Always enable offsite stats + refactor test to initialize crawler

This commit is contained in:
Paul Tremberth 2014-01-29 14:33:12 +01:00
parent 1a545157c6
commit fd5b40593a
2 changed files with 8 additions and 13 deletions

View File

@ -13,12 +13,12 @@ from scrapy import log
class OffsiteMiddleware(object):
def __init__(self, stats=False):
self.stats_enabled = stats
def __init__(self, stats):
self.stats = stats
@classmethod
def from_crawler(cls, crawler):
o = cls(stats=True)
o = cls(crawler.stats)
crawler.signals.connect(o.spider_opened, signal=signals.spider_opened)
return o
@ -33,15 +33,8 @@ class OffsiteMiddleware(object):
self.domains_seen.add(domain)
log.msg(format="Filtered offsite request to %(domain)r: %(request)s",
level=log.DEBUG, spider=spider, domain=domain, request=x)
if self.stats_enabled:
spider.crawler.stats.inc_value('offsite/domains',
spider=spider)
if self.stats_enabled:
spider.crawler.stats.inc_value('offsite/filtered',
spider=spider)
self.stats.inc_value('offsite/domains', spider=spider)
self.stats.inc_value('offsite/filtered', spider=spider)
else:
yield x

View File

@ -3,13 +3,15 @@ from unittest import TestCase
from scrapy.http import Response, Request
from scrapy.spider import Spider
from scrapy.contrib.spidermiddleware.offsite import OffsiteMiddleware
from scrapy.utils.test import get_crawler
class TestOffsiteMiddleware(TestCase):
def setUp(self):
self.spider = self._get_spider()
self.mw = OffsiteMiddleware()
crawler = get_crawler()
self.mw = OffsiteMiddleware.from_crawler(crawler)
self.mw.spider_opened(self.spider)
def _get_spider(self):