python处理txt文件内容

python实现txt文件内容处理（去重序列及排序，求唯一序列）

有如下生物信息学数据，存在内容完全相同的序列。

• 需求1：找出相同序列，然后在文件中只保留他们的一个副本，并在文件中分别保留对应的原始标识符列表
• 需求2：在另外一个文件保存唯一序列

需求1

#去重序列及排序
lines_seen = set()
readDir = "123.txt"
f = open(readDir,"r")
writeDir = "456.txt"
outfile=open(writeDir,"w")

while True:
    line1 = f.readline()
    line2 = f.readline()
    if not line2: break  # EOF
    if line2 not in lines_seen:
        outfile.write(line1)
        lines_seen.add(line2)
        e = open(readDir, "r")
        while True:
            line3 = e.readline()
            line4 = e.readline()
            if not line4: break  # EOF
            if (line4 == line2) and (line3 != line1):
                outfile.write(line3)
        outfile.write(line2)

outfile.close()
print ("success")

result：

需求2

#求唯一序列
readDir = "123.txt"
writeDir = "789.txt"
lines_seen = set()
lines_remove = set()
seen = set()
outfile=open(writeDir,"w")
f = open(readDir,"r")

while True:
    line1 = f.readline()
    line2 = f.readline()
    if not line2: break  # EOF
    if line2 in seen:
        lines_remove.add(line2)
    else:
        seen.add(line2)

e = open(readDir,"r")
while True:
    line1 = e.readline()
    line2 = e.readline()
    if not line2: break  # EOF
    if line2 not in lines_remove:
        outfile.write(line1)
        outfile.write(line2)

outfile.close()
print ("success")

result：