问在脚本文件函数中获取Scrapy crawler输出/结果

EN

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())

from scrapyscript import Job, Processor
from scrapy.spiders import Spider
from scrapy import Request
import json

# Define a Scrapy Spider, which can accept *args or **kwargs
# https://doc.scrapy.org/en/latest/topics/spiders.html#spider-arguments
class PythonSpider(Spider):
    name = 'myspider'

    def start_requests(self):
        yield Request(self.url)

    def parse(self, response):
        title = response.xpath('//title/text()').extract()
        return {'url': response.request.url, 'title': title}

# Create jobs for each instance. *args and **kwargs supplied here will
# be passed to the spider constructor at runtime
githubJob = Job(PythonSpider, url='http://www.github.com')
pythonJob = Job(PythonSpider, url='http://www.python.org')

# Create a Processor, optionally passing in a Scrapy Settings object.
processor = Processor(settings=None)

# Start the reactor, and block until all spiders complete.
data = processor.run([githubJob, pythonJob])

# Print the consolidated results
print(json.dumps(data, indent=4))

[
    {
        "title": [
            "Welcome to Python.org"
        ],
        "url": "https://www.python.org/"
    },
    {
        "title": [
            "The world's leading software development platform \u00b7 GitHub",
            "1clr-code-hosting"
        ],
        "url": "https://github.com/"
    }
]