import requests
import re
import json

def spider(sn):
    url = 'https://s.taobao.com/search?q={0}'.format(sn)
    #get html content
    text = requests.get(url, headers={
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.344'
                      '0.106 Safari/537.36',
        'cookie': '我的cookies'
    }).text

    #get json obect by using regular expression
    p = re.compile(r'g_page_config = (\{.+\});\s*', re.M)

    rest = p.search(text)
    print(rest)

    if rest:
        print(rest.group(1))
        data = json.loads(rest.group(1))
        bk_list = data['mods']['itemlist']['data']['auctions']
        print(len(bk_list))

        #get book list
        for bk in bk_list:
            #name
            title = bk['raw_title']

            #price
            price = bk['view_price']

            #link
            link = bk['detail_url']

            #store
            store = bk['nick']
            
            book_list.append({'title': title, 'price': price, 'link': link, 'store': store})
            print('{title}:{price}:{link}:{store}'.format(title=title, price=price, link=link, store=store))

           

if __name__ == '__main__':
    sn = '9787115428028'
    spider(sn)