ion 专注＆＃39;，属性= {u＆＃39; UI＆＃39 ;: u＆＃39; D006863＆＃39;，u＆＃39; MajorTopicYN＆＃39;：你＆＃39; N＆＃39;}}，{u＆＃39; QualifierName＆＃39;：[StringElement（＆＃39; blood＆＃39;，attributes = {u＆＃39; UI＆＃39;：你＆＃39; Q000097＆＃39;，你＆＃39; MajorTopicYN＆＃39;：你＆＃39; N＆＃39;}），你＆＃39; DescriptorName＆＃39;： StringElement（＆＃39; Iron＆＃39;，attributes = {u＆＃39; UI＆＃39 ;: u＆＃39; D007501＆＃39;，u＆＃39; MajorTopicYN＆＃39;：你＆＃39; N＆＃39;}}}，{u＆＃39; QualifierName＆＃39;：[]，u＆＃39; DescriptorName＆＃39;： StringElement（＆＃39; Ligands＆＃39;，attributes = {u＆＃39; UI＆＃39;：u＆＃39; D008024＆＃39;，你是MajorTopicYN＆＃39;：你＆＃39;}}}}，{u＆＃39; QualifierName＆＃39;：[]，u＆＃39; DescriptorName＆＃39;： StringElement（＆＃39;数学＆＃39;，属性= {u＆＃39; UI＆＃39;：你＆＃39; D008433＆＃39;，你是MajorTopicYN＆＃39;：你＆＃39;}}}}，{u＆＃39; QualifierName＆＃39;：[StringElement（＆＃39; blood＆＃39;， attributes = {u＆＃39; UI＆＃39 ;: u＆＃39; Q000097＆＃39;，u＆＃39; MajorTopicYN＆＃39;：u＆＃39; Y＆＃39;}）]，你的DescriptorName＆＃39 ;: StringElement（＆＃39; Oxygen＆＃39;，attributes = {u＆＃39; UI＆＃39;：你＆＃39; D010100＆＃39;，你＆＃39; MajorTopicYN＆＃39;：你＆＃39;}}}}，{u＆＃39; QualifierName＆＃39;：[]，你的DescriptorName＆＃39 ;: StringElement（＆＃39; Oxyhemoglobins＆＃39;，attributes = {u＆＃39; UI＆＃39;：你＆＃39; D010108＆＃39;，你＆＃39; MajorTopicYN＆＃39;：你＆＃39;}}}}，{u＆＃39; QualifierName＆＃39;：[]，你的DescriptorName＆＃39 ;: StringElement（＆＃39; Protein Binding＆＃39;，attributes = {u＆＃39; UI＆＃39;：你＆＃39; D011485＆＃39;，你＆＃39; MajorTopicYN＆＃39;：你＆＃39; N＆＃39;}}，{u＆＃39; QualifierName＆＃39;：[]， u＆＃39; DescriptorName＆＃39 ;: StringElement（＆＃39; Spectrum Analysis＆＃39;， attributes = {u＆＃39; UI＆＃39 ;: u＆＃39; D013057＆＃39;，u＆＃39; MajorTopicYN＆＃39;：u＆＃39; N＆＃39;}）}]，你＆＃39; OtherAbstract＆＃39;：[]，你＆＃39; CitationSubset＆＃39;：[＆＃39; IM＆＃39;]，u＆＃39; ChemicalList＆＃39;： [{u＆＃39; NameOfSubstance＆＃39 ;: StringElement（＆＃39; Hemoglobins＆＃39;，attributes = {u＆＃39; UI＆＃39;：你＆＃39; D006454＆＃39;}），你＆＃39; RegistryNumber＆＃39;：＆＃39; 0＆＃39;}，{u＆＃39; NameOfSubstance＆＃39;： StringElement（＆＃39; Ligands＆＃39;，attributes = {u＆＃39; UI＆＃39;：u＆＃39; D008024＆＃39;}），你的注册管理机构编号＆＃39;：＆＃39; 0＆＃39;}，{u＆＃39; NameOfSubstance＆＃39;： StringElement（＆＃39; Oxyhemoglobins＆＃39;，attributes = {u＆＃39; UI＆＃39;：u＆＃39; D010108＆＃39;}），你注册登记号码＆＃39;：＆＃39; 0＆＃39;}，{u＆＃39; NameOfSubstance＆＃39 ;: StringElement（＆＃39; Cobalt＆＃39;， attributes = {u＆＃39; UI＆＃39;：u＆＃39; D003035＆＃39;}），u＆＃39; RegistryNumber＆＃39;：＆＃39; 3G0H8C9362＆＃39;}， {u＆＃39; NameOfSubstance＆＃39 ;: StringElement（＆＃39; Iron＆＃39;，attributes = {u＆＃39; UI＆＃39;：你＆＃39; D007501＆＃39;}），你＆＃39; RegistryNumber＆＃39;：＆＃39; E1UOL152H7＆＃39;}，{u＆＃39; NameOfSubstance＆＃39;： StringElement（＆＃39; Oxygen＆＃39;，attributes = {u＆＃39; UI＆＃39;：u＆＃39; D010100＆＃39;}），你注册登记号码＆＃39;：＆＃39; S88TT14065＆＃39;}]，你＆＃39; KeywordList＆＃39;：[]，你＆＃39; DateCreated＆＃39;： {u＆＃39;月＆＃39;：＆＃39; 01＆＃39;，你＆＃39; Day＆＃39;：＆＃39; 10＆＃39;，u＆＃39;年＆＃39;：＆＃39; 1976＆＃39;}，你和SpaceFlightMission＆＃39;：[]，你＆＃39; GeneralNote＆＃39;：[]，你＆＃39;文章＆＃39;： DictElement（{u＆＃39; ArticleDate＆＃39;：[]，u＆＃39;分页＆＃39;：{u＆＃39; MedlinePgn＆＃39;：＆＃39; 