#!/usr/bin/env python#_*_ coding utf-8 _*_import reimport urllib.requestimport urllibimport osdef getHtml(url):
page = urllib.request.urlopen(url)
html = page.read() return html.decode('GBK')def getImg(html):
reg = r'[src=|"p_img_url":]"(http://pic.xxxx.com/upload/.+?.jpg)'
imgre = re.compile(reg,re.I)
imglist = imgre.findall(html) for imgurl in imglist:
print(imgurl)
urllib.request.urlretrieve(imgurl,'{}{}'.format(paths,imgurl.split("//")[1].split('/')[-1]))#根据商品ID抓取图片f=open('id1.txt','r')for i in f.readlines():
num1=i.replace('n','')
path = 'D:\test\'+num1 if not os.path.isdir(path):
os.makedirs(path)
paths = path+'\'
html = getHtml("http://www.xxxx.com/Product-0-%s.htm" % num1)
getImg(html)
f.close()
