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

Remove the cache from the provider. #172

Closed
wants to merge 1 commit into from
Closed

Remove the cache from the provider. #172

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
21 changes: 0 additions & 21 deletions scrapy_zyte_api/providers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,4 @@
from typing import Any, Callable, Dict, List, Sequence, Set
from weakref import WeakKeyDictionary

from andi.typeutils import is_typing_annotated, strip_annotated
from scrapy import Request
Expand Down Expand Up @@ -44,33 +43,16 @@ class ZyteApiProvider(PageObjectInputProvider):
Geolocation,
}

def __init__(self, injector):
super().__init__(injector)
self._cached_instances: WeakKeyDictionary[Request, Dict] = WeakKeyDictionary()

def is_provided(self, type_: Callable) -> bool:
return super().is_provided(strip_annotated(type_))

def update_cache(self, request: Request, mapping: Dict[Any, Any]) -> None:
if request not in self._cached_instances:
self._cached_instances[request] = {}
self._cached_instances[request].update(mapping)

async def __call__( # noqa: C901
self, to_provide: Set[Callable], request: Request, crawler: Crawler
) -> Sequence[Any]:
"""Makes a Zyte API request to provide BrowserResponse and/or item dependencies."""
# TODO what if ``response`` is already from Zyte API and contains something we need
results: List[Any] = []

for cls in list(to_provide):
item = self._cached_instances.get(request, {}).get(cls)
if item:
results.append(item)
to_provide.remove(cls)
if not to_provide:
return results

html_requested = BrowserResponse in to_provide or BrowserHtml in to_provide
item_keywords: Dict[type, str] = {
Product: "product",
Expand Down Expand Up @@ -142,15 +124,13 @@ async def __call__( # noqa: C901
html = None
if BrowserHtml in to_provide:
results.append(html)
self.update_cache(request, {BrowserHtml: html})
if BrowserResponse in to_provide:
response = BrowserResponse(
url=api_response.url,
status=api_response.status,
html=html,
)
results.append(response)
self.update_cache(request, {BrowserResponse: response})

for cls in to_provide:
cls_stripped = strip_annotated(cls)
Expand All @@ -167,5 +147,4 @@ async def __call__( # noqa: C901
if is_typing_annotated(cls):
item = AnnotatedResult(item, cls.__metadata__) # type: ignore[attr-defined]
results.append(item)
self.update_cache(request, {cls: item})
return results
Loading