Python实现从脚本里运行scrapy的方法

本文实例讲述了python/' target='_blank'>python实现从脚本里运行scrapy的方法。分享给大家供大家参考。具体如下：

复制代码 代码如下:#!/usr/bin/Python
import os
os.environ.setdefault('SCRAPY_SETTINGS_MODULE', 'project.settings') #Must be at the top before other imports
from scrapy import log, signals, project
from scrapy.xlib.pydispatch import dispatcher
from scrapy.conf import settings
from scrapy.crawler import CrawlerProcess
from multiprocessing import Process, Queue
class CrawlerScript():
def __init__(self):
self.crawler = CrawlerProcess(settings)
if not hasattr(project, 'crawler'):
self.crawler.install()
self.crawler.configure()
self.items = []
dispatcher.connect(self._item_passed, signals.item_passed)
def _item_passed(self, item):
self.items.append(item)
def _crawl(self, queue, spider_name):
spider = self.crawler.spiders.create(spider_name)
if spider:
self.crawler.queue.append_spider(spider)
self.crawler.start()
self.crawler.stop()
queue.put(self.items)
def crawl(self, spider):
queue = Queue()
p = Process(target=self._crawl, args=(queue, spider,))
p.start()
p.join()
return queue.get(True)
# Usage
if __name__ == "__main__":
log.start()
"""
This example runs spider1 and then spider2 three times.
"""
items = list()
crawler = CrawlerScript()
items.append(crawler.crawl('spider1'))
for i in range(3):
items.append(crawler.crawl('spider2'))
print items

希望本文所述对大家的Python程序设计有所帮助。