爬取淘宝图片

import os
import re
import urllib.request

import requests


def getHtml(url,headers):
    # 代理设置
    proxy = urllib.request.ProxyHandler({'http': '118.190.95.26:9001'})  # 字典
    # 基本的urlopen不支持代理、cookie等其他Http/Https高级功能,自定义opener()
    opener = urllib.request.build_opener(proxy, urllib.request.HTTPHandler)
    urllib.request.install_opener(opener)
    opener.addheaders = [headers]  # 列表
    data = urllib.request.urlopen(url).read().decode('utf-8', 'ignore')
    pat='"pic_url":"(.*?)"'
    imgUrls=re.findall(pat,data)
    return data,imgUrls


if __name__=='__main__':
    keyword='李冰冰'
    #quote编码
    keyword=urllib.request.quote(keyword)
    pageString='0'
    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=-3&ntoffset=-3&p4ppushleft=1%2C48&s='+pageString
    headers = ('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64; rv:43.0) Gecko/20100101 Firefox/43.0')
    data = getHtml(url,headers)[0]
    print(data)
    pat='"totalPage":(.*?),'
    totalPage=int(re.findall(pat,data)[1])
    print(totalPage)
    path = os.path.join(os.getcwd(), 'img')
    os.makedirs(path)
    for page in range(totalPage):
        pathpage = os.path.join(path, '第'+str(page+1)+'页')
        os.makedirs(pathpage)
        pageString=str(page*44)
        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=-3&ntoffset=-3&p4ppushleft=1%2C48&s=' + pageString
        imgUrls=getHtml(url, headers)[1]
        for i in range(1, len(imgUrls)):
            try:
                url='http:'+imgUrls[i]
                print(url)
                fileurl=pathpage+'/'+str(i)+'.jpg'
                r=requests.get(url)
                with open(fileurl,"wb") as f:
                    f.write(r.content)
            except :
                print('fuck off')