从 pubmed 获取摘要
fetching abstracts from pubmed
我无法通过以下查询获取摘要
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
输出结果如下（仅以其中一项为例）
{u'PubmedArticle': [{u'MedlineCitation':
DictElement({u'DateCompleted': {u'Month': '01', u'Day': '10', u'Year':
'1976'}, u'OtherID': [], u'DateRevised': {u'Month': '03', u'Day':
'22', u'Year': '2017'}, u'MeshHeadingList': [{u'QualifierName': [],
u'DescriptorName': StringElement('Binding Sites', attributes={u'UI':
u'D001665', u'MajorTopicYN': u'N'})}, {u'QualifierName':
[StringElement('blood', attributes={u'UI': u'Q000097',
u'MajorTopicYN': u'N'})], u'DescriptorName': StringElement('Cobalt',
attributes={u'UI': u'D003035', u'MajorTopicYN': u'N'})},
{u'QualifierName': [], u'DescriptorName': StringElement('Hemoglobins',
attributes={u'UI': u'D006454', u'MajorTopicYN': u'Y'})},
{u'QualifierName': [], u'DescriptorName': StringElement('Humans',
attributes={u'UI': u'D006801', u'MajorTopicYN': u'N'})},
{u'QualifierName': [], u'DescriptorName': StringElement('Hydrogen-Ion
Concentration', attributes={u'UI': u'D006863', u'MajorTopicYN':
u'N'})}, {u'QualifierName': [StringElement('blood', attributes={u'UI':
u'Q000097', u'MajorTopicYN': u'N'})], u'DescriptorName':
StringElement('Iron', attributes={u'UI': u'D007501', u'MajorTopicYN':
u'N'})}, {u'QualifierName': [], u'DescriptorName':
StringElement('Ligands', attributes={u'UI': u'D008024',
u'MajorTopicYN': u'N'})}, {u'QualifierName': [], u'DescriptorName':
StringElement('Mathematics', attributes={u'UI': u'D008433',
u'MajorTopicYN': u'N'})}, {u'QualifierName': [StringElement('blood',
attributes={u'UI': u'Q000097', u'MajorTopicYN': u'Y'})],
u'DescriptorName': StringElement('Oxygen', attributes={u'UI':
u'D010100', u'MajorTopicYN': u'N'})}, {u'QualifierName': [],
u'DescriptorName': StringElement('Oxyhemoglobins', attributes={u'UI':
u'D010108', u'MajorTopicYN': u'N'})}, {u'QualifierName': [],
u'DescriptorName': StringElement('Protein Binding', attributes={u'UI':
u'D011485', u'MajorTopicYN': u'N'})}, {u'QualifierName': [],
u'DescriptorName': StringElement('Spectrum Analysis',
attributes={u'UI': u'D013057', u'MajorTopicYN': u'N'})}],
u'OtherAbstract': [], u'CitationSubset': ['IM'], u'ChemicalList':
[{u'NameOfSubstance': StringElement('Hemoglobins', attributes={u'UI':
u'D006454'}), u'RegistryNumber': '0'}, {u'NameOfSubstance':
StringElement('Ligands', attributes={u'UI': u'D008024'}),
u'RegistryNumber': '0'}, {u'NameOfSubstance':
StringElement('Oxyhemoglobins', attributes={u'UI': u'D010108'}),
u'RegistryNumber': '0'}, {u'NameOfSubstance': StringElement('Cobalt',
attributes={u'UI': u'D003035'}), u'RegistryNumber': '3G0H8C9362'},
{u'NameOfSubstance': StringElement('Iron', attributes={u'UI':
u'D007501'}), u'RegistryNumber': 'E1UOL152H7'}, {u'NameOfSubstance':
StringElement('Oxygen', attributes={u'UI': u'D010100'}),
u'RegistryNumber': 'S88TT14065'}], u'KeywordList': [], u'DateCreated':
{u'Month': '01', u'Day': '10', u'Year': '1976'},
u'SpaceFlightMission': [], u'GeneralNote': [], u'Article':
DictElement({u'ArticleDate': [], u'Pagination': {u'MedlinePgn':
'1424-31'}, u'AuthorList': ListElement([DictElement({u'LastName':
'Chow', u'Initials': 'YW', u'Identifier': [], u'AffiliationInfo': [],
u'ForeName': 'Y W'}, attributes={u'ValidYN': u'Y'}),
DictElement({u'LastName': 'Pietranico', u'Initials': 'R',
u'Identifier': [], u'AffiliationInfo': [], u'ForeName': 'R'},
attributes={u'ValidYN': u'Y'}), DictElement({u'LastName': 'Mukerji',
u'Initials': 'A', u'Identifier': [], u'AffiliationInfo': [],
u'ForeName': 'A'}, attributes={u'ValidYN': u'Y'})],
attributes={u'CompleteYN': u'Y'}), u'Language': ['eng'],
u'PublicationTypeList': [StringElement('Journal Article',
attributes={u'UI': u'D016428'}), StringElement("Research Support, U.S.
