python爬虫抓取淘宝图片

训练模型需要data，于是从网上抓取相关图片集，之后进行筛选标注。

import urllib.request
import re

keyword = '骚猪'#定义搜索关键字
keyword = urllib.request.quote(keyword)#对关键字编码

headers = ('User-Agent',"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36")
opener = urllib.request.build_opener()
opener.addheaders = [headers]
urllib.request.install_opener(opener)

for i in range(0, 20):#设定爬取页数0到20页
    #淘宝搜索页面规律
    url = 'https://s.taobao.com/search?q='+keyword+'&imgfile=&commend=all&ssid=s5-e&search_type=item&sourceId=tb.index&spm=a21bo.2017.201856-taobao-item.1&ie=utf8&initiative_id=tbindexz_20170306&bcoffset=4&ntoffset=4&p4ppushleft=1%2C48&s='+str(i*44)
    data = urllib.request.urlopen(url).read().decode('utf-8', 'ignore')
    pat = 'pic_url":"//(.*?)"'
    imagelist = re.compile(pat).findall(data)
    for j in range(0, len(imagelist)):
        thisimage = imagelist[j]
        thisurl = 'http://'+thisimage
        file = 'E:/datatb/tshirt/tshirt'+str(i)+str(j)+'.jpg'#保存图片位置
        urllib.request.urlretrieve(thisurl,file)

建议一次获取页面不要太多，不然会请求失败。