Python开发【笔记】：从海量文件的目

for i in $(seq 1 1000000);do echo text >>$i.txt;done

# 系统命令 ls -l

import time
import subprocess

start = time.time()
result = subprocess.Popen('ls -l /dd/', stdout=subprocess.PIPE,shell=True)

for file in result.stdout:
    pass
print(time.time()-start)

# 直接卡死

# glob 模块

import glob
import time


start = time.time()
result = glob.glob("/dd/*")
for file in result:
    pass
print(time.time()-start)

# 49.60481119155884

# os.walk 模块

import os
import time

start = time.time()
for root, dirs, files in os.walk("/dd/", topdown=False):
        pass
print(time.time()-start)

# 8.906772375106812

# os.scandir 模块

import os
import time

start = time.time()
path = os.scandir("/dd/")
for i in path:
    pass
print(time.time()-start)

# 4.118424415588379

# shell find命令

import time
import subprocess

start = time.time()
result = subprocess.Popen('find /dd/', stdout=subprocess.PIPE,shell=True)

for file in result.stdout:
    pass
print(time.time()-start)

# 6.205533027648926

# shell ls -1  -f 命令

import time
import subprocess

start = time.time()
result = subprocess.Popen('ls -1 -f /dd/', stdout=subprocess.PIPE,shell=True)

for file in result.stdout:
    pass
print(time.time()-start)

# 3.3476643562316895

# os.listdir

import os
import time


start = time.time()
result = os.listdir('/dd')
for file in result:
    pass
print(time.time()-start)

# 2.6720399856567383