Gov't, Non-P.H.S.", attributes={u'UI': u'D013486'})], u'Journal':
{u'ISSN': StringElement('0006-291X', attributes={u'IssnType':
u'Print'}), u'ISOAbbreviation': 'Biochem. Biophys. Res. Commun.',
u'JournalIssue': DictElement({u'Volume': '66', u'Issue': '4',
u'PubDate': {u'Month': 'Oct', u'Day': '27', u'Year': '1975'}},
attributes={u'CitedMedium': u'Print'}), u'Title': 'Biochemical and
biophysical research communications'}, u'ArticleTitle': 'Studies of
oxygen binding energy to hemoglobin molecule.', u'ELocationID': []},
attributes={u'PubModel': u'Print'}), u'PMID': StringElement('6',
attributes={u'Version': u'1'}), u'MedlineJournalInfo': {u'MedlineTA':
'Biochem Biophys Res Commun', u'Country': 'United States',
u'NlmUniqueID': '0372516', u'ISSNLinking': '0006-291X'}},
attributes={u'Status': u'MEDLINE', u'Owner': u'NLM'}), u'PubmedData':
{u'ArticleIdList': [StringElement('6', attributes={u'IdType':
u'pubmed'}), StringElement('0006-291X(75)90518-5',
attributes={u'IdType': u'pii'})], u'PublicationStatus': 'ppublish',
u'History': [DictElement({u'Month': '10', u'Day': '27', u'Year':
'1975'}, attributes={u'PubStatus': u'pubmed'}),
DictElement({u'Minute': '1', u'Month': '10', u'Day': '27', u'Hour':
'0', u'Year': '1975'}, attributes={u'PubStatus': u'medline'}),
DictElement({u'Minute': '0', u'Month': '10', u'Day': '27', u'Hour':
'0', u'Year': '1975'}, attributes={u'PubStatus': u'entrez'})]}}],
u'PubmedBookArticle': []}
我怎样才能得到摘要？？最终的想法是在 sql 数据库中包含一些字段（例如 title 、 abstract..）。
谢谢，
大卫
可能对您不利的是，通常没有 1975 年之前的 MEDLINE PubMed 记录的摘要——您的示例恰好在 1975 年处于风口浪尖。我使用了您的代码和一个不同的查询，结果出现了两个文章 id，一篇有摘要，一篇没有：
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'])
截断输出
['This report catalogues all spontaneous proliferations in macropods,
koalas, wombats, and possums and gliders held by the Comparative
Pathology Registry at Taronga Zoo. Proliferative lesions were present
in 14 macropods, 26 koalas, two wombats and 22 possums and gliders.
Most neoplasms recorded in macropods were singular and ....']
我无法通过以下查询获取摘要
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
输出结果如下（仅以其中一项为例）
{u'PubmedArticle': [{u'MedlineCitation': DictElement({u'DateCompleted': {u'Month': '01', u'Day': '10', u'Year': '1976'}, u'OtherID': [], u'DateRevised': {u'Month': '03', u'Day': '22', u'Year': '2017'}, u'MeshHeadingList': [{u'QualifierName': [], u'DescriptorName': StringElement('Binding Sites', attributes={u'UI': u'D001665', u'MajorTopicYN': u'N'})}, {u'QualifierName': [StringElement('blood', attributes={u'UI': u'Q000097', u'MajorTopicYN': u'N'})], u'DescriptorName': StringElement('Cobalt', attributes={u'UI': u'D003035', u'MajorTopicYN': u'N'})}, {u'QualifierName': [], u'DescriptorName': StringElement('Hemoglobins', attributes={u'UI': u'D006454', u'MajorTopicYN': u'Y'})}, {u'QualifierName': [], u'DescriptorName': StringElement('Humans', attributes={u'UI': u'D006801', u'MajorTopicYN': u'N'})}, {u'QualifierName': [], u'DescriptorName': StringElement('Hydrogen-Ion Concentration', attributes={u'UI': u'D006863', u'MajorTopicYN': u'N'})}, {u'QualifierName': [StringElement('blood', attributes={u'UI': u'Q000097', u'MajorTopicYN': u'N'})], u'DescriptorName': StringElement('Iron', attributes={u'UI': u'D007501', u'MajorTopicYN': u'N'})}, {u'QualifierName': [], u'DescriptorName': StringElement('Ligands', attributes={u'UI': u'D008024', u'MajorTopicYN': u'N'})}, {u'QualifierName': [], u'DescriptorName': StringElement('Mathematics', attributes={u'UI': u'D008433', u'MajorTopicYN': u'N'})}, {u'QualifierName': [StringElement('blood', attributes={u'UI': u'Q000097', u'MajorTopicYN': u'Y'})], u'DescriptorName': StringElement('Oxygen', attributes={u'UI': u'D010100', u'MajorTopicYN': u'N'})}, {u'QualifierName': [], u'DescriptorName': StringElement('Oxyhemoglobins', attributes={u'UI': u'D010108', u'MajorTopicYN': u'N'})}, {u'QualifierName': [], u'DescriptorName': StringElement('Protein