diff sra_fetch.py @ 0:ffdd41766195 draft

Initial version - still need to test if datatype works correctly, and implement scripted download of SRA binaries.
author matt-shirley <mdshw5@gmail.com>
date Tue, 27 Nov 2012 13:44:28 -0500
parents
children 45031bbf6b27
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/sra_fetch.py	Tue Nov 27 13:44:28 2012 -0500
@@ -0,0 +1,30 @@
+from ftplib import FTP
+import sys
+
+# Get accession number from argument
+accession = sys.argv[1]
+outfile = sys.argv[2]
+prefix = accession[0:3]
+middle = accession[3:6]
+suffix = accession[6:9]
+
+# NCBI SRA FTP site
+ftp = FTP('ftp-trace.ncbi.nih.gov')
+
+# Open file and transfer requested SRA as a file
+# Try to change the working directory until it works
+sra = open(outfile, 'wb')
+ftp.login('ftp')
+connected = False
+while not connected:
+    try:
+        ftp.cwd('/sra/sra-instant/reads/ByRun/sra/' + 
+                prefix + '/' +
+                prefix + middle + '/' +
+                prefix + middle + suffix + '/')
+        connected = True
+    except:
+        pass
+        
+ftp.retrbinary('RETR ' + prefix + middle + suffix + '.sra', sra.write)
+ftp.quit()