python抓取图片
#!/usr/bin/env python #_*_ coding utf-8 _*_import re
import urllib.request
import urllib
import os
def getHtml(url):
page = urllib.request.urlopen(url)
html = page.read()
return html.decode('GBK')
def getImg(html):
reg = r'"(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("//").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()
页:
[1]