# see: http://stackoverflow.com/questions/7993680/running-scrapy-tasks-in-python
from scrapy import project, signals
from scrapy.conf import settings
from scrapy.crawler import CrawlerProcess
from scrapy.xlib.pydispatch import dispatcher
from multiprocessing.queues import Queue
from multiprocessing import Process
class CrawlerWorker(Process):
def __init__(self, spider, results):
Process.__init__(self)
self.results = results
self.crawler = CrawlerProcess(settings)
if not hasattr(project, 'crawler'):
self.crawler.install()
self.crawler.configure()
self.items = []
self.spider = spider
dispatcher.connect(self._item_passed, signals.item_passed)
def _item_passed(self, item):
self.items.append(item)
def run(self):
self.crawler.crawl(self.spider)
self.crawler.start()
self.crawler.stop()
self.results.put(self.items)