58 lines
1.6 KiB
Python
58 lines
1.6 KiB
Python
# -*- coding: utf-8 -*-
|
||
import sys
|
||
import copy
|
||
|
||
|
||
def read_files(filename):
|
||
all = dict()
|
||
with open(filename, 'r') as f:
|
||
data = f.read().strip()
|
||
for line in data.split("\n"):
|
||
try:
|
||
all[line.split("======")[-1]] = line.split("======")[0]
|
||
|
||
except Exception:
|
||
pass
|
||
return all
|
||
|
||
|
||
def main():
|
||
# 要读的文件写入其中，多条记录用,分割，注意不要用全角的"，"
|
||
filenames = ("a.txt", "b.txt")
|
||
|
||
# 记录所有数据，标题为字典的key，URL为字典的值(如果有价格，可以将(url,价格)作为字典的values)
|
||
new_data = dict()
|
||
# 这个列表记录有交集的标题，会在数据统计完毕从new_data中删除
|
||
intersection = list()
|
||
for filename in filenames:
|
||
data = read_files(filename)
|
||
for key in data.keys():
|
||
if key in new_data:
|
||
intersection.append(key)
|
||
else:
|
||
new_data[key] = data[key]
|
||
# 将全部数据做一个备份，可能会有其他需求用到
|
||
all_data = copy.deepcopy(new_data)
|
||
with open('out1.txt', "a+") as f:
|
||
for item in intersection:
|
||
all_data.pop(item)
|
||
#将重复的内容写入out1.txt
|
||
temp = f"{new_data[item]}===={item}\n"
|
||
f.write(temp)
|
||
|
||
|
||
|
||
out = list()
|
||
with open('out.txt', "a+") as f:
|
||
for key in all_data:
|
||
# 这种写法是python3.6后支持的，版本低的话可以写temp="{0}===={1}".format(all_data[key],key)
|
||
temp = f"{all_data[key]}===={key}\n"
|
||
out.append(temp)
|
||
f.write(temp)
|
||
|
||
print(out)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
main()
|