爬取淘宝上面图片

#自动爬取淘宝图片
#先看看淘宝上月饼相连的三个链接的例子（分别是第二页、第三页、第四页）：
#可以看到&p4ppushleft=1%2C48&s=44,88,132  每跳转一页增加44  这里是跳转页面抓图片的关键
'''
https://s.taobao.com/search?q=%E6%9C%88%E9%A5%BC
&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=3
&ntoffset=3
&p4ppushleft=1%2C48&s=44'''

'''
https://s.taobao.com/search?q=%E6%9C%88%E9%A5%BC
&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=0
&ntoffset=6
&p4ppushleft=1%2C48&s=88'''

'''
https://s.taobao.com/search?q=%E6%9C%88%E9%A5%BC
&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=-3
&ntoffset=-3
&p4ppushleft=1%2C48&s=132'''
import urllib.request
import re
keyname="月饼"
#汉字编码keyname可任意更换
key=urllib.request.quote(keyname)

#伪装成google浏览器报头  去浏览器中找到 use-Agent
headers=("User-Agent","Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36")
#创建oenener对象
opener=urllib.request.build_opener()
opener.addheaders=[headers]
#把opener添加为全局
urllib.request.install_opener(opener)

for i in range(0,3):
    url="https://s.taobao.com/search?q="+key+"&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=-3&ntoffset=-3&p4ppushleft=1%2C48&s="+str(i*44);
    data=urllib.request.urlopen(url).read().decode("utf-8","ignore")
#找某一个图片的地址关键（加黑地方）https://g-search1.alicdn.com/img/bao/uploaded/i4/i3/1743116853/TB2mzuwaxnaK1RjSZFtXXbC2VXa_!!1743116853-0-item_pic.jpg_180x180.jpg_.webp  在淘宝后台利用正则找到图片的链接
    pat='pic_url":"//(.*?)"'
    imagelist=re.compile(pat).findall(data)
    for j in range(0,len(imagelist)):
        thisimg=imagelist[j]
        thisimagurl="http://"+thisimg
        file="F:/python/python爬虫/img/"+str(i)+str(j)+".jpg"
        urllib.request.urlretrieve(thisimagurl,filename=file)