为了使处理文件时用 utf-8 编码,做如上编码声明
1 2 3 4 5
| import hashlib def md5(text): m = hashlib.md5() m.update(text) return m.hexdigest()
|
利用 hashlib 进行 md5 编码
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34
| def import_points_csv(filename,outfilename): print(filename) g=file(outfilename,"w+") with open(filename, 'r') as f: line = f.readline() while line: line = line.replace('n','') line = line.replace('r','') row = line.split(',') state = row[0].strip() date = row[20] thistype = '国控' print(thistype) name = row[1].strip() stationid = md5(name+state+thistype) row[21] = stationid md5id = md5(date+stationid) row[22] = md5id row[1] print(row) for i in range(0, len(row)-1): row[i] = row[i] + ',' g.writelines(row) g.writelines('n') line = f.readline() g.close()
|
1
| import_points_csv('国控2.csv'.decode('utf-8').encode('gbk'),'contry_2.csv')
|
由于文件名是中文,因此要将其编码才能被程序读取,不然在运行时显示文件名为乱码且无法读取