python爬取内容重复输出_python爬取两个excel表里的相同数据并匹配输出

import xlrd

def extract(inpath):

data = xlrd.open_workbook(inpath, encoding_override='utf-8')

table = data.sheets()[0] # 选定表

nrows = table.nrows # 获取行号

ncols = table.ncols # 获取列号

all_info =[]

teacher = getnew(inpathnew)

print(teacher)

# print(nrows)

for i in range(0, nrows): # 第0行为表头

if i == 10:

break

else:

alldata = table.row_values(i) # 循环输出excel表中每一行，即所有数据

result = alldata[0] + '、' + alldata[1] + '、' + alldata[2] + '、' + alldata[3] + '、' + alldata[4] # 取出表中第二列数据

name = '刘诗诗'

data = name in result

if data:

index = i

same_name = name

#print(result)

def getnew(inpathnew):

data = xlrd.open_workbook(inpathnew, encoding_override='utf-8')

table = data.sheets()[0] # 选定表

nrows = table.nrows # 获取行号

ncols = table.ncols # 获取列号

all_info =[]

for i in range(1, nrows): # 第0行为表头

alldata = table.row_values(i) # 循环输出excel表中每一行，即所有数据

result = alldata

#result = alldata[0] + '、' + alldata[1] + '、' + alldata[2] + '、' + alldata[3] + '、' + alldata[4] + '、' + alldata[5] # 取出表中第二列数据

all_info.append(result)

print(all_info)

#all_info = (2, 5, 8, 10, 8, 12, 23, 3, 2, 3, 5)

import itertools

original_list = all_info

new_merged_list = list(itertools.chain(*original_list))

print(new_merged_list)

arr = new_merged_list

print(arr)

n = len(arr)

for i in range(0, n):

for j in range(i + 1, n):

if (arr[i] == arr[j]):

print("%s,%s" % (arr[i], arr[j]))

# # 定义列表

# l = ["a", "b", "c", "a", "b", "c", "a"]

# # 获取第一个"a"的下标

# index_one = l.index("a")

# # 从第一个"a"的下一个位置开始查找, 所以加1

# print(l.index("a", index_one + 1))

#return all_info

inpath = ("111.xlsx") # excel文件所在路径

inpathnew = ("222.xlsx") # excel文件所在路径

#extract(inpath)

getnew(inpathnew)