私は現在、私の最初の治療プロジェクトを構築中です。現在、私はHTMLテーブルからデータを抽出しようとしています。ここに私のクロールスパイダーは、これまでのところです:Scrapy Csv exportにはすべてのデータが1つのセルに抽出されています
import scrapy
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor
from digikey.items import DigikeyItem
from scrapy.selector import Selector
class DigikeySpider(CrawlSpider):
name = 'digikey'
allowed_domains = ['digikey.com']
start_urls = ['https://www.digikey.com/products/en/capacitors/aluminum-electrolytic-capacitors/58/page/3?stock=1']
['www.digikey.com/products/en/capacitors/aluminum-electrolytic-capacitors/58/page/4?stock=1']
rules = (
# Extract links matching 'category.php' (but not matching 'subsection.php')
# and follow links from them (since no callback means follow=True by default).
Rule(LinkExtractor(allow=('/products/en/capacitors/aluminum-electrolytic-capacitors/58/page/3?stock=1',), deny=('subsection\.php',))),
)
def parse_item(self, response):
item = DigikeyItem()
item['partnumber'] = response.xpath('//td[@class="tr-mfgPartNumber"]/a/span[@itemprop="name"]/text()').extract()
item['manufacturer'] = response.xpath('///td[6]/span/a/span/text()').extract()
item['description'] = response.xpath('//td[@class="tr-description"]/text()').extract()
item['quanity'] = response.xpath('//td[@class="tr-qtyAvailable ptable-param"]//text()').extract()
item['price'] = response.xpath('//td[@class="tr-unitPrice ptable-param"]/text()').extract()
item['minimumquanity'] = response.xpath('//td[@class="tr-minQty ptable-param"]/text()').extract()
yield item
parse_start_url = parse_item
それはwww.digikey.com/products/en/capacitors/aluminum-electrolytic-capacitors/58/page/4?stock=1でテーブルを掻き取ります。その後、すべてのデータをdigikey.csvファイルにエクスポートしますが、すべてのデータは1つのセルに格納されます。 Csv file with scraped data in one cell
setting.py
BOT_NAME = 'digikey'
SPIDER_MODULES = ['digikey.spiders']
NEWSPIDER_MODULE = 'digikey.spiders'
# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'digikey ("Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36")'
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
私は情報がその部品番号に関連付けられた対応する情報を一度に1行で掻き取りたいです。すべてのヘルプははるかに高く評価されて
import scrapy
class DigikeyItem(scrapy.Item):
partnumber = scrapy.Field()
manufacturer = scrapy.Field()
description = scrapy.Field()
quanity= scrapy.Field()
minimumquanity = scrapy.Field()
price = scrapy.Field()
pass
items.py
!