发布时间:2019-08-30 08:31:09编辑:auto阅读(1910)
一个同事有两个excel表格要比较差异, 找了一下有相关软件,如: beyond compare, excel compare
但这两个似乎都是直接排序再比较的.
然后没办法,就用python折腾了一个脚本. 这个脚本先读入要比较的文件中的表. 读的时候 ,如果没有空行就把它和它前面的加一起,直到有空行. 这样比较的话, 不能得到具体那一行有差异, 只有一个大概的位置. 如果表格中间空行越少,越精确.
#!/usr/bin/python #-*- coding:utf-8 -*- import xlrd, os, sys if len(sys.argv) != 3: print "\n ./script diff_1.xlsx diff_2.xlsx \n" sys.exit() diff = {} xls1 = sys.argv[1] xls2 = sys.argv[2] if os.path.isfile(xls1) and os.path.isfile(xls2): pass else: print "\n ./script diff_1.xlsx diff_2.xlsx \n" sys.exit() def getcontent(table): #获取xlsx表内容 tmp_data = {} tmp_table = '' all_data = {} for j in xrange(table.nrows): tmp = table.row_values(j) if list(set(tmp)) == ['']: tmp_data[tmp_table] = '' if tmp_table != '': all_data[j] = tmp_table tmp_table = '' else: tmp2 = "" for i in tmp: try: tmp2 = tmp2 + i + "," except: tmp2 = tmp2 + str(i)+ "," tmp_table = tmp_table + tmp2 + "\n" #把多行的内容放一起 return (tmp_data, all_data) def write_file(excel_diff, filename): f = open(filename, 'w') f.write(excel_diff) f.close() def diff_content(table1,table2): #检查两个表差异 diff_tmp = [] for i in table1: if i in table2: pass else: diff_tmp.append(i) return list(set(diff_tmp)) def get_rows(diff, all_data): #获取差异位置 tmp = [] for i in diff: for j in all_data: if all_data[j].strip() == i.strip(): tmp.append(j) break return tmp for i in range(0,2): # 比较几个表 data1 = xlrd.open_workbook(xls1) table1 = data1.sheets()[i] data2 = xlrd.open_workbook(xls2) table2 = data2.sheets()[i] tmp1, all1 = getcontent(table1) tmp2, all2 = getcontent(table2) result = diff_content(tmp1, tmp2) #1 中有 2 没有的具体内容 # result2= diff_content(tmp2, tmp1) #2 中有 1 没有的具体内容 diff[i] = get_rows(result,all1) print sorted(diff[i]) # write_file(sorted(diff[i]), "/tmp/diff.txt") # diff[i] = get_rows(result2,all2) # print sorted(diff[i])
上一篇: python 产生随机数,随机字符串
下一篇: 【AI基础】python:opencv—
47874
46440
37327
34769
29340
26004
24954
19973
19573
18069
5815°
6443°
5955°
5983°
7088°
5932°
5973°
6466°
6430°
7813°