import os
import re
import urllib.requestimport requestsdef 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,imgUrlsif __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&#