執行程式，輸入想要爬取的商品關鍵詞，在程式碼中的‘###’可以進一步約束商品的屬性，比如某某作者的書籍，可以在###處輸入作者名字，以及時期等等。最後可以得到所要商品的總銷量

import requests
import bs4
import re
import json

def open(keywords, page):
      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"}

      payload = {'q':keywords, 'sort':"sale-desc", 's':(page-1)*44}
      url = "https://s.taobao.com/search"

      res = requests.get(url, params = payload)
      return res
      
      
def get_item(res):

      g_page_config = re.search(r'g_page_config = (.*?);\n', res.text)
      page_config_json = json.loads(g_page_config.group(1))
      page_item = page_config_json['mods']['itemlist']['data']['auctions']

      result = []#整理出我們關注的資訊(ID,標題，連結，售價，銷量和商家)
      for each in page_item:
            dict1 = dict.fromkeys(('id','title','link','price','sale','shoper'))
            dict1['id'] = each['nid']
            dict1['title'] = each['title']
            dict1['link'] = each['detail_url']
            dict1['price'] = each['view_price']
            dict1['sale'] = each['view_sales']
            dict1['shoper'] = each['nick']
            result.append(dict1)

      return result
            
def count_sales(items):
      count = 0
      for each in items:
            if '###' in each['title']:#規定只取標題中‘###’的商品
                  count += int(re.search(r'\d+',each['sale']).group())
                  
      return count

def main():

      keywords = input("請輸入搜尋關鍵詞：")#可以為各種商品名稱
      length = 10#淘寶商品頁數
      total = 0
      
      for each in range(length):
            res = open(keywords, each+1)
            items = get_item(res)
            total += count_sales(items)#銷售總量
      print(total)


if __name__ == "__main__":
      main()