Created
July 25, 2011 16:27
-
-
Save ehazlett/1104507 to your computer and use it in GitHub Desktop.
Search PubMed with BioPython
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
# numpy and biopython are required -- pip install numpy biopython | |
from Bio import Entrez | |
from Bio import Medline | |
MAX_COUNT = 10 | |
TERM = 'Tuberculosis' | |
print('Getting {0} publications containing {1}...'.format(MAX_COUNT, TERM)) | |
Entrez.email = '[email protected]' | |
h = Entrez.esearch(db='pubmed', retmax=MAX_COUNT, term=TERM) | |
result = Entrez.read(h) | |
print('Total number of publications containing {0}: {1}'.format(TERM, result['Count'])) | |
ids = result['IdList'] | |
h = Entrez.efetch(db='pubmed', id=ids, rettype='medline', retmode='text') | |
records = Medline.parse(h) | |
authors = [] | |
for record in records: | |
au = record.get('AU', '?') | |
for a in au: | |
if a not in authors: | |
authors.append(a) | |
authors.sort() | |
print('Authors: {0}'.format(', '.join(authors))) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment