PyPy optimized version for http://saml.rilspace.org/gc-content-continued-python-vs-d-vs-c-vs-free-pascal optimizations: reading file in binary mode and readlines with size hint

gistfile1.py

import timeit
tfunc = timeit.default_timer

def main():
    file = open("Homo_sapiens.GRCh37.61.dna_rm.chromosome.Y.fa","rb")
    gcCount = 0
    totalBaseCount = 0
    while 1:
        lines = file.readlines(10000)
        if not lines:
            break        
        for line in lines:
            if line and not line[0] == ">":
                for c in line:
                    if c == 'C' or c == 'T' or c == 'G' or c == 'A':
                        totalBaseCount += 1
                        if c == 'G' or c == 'C':
                            gcCount += 1
    gcFraction = float(gcCount) / float(totalBaseCount) 
    return gcFraction

if __name__ == '__main__':
    t0 = tfunc()
    gcFraction = main()
    elapsed = tfunc() - t0
    print(gcFraction * 100)
    print(elapsed)