scrapy run spider from script code example

Example 1: how to run scrapy inside a nm

import scrapy
from scrapy.crawler import CrawlerProcess

class MySpider(scrapy.Spider):
    # Your spider definition
    ...

process = CrawlerProcess(settings={
    "FEEDS": {
        "items.json": {"format": "json"},
    },
})

process.crawl(MySpider)
process.start() # the script will block here until the crawling is finished

Example 2: simple scrapy spider file

import scrapy


class QuotesSpider(scrapy.Spider):
    name = "quotes"
    start_urls = [
        'http://quotes.toscrape.com/page/1/',
    ]

    def parse(self, response):
        for quote in response.css('div.quote'):
            yield {
                'text': quote.css('span.text::text').get(),
                'author': quote.css('small.author::text').get(),
                'tags': quote.css('div.tags a.tag::text').getall(),
            }

        next_page = response.css('li.next a::attr(href)').get()
        if next_page is not None:
            next_page = response.urljoin(next_page)
            yield scrapy.Request(next_page, callback=self.parse)