citespace数据处理:用python对Ref文档进行去重方式

#coding:utf-8
#__author__ ='pig'

# 实现去重功能

import re
# 需要去重的标题列表
title_need_delete = []

f0 = open('D:\Desktop\数据\\need_delete.txt',encoding='utf-8')
for line in f0.readlines():
    title_need_delete.append(line)
#print(title_need_delete)
# 一键多值字典0
dict={}

# 标题列表
title_list = []

f1=open('D:\Desktop\数据\\sum.txt',encoding='utf-8')
data=f1.readlines()
# print data1
f1.close()
num = 0
# 第一次遍历：构建字典，能看出每篇文章出现的次数
for index,line in enumerate(data):
    if line[0:2] == 'T1':
        num+=1
        title = line[3:]
        if title not in title_list:
            # 向字典中添加新key
            dict.setdefault(title,[]).append(1)
            title_list.append(title)

        else:
            # 修改该文章出现的次数
            dict[title][0] += 1

#print(dict)
print("原数据量："+str(num))

f2 = open('after_delete.txt', 'w', encoding='utf-8')

delete_num = 0
after_num = 0
# 第二次遍历：将文本写入新文件（每篇文章数据整段写入），对于每篇文章，若出现在黑名单中，则需要跳过，直到最后一次出现才写入
for index,line in enumerate(data):
    # 每篇文章先判定
    if line[0:2] == 'RT':
        # 定位至标题行
        index_1 = index
        while(data[index_1][0:2] != 'T1'):
            index_1 += 1
        # 提取标题
        title = data[index_1][3:]
        # 如果在黑名单里且不是最后一次出现,则跳过此文章，并将字典中次数-1
        if title in title_need_delete and dict[title][0] > 1:
            # print('跳过：'+ title)
            dict[title][0] -= 1
            delete_num += 1
            # 跳过
            continue
        else :
            # 不在黑名单中则正常写
            f2.writelines(data[index])
            after_num += 1
            index += 1
            while(data[index][0:2] != 'RT'):
                f2.writelines(data[index])
                index += 1
                if index == len(data):
                    break
print("去重完成！")
print("删除重复数据：" + str(delete_num))
print("剩余数据：" + str(after_num))
f2.close()

# -*- coding:utf-8 -*-
 
import os
import hashlib
import time
import sys
#搞到文件的MD5
def get_ms5(filename):
    m = hashlib.md5()
    mfile = open(filename , "rb")
    m.update(mfile.read())
    mfile.close()
    md5_value = m.hexdigest()
    return md5_value
#搞到文件的列表
def get_urllist():
    base = ("D:\\lwj\\spider\\pic\\")#这里就是你要清缴的文件们了
    list = os.listdir(base)
    urllist = []
    for i in list:
        url = base + i
        urllist.append(url)
 
    return urllist
#主函数
if __name__ == '__main__':
    md5list = []
    urllist = get_urllist()
    print("test1")
    for a in urllist:
        md5 = get_ms5(a)
        if(md5 in md5list):
            os.remove(a)
            print("重复：%s" % a)
        else:
            md5list.append(md5)
            print("一共%s张照片" % len(md5list))