淘宝商品图片爬虫

# 淘宝商品图片爬虫
import urllib.request
import re
import random
keyname="连衣裙"
key=urllib.request.quote(keyname)
uapools=[
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/61.0.3163.100 Safari/537.36",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.106 BIDUBrowser/8.7 Safari/537.36",
]

def ua(uapools):
    thisua=random.choice(uapools)
    print(thisua)
    headers=("User-Agent",thisua)
    opener=urllib.request.build_opener()
    opener.addheaders=[headers]
    # 安装为全局
    urllib.request.install_opener(opener)
for i in range(1,101):
    url="https://s.taobao.com/search?q="+key+"&s="+str((i-1)*44)
    ua(uapools)
    data=urllib.request.urlopen(url).read().decode("utf-8","ignore")
    pat='"pic_url":"//(.*?)"'
    imglist=re.compile(pat).findall(data)
    for j in range(0,len(imglist)):
        thisimg=imglist[j]
        thisimgurl="http://"+thisimg
        localfile="F:/pycharmxuexi/淘宝图片/"+str(i)+str(j)+".jpg"
        urllib.request.urlretrieve(thisimgurl,filename=localfile)