You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
58 lines
2.1 KiB
58 lines
2.1 KiB
from rest_framework import viewsets, status
|
|
from rest_framework.decorators import action
|
|
from rest_framework.response import Response
|
|
from .models import CrawlTask, CrawlRun
|
|
from .serializers import CrawlTaskSerializer, CrawlRunSerializer
|
|
|
|
class CrawlTaskViewSet(viewsets.ModelViewSet):
|
|
"""
|
|
ViewSet for CrawlTask models. Supports CRUD and custom trigger/runs actions.
|
|
"""
|
|
queryset = CrawlTask.objects.all().order_by('-created_at')
|
|
serializer_class = CrawlTaskSerializer
|
|
|
|
@action(detail=True, methods=['post'], url_path='trigger')
|
|
def trigger(self, request, pk=None):
|
|
task = self.get_object()
|
|
|
|
# Create a new CrawlRun with status RUNNING
|
|
run = CrawlRun.objects.create(
|
|
crawl_task=task,
|
|
status='RUNNING'
|
|
)
|
|
|
|
# Check if tasks can be imported.
|
|
try:
|
|
from crawler.tasks import run_crawl_pipeline
|
|
# run asynchronously
|
|
run_crawl_pipeline.delay(str(run.id), force=True)
|
|
is_queued = True
|
|
except ImportError:
|
|
# Fallback if tasks.py doesn't exist yet or run_crawl_pipeline is not defined
|
|
is_queued = False
|
|
|
|
return Response({
|
|
"status": "queued" if is_queued else "queued_stub",
|
|
"run_id": str(run.id)
|
|
}, status=status.HTTP_202_ACCEPTED)
|
|
|
|
@action(detail=True, methods=['get'], url_path='runs')
|
|
def runs(self, request, pk=None):
|
|
task = self.get_object()
|
|
runs = task.runs.all().order_by('-started_at')
|
|
page = self.paginate_queryset(runs)
|
|
if page is not None:
|
|
serializer = CrawlRunSerializer(page, many=True)
|
|
return self.get_paginated_response(serializer.data)
|
|
|
|
serializer = CrawlRunSerializer(runs, many=True)
|
|
return Response(serializer.data)
|
|
|
|
|
|
class CrawlRunViewSet(viewsets.ModelViewSet):
|
|
"""
|
|
ViewSet for CrawlRun models. Supports CRUD (including DELETE).
|
|
"""
|
|
queryset = CrawlRun.objects.all().order_by('-started_at')
|
|
serializer_class = CrawlRunSerializer
|
|
|