python - Get Scrapy crawler output/results in script file function

Question

I am using a script file to run a spider within scrapy project and spider is logging the crawler output/results. But i want to use spider output/results in that script file in some function .I did not want to save output/results in any file or DB. Here is Script code get from https://doc.scrapy.org/en/latest/topics/practices.html#run-from-script

from twisted.internet import reactor
from scrapy.crawler import CrawlerRunner
from scrapy.utils.log import configure_logging
from scrapy.utils.project import get_project_settings

configure_logging({'LOG_FORMAT': '%(levelname)s: %(message)s'})
runner = CrawlerRunner(get_project_settings())


d = runner.crawl('my_spider')
d.addBoth(lambda _: reactor.stop())
reactor.run()

def spider_output(output):
#     do something to that output

How can i get spider output in 'spider_output' method. It is possible to get output/results.

Answer 1

Here is the solution that get all output/results in a list

from scrapy import signals
from scrapy.crawler import CrawlerProcess
from scrapy.utils.project import get_project_settings

from scrapy.signalmanager import dispatcher


def spider_results():
    results = []

    def crawler_results(signal, sender, item, response, spider):
        results.append(item)

    dispatcher.connect(crawler_results, signal=signals.item_scraped)

    process = CrawlerProcess(get_project_settings())
    process.crawl(MySpider)
    process.start()  # the script will block here until the crawling is finished
    return results


if __name__ == '__main__':
    print(spider_results())