0
from scrapy import project, signals
from scrapy.crawler import Settings
from scrapy.crawler import CrawlerProcess
from scrapy.xlib.pydispatch import dispatcher
from multiprocessing.queues import Queue
import multiprocessing
class CrawlerWorker(multiprocessing.Process):
def __init__(self, spider, result_queue):
multiprocessing.Process.__init__(self)
self.result_queue = result_queue
self.crawler = Crawler(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.result_queue.put(self.items)
尝试从scrapy.conf.settings只使用CrawlerProcess(设置)我得到一个错误,它看起来像有之间的scrapy医生说这里什么http://doc.scrapy.org/en/latest/topics/practices.htmlScrapy:导入错误:无法导入名称设置
的差异我正在遵循一个较旧的scrapy版本,我正在试图使它与0.16的scrapy一起工作。
这是运行python脚本后的错误。
Traceback (most recent call last):
File "server.py", line 5, in <module>
from scraper import Scraper
File "/home/me/spider/spider/scraper.py", line 6, in <module>
from crawlerworker import CrawlerWorker
File "/home/me/spider/spider/crawlerworker.py", line 2, in <module>
from scrapy.crawler import Settings
ImportError: cannot import name Settings
你能错误添加到问题吗? – Talvalin 2013-04-09 10:10:33
更新了有错误的问题 – KJW 2013-04-09 15:25:21