用python从gbff文件中提取cds序列

import re

FILE_PATH = './input.gb'
OUT_FILE_PATH = './output.fasta'

d = {}
g = {}
tem = []

def con_spl(list_,n = 2):
    return [list_[i:i + n] for i in range(0, len(list_), n)]

with open (FILE_PATH,'r')as f:
    
    while True:

        text_line = f.readline().strip('t').split()

        if text_line:

            if text_line[0] == 'DEFINITION':

                c = ' '.join(i for i in text_line[2:])
                d[c] = []
                g[c] = []

                print (text_line)

            elif text_line[0] == 'CDS':

                cds = re.findall(r"d+d*?",text_line[1])
                if len(cds) == 2:
                    d[c].append(cds)

                else:
                    for i in con_spl(cds):
                        d[c].append(i)

            elif text_line[0] == 'ORIGIN':

                while text_line[0] != '//':

                    for i in text_line[1:]:
                        tem.append(i)

                    text_line = f.readline().strip('t').split()
                
                e = ''.join(i for i in tem)
                g[c].append(e)

            else:
                pass

        elif f.readline().strip('t').split():

            continue

        else:
            break

with open (OUT_FILE_PATH,'w')as f:
    for i,o in d.items():
        G = ''.join(g[i])
        p = ''
        for u in o:
            u1 = int(u[0])
            u2 = int(u[1])+1
            p += G[u1:u2]
        print ('>',i,sep='',file=f)
        print (p,file=f)