update docs for settings

This commit is contained in:
darshanime 2016-07-25 17:55:05 +05:30
parent 2d9e5937c6
commit 0c77b6d033
3 changed files with 18 additions and 8 deletions

View File

@ -96,6 +96,8 @@ 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.
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

View File

@ -1033,8 +1033,15 @@ SCHEDULER_DEBUG
Default: ``False``
Setting to ``True`` will log the first unserializable request encountered.
Stats collected.
Setting to ``True`` will log debug information about the requests scheduler.
This currently logs(only once) if the requests cannot be serialized to disk.
Stats counter (``scheduler/unserializable``) tracks the number of times this happens.
Example entry in logs::
1956-01-31 00:00:00+0800 [scrapy] ERROR: Unable to serialize request: <request>
- reason: <exception> - no more unserializable requests will be logged (stats being
collected)
.. setting:: SPIDER_CONTRACTS

View File

@ -84,15 +84,16 @@ class Scheduler(object):
try:
reqd = request_to_dict(request, self.spider)
self.dqs.push(reqd, -request.priority)
except ValueError as e: # non serializable request
except ValueError as e: # non serializable request
if self.logunser:
msg = ("Unable to serialize request: %(request)s - reason: %(reason)s"
" - no more unserializable requests will be logged"
" (stats being collected)")
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)
self.stats.inc_value('scheduler/unserializable',
spider=self.spider)
return
else:
return True