发布于 2015-10-10 03:26:02 | 238 次阅读 | 评论: 0 | 来源: 网友投递
Python编程语言
Python 是一种面向对象、解释型计算机程序设计语言,由Guido van Rossum于1989年底发明,第一个公开发行版发行于1991年。Python语法简洁而清晰,具有丰富和强大的类库。它常被昵称为胶水语言,它能够把用其他语言制作的各种模块(尤其是C/C++)很轻松地联结在一起。
本文实例讲述了Python实现在线程里运行scrapy的方法。分享给大家供大家参考。具体如下:
如果你希望在一个写好的程序里调用scrapy,就可以通过下面的代码,让scrapy运行在一个线程里。
""" Code to run Scrapy crawler in a thread - works on Scrapy 0.8 """ import threading, Queue from twisted.internet import reactor from scrapy.xlib.pydispatch import dispatcher from scrapy.core.manager import scrapymanager from scrapy.core.engine import scrapyengine from scrapy.core import signals class CrawlerThread(threading.Thread): def __init__(self): threading.Thread.__init__(self) self.running = False def run(self): self.running = True scrapymanager.configure(control_reactor=False) scrapymanager.start() reactor.run(installSignalHandlers=False) def crawl(self, *args): if not self.running: raise RuntimeError("CrawlerThread not running") self._call_and_block_until_signal(signals.spider_closed, scrapymanager.crawl, *args) def stop(self): reactor.callFromThread(scrapyengine.stop) def _call_and_block_until_signal(self, signal, f, *a, **kw): q = Queue.Queue() def unblock(): q.put(None) dispatcher.connect(unblock, signal=signal) reactor.callFromThread(f, *a, **kw) q.get() # Usage example below: import os os.environ.setdefault('SCRAPY_SETTINGS_MODULE', 'myproject.settings') from scrapy.xlib.pydispatch import dispatcher from scrapy.core import signals from scrapy.conf import settings from scrapy.crawler import CrawlerThread settings.overrides['LOG_ENABLED'] = False # avoid log noise def item_passed(item): print "Just scraped item:", item dispatcher.connect(item_passed, signal=signals.item_passed) crawler = CrawlerThread() print "Starting crawler thread..." crawler.start() print "Crawling somedomain.com...." crawler.crawl('somedomain.com) # blocking call print "Crawling anotherdomain.com..." crawler.crawl('anotherdomain.com') # blocking call print "Stopping crawler thread..." crawler.stop()