View difference between Paste ID: 0reVKMCg and QkVyPXRQ
SHOW: | | - or go back to the newest paste.
1-
import subprocess
1+
import subprocess, os
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
for organism in dirs:
10
    latest = os.path.join(organism, "latest_assembly_versions")
11
    for path in ftp.nlst(latest):
12-
    for path in ftp.nlst(organism+"/latest_assembly_versions"):
12+
13
        fasta = accession+"_genomic.fna.gz"
14
        subprocess.call(['rsync',
15-
        #print(path)
15+
                         '--recursive',
16-
        #print(accession)
16+
                         '-vv',
17-
        #print(fasta)
17+
                         '--copy-links',
18
                         '--dry-run',
19-
                        # path is symbolically link at genomes/genbank/bacteria/organism
19+
                         '-f=+ '+fasta,
20-
                        '--recursive',
20+
                         #'-f=- *',
21-
                        '--copy-links',
21+
                         'ftp.ncbi.nlm.nih.gov::genomes/genbank/bacteria/'+latest,
22-
                        '--dry-run',
22+
                         '--log-file=scratch/test_dir/log.txt',
23-
                        '--include='+fasta,
23+
                         'scratch/' + organism])