Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- import subprocess
- from ftplib import FTP
- ftp_site = 'ftp.ncbi.nlm.nih.gov'
- ftp = FTP(ftp_site)
- ftp.login()
- ftp.cwd('genomes/genbank/bacteria')
- dirs = ftp.nlst()
- for organism in dirs:
- for path in ftp.nlst(organism+"/latest_assembly_versions"):
- accession = path.split("/")[-1]
- fasta = accession+"_genomic.fna.gz"
- #print(path)
- #print(accession)
- #print(fasta)
- subprocess.call(['rsync',
- # path is symbolically link at genomes/genbank/bacteria/organism
- '--recursive',
- '--copy-links',
- '--dry-run',
- '--include='+fasta,
- # exclude all every dir and its contents beyond path
- '-f=- '+path+'/**/*'
- 'ftp.ncbi.nlm.nih.gov::genomes/genbank/bacteria/'+path,
- 'scratch/'+organism])
Advertisement
Add Comment
Please, Sign In to add comment