本文实例讲述了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。
版权声明：本文内容由互联网用户自发贡献，该文观点仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌抄袭侵权/违法违规的内容， 请发送邮件至253000106@qq.com举报，一经查实，本站将立刻删除。
发布者：PHP中文网，转转请注明出处：https://www.chuangxiangniao.com/p/2293968.html