1424-31＆＃39;}，u＆＃39;作者列表＆＃39;：ListElement（[DictElement（{u＆＃39; LastName＆＃39;：＆＃39; Chow＆＃39;，u＆＃39;缩写＆＃39;：＆＃39; YW＆＃39;，u＆＃39;标识符＆＃39;：[]，u＆＃39; AffiliationInfo＆＃39;：[] ，你＆＃39; ForeName＆＃39;：＆＃39; Y W＆＃39;}，attributes = {u＆＃39; ValidYN＆＃39;：你＆＃39; Y＆＃39;}）， DictElement（{u＆＃39; LastName＆＃39;：＆＃39; Pietranico＆＃39;，u＆＃39;缩写＆＃39;：＆＃39; R＆＃39;，你＆＃39;标识符：[]，你＆＃39; AffiliationInfo＆＃39;：[]，你＆＃39; ForeName＆＃39;：＆＃39; R＆＃39;}， attributes = {u＆＃39; ValidYN＆＃39;：u＆＃39; Y＆＃39;}），DictElement（{u＆＃39; LastName＆＃39;：＆＃39; Mukerji＆＃39;，你＆＃39;缩写＆＃39;：＆＃39; A＆＃39;，u＆＃39;标识符＆＃39;：[]，u＆＃39; AffiliationInfo＆＃39;：[]，你的名字＆＃39;：＆＃39; A＆＃39;}，属性= {u＆＃39; ValidYN＆＃39;：你＆＃39; Y＆＃39;}）]， attributes = {u＆＃39; CompleteYN＆＃39 ;: u＆＃39; Y＆＃39;}），u＆＃39;语言＆＃39;：[＆＃39; eng＆＃39;]， u＆＃39; PublicationTypeList＆＃39;：[StringElement（＆＃39; Journal Article＆＃39;， attributes = {u＆＃39; UI＆＃39;：u＆＃39; D016428＆＃39;}），StringElement（＆＃34; Research Support，U.S. Gov＆＃t; tt，Non-P.H.S。＆＃34;，attributes = {u＆＃39; UI＆＃39;：u＆＃39; D013486＆＃39;}）]，u＆＃39; Journal＆＃39;： {u＆＃39; ISSN＆＃39 ;: StringElement（＆＃39; 0006-291X＆＃39;，attributes = {u＆＃39; IssnType＆＃39;：你打印＆＃39;}），u＆＃39; ISOA缩写＆＃39;：＆＃39; Biochem。生物物理学。 RES。 COMMUN。＆＃39 ;, 你的日记问题：DictElement（{u＆＃39;卷＆＃39;：＆＃39; 66＆＃39;，你＆＃39;问题＆＃39;：＆＃39; 4＆＃39;，你＆＃39; PubDate＆＃39;：{u＆＃39;月＆＃39;：＆＃39; 10月＆＃39;，＆＃39; Day＆＃39;：＆＃39; 27＆＃39;，u＆＃39;年＆＃39;：＆＃39; 1975＆＃39;}}， attributes = {u＆＃39; CitedMedium＆＃39;：u＆＃39; Print＆＃39;}），u＆＃39; Title＆＃39;：＆＃39; Biochemical and 生物物理研究通讯＆＃39;}，＆＃39; ArticleTitle＆＃39;：＆＃39;研究氧与血红蛋白分子的结合能。＆＃39;，u＆＃39; ELocationID＆＃39;：[]}， attributes = {u＆＃39; PubModel＆＃39;：u＆＃39; Print＆＃39;}），u＆＃39; PMID＆＃39 ;: StringElement（＆＃39; 6＆＃39;， attributes = {u＆＃39; Version＆＃39 ;: u＆＃39;}），u＆＃39; MedlineJournalInfo＆＃39;：{u＆＃39; MedlineTA＆＃39;：＆＃39; Biochem Biophys Res Commun＆＃39;，u＆＃39; Country＆＃39;：＆＃39; United States＆＃39;，你好，我是＆＃39; 0372516＆＃39;，你＆＃39; ISSNLinking＆＃39;：＆＃39; 0006-291X＆＃39;}}， attributes = {u＆＃39;状态＆＃39;：你＆＃39; MEDLINE＆＃39;，你＆＃39;所有者＆＃39;：你＆＃39; NLM＆＃39;}），u＆＃39; PubmedData＆＃39;： {u＆＃39; ArticleIdList＆＃39;：[StringElement（＆＃39; 6＆＃39;，attributes = {u＆＃39; IdType＆＃39;：你发布了＆＃39;}），StringElement（＆＃39; 0006-291X（75）90518-5＆＃39;， attributes = {u＆＃39; IdType＆＃39;：u＆＃39; pii＆＃39;}）]，u＆＃39; PublicationStatus＆＃39;：＆＃39; ppublish＆＃39;，你的历史＆＃39;：[DictElement（{u＆＃39;月＆＃39;：＆＃39; 10＆＃39;，你＆＃39; Day＆＃39;：＆＃39; 27＆＃39;，你＆＃39;年＆＃39 ;: ＆＃39; 1975＆＃39;}，attributes = {u＆＃39; PubStatus＆＃39;：u＆＃39; pubmed＆＃39;}）， DictElement（{u＆＃39; Minute＆＃39;：＆＃39; 1＆＃39;，u＆＃39; Month＆＃39;：＆＃39; 10＆＃39;，u＆＃39; Day＆＃39;：＆＃ 39; 27＆＃39;，你＆＃39;小时＆＃39;：＆＃39; 0＆＃39;，你＆＃39;年＆＃39;：＆＃39; 1975＆＃39;}，attributes = {u＆＃39; PubStatus＆＃39;：你＆＃39; medline＆＃39;}）， DictElement（{u＆＃39;分钟＆＃39;：＆＃39; 0＆＃39;，你＆＃39;月＆＃39;：＆＃39; 10＆＃39;，你＆＃39; Day＆＃39;：＆＃ 39; 27＆＃39;，你＆＃39;小时＆＃39;：＆＃39; 0＆＃39;，你＆＃39;年＆＃39;：＆＃39; 1975＆＃39;}，attributes = {u＆＃39; PubStatus＆＃39;：u＆＃39; entrez＆＃39;}） ]}}]，你和PubmedBookArticle＆＃39;：[]}

