使用python处理txt到csv

 

 代码如下

import os
import pandas as pd
import re
# 获取目标文件夹的路径
filedir = 'D:\xxxx'
# 获取当前文件夹中的文件名称列表
filenames = os.listdir(filedir)
# 打开当前目录下的result.txt文件，如果没有则创建
post_title = []
post_kind = []
post_content = []


i = 0
# 先遍历文件名
for filename in filenames:
    i += 1
    print(i)
    keystart1='xxx'
    keyend1='xx'
    keystart2='xxxx'
    keyend2='xxxxx'
    if i > 0:
        filepath = filedir + '\\' + filename
        print(filepath[:-4])
        post_title.append(filename[:-4])

        g = open(filepath, encoding='gbk', errors='ignore')
      #  pat1 = re.compile(keystart1 + '(.*?)' + keyend1, re.S)
      #  result1 = pat1.findall(g.read())
        pat2 = re.compile(keystart2 + '(.*?)' + keyend2, re.S)
        result2 = pat2.findall(g.read())
        post_content.append(result2)
      #  post_kind.append(result1)
       # print(result1)
        #print(result2)
    g = open(filepath, encoding='gbk', errors='ignore')
    pat1 = re.compile(keystart1 + '(.*?)' + keyend1, re.S)
    result1 = pat1.findall(g.read())
    if "[]" in result1:
        #pat3 = re.compile('类别' + '(.*?)' + '种类', re.S)
        ret = re.search('类别(.*?)种类', g.read(),re.S)
        #result3 = pat3.findall(g.read())
        post_kind.append(ret.group(1))
    else:
        post_kind.append(result1)
print(post_title)
#print(post_content)

df = pd.DataFrame({'post_title': post_title,
                   'post_kind':post_kind,
                   'post_content': post_content
                   })
print(df)
df.to_csv("D:xxx\output3.csv", encoding='utf_8_sig')
print('########导出完成############')