import os header = ["[REF]", "[QRY]", "[Sequences]", "TotalSeqs", "AlignedSeqs", "UnalignedSeqs", "[Bases]", "TotalBases","AlignedBases", "UnalignedBases", "[Alignments]", "1-to-1", "TotalLength", "AvgLength", "AvgIdentity","M-to-M", "TotalLength", "AvgLength", "AvgIdentity", "[Feature Estimates]", "Breakpoints", "Relocations", "Translocations", "Inversions", "Insertions", "InsertionSum", "InsertionAvg", "TandemIns", "TandemInsSum","TandemInsAvg", "[SNPs]", "TotalSNPs"] data = {} for file_name in os.listdir("/public/work/Personal/wuxu/qiantao_17"): if file_name.endswith(".report"): # print(file_name, end="\n") with open(os.path.join("/public/work/Personal/wuxu/qiantao_17", file_name), "r") as f: for line in f: split_line = line.strip().split() if len(split_line) < 2: # 检查是否有足够的元素 continue # 没有则忽略该行 key, value = split_line[:2] if key not in data: # 创建一个包含标题行的列表，以避免在处理某些键时出现“Index out of range”错误 data[key] = header if key == "[REF]" else [value] else: data[key].append(value) # 输出表头 #print(*header, sep="\t") print("file_name", *header, sep="\t") # 输出数据 for file_name in os.listdir("/public/work/Personal/wuxu/qiantao_17"): if file_name.endswith(".report"): print(file_name, end="\n") for i in range(len(data.get("[REF]", []))): row = [data.get(key, [""] * len(data.get("[REF]", [])))[i] for key in header] print(*row, sep="\t")修改此脚本，将file_name作为每行的第一列，其余每行每列为与其对应的row

修改后的代码如下：

import os

header = ["[REF]", "[QRY]", "[Sequences]", "TotalSeqs", "AlignedSeqs", "UnalignedSeqs", "[Bases]", "TotalBases","AlignedBases", "UnalignedBases", "[Alignments]", "1-to-1", "TotalLength", "AvgLength", "AvgIdentity","M-to-M", "TotalLength", "AvgLength", "AvgIdentity", "[Feature Estimates]", "Breakpoints", "Relocations", "Translocations", "Inversions", "Insertions", "InsertionSum", "InsertionAvg", "TandemIns", "TandemInsSum","TandemInsAvg", "[SNPs]", "TotalSNPs"]

data = {}
for file_name in os.listdir("/public/work/Personal/wuxu/qiantao_17"):
    if file_name.endswith(".report"):
        with open(os.path.join("/public/work/Personal/wuxu/qiantao_17", file_name), "r") as f:
            for line in f:
                split_line = line.strip().split()
                if len(split_line) < 2:
                    continue
                key, value = split_line[:2]
                if key not in data:
                    data[key] = header if key == "[REF]" else [value]
                else:
                    data[key].append(value)

# 输出表头
print("file_name", *header, sep="\t")

# 输出数据
for file_name in os.listdir("/public/work/Personal/wuxu/qiantao_17"):
    if file_name.endswith(".report"):
        for i in range(len(data.get("[REF]", []))):
            row = [file_name] + [data.get(key, [""] * len(data.get("[REF]", [])))[i] for key in header]
            print(*row, sep="\t")

修改后，每行的第一列为文件名，其余每列为对应的数据。