Quick script to download Uniprot info for proteins from Pfam trees (Newick tree format)
from ete3 import Tree
import sys
import os
import urllib.request
t = Tree(sys.argv[1])
for l in t:
id = l.name.split("/")[0]
print(f"Accession: {id}")
if os.path.exists(f"{id}.txt") == False:
print("Downloading...")
page = urllib.request.urlopen(f"https://www.uniprot.org/uniprot/{id}.txt")
out_file = open(f"{id}.txt","wb")
out_file.write(page.read())
out_file.close()
RSS