python 中实现 根据scaffold从fasta文件中提取数据

001、

root@PC1:/home/test# ls
a.fasta  target.txt  test.py
root@PC1:/home/test# cat test.py                 ## 测试程序
#!/usr/bin/python

in_file = open("a.fasta", "r")
target = open("target.txt", "r")
lines = target.readlines()
dict1 = dict()

for i in in_file:
    i = i.strip()
    if i[0] == ">":
        key = i
        dict1[key] = []
    else:
        dict1[key].append(i)

for i in dict1.keys():
    if (i + "\n") in lines:
        print(i)
        for j in dict1[i]:
            print(j)
in_file.close()
target.close()
root@PC1:/home/test# cat a.fasta                ## 测试fasta文件
>gene2 myc
AGCTGCCTAAGCMMMM
GGCATAGCTAATCG
>gene3 jun
ACCGAATCGGAGCGATGEEE
GGCATTAAAGATCTAGCT
>gene1 malat1
AGGCTAGCGAG
GCGCGAGKKK
GATTAGGCG
>gene4 jun
ACCGAATCGGAGCGATGYY
GGCATTAAAGATCTAGCTXXX
root@PC1:/home/test# cat target.txt                 ## 目的scaffold
>gene3 jun
>gene1 malat1
root@PC1:/home/test# python test.py                 ## 执行程序
>gene3 jun
ACCGAATCGGAGCGATGEEE
GGCATTAAAGATCTAGCT
>gene1 malat1
AGGCTAGCGAG
GCGCGAGKKK
GATTAGGCG

参考：https://www.jianshu.com/p/5ee54bea4cb0