pfam_to_uniprot.py

from collections import defaultdict
import requests
from bs4 import beautifulsoup
num_sequences = defaultdict(int)
with open("/Users/edraizen/Dropbox/Membrane-Proteins/data/pfam-uniprot/pfam-polytopic_201601.txt") as pfam_f:
    pfam_f.next()
    for line in pfam_f:
        pfam = line.split()[1]
        r  = requests.get("http://pfam.xfam.org/family/{}#tabview=tab3".format(pfam))
        soup = BeautifulSoup(r.text)
        for th in soup.find_all('th'):
            if "UniProt" in th.text:
                try: num_sequences[pfam] = int(th.text.split("(")[1][:-1])
                except Exception as e: print e, pfam, th.text