如何用python清洗文件中的数据

import io;
with open('a.txt', 'w') as f:    
    for line in open('c:/201509.txt'):    
        if line.find('更改项目')>0 and line.find('500')>0:  
            f.write(line+"\n");
print("输出完成");

import io;
def isData(s):
    return s.find('更改项目')>0 and s.find('500')>0;
with open('a.txt', 'w') as f:             
       list1=list(filter(isData,open('c:/201509.txt')));    
       for (offset,item) in enumerate(list1):
            f.write(str(offset)+":"+item);

import codecs
with codecs.open('c:/20160907205.log', encoding='utf_8_sig') as f:
    for line in f:
        print(line)

import codecs
with codecs.open('a.txt','a', encoding='utf_8_sig') as f:
    for i in range(205,210):
        f.write(str(i)+"\r\n");   
        print(str(i)); 
        for line in open('c:/20160907'+str(i)+'.log', encoding='utf_8_sig'): 
            if line.find('url为')>=0 :  
                print(line);
                f.write(line+"\r\n");
print("输出完成");

import codecs
a=0;
List=[];
with codecs.open('a.txt','a', encoding='utf_8_sig') as f:    
    for i in range(205,210): 
        for line in open('c:/20160907'+str(i)+'.log', encoding='utf_8_sig'): 
            if line.find('url为')>=0 :  
                ind=line.find("XFLucky");                
                if ind>=0:
                    nums=line[ind:ind+22];                    
                    print(nums);
                    List.append(nums);                   
                a=a+1;
                print(line);
                f.write(str(i)+line+"\r\n");              
List.sort(); 
for item in List:
    print(item);          
print("输出完成"+str(a));

pip install openpyxl

import re
import openpyxl

data = []
temp = []
wb = openpyxl.load_workbook('data.xlsx')
ws2 = wb.create_sheet(index=2, title='addSheet_test')
for line in open('wlzcool.sql', encoding='utf-8'):
    if line.find('CREATE TABLE') >= 0:
        matchObj1 = re.search('`(.*?)`', line, re.M | re.I)
        if matchObj1:
            # print("matchObj.group(1) : ", matchObj1.group(1))
            print(matchObj1.group(1))
            temp.append(matchObj1.group(1))
    if line.find('ROW_FORMAT = Dynamic') >= 0:
        matchObj2 = re.search('\'(.*?)\'', line, re.M | re.I)
        if matchObj2:
            # print("matchObj.group(1) : ", matchObj2.group(1))
            print(matchObj2.group(1))
            temp.append(matchObj2.group(1))
        else:
            print("no comment")
            temp.append("no comment")
        data.append(temp)
        temp = []
for row in data:
    ws2.append(row)
wb.save('data.xlsx')
print("输出完成")