Python爬取唯品会商品数据，钱包准备好了嘛

这里就省略了~

• 第一页

• 第二页

pageOffset参数的变化每120个数据翻一页嘛，ID都获取了，前面也看到每个商品数据接口对应的是50条数据，经过分析就知道 120个商品划分为是三个 50,50,20 分别传入相对应的商品ID就可以了。

[](()实现代码

---

• 获取每页商品ID值

for page in range(0, 1201, 120):

url = 'https://mapi.vip.com/vips-mobile/rest/shopping/pc/search/product/rank'

headers = {

'referer': 'https://category.vip.com/suggest.php?keyword=%E5%8F%A3%E7%BA%A2&ff=235%7C12%7C1%7C1&page=3',

'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36'

}

params = {

'callback': 'getMerchandiseIds',

'app_name': 'shop_pc',

'app_version': '4.0',

'warehouse': 'VIP_NH',

'fdc_area_id': '104104101',

'client': 'pc',

'mobile_platform': '1',

'province_id': '104104',

'api_key': '70f71280d5d547b2a7bb370a529aeea1',

'user_id': '',

'mars_cid': '1602569282048_0b4beb3d18306a0a0143c359ddb34fae',

'wap_consumer': 'a',

'standby_id': 'nature',

'keyword': '口红',

'lv3CatIds': '',

'lv2CatIds': '',

'lv1CatIds': '',

'brandStoreSns': '',

'props': '',

'priceMin': '',

'priceMax': '',

'vipService': '',

'sort': '0',

'pageOffset': '{}'.format(page),

'channelId': '1',

'gPlatform': 'PC',

'batchSize': '120',

'_': '1603721644362',

}

response = requests.get(url=url, params=params, headers=headers)

ids = re.findall('"pid":"(.*?)"', response.text, re.S)

• 获取商品数据

def get_data(num_id):

data_url = 'https://mapi.vip.com/vips-mobile/rest/shopping/pc/product/module/list/v2'

headers = {

'referer': 'https://category.vip.com/suggest.php?keyword=%E5%8F%A3%E7%BA%A2&ff=235%7C12%7C1%7C1&page=3',

'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36'

}

params = {

'callback': 'getMerchandiseDroplets2',

'app_name': 'shop_pc',

'app_version': '4.0',

'warehouse': 'VIP_NH',

'fdc_area_id': '104104101',

'client': 'pc',

'mobile_platform': '1',

'province_id': '104104',

'api_key': '70f71280d5d547b2a7bb370a529aeea1',

'user_id': '',

'mars_cid': '1602569282048_0b4beb3d18306a0a0143c359ddb34fae',

'wap_consumer': 'a',

'productIds': '{}'.format(num_id),

'scene': 'search',

'standby_id': 'nature',

'extParams': '{"stdSizeVids":"","preheatTipsVer":"3","couponVer":"v2","exclusivePrice":"1","iconSpec":"2x"}',

'context': '',

'_': '1603721644366',

}

response_2 = requests.get(url=data_url, params=params, headers=headers)

titles = re.findall('"title":"(.*?)"', response_2.text, re.S) # 标题

salePrice = re.findall(',"salePrice":"(.*?)",', response_2.text, re.S) # 售价

marketPrice = re.findall('"marketPrice":"(.*?)"', response_2.text, re.S) # 原价

saleDiscount = re.findall('"saleDiscount":"(.*?)"', response_2.text, re.S) # 折扣

smallImage = re.findall('"smallImage":"(.*?)"', response_2.text, re.S) # 商品图片地址

lis = zip(titles, salePrice, marketPrice, saleDiscount, smallImage)

dit = {}

for li in lis:

dit['商品名字'] = li[0]

dit['售价'] = li[1]

dit['原价'] = li[2]

dit['折扣'] = li[3]

dit['商品图片地址'] = li[4]

print(dit)