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

Jump to bottom

fix: Scheduler not compatible with BaseDupeFilter #294

Merged
merged 4 commits into from
Jul 6, 2024
Merged

fix: Scheduler not compatible with BaseDupeFilter #294

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
86aeda9
fix: Scheduler not compatible with BaseDupeFilter
HairlessVillager Jun 22, 2024
6079448
Merge branch 'master' into fix-Scheduler
rmax Jul 2, 2024
8128530
Merge branch 'master' into fix-Scheduler
rmax Jul 6, 2024
8412be9
fix: linting
rmax Jul 6, 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
11 changes: 10 additions & 1 deletion src/scrapy_redis/scheduler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,6 +37,7 @@ def __init__(
flush_on_start=False,
queue_key=defaults.SCHEDULER_QUEUE_KEY,
queue_cls=defaults.SCHEDULER_QUEUE_CLASS,
dupefilter=None,
dupefilter_key=defaults.SCHEDULER_DUPEFILTER_KEY,
dupefilter_cls=defaults.SCHEDULER_DUPEFILTER_CLASS,
idle_before_close=0,
Expand All @@ -56,6 +57,8 @@ def __init__(
Requests queue key.
queue_cls : str
Importable path to the queue class.
dupefilter: Dupefilter
Custom dupefilter instance.
dupefilter_key : str
Duplicates filter key.
dupefilter_cls : str
Expand All @@ -72,6 +75,7 @@ def __init__(
self.flush_on_start = flush_on_start
self.queue_key = queue_key
self.queue_cls = queue_cls
self.df = dupefilter
self.dupefilter_cls = dupefilter_cls
self.dupefilter_key = dupefilter_key
self.idle_before_close = idle_before_close
Expand Down Expand Up @@ -105,6 +109,10 @@ def from_settings(cls, settings):
if val:
kwargs[name] = val

dupefilter_cls = load_object(kwargs["dupefilter_cls"])
if not hasattr(dupefilter_cls, "from_spider"):
kwargs["dupefilter"] = dupefilter_cls.from_settings(settings)

# Support serializer as a path to a module.
if isinstance(kwargs.get("serializer"), str):
kwargs["serializer"] = importlib.import_module(kwargs["serializer"])
Expand Down Expand Up @@ -137,7 +145,8 @@ def open(self, spider):
f"Failed to instantiate queue class '{self.queue_cls}': {e}"
)

self.df = load_object(self.dupefilter_cls).from_spider(spider)
if not self.df:
self.df = load_object(self.dupefilter_cls).from_spider(spider)

if self.flush_on_start:
self.flush()
Expand Down
Loading