Django & Celery: нет такой таблицы

Я пытаюсь создать пару задач с Celery, которые отправляют данные в модель Django, у меня все работает, но по какой-то причине задачи Celery не могут увидеть таблицу, хотя она существует в БД и Django может отправлять данные в нее.

Это происходит с PostgreSQL, это работает при использовании SQLite3.

Сталкивался ли кто-нибудь с подобной проблемой и как вы смогли ее решить?

tasks.py
--------
# tasks
from __future__ import absolute_import, unicode_literals
from celery import Celery
from celery import app, shared_task

# scraping
import requests
from bs4 import BeautifulSoup
import json
from datetime import datetime
import lxml

from rss_feed_scraper.models import PressReleases

# logging
from celery.utils.log import get_task_logger

logger = get_task_logger(__name__)
@shared_task(serializer='json')
def save_function(article_list):
    for article in article_list:
        try:
            PressReleases.objects.create(
                title=article['title'],
                description=article['description'],
                link=article['link'],
                image_url=article['image_url'],
                published=article['published'],
                source=article['source']
            )
        except Exception as e:
            print('failed at inserting article')
            print(e)
            break


@shared_task
def prnewswire_rss():
    article_list = []
    try:
        print('Starting the scraping tool')
        r = requests.get('https://www.prnewswire.com/rss/all-news-releases-from-PR-newswire-news.rss')
        soup = BeautifulSoup(r.content, features='lxml')

        articles = soup.findAll('item')

        for a in articles:
            title = a.find('title').text
            description = a.find('description').text
            # Get Link
            link = str(a)
            i = link.find("<link/>")
            j = link.find("<guid")
            media_content = a.find('media:content')
            image_url = None
            if media_content:
                image_url = media_content['url']
            published_wrong = a.find('pubdate').text
            published = datetime.strptime(published_wrong, '%a, %d %b %Y %H:%M:%S %z')

            article = {
                'title': title,
                'description': description,
                'link': link[i + 7:j],
                'image_url': image_url,
                'published': published,
                'source': 'PR News Wire'
            }

            article_list.append(article)

        # print(article_list)
        print('Finished scraping the articles')

        # Save to DB
        return save_function(article_list)
    except Exception as e:
        print('The scraping job failed. See exception: ')
        print(e)

celery.py
---------

from __future__ import absolute_import
import os
from celery import Celery

from celery.schedules import crontab  # scheduler

os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'config.settings')

app = Celery('config')

app.conf.timezone = 'UTC'
app.config_from_object('django.conf:settings', namespace='CELERY')
app.autodiscover_tasks()

app.conf.beