Locally run all of the spiders in Scrapy

问题:

Is there a way to run all of the spiders in a Scrapy project without using the Scrapy daemon? There used to be a way to run multiple spiders with scrapy crawl, but that syntax was removed and Scrapy's code changed quite a bit.

I tried creating my own command:

from scrapy.command import ScrapyCommand
from scrapy.utils.misc import load_object
from scrapy.conf import settings

class Command(ScrapyCommand):
    requires_project = True

    def syntax(self):
        return '[options]'

    def short_desc(self):
        return 'Runs all of the spiders'

    def run(self, args, opts):
        spman_cls = load_object(settings['SPIDER_MANAGER_CLASS'])
        spiders = spman_cls.from_settings(settings)

        for spider_name in spiders.list():
            spider = self.crawler.spiders.create(spider_name)
            self.crawler.crawl(spider)

        self.crawler.start()

But once a spider is registered with self.crawler.crawl(), I get assertion errors for all of the other spiders:

Traceback (most recent call last):
  File "/usr/lib/python2.7/site-packages/scrapy/cmdline.py", line 138, in _run_command
    cmd.run(args, opts)
  File "/home/blender/Projects/scrapers/store_crawler/store_crawler/commands/crawlall.py", line 22, in run
    self.crawler.crawl(spider)
  File "/usr/lib/python2.7/site-packages/scrapy/crawler.py", line 47, in crawl
    return self.engine.open_spider(spider, requests)
  File "/usr/lib/python2.7/site-packages/twisted/internet/defer.py", line 1214, in unwindGenerator
    return _inlineCallbacks(None, gen, Deferred())
--- <exception caught here> ---
  File "/usr/lib/python2.7/site-packages/twisted/internet/defer.py", line 1071, in _inlineCallbacks
    result = g.send(result)
  File "/usr/lib/python2.7/site-packages/scrapy/core/engine.py", line 215, in open_spider
    spider.name
exceptions.AssertionError: No free spider slots when opening 'spidername'

Is there any way to do this? I'd rather not start subclassing core Scrapy components just to run all of my spiders like this.

回答1:

Here is an example that does not run inside a custom command, but runs the Reactor manually and creates a new Crawler for each spider:

from twisted.internet import reactor
from scrapy.crawler import Crawler
# scrapy.conf.settings singlton was deprecated last year
from scrapy.utils.project import get_project_settings
from scrapy import log

def setup_crawler(spider_name):
    crawler = Crawler(settings)
    crawler.configure()
    spider = crawler.spiders.create(spider_name)
    crawler.crawl(spider)
    crawler.start()

log.start()
settings = get_project_settings()
crawler = Crawler(settings)
crawler.configure()

for spider_name in crawler.spiders.list():
    setup_crawler(spider_name)

reactor.run()

You will have to design some signal system to stop the reactor when all spiders are finished.

EDIT: And here is how you can run multiple spiders in a custom command:

from scrapy.command import ScrapyCommand
from scrapy.utils.project import get_project_settings
from scrapy.crawler import Crawler

class Command(ScrapyCommand):

    requires_project = True

    def syntax(self):
        return '[options]'

    def short_desc(self):
        return 'Runs all of the spiders'

    def run(self, args, opts):
        settings = get_project_settings()

        for spider_name in self.crawler.spiders.list():
            crawler = Crawler(settings)
            crawler.configure()
            spider = crawler.spiders.create(spider_name)
            crawler.crawl(spider)
            crawler.start()

        self.crawler.start()

回答2:

Why didn't you just use something like:

scrapy list|xargs -n 1 scrapy crawl

?

回答3:

the answer of @Steven Almeroth will be failed in Scrapy 1.0, and you should edit the script like this:

from scrapy.commands import ScrapyCommand
from scrapy.utils.project import get_project_settings
from scrapy.crawler import CrawlerProcess

class Command(ScrapyCommand):

    requires_project = True
    excludes = ['spider1']

    def syntax(self):
        return '[options]'

    def short_desc(self):
        return 'Runs all of the spiders'

    def run(self, args, opts):
        settings = get_project_settings()
        crawler_process = CrawlerProcess(settings) 

        for spider_name in crawler_process.spider_loader.list():
            if spider_name in self.excludes:
                continue
            spider_cls = crawler_process.spider_loader.load(spider_name) 
            crawler_process.crawl(spider_cls)
        crawler_process.start()

回答4:

this code is works on My scrapy version is 1.3.3 (save it in same directory in scrapy.cfg):

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

setting = get_project_settings()
process = CrawlerProcess(setting)

for spider_name in process.spiders.list():
    print ("Running spider %s" % (spider_name))
    process.crawl(spider_name,query="dvh") #query dvh is custom argument used in your scrapy

process.start()