Skip to content

Scrapy, a fast high-level web crawling & scraping framework for Python.

Change name, log once

Darshan Chaudhary472a8a47d0b2
diff --git a/docs/topics/jobs.rst b/docs/topics/jobs.rst
index 303076015..093cf9bb5 100644
--- a/docs/topics/jobs.rst
+++ b/docs/topics/jobs.rst
@@ -96,4 +96,6 @@ But this will::
somearg = response.meta['somearg']
print "the argument passed is:", somearg
+If you wish to log the requests that couldn't be serialized, you can set the ``SCHEDULER_DEBUG`` setting to ``True`` in the project's settings page. It is ``False`` by default.
+
.. _pickle: http://docs.python.org/library/pickle.html
diff --git a/docs/topics/settings.rst b/docs/topics/settings.rst
index c845c59b9..d03da44c6 100644
--- a/docs/topics/settings.rst
+++ b/docs/topics/settings.rst
@@ -1026,6 +1026,16 @@ Default: ``'scrapy.core.scheduler.Scheduler'``
The scheduler to use for crawling.
+.. setting:: SCHEDULER_DEBUG
+
+SCHEDULER_DEBUG
+---------------
+
+Default: ``False``
+
+Setting to ``True`` will log the first unserializable request encountered.
+Stats collected.
+
.. setting:: SPIDER_CONTRACTS
SPIDER_CONTRACTS
diff --git a/scrapy/core/scheduler.py b/scrapy/core/scheduler.py
index 8be9a0019..e0788a8c5 100644
--- a/scrapy/core/scheduler.py
+++ b/scrapy/core/scheduler.py
@@ -30,7 +30,7 @@ class Scheduler(object):
pqclass = load_object(settings['SCHEDULER_PRIORITY_QUEUE'])
dqclass = load_object(settings['SCHEDULER_DISK_QUEUE'])
mqclass = load_object(settings['SCHEDULER_MEMORY_QUEUE'])
- logunser = settings.getbool('LOG_UNSERIALIZABLE_REQUESTS')
+ logunser = settings.getbool('SCHEDULER_DEBUG')
return cls(dupefilter, jobdir=job_dir(settings), logunser=logunser,
stats=crawler.stats, pqclass=pqclass, dqclass=dqclass, mqclass=mqclass)
@@ -86,9 +86,13 @@ class Scheduler(object):
self.dqs.push(reqd, -request.priority)
except ValueError as e: # non serializable request
if self.logunser:
- logger.error("Unable to serialize request: %(request)s - reason: %(reason)s",
- {'request': request, 'reason': e},
+ msg = ("Unable to serialize request: %(request)s - reason: %(reason)s"
+ " - no more unserializable requests will be logged"
+ " (stats being collected)")
+ logger.error(msg, {'request': request, 'reason': e},
exc_info=True, extra={'spider': self.spider})
+ self.logunser = False
+ self.stats.inc_value('scheduler/unserializable', spider=self.spider)
return
else:
return True
diff --git a/scrapy/settings/default_settings.py b/scrapy/settings/default_settings.py
index 2c267b4cc..673df5129 100644
--- a/scrapy/settings/default_settings.py
+++ b/scrapy/settings/default_settings.py
@@ -191,7 +191,7 @@ LOG_STDOUT = False
LOG_LEVEL = 'DEBUG'
LOG_FILE = None
-LOG_UNSERIALIZABLE_REQUESTS = False
+SCHEDULER_DEBUG = False
LOGSTATS_INTERVAL = 60.0