-
Notifications
You must be signed in to change notification settings - Fork 93
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Close spider by stats [#47][#50] #216
Closed
Closed
Changes from all commits
Commits
Show all changes
4 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change | ||||
---|---|---|---|---|---|---|
|
@@ -20,6 +20,7 @@ | |||||
DEFAULT_ERRORS_FIELD = "_validation" | ||||||
DEFAULT_ADD_ERRORS_TO_ITEM = False | ||||||
DEFAULT_DROP_ITEMS_WITH_ERRORS = False | ||||||
DEFAULT_CLOSESPIDER_BY_STATS = {} | ||||||
|
||||||
|
||||||
class ItemValidationPipeline(object): | ||||||
|
@@ -29,13 +30,15 @@ def __init__( | |||||
stats, | ||||||
drop_items_with_errors=DEFAULT_DROP_ITEMS_WITH_ERRORS, | ||||||
add_errors_to_items=DEFAULT_ADD_ERRORS_TO_ITEM, | ||||||
close_spider_by_stats=DEFAULT_CLOSESPIDER_BY_STATS, | ||||||
errors_field=None, | ||||||
): | ||||||
self.drop_items_with_errors = drop_items_with_errors | ||||||
self.add_errors_to_items = add_errors_to_items or DEFAULT_ADD_ERRORS_TO_ITEM | ||||||
self.errors_field = errors_field or DEFAULT_ERRORS_FIELD | ||||||
self.validators = validators | ||||||
self.stats = ValidationStatsManager(stats) | ||||||
self.close_spider_by_stats = close_spider_by_stats or DEFAULT_CLOSESPIDER_BY_STATS | ||||||
for _type, vals in validators.items(): | ||||||
[self.stats.add_validator(_type, val.name) for val in vals] | ||||||
|
||||||
|
@@ -70,7 +73,7 @@ def set_validators(loader, schema): | |||||
if not validators: | ||||||
raise NotConfigured("No validators were found") | ||||||
|
||||||
return cls( | ||||||
pipeline = cls( | ||||||
validators=validators, | ||||||
stats=crawler.stats, | ||||||
drop_items_with_errors=crawler.settings.getbool( | ||||||
|
@@ -80,7 +83,14 @@ def set_validators(loader, schema): | |||||
"SPIDERMON_VALIDATION_ADD_ERRORS_TO_ITEMS" | ||||||
), | ||||||
errors_field=crawler.settings.get("SPIDERMON_VALIDATION_ERRORS_FIELD"), | ||||||
close_spider_by_stats=crawler.settings.get('SPIDERMON_CLOSESPIDER_BY_STATS'), | ||||||
) | ||||||
pipeline._set_crawler(crawler) | ||||||
return pipeline | ||||||
|
||||||
@classmethod | ||||||
def _set_crawler(self, crawler): | ||||||
self.crawler = crawler | ||||||
|
||||||
@classmethod | ||||||
def _load_jsonschema_validator(cls, schema): | ||||||
|
@@ -105,7 +115,7 @@ def _load_schematics_validator(cls, model_path): | |||||
) | ||||||
return SchematicsValidator(model_class) | ||||||
|
||||||
def process_item(self, item, _): | ||||||
def process_item(self, item, spider): | ||||||
validators = self.find_validators(item) | ||||||
if not validators: | ||||||
# No validators match this specific item type | ||||||
|
@@ -122,6 +132,9 @@ def process_item(self, item, _): | |||||
self._add_errors_to_item(item, errors) | ||||||
if self.drop_items_with_errors: | ||||||
self._drop_item(item, errors) | ||||||
if self.close_spider_by_stats: | ||||||
stats_dict = self.close_spider_by_stats | ||||||
self._close_spider_by_stats (spider, stats_dict) | ||||||
return item | ||||||
|
||||||
def find_validators(self, item): | ||||||
|
@@ -168,3 +181,19 @@ def _add_error_stats(self, errors): | |||||
for message in messages: | ||||||
self.stats.add_field_error(field_name, message) | ||||||
self.stats.add_item_with_errors() | ||||||
|
||||||
def _close_spider_by_stats(self, spider, stats_dict): | ||||||
""" | ||||||
This method evaluate each stat value and if no of errors are greater then | ||||||
max_errors_allowed. Spider will be closed gracefully. | ||||||
""" | ||||||
for stat_name, max_errors_allowed in stats_dict.iteritems(): | ||||||
stat_current_value = self.stats.stats.get_value(stat_name, 0) | ||||||
|
||||||
if stat_current_value > max_errors_allowed: | ||||||
self.crawler.engine.close_spider( | ||||||
spider, | ||||||
'Spidermon: No of errors are greater then the expected no of errors {} > {}'.format( | ||||||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I think we should not call them errors (they could be warnings or something else entirely), and I would include the name of the specific stat that triggers the spider closing.
Suggested change
|
||||||
stat_current_value, max_errors_allowed | ||||||
) | ||||||
) |
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Why not pass it as a parameter to
cls()
?