import sys import os f1 = open(sys.argv[1],'r') f2 = open(sys.argv[2],'r') f3 = open(sys.argv[3],'r') fout = open(sys.argv[4],'w') dic1 = {} for line1 in f1: tmp1 = line1.strip().split() Gene_ID = tmp1[0] # anno = tmp1[1:] # dic1[Gene_ID] = anno dic2 = {} for line2 in f2: tmp2 = line2.strip().split("\t") Gene_ID = tmp2[0] gene_name = tmp2[6] dic2[Gene_ID] = gene_name dic3 = {} for line3 in f3: tmp3 = line3.strip().split("\t") new_name = tmp3[0] raw_name = tmp3[1] dic3[new_name] = raw_name for key in dic2: if key in dic1: fout.write(key + "\t" + dic2[key] + "\n") else: fout.write(key + "\t" + dic2[key] + "\t" + "NA" + "\n" ) f1.close() f2.close() fout.close()修改代码，其中f1中只有一列数据，需要根据f1文件的内容去f2文件检索找到对应的第7列信息，由于第7列每行的字符串由逗号分割，需去掉逗号并进行换行成为新的一列，再根据新的一列信息去和f3第1列匹配，最后打印出f3中与匹配结果对应的第二列信息

import sys
import os

f1 = open(sys.argv[1],'r')
f2 = open(sys.argv[2],'r')
f3 = open(sys.argv[3],'r')
fout = open(sys.argv[4],'w')

dic2 = {}
for line2 in f2:
tmp2 = line2.strip().split("\t")
Gene_ID = tmp2[0]
gene_info = tmp2[6].replace(",", "\n")
dic2[Gene_ID] = gene_info

dic3 = {}
for line3 in f3:
tmp3 = line3.strip().split("\t")
new_name = tmp3[0]
raw_name = tmp3[1]
dic3[new_name] = raw_name

for line1 in f1:
Gene_ID = line1.strip()
if Gene_ID in dic2:
gene_info = dic2[Gene_ID].strip()
if gene_info in dic3:
fout.write(Gene_ID + "\t" + gene_info + "\t" + dic3[gene_info] + "\n")
else:
fout.write(Gene_ID + "\t" + gene_info + "\t" + "NA" + "\n")
else:
fout.write(Gene_ID + "\t" + "NA" + "\t" + "NA" + "\n")

f1.close()
f2.close()
fout.close()