云盘本地数据查重
''' 功能: 1.查询所有md5 2.找出重复值 3.根据重复值输出 文件目录(parent_path)+文件名(server_filename) a = [99,1,2,1,3,4] # 集合存储重复数据 b=set() for i in a: if a.count(i)>1: b.update([i]) dict ={} # 遍历重复数据 for j in b: list = [] for A in range(len(a)): if j == a[A]: list.append(A) dict[j] = list print(dict) ''' import sqlite3,time def repeats(): db=sqlite3.connect('hxz.db') c=db.cursor() c.execute('SELECT md5 from cache_file') md5s=c.fetchall() md5s_cf=set() for i in md5s: if md5s.count(i)>1: md5s_cf.update([i]) md5s=list(md5s_cf) print(type(md5s)) md5_l=[] for (i,) in md5s: ## print(i) md5_l.append(i) #print(md5_l) paths={} for j in md5_l: c.execute('SELECT parent_path, server_filename FROM cache_file WHERE md5='+'\''+j+'\'') paths[]=c.fetchone() paths.append(path) ##for (path,) in paths: ## print(path) print('paths长度是:',len(paths)) while "" in paths: paths.remove(" ") db.close() print('去空后的paths长度是:',len(paths)) ## return paths repeats()
数据库(右键打开位置,找到users点进去,第一个.db即文件列表,内含hd5),复制到同一目录:
''' 功能: 1.查询所有md5 2.找出重复值 3.根据重复值输出 文件目录(parent_path)+文件名(server_filename) a = [99,1,2,1,3,4] # 集合存储重复数据 b=set() for i in a: if a.count(i)>1: b.update([i]) dict ={} # 遍历重复数据 for j in b: list = [] for A in range(len(a)): if j == a[A]: list.append(A) dict[j] = list print(dict) ''' import sqlite3,time def repeats(): db=sqlite3.connect('hxz.db') c=db.cursor() c.execute('SELECT md5 from cache_file') md5s=c.fetchall() md5s_cf=set() for i in md5s: if md5s.count(i)>1: md5s_cf.update([i]) md5s=list(md5s_cf) print(type(md5s)) md5_l=[] for (i,) in md5s: ## print(i) md5_l.append(i) #print(md5_l) paths=[] for j in md5_l: c.execute('SELECT server_filename FROM cache_file WHERE md5='+'\''+j+'\'') path=c.fetchone() paths.append(path) ##for (path,) in paths: ## print(path) print('paths长度是:',len(paths)) while "" in paths: paths.remove(" ") db.close() print('去空后的paths长度是:',len(paths)) return paths ##repeats()