Private
Public Access
Implements OPML parsing with defusedxml (untrusted upload, XXE risk) and export with the stdlib's plain ElementTree (trusted, app-generated output). Nesting deeper than one level flattens into its nearest enclosing folder, matching the app's flat-folder model. Import reuses existing Feed/Subscription rows via get_or_create, so re-importing the same file is idempotent and cross-user Feed dedup is preserved. Large imports (>50 entries) dispatch to a Celery task instead of blocking the request; newly imported feeds aren't fetched immediately since they have no last_fetched_at, so the next poll_due_feeds beat cycle picks them up naturally. Adds a Subscriptions page (replacing the standalone "Add feed" link in nav) listing current subscriptions with unsubscribe, plus Import/ Export OPML actions. Verified live: imported a 2-feed/1-folder OPML file against the running dev server (via an authenticated session, since this browser tool has no file-picker automation), confirmed the resulting subscriptions and folder in the UI, exported and inspected the resulting OPML structure, and unsubscribed from one feed. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
87 lines
2.6 KiB
Python
87 lines
2.6 KiB
Python
import logging
|
|
from datetime import timedelta
|
|
from io import BytesIO
|
|
|
|
from celery import shared_task
|
|
from django.contrib.auth import get_user_model
|
|
from django.utils import timezone
|
|
|
|
from apps.articles.tasks import apply_filter_rules_for_feed
|
|
|
|
from .models import Feed
|
|
from .opml import import_opml
|
|
from .services.fetcher import effective_interval_minutes, fetch_and_ingest
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
@shared_task
|
|
def poll_due_feeds():
|
|
"""Find every active Feed whose polling interval has elapsed and
|
|
dispatch a fetch_feed task for each — fan-out happens here, not via one
|
|
Celery Beat entry per feed.
|
|
"""
|
|
due_feed_ids = [
|
|
feed.id
|
|
for feed in Feed.objects.filter(is_active=True).only(
|
|
"id", "last_fetched_at", "fetch_interval_minutes", "fetch_error_count"
|
|
)
|
|
if _is_due(feed)
|
|
]
|
|
for feed_id in due_feed_ids:
|
|
fetch_feed.delay(feed_id)
|
|
return len(due_feed_ids)
|
|
|
|
|
|
def _is_due(feed: Feed) -> bool:
|
|
if feed.last_fetched_at is None:
|
|
return True
|
|
interval = effective_interval_minutes(feed)
|
|
return feed.last_fetched_at <= timezone.now() - timedelta(minutes=interval)
|
|
|
|
|
|
@shared_task
|
|
def fetch_feed(feed_id: int):
|
|
try:
|
|
feed = Feed.objects.get(pk=feed_id, is_active=True)
|
|
except Feed.DoesNotExist:
|
|
return None
|
|
|
|
result = fetch_and_ingest(feed)
|
|
feed.save()
|
|
|
|
changed_article_ids = result.new_article_ids + result.updated_article_ids
|
|
if changed_article_ids:
|
|
logger.info(
|
|
"Feed %s: %d new article(s), %d updated",
|
|
feed.feed_url,
|
|
len(result.new_article_ids),
|
|
len(result.updated_article_ids),
|
|
)
|
|
apply_filter_rules_for_feed.delay(feed_id, changed_article_ids)
|
|
|
|
return {
|
|
"status": result.status,
|
|
"new": len(result.new_article_ids),
|
|
"updated": len(result.updated_article_ids),
|
|
}
|
|
|
|
|
|
@shared_task
|
|
def reset_feed_backoff(feed_id: int):
|
|
"""Admin-triggered: clear a feed's error count so it's retried at its
|
|
normal configured interval instead of the backed-off one."""
|
|
Feed.objects.filter(pk=feed_id).update(fetch_error_count=0)
|
|
|
|
|
|
@shared_task
|
|
def import_opml_task(user_id: int, opml_content: str):
|
|
"""Background path for large OPML imports — see OPML_ASYNC_THRESHOLD
|
|
in apps.feeds.views. opml_content is passed as text rather than a
|
|
file handle since Celery tasks must be JSON-serializable."""
|
|
try:
|
|
user = get_user_model().objects.get(pk=user_id)
|
|
except get_user_model().DoesNotExist:
|
|
return None
|
|
return import_opml(user, BytesIO(opml_content.encode("utf-8")))
|