I'm hoping to query the PubMed API based on a list of paper IDs and return the title, abstract and content.
So far I have been able to do the first three things doing the following:
from metapub import PubMedFetcher
pmids = [2020202, 1745076, 2768771, 8277124, 4031339]
fetch = PubMedFetcher()
title_list = []
abstract_list = []
for pmid in pmids:
article = fetch.article_by_pmid(pmid)
abstract = article.abstract # str
abstract_list.append(abstract)
title = article.title # str
title_list.append(title)
OR get the full paper content, but the query is based on keywords rather than IDs
email = 'myemail@gmail.com'
pubmed = PubMed(tool="PubMedSearcher", email=email)
## PUT YOUR SEARCH TERM HERE ##
search_term = "test"
results = pubmed.query(search_term, max_results=300)
articleList = []
articleInfo = []
for article in results:
# Print the type of object we've found (can be either PubMedBookArticle or PubMedArticle).
# We need to convert it to dictionary with available function
articleDict = article.toDict()
articleList.append(articleDict)
# Generate list of dict records which will hold all article details that could be fetch from PUBMED API
for article in articleList:
#Sometimes article['pubmed_id'] contains list separated with comma - take first pubmedId in that list - thats article pubmedId
pubmedId = article['pubmed_id'].partition('\n')[0]
# Append article info to dictionary
articleInfo.append({u'pubmed_id':pubmedId,
u'title':article['title'],
u'keywords':article['keywords'],
u'journal':article['journal'],
u'abstract':article['abstract'],
u'conclusions':article['conclusions'],
u'methods':article['methods'],
u'results': article['results'],
u'copyrights':article['copyrights'],
u'doi':article['doi'],
u'publication_date':article['publication_date'],
u'authors':article['authors']})
