Skip to content
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.

Sign up for GitHub

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

Add support for custom attr results to DropLowProbabilityItemPipeline. #125

Open
wants to merge 8 commits into
base: main
Choose a base branch
from
Open

Add support for custom attr results to DropLowProbabilityItemPipeline. #125

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
70f6204
Add support for custom attr results to DropLowProbabilityItemPipeline.
wRAR Dec 20, 2024
719b841
Change the DropLowProbabilityItemPipeline logic for nested items.
wRAR Dec 24, 2024
1327741
Fix handling of customAttributes sub-items.
wRAR Dec 24, 2024
447c503
Update the DropLowProbabilityItemPipeline test.
wRAR Dec 24, 2024
205221e
Small cleanup.
wRAR Dec 24, 2024
5b96eb9
Remove special handling of customAttributes in DropLowProbabilityItem…
wRAR Dec 25, 2024
2ebcf5d
Improve handling of items without probability.
wRAR Dec 26, 2024
1373297
Fixes.
wRAR Dec 26, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
46 changes: 37 additions & 9 deletions tests/test_pipelines.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,15 @@

import pytest

from zyte_common_items import Article, ArticleListPage, Product, ProductNavigation
from zyte_common_items import (
Article,
ArticleListPage,
CustomAttributes,
CustomAttributesMetadata,
CustomAttributesValues,
Product,
ProductNavigation,
)
from zyte_common_items.pipelines import DropLowProbabilityItemPipeline

scrapy = pytest.importorskip("scrapy") # noqa
Expand Down Expand Up @@ -109,7 +117,7 @@ def test_get_threshold_for_item(


@pytest.mark.parametrize(
"items, item_proba, threshold, expected_stats_calls, expected_return",
"items, item_proba, threshold, expected_stats_calls",
[
(
[
Expand All @@ -126,7 +134,6 @@ def test_get_threshold_for_item(
("drop_low_probability_item/kept/Product", 1),
("drop_low_probability_item/kept/Article", 1),
],
True,
),
(
[
Expand All @@ -143,7 +150,6 @@ def test_get_threshold_for_item(
("drop_low_probability_item/kept/Product", 1),
("drop_low_probability_item/kept/Article", 1),
],
True,
),
(
[
Expand All @@ -160,13 +166,31 @@ def test_get_threshold_for_item(
("drop_low_probability_item/dropped/Product", 1),
("drop_low_probability_item/dropped/Article", 1),
],
None,
),
(
[
{
"product": MagicMock(spec=Product(url="http://example.com")),
"customAttributes": MagicMock(
spec=CustomAttributes(
values=CustomAttributesValues({"foo": "bar"}),
metadata=CustomAttributesMetadata(),
)
),
},
],
0.01,
0.1,
[
("drop_low_probability_item/processed", 1),
("drop_low_probability_item/processed/Product", 1),
("drop_low_probability_item/dropped", 1),
("drop_low_probability_item/dropped/Product", 1),
],
),
],
)
def test_process_item(
items, item_proba, threshold, expected_stats_calls, expected_return
):
def test_process_item(items, item_proba, threshold, expected_stats_calls):
mock_crawler = MagicMock(spec=["spider", "stats"])

pipeline = DropLowProbabilityItemPipeline(mock_crawler)
Expand All @@ -176,7 +200,11 @@ def test_process_item(
mock_get_threshold_for_item.return_value = threshold

for item in items:
item.get_probability.return_value = item_proba
if isinstance(item, dict):
real_item = item["product"]
else:
real_item = item
real_item.get_probability.return_value = item_proba
try:
returned_item = pipeline.process_item(item, mock_crawler.spider)
except scrapy.exceptions.DropItem as e:
Expand Down
19 changes: 15 additions & 4 deletions zyte_common_items/pipelines.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
from copy import deepcopy
from warnings import warn

from zyte_common_items import ae
from zyte_common_items import CustomAttributes, ae


class AEPipeline:
Expand Down Expand Up @@ -118,9 +118,20 @@ def get_item_name(self, item):
def process_item(self, item, spider):
from scrapy.exceptions import DropItem

item_name = self.get_item_name(item)
item_proba = item.get_probability()
threshold = self.get_threshold_for_item(item, spider)
if isinstance(item, dict):
# support for custom attrs
for item_type, item_instance in item.items():
if item_type is not CustomAttributes:
real_item = item_instance
break
else:
return item
else:
real_item = item

item_name = self.get_item_name(real_item)
item_proba = real_item.get_probability()
threshold = self.get_threshold_for_item(real_item, spider)

self.stats.inc_value("drop_low_probability_item/processed")
self.stats.inc_value(f"drop_low_probability_item/processed/{item_name}")
Expand Down
Loading