python txt文件处理

输入为：

要求输出为：

代码：

file = open('test.txt','rb')
file_context = file.read().decode('utf-8')
#print ("整个文件内容:", file_context)
#写文件
outdata = open('test1.txt', 'w', encoding="utf-8")
# 以换行符为分隔符，从而将这个文件以行为单位进行分割
line = file_context.split('\n')

for i in range(0, len(line)):
    #读取每一行
    line_context = line[i]
    # print ("line_context:", line_context) 宝马 奔驰：0.9，奥迪：0.8，hh：99
    # 先以 ，为分割符进行分割
    line_context_split = line_context.split('，')
    #print(line_context_split)['\ufeff宝马 奔驰：0.9', '奥迪：0.8', 'hh：99\r']
    #将宝马取出来
    first_split = line_context_split[0].split(" ")
    first = first_split[0]
    # print ("first:", first) 宝马

    for j in range(0, len(line_context_split)):
        # print (j, line_context_split[j])
        #['\ufeff宝马 奔驰：0.9', '奥迪：0.8', 'hh：99\r']
        if j == 0:
            if "" in line_context_split[j] and "：" in line_context_split[j]:
                string = line_context_split[j].replace(" ", "\t").replace("：","\t")
                outdata.write(string+'\n')
        elif j >= 1:
            if "：" in line_context_split[j]:
                line_context_split[j] = line_context_split[j].replace("：","\t")
                string = first + "\t"+ line_context_split[j]
                outdata.write(string+'\n')

文件读取的时候是全文读取，效率低下，使用按行读取会出现空行，用另一段代码将空行删除。

file = open('test.txt',encoding='utf-8')
#print ("整个文件内容:", file_context)
#print ("--------------------------------")
#写文件
outdata = open('test1.txt', 'w', encoding="utf-8")
# 以换行符为分隔符，从而将这个文件以行为单位进行分割
for line in file.readlines():
    #读取每一行
    #line_context = str(line)
    #为分割符进行分割
    line_context_split = line.split('，')
    #print(line_context_split)['\ufeff宝马 奔驰：0.9', '奥迪：0.8', 'hh：99\r']
    #将宝马取出来
    first_split = line_context_split[0].split(" ")
    first = first_split[0]
    # print ("first:", first) 宝马

    for j in range(0, len(line_context_split)):
        # print (j, line_context_split[j])
        #['\ufeff宝马 奔驰：0.9', '奥迪：0.8', 'hh：99\r']
        if j == 0:
            if "" in line_context_split[j] and "：" in line_context_split[j]:
                string = line_context_split[j].replace(" ", "\t").replace("：","\t")
                outdata.write(string+'\n')
        elif j >= 1:
            if "：" in line_context_split[j]:
                line_context_split[j] = line_context_split[j].replace("：","\t")
                string = first + "\t"+ line_context_split[j]
                outdata.write(string+'\n')

删除空行代码：

# coding:utf-8
def delblankline(infile, outfile):
    infp = open(infile, "r",encoding='utf-8')
    outfp = open(outfile, "w",encoding='utf-8')
    lines = infp.readlines()
    for li in lines:
        if li.split():
            outfp.writelines(li)
    infp.close()
    outfp.close()

# 调用示例
if __name__ == "__main__":
    delblankline("test1.txt", "2.txt")