Binding', attributes={u'UI': u'D011485', u'MajorTopicYN': u'N'})}, {u'QualifierName': [], u'DescriptorName': StringElement('Spectrum Analysis', attributes={u'UI': u'D013057', u'MajorTopicYN': u'N'})}], u'OtherAbstract': [], u'CitationSubset': ['IM'], u'ChemicalList': [{u'NameOfSubstance': StringElement('Hemoglobins', attributes={u'UI': u'D006454'}), u'RegistryNumber': '0'}, {u'NameOfSubstance': StringElement('Ligands', attributes={u'UI': u'D008024'}), u'RegistryNumber': '0'}, {u'NameOfSubstance': StringElement('Oxyhemoglobins', attributes={u'UI': u'D010108'}), u'RegistryNumber': '0'}, {u'NameOfSubstance': StringElement('Cobalt', attributes={u'UI': u'D003035'}), u'RegistryNumber': '3G0H8C9362'}, {u'NameOfSubstance': StringElement('Iron', attributes={u'UI': u'D007501'}), u'RegistryNumber': 'E1UOL152H7'}, {u'NameOfSubstance': StringElement('Oxygen', attributes={u'UI': u'D010100'}), u'RegistryNumber': 'S88TT14065'}], u'KeywordList': [], u'DateCreated': {u'Month': '01', u'Day': '10', u'Year': '1976'}, u'SpaceFlightMission': [], u'GeneralNote': [], u'Article': DictElement({u'ArticleDate': [], u'Pagination': {u'MedlinePgn': '1424-31'}, u'AuthorList': ListElement([DictElement({u'LastName': 'Chow', u'Initials': 'YW', u'Identifier': [], u'AffiliationInfo': [], u'ForeName': 'Y W'}, attributes={u'ValidYN': u'Y'}), DictElement({u'LastName': 'Pietranico', u'Initials': 'R', u'Identifier': [], u'AffiliationInfo': [], u'ForeName': 'R'}, attributes={u'ValidYN': u'Y'}), DictElement({u'LastName': 'Mukerji', u'Initials': 'A', u'Identifier': [], u'AffiliationInfo': [], u'ForeName': 'A'}, attributes={u'ValidYN': u'Y'})], attributes={u'CompleteYN': u'Y'}), u'Language': ['eng'], u'PublicationTypeList': [StringElement('Journal Article', attributes={u'UI': u'D016428'}), StringElement("Research Support, U.S. Gov't, Non-P.H.S.", attributes={u'UI': u'D013486'})], u'Journal': {u'ISSN': StringElement('0006-291X', attributes={u'IssnType': u'Print'}), u'ISOAbbreviation': 'Biochem. Biophys. Res. Commun.', u'JournalIssue': DictElement({u'Volume': '66', u'Issue': '4', u'PubDate': {u'Month': 'Oct', u'Day': '27', u'Year': '1975'}}, attributes={u'CitedMedium': u'Print'}), u'Title': 'Biochemical and biophysical research communications'}, u'ArticleTitle': 'Studies of oxygen binding energy to hemoglobin molecule.', u'ELocationID': []}, attributes={u'PubModel': u'Print'}), u'PMID': StringElement('6', attributes={u'Version': u'1'}), u'MedlineJournalInfo': {u'MedlineTA': 'Biochem Biophys Res Commun', u'Country': 'United States', u'NlmUniqueID': '0372516', u'ISSNLinking': '0006-291X'}}, attributes={u'Status': u'MEDLINE', u'Owner': u'NLM'}), u'PubmedData': {u'ArticleIdList': [StringElement('6', attributes={u'IdType': u'pubmed'}), StringElement('0006-291X(75)90518-5', attributes={u'IdType': u'pii'})], u'PublicationStatus': 'ppublish', u'History': [DictElement({u'Month': '10', u'Day': '27', u'Year': '1975'}, attributes={u'PubStatus': u'pubmed'}), DictElement({u'Minute': '1', u'Month': '10', u'Day': '27', u'Hour': '0', u'Year': '1975'}, attributes={u'PubStatus': u'medline'}), DictElement({u'Minute': '0', u'Month': '10', u'Day': '27', u'Hour': '0', u'Year': '1975'}, attributes={u'PubStatus': u'entrez'})]}}], u'PubmedBookArticle': []}
我怎样才能得到摘要？？最终的想法是在 sql 数据库中包含一些字段（例如 title 、 abstract..）。
谢谢， 大卫
可能对您不利的是，通常没有 1975 年之前的 MEDLINE PubMed 记录的摘要——您的示例恰好在 1975 年处于风口浪尖。我使用了您的代码和一个不同的查询，结果出现了两个文章 id，一篇有摘要，一篇没有：
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'])
截断输出
['This report catalogues all spontaneous proliferations in macropods, koalas, wombats, and possums and gliders held by the Comparative Pathology Registry at Taronga Zoo. Proliferative lesions were present in 14 macropods, 26 koalas, two wombats and 22 possums and gliders. Most neoplasms recorded in macropods were singular and ....']