刚刚学习Python,写了几行小代码,记录在此~
下载图片小爬虫~
# -*- coding: utf-8 -*-
__author__ = 'hcs'
import re
import urllib
def getHtml(url):
page = urllib.urlopen(url)
html = page.read()
return html
def getImg(html, save):
reg = r'src="(.+?\.jpg)" pic_ext'
imgre = re.compile(reg)
imglist = imgre.findall(html)
x = 0
for imgurl in imglist:
urllib.urlretrieve(imgurl, save+'\\%s.jpg' % x)
x = x + 1
yoururl = str(raw_input('input the url'))
savefile = str(raw_input('the path you want to save'))
html = getHtml(yoururl)
getImg(html,savefile)
删除指定后缀名的文件
# -*- coding: utf-8 -*- __author__ = 'hcs' import os yourpath = raw_input('input the path') file_end = raw_input('the file you want to delete') for path, list, file in os.walk(yourpath): for i in file: if i[-len(file_end):] == file_end: os.remove(yourpath+'\\'+i)