写个函数，用来批量输出字符串上多次匹配的位置信息

def findplace(str,seq):
	import re
	place = []
	end = 0
	pattern = re.compile(seq)
	while(1):
		a = pattern.search(str,end)
		if a  == None:
			return place
			break
		else:
			position  = a.span()
			place.append(position)
			end = position[1]

使用方式：

position = findplace(seq1,"N+")

seq1为字符串，本次全部脚本是为了找出一个fasta序列中的全部NNN所在的位置信息

现将全部脚本列下

#find the place of N
import sys,re
f1 = open(sys.argv[1],'r')
seq1 = ""
for i in f1:
	if re.match(">",i):
		continue
	else:
		i=i.strip("\n")
		seq1 = seq1+i
#print(seq1[97865:97983])
def findplace(str,seq):
	import re
	place = []
	end = 0
	pattern = re.compile(seq)
	while(1):
		a = pattern.search(str,end)
		if a  == None:
			return place
			break
		else:
			position  = a.span()
			place.append(position)
			end = position[1]

position = findplace(seq1,"N+")
#print(position)
for i in range(len(position)):
	num = i+1
	st = position[i][0]+1
	ed = position[i][1]
	le = ed - st +1
	print("loc{}\t{}\t{}\t{}".format(num,st,ed,le))

使用脚本的命令为：

python find_N.py data\out.masked.fasta > position.xlsx

输出的结果为：