我怎样才能得到摘要？最后的想法是在sql数据库中包含一些字段（例如title，abstract ..）。

谢谢，大卫

Answer 1

可能对你不利的是，通常没有1975年以前MEDLINE PubMed记录的摘要 - 你的例子就在1975年的尖端。我使用你的代码和另一个查询，发现了两篇文章ID ，一个有摘要，一个没有：

from Bio import Entrez

Entrez.email = "anonymous@gmail.com"

esearch_query = Entrez.esearch(db="pubmed", term="cancer AND wombats", retmode="xml")
esearch_result = Entrez.read(esearch_query)

for identifier in esearch_result['IdList']:
    pubmed_entry = Entrez.efetch(db="pubmed", id=identifier, retmode="xml")
    result = Entrez.read(pubmed_entry)

    article = result['PubmedArticle'][0]['MedlineCitation']['Article']

    if 'Abstract' in article:
        print(article['Abstract']['AbstractText'])

截止输出

[＆＃39;本报告编目了巨型动物的所有自发增殖，比较时期举行的考拉，袋熊，负鼠和滑翔机 Taronga动物园病理学登记处。存在增生性病变在14个巨型动物，26只考拉，2只袋熊和22只负鼠和滑翔机中。记录在macropods中的大多数肿瘤都是单数的......＆＃39;]

详细信息可在文档中找到：MEDLINE PubMed XML Element Descriptions

从pubmed

1 个答案: