Scrapy, a fast high-level web crawling & scraping framework for Python.
Logging the cache directory at HttpCacheMiddleware instantiation #2604
jorenham97d84d920bf9
diff --git a/scrapy/downloadermiddlewares/httpcache.py b/scrapy/downloadermiddlewares/httpcache.pyindex 30e49b886..6f1ccce68 100644--- a/scrapy/downloadermiddlewares/httpcache.py+++ b/scrapy/downloadermiddlewares/httpcache.py@@ -1,3 +1,5 @@+import logging+from email.utils import formatdatefrom twisted.internet import deferfrom twisted.internet.error import TimeoutError, DNSLookupError, \@@ -9,6 +11,9 @@ from scrapy.exceptions import NotConfigured, IgnoreRequestfrom scrapy.utils.misc import load_object+logger = logging.getLogger(__name__)++class HttpCacheMiddleware(object):DOWNLOAD_EXCEPTIONS = (defer.TimeoutError, TimeoutError, DNSLookupError,@@ -24,6 +29,8 @@ class HttpCacheMiddleware(object):self.ignore_missing = settings.getbool('HTTPCACHE_IGNORE_MISSING')self.stats = stats+ logger.debug("Using cache directory %(cachedir)s" % {'cachedir': self.storage.cachedir})+@classmethoddef from_crawler(cls, crawler):o = cls(crawler.settings, crawler.stats)