我正在尝试建立一个通知程序，当缺货的商品重新入库时，它将向我发送电子邮件。到目前为止，我已经缩小了如何检索商品名称和价格的范围。但是，当我尝试使用“在商店中查找”旁边的蓝色按钮“缺货”作为标签时，由于某种原因，它会检索“仅在有库存时出现”的“添加到购物车”。因此，我尝试使用标题上方的“存货不足”文本将oos_status设置为True。根据网页上i7的配置是否缺货，它应该显示为True，这在撰写本文时是这样，但是仍然显示为False，表示它有库存。改进将不胜感激。这是代码：
from urllib.request import Request, urlopen
from bs4 import BeautifulSoup as soup
url = 'https://www.microsoft.com/en-ca/p/huawei-matebook-x-pro-
laptop/8n4k86d4j006/4X0P?activetab=pivot%3aoverviewtab'
req = Request(url, headers={'User-Agent': 'Mozilla/5.0'})
uClient = urlopen(req)
page_html = uClient.read()
uClient.close()
# html parsing
page_soup = soup(page_html, 'html.parser')
# grabs OOS container
# container_oos = page_soup.findAll("div", {"class": "cli_badge context-buy-
box-badge"})
container_oos = page_soup.findAll('div', {"class": "cli_badge context-buy-
box-badge"})
# grabs price container
container_price_disclaimer = page_soup.findAll("div", {'class': "price-
disclaimer"})
# grabs name container
container_name = page_soup.findAll("div", {"class": "m-product-detail-hero-
product-placement oneui-override"})
# finds text of name, price and out of stock status
name = container_name[0].findAll('h1', {'id': 'page-title'})[0].text.strip()
price = container_price_disclaimer[0].findAll('span')[0].text.strip()
oos_status = False
# Using 'OUT OF STOCK' text above title to decide whether out of stock
if container_oos[0].find('span', {'id': 'out-of-stock-badge'}) == None:
oos_status = False
elif container_oos[0].find('span', {'id': 'out-of-stock-badge'})
[0].text.strip() == 'OUT OF STOCK':
oos_status = True
最佳答案
该页面通过AJAX调用从外部站点加载其数据。如果您查看Firefox / Chrome网络检查器，您将看到呼叫的去向。
本示例将获取有关在页面上找到的所有SKU的信息：
from bs4 import BeautifulSoup
import requests
import json
from pprint import pprint
url = 'https://www.microsoft.com/en-ca/p/huawei-matebook-x-pro-laptop/8n4k86d4j006/4X0P?activetab=pivot:overviewtab'
headers = {'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:61.0) Gecko/20100101 Firefox/61.0'}
soup = BeautifulSoup(requests.get(url, headers=headers).text, 'lxml')
url = soup.select_one('[data-availability-url]')['data-availability-url']
data = []
for data_availability_id, data_inventory_sku_id, data_sku in zip(soup.select('div.context-configuration-buttons [data-availability-id]'), \
soup.select('div.context-configuration-buttons [data-inventory-sku-id]'), \
soup.select('div#TechSpec [data-sku]')):
data.append({
'availabilityId': data_availability_id['data-availability-id'],
'distributorId': 9000000013,
'inventorySkuId': data_inventory_sku_id['data-inventory-sku-id'],
'preorder': False,
'productId': soup.select_one('[data-product-id]')['data-product-id'],
'skuId':data_sku['data-sku'],
})
r = requests.post(url, headers={'Content-Type': 'application/json'}, data=json.dumps(data))
pprint(json.loads(r.text))
这将打印：
{'availabilities': [{'Allocations': {},
'availabilityId': '8W2321TK7D0Q',
'availableLots': {'0001-01-01T00:00:00.0000000Z': {'9000000013': {'deliverByDates': {'0001': '2018-08-09T12:00:00.0000000Z',
'0004': '2018-08-16T12:00:00.0000000Z'},
'deliveryType': 'Ship',
'hasArbitraryLimitPolicy': 'False',
'inStock': 'False',
'isUnknownDate': 'False',
'onlineOrderAvailable': 'True',
'render': 'True',
'showDateOverride': 'False'}}},
'catalogSkuId': 'HB3R',
'distributorSkuId': 'QF9-01635',
'futureLots': {'2018-08-07T04:00:00.0000000Z': {'9000000013': {'deliverByDates': {'0001': '2018-08-12T12:00:00.0000000Z',
'0004': '2018-08-19T12:00:00.0000000Z'},
'deliveryType': 'Ship',
'doNotFulfillBeforeDate': 'True',
'hasManuallyConfiguredDeliveryDate': 'False',
'inStock': 'True',
'isProductLaunchFutureLot': 'True',
'isUnknownDate': 'False',
'onlineOrderAvailable': 'True',
'render': 'True',
'showDateOverride': 'False',
'warehouseAllocation': {}}}},
'inventoryControlSkuId': 'QF9-01635',
'lastWarehouseUpdateTime': '2018-08-04T06:46:49.0000000Z',
'productId': '8N4K86D4J006'},
{'Allocations': {},
'availabilityId': '8WDNCCR153LS',
'availableLots': {'0001-01-01T00:00:00.0000000Z': {'9000000013': {'deliverByDates': {'0001': '2018-08-09T12:00:00.0000000Z',
'0004': '2018-08-16T12:00:00.0000000Z'},
'deliveryType': 'Ship',
'hasArbitraryLimitPolicy': 'False',
'inStock': 'False',
'isUnknownDate': 'False',
'onlineOrderAvailable': 'False',
'render': 'True',
'showDateOverride': 'False'}}},
'catalogSkuId': '4X0P',
'distributorSkuId': 'QF9-01638',
'futureLots': {'2018-08-07T04:00:00.0000000Z': {'9000000013': {'deliverByDates': {'0001': '2018-08-12T12:00:00.0000000Z',
'0004': '2018-08-19T12:00:00.0000000Z'},
'deliveryType': 'Ship',
'doNotFulfillBeforeDate': 'True',
'hasManuallyConfiguredDeliveryDate': 'False',
'inStock': 'False',
'isProductLaunchFutureLot': 'True',
'isUnknownDate': 'False',
'onlineOrderAvailable': 'False',
'render': 'True',
'showDateOverride': 'False',
'warehouseAllocation': {}}},
'2018-09-04T04:00:00.0000000Z': {'9000000013': {'deliverByDates': {'0001': '2018-09-09T12:00:00.0000000Z',
'0004': '2018-09-16T12:00:00.0000000Z'},
'deliveryType': 'Ship',
'doNotFulfillBeforeDate': 'True',
'hasManuallyConfiguredDeliveryDate': 'False',
'inStock': 'False',
'isProductLaunchFutureLot': 'False',
'isUnknownDate': 'False',
'onlineOrderAvailable': 'False',
'render': 'True',
'showDateOverride': 'False',
'warehouseAllocation': {}}}},
'inventoryControlSkuId': 'QF9-01638',
'lastWarehouseUpdateTime': '2018-08-04T06:46:49.0000000Z',
'productId': '8N4K86D4J006'}],
'inStock': 'False'}
如您所见，有些SKU（配置）有库存，有些则没有。这取决于您要搜索的配置，该页面URL上有多个。