Question

只有2个快速怀疑：

1-我希望我的最终JSON文件替换文本提取（例如，提取的文本是ADD TO CART但我想在最终的JSON中更改为IN STOCK。是否可能？

2-我还想在我的最终JSON文件中添加一些不在网站中的自定义数据，例如“商店名称”...所以我刮的每个产品都会有商店名称。有可能吗？

我正在使用Portia和Scrapy，因此欢迎您在两个平台上提出建议。

我的Scrapy蜘蛛代码如下：

import scrapy
from __future__ import absolute_import
from scrapy import Request
from scrapy.linkextractors import LinkExtractor
from scrapy.loader import ItemLoader
from scrapy.loader.processors import Identity
from scrapy.spiders import Rule
from ..utils.spiders import BasePortiaSpider
from ..utils.starturls import FeedGenerator, FragmentGenerator
from ..utils.processors import Item, Field, Text, Number, Price, Date, Url, 
Image, Regex
from ..items import PortiaItem


class Advent(BasePortiaSpider):
    name = "advent"
    allowed_domains = [u'www.adventgames.com.au']
    start_urls = [u'http://www.adventgames.com.au/c/4504822/1/all-games-a---k.html',
                  {u'url': u'http://www.adventgames.com.au/Listing/Category/?categoryId=4504822&page=[1-5]',
                   u'fragments': [{u'valid': True,
                                   u'type': u'fixed',
                                   u'value': u'http://www.adventgames.com.au/Listing/Category/?categoryId=4504822&page='},
                                  {u'valid': True,
                                   u'type': u'range',
                                   u'value': u'1-5'}],
                   u'type': u'generated'}]
    rules = [
        Rule(
            LinkExtractor(
                allow=('.*'),
                deny=()
            ),
            callback='parse_item',
            follow=True
        )
    ]
    items = [
        [
            Item(
                PortiaItem,
                None,
                u'.DataViewCell > form > table',
                [
                    Field(
                        u'Title',
                        'tr:nth-child(1) > td > .DataViewItemProductTitle > a *::text',
                        []),
                    Field(
                        u'Price',
                        'tr:nth-child(1) > td > .DataViewItemOurPrice *::text',
                        []),
                    Field(
                        u'Img_src',
                        'tr:nth-child(1) > td > .DataViewItemThumbnailImage > div > a > img::attr(src)',
                        []),
                    Field(
                        u'URL',
                        'tr:nth-child(1) > td > .DataViewItemProductTitle > a::attr(href)',
                        []),
                    Field(
                        u'Stock',
                        'tr:nth-child(2) > td > .DataViewItemAddToCart > .wButton::attr(value)',
                        [])])]]

Answer 1

我从未使用items类变量，它看起来非常难以理解且难以理解。

我建议您使用回调方法并像这样解析它

def my_callback_func(self, response):

    myitem = PortiaItem()


    for item in response.css(".DataViewCell > form > table"):

        item['Title'] = item.css('tr:nth-child(1) > td > .DataViewItemProductTitle > a *::text').extract_first()

        item['Stock'] = item.css('tr:nth-child(2) > td > .DataViewItemAddToCart > .wButton::attr(value)').extract_first()

        if item['Stock'] == "ADD TO CART":

            item['is_available'] = "YES"

        ...... and so on

        yield item

Portia / Scrapy - 如何替换或添加值以输出JSON

1 个答案: