extract_SeqFindR_hits.py

from Bio.Blast import NCBIXML

input = 'CFT073.B2_comp.fa_blast.xml'

for record in NCBIXML.parse(open('CFT073.B2_comp.fa_blast.xml')):
    for align in record.alignments:
        for idx, hsp in enumerate(align.hsps):
            if idx == 0:
                print ">"+input.split("_")[0]+"_"+record.query.split(',')[1].strip()
                print hsp.sbjct
            else:
                print ">Multiple HSP's for"+record.query.split(',')[1].strip()+str(hsp.sbjct_start)+":"+str(hsp.sbjct_end)