Guest User

Untitled

a guest
Jun 21st, 2016
145
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Python 0.92 KB | None | 0 0
  1. import subprocess
  2. from ftplib import FTP
  3.  
  4. ftp_site = 'ftp.ncbi.nlm.nih.gov'
  5. ftp = FTP(ftp_site)
  6. ftp.login()
  7. ftp.cwd('genomes/genbank/bacteria')
  8. dirs = ftp.nlst()
  9.  
  10.  
  11. for organism in dirs:
  12.     for path in ftp.nlst(organism+"/latest_assembly_versions"):
  13.         accession = path.split("/")[-1]
  14.         fasta = accession+"_genomic.fna.gz"
  15.         #print(path)
  16.         #print(accession)
  17.         #print(fasta)
  18.         subprocess.call(['rsync',
  19.                         # path is symbolically link at genomes/genbank/bacteria/organism
  20.                         '--recursive',
  21.                         '--copy-links',
  22.                         '--dry-run',
  23.                         '--include='+fasta,
  24.                         # exclude all every dir and its contents beyond path
  25.                         '-f=- '+path+'/**/*'
  26.                         'ftp.ncbi.nlm.nih.gov::genomes/genbank/bacteria/'+path,
  27.                         'scratch/'+organism])
Advertisement
Add Comment
Please, Sign In to add comment