Scrapy Spider that scrapes Google's Codelabs for Category, Description, Link, Last Updated, Duration and Tags.

codelabs_spider.py

import scrapy

class CodelabsSpider(scrapy.Spider):
    name = "codelabs"

    def start_requests(self):
        urls = [
            'https://codelabs.developers.google.com/'
        ]
        for url in urls:
            yield scrapy.Request(url=url, callback=self.parse)

    def parse(self, response):
        for card in response.css('a.codelab-card'):
            yield {
                'description': card.css('a div.description::text').extract_first(),
                'link': response.urljoin(card.css('a::attr(href)').extract_first()),
                'category': card.css('a::attr(data-category)').extract_first(),
                'updated' : card.css('a::attr(data-updated)').extract_first(),
                'duration': card.css('a::attr(data-duration)').extract_first(),
                'tags': card.css('a::attr(data-tags)').extract_first()
            }