# coding=utf-8
import pandas as pd
# 读取txt 保存到csv
f = open('right.txt', 'r', encoding='utf-8')
lines = f.readlines()#读取全部内容
l = []
for line in lines:
res = [line.split(',')[0], line.split(',')[1], line.split(',')[2].split('>')[0], line.split(',')[2].split('>')[1], line.split(',')[2].split('>')[2].replace('"', '').replace('\n', '')]
# res = [line.split(',')[0], line.split(',')[1], line.split(',')[2], line.split(',')[3], line.split(',')[4]]
print(res)
l.append(res)
df = pd.DataFrame(l)
df.to_csv('right_new.csv', index=False, header=['id', 'title', 'class1', 'class2', 'class3'])
#********************************************************************************************************************
# coding=utf-8
import pandas as pd
# 两个csv文件,源文件,新文件, 根据源文件筛选出 新文件中重复的id,
def read_y_csv():
# 读取源文件
read_y = pd.read_csv('right_new_new.csv')
# read_y.set_index('id')
# print(read_y)
all_data = []
rows = read_y.iterrows()
for index, row in rows:
# print(row)
all_data.append(row)
print('all_data = ', len(all_data))
def read_n_csv():
# 读取新文件
read_n = pd.read_csv('right_new_1.csv', header=1)
# read_y.set_index('id')
# print(read_y)
id_list = [] # 不重复数据
id_repeat_list = [] # 重复数据
datas = []
rows = read_n.iterrows()
for index, row in rows:
# print(row[0])
if str(row[0]) not in id_list:
id_list.append(str(row[0]))
datas.append(row)
else:
id_repeat_list.append(str(row[0]))
print('id_list = ', len(id_list))
print('id_repeat_list = ', len(id_repeat_list))
# 保存不重复的数据到csv
df = pd.DataFrame(datas)
df.to_csv('right_new_new.csv', index=False)
read_n_csv()
read_y_csv()