本文實例講述了Python實現從腳本里運行scrapy的方法。分享給大家供大家參考。具體如下：

代碼如下:#!/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

希望本文所述對大家的Python程序設計有所幫助。