scrapy按顺序启动多个爬虫代码片段(python3)

# !/usr/bin/env python3
# -*- coding:utf-8 -*-
from scrapy import cmdline
from twisted.internet import reactor, defer
from scrapy.crawler import CrawlerRunner
from scrapy.utils.log import configure_logging
from torrentSpider.spiders.proxy_ip_spider import ProxyIpSpider
from torrentSpider.spiders.douban_spider import DoubanSpider
from scrapy.utils.project import get_project_settings

‘‘‘
以下是多个爬虫顺序执行的命令
‘‘‘
configure_logging()
# 加入setting配置文件，否则配置无法生效
# get_project_settings()获取的是setting.py的配置

runner = CrawlerRunner(get_project_settings())

@defer.inlineCallbacks
def crawl():
    yield runner.crawl(ProxyIpSpider)
    yield runner.crawl(DoubanSpider)
    reactor.stop()


crawl()
reactor.run()  # the script will block here until the last crawl call is finished

‘‘‘
以下是单个爬虫执行的命令
‘‘‘
# def execute():
    # cmdline.execute([‘scrapy‘, ‘crawl‘, ‘proxy_ip_spider‘])
#
#
# execute()