Advanced Search

Batch Download Sequence data from NCBI using EUtils

/ Published in: Python
Save to your folder(s)
Based on http://www.ncbi.nlm.nih.gov/books/NBK25498/#chapter3.Application_3_Retrieving_large

Expand | Embed | Plain Text

Copy this code and paste it in your HTML 
  1. #!/usr/bin/python
  2. # Author: Dr. Kumaran Kandasamy
  3. # E-Mail: [email protected]
  4.  
  5. import urllib, urllib2, re
  6.  
  7. def main(giList, database, rettype):
  8. 	output = "NO_DATA"
  9. 	base = "http://eutils.ncbi.nlm.nih.gov/entrez/eutils/"
  10. 	url = base+"epost.fcgi"
  11. 	values = {'db' : database,
  12.           'id' : giList,
  13.           }
  14.  
  15. 	data = urllib.urlencode(values)
  16. 	req = urllib2.Request(url, data)
  17. 	response = urllib2.urlopen(req)
  18. 	queryKey = ""; webEnv = "";
  19. 	for line in response.readlines():
  20. 		line = line.strip()
  21. 		if re.search("<WebEnv>(.*)</WebEnv>", line):
  22. 			webEnv = re.search("<WebEnv>(.*)</WebEnv>", line).groups()[0]
  23. 		if re.search("<QueryKey>(.*)</QueryKey>", line):
  24. 			queryKey = re.search("<QueryKey>(.*)</QueryKey>", line).groups()[0]
  25. 	if queryKey != "" and webEnv != "":
  26. 		print queryKey, webEnv
  27. 		url = base+"efetch.fcgi";
  28. 		values = {
  29. 					'db':database,
  30. 					'query_key':queryKey,
  31. 					'WebEnv':webEnv,
  32. 					'rettype':rettype,
  33. 					'retmode':'text'
  34. 				}
  35. 		#post the efetch URL
  36. 		data = urllib.urlencode(values)
  37. 		req = urllib2.Request(url, data)
  38. 		response = urllib2.urlopen(req)
  39. 		output = response.readlines()
  40. 	return output
  41.  
  42. if __name__ == "__main__":
  43. 	gi = "24475906,224465210,50978625,9507198"
  44. 	main(gi, 'nucleotide', 'fasta')

Report this snippet


Comments

RSS Icon Subscribe to comments

You need to login to post a comment.