fasta_parse.py

from itertools import groupby

def fasta_iter(fasta_name):
    '''
    given a fasta file. yield tuples of header, sequence
    modified from Brent Pedersen
    Correct Way To Parse A Fasta File In Python
    https://www.biostars.org/p/710/
    '''
    with open(fasta_name) as f:
        # ditch the boolean (x[0]) and just keep the header or sequence since
        # we know they alternate.
        data = (x[1] for x in groupby(f, lambda line: line[0] == ">"))
        for header in data:
            # drop the ">"
            header = header.__next__()[1:].strip()
            # join all sequence lines to one.
            seq = "".join(s.strip() for s in data.__next__())
            yield(header, seq)