Question

我正在抓取以下网站https://www.trollandtoad.com/magic-the-gathering/magic-2020-m20-/14878?Keywords=&min-price=&max-price=&items-pp=60&item-condition=&selected-cat=14878&sort-order=&page-no=1&view=list&Rarity=&Ruleset=&minMana=&maxMana=&minPower=&maxPower=&minToughness=&maxToughness=，并且我需要遍历下拉列表中的数量，直到数量到尽为止，以便确定剩余库存。我在其中放置一个计数器，以确定它在循环中运行了多少次以确定剩余的库存量，但它仅在循环中运行了一次。

# Function to parse needed data
    def parse(self, response):

        # For loop to run through html code until all needed data is scraped
        for data in response.css('div.card > div.row'):
            # import items from items.py
            item = DataItem()
            # Scrape Category name
            item["Category"] = data.css("div.col-12.prod-cat a::text").get()
            # Scrape card name
            item["Card_Name"]  = data.css("a.card-text::text").get()
            item["Stock"] = data.css("div.font-weight-bold.font-smaller.text-muted::text").get()
            if item["Stock"] == None:
                item["Stock"] = "In Stock"
            # For loop to run through all the buying information needed, skips first row
            for buying_option in data.css('div.buying-options-table div.row')[1:]:
                # Scrape seller, condition, and price
                item["Seller"] = buying_option.css('div.row.align-center.py-2.m-auto > div.col-3.text-center.p-1 > img::attr(title)').get()
                if item["Seller"] == "PRE ORDER":
                    item["Seller"] = "TrollAndToad Com"
                item["Condition"] = buying_option.css("div.col-3.text-center.p-1::text").get()
                num = 0
                for select in buying_option.css('select.w-100'): # Right here is where I am trying to determine the stock by looping through drop down lsit
                    num = num + 1
                item["Price"] = buying_option.css("div.col-2.text-center.p-1::text").get()
                # Return data
                yield item

Answer 1

XPath有一种非常简单的方法：

stock_quantity = row.xpath('//select[@name="qtyToBuy"]/option[last()]/@value').get()

Answer 2

我通过基本上选择所有<option>，提取其value属性并取其最大整数值来计算数量。像这样：

quantity_options = p.css('.product-add-container .box-quantity option::attr(value)').getall()
quantity = max(map(int, quantity_options))

我也重构了您的代码

import scrapy
from scrapy.crawler import CrawlerProcess


class TrollandtoadSpider(scrapy.Spider):
    name = 'TrollAndSpider'
    start_urls = [
        'https://www.trollandtoad.com/magic-the-gathering/magic-2020-m20-/14878'
    ]
    logger = None

    def parse(self, response: scrapy.http.Response):
        for p in response.css('.product-col > .card > .row'):
            p: scrapy.Selector

            title = p.css('.prod-title a::text').get()
            category = p.css('.prod-cat a::text').get()
            stock = p.css("div.text-muted::text").get() or 'In Stock'
            quantity_options = p.css('.product-add-container .box-quantity option::attr(value)').getall()
            quantity = max(map(int, quantity_options))

            buying_opts = p.css('.buying-options-table .row:last-child [class*=col-]')
            seller = buying_opts[0].css('img::attr(title)').get()
            if seller == 'PRE ORDER':
                seller = 'TrollAndToad Com'
            condition = buying_opts[1].css('::text').get()
            price = buying_opts[3].css('::text').get()

            product = {
                'title': title,
                'category': category,
                'stock': stock,
                'seller': seller,
                'condition': condition,
                'quantity': quantity,
                'price': price,
            }

            yield product


if __name__ == '__main__':
    p = CrawlerProcess()
    p.crawl(TrollandtoadSpider)
    p.start()

输出：

{
    'title': 'Leyline of the Void 107/280',
    'category': 'Magic 2020 (M20) Singles',
    'stock': 'In Stock',
    'seller': 'TrollAndToad Com',
    'condition': 'Near Mint',
    'quantity': 6,
    'price': '$17.49'
},
{
    'title': "Sephara, Sky's Blade 036/280",
    'category': 'Magic 2020 (M20) Singles',
    'stock': 'In Stock',
    'seller': 'TrollAndToad Com',
    'condition': 'Near Mint',
    'quantity': 3,
    'price': '$3.99'
}

Answer 3

Items.py

import scrapy

class MagiccardsiteItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    Category = scrapy.Field()
    Card_Name = scrapy.Field()
    Stock = scrapy.Field()
    Seller = scrapy.Field()
    Condition = scrapy.Field()
    Price = scrapy.Field()
    Num = scrapy.Field()

蜘蛛代码

import scrapy
from MagicCardSite.items import MagiccardsiteItem


class CardinfoSpider(scrapy.Spider):
    name = 'CardInfo'

    url = 'https://www.trollandtoad.com/magic-the-gathering/magic-2020-m20-singles/15088'

    def start_requests(self):
        yield scrapy.Request(url=self.url, callback=self.parse)

    def parse(self, response):
    for row in response.xpath('//div[contains(@class,"product-col")]'):
        num = 0
        item = MagiccardsiteItem()
        item['Category'] = row.xpath('.//div[@class="col-12 prod-cat"]/u/a/text()').get()
        item['Card_Name'] = row.xpath('.//div[@class="col-12 prod-title"]/a/text()').get()
        stock = row.xpath('.//div[@class="box-quantity col-2 p-1"]/select[@class="w-100"]/option[last()]/text()').get()
        item['Stock'] = 'In Stock' if int(stock) > 0 else None
        item['Seller'] = row.xpath('.//div[@class="buying-options-table pb-3"]//img/@src').get().split('logos/')[1].replace('.png', '')
        item['Condition'] = row.xpath('.//div[@class="buying-options-table pb-3"]/div[2]/div[2]/text()').get()
        item['Price'] = row.xpath('.//div[@class="buying-options-table pb-3"]/div[2]/div[4]/text()').get()

        for option in row.xpath('.//div[@class="box-quantity col-2 p-1"]/select[@class="w-100"]/option'):
            num += 1
        item['Num'] = num

        yield item

结果

如何遍历下拉列表Scrapy

3 个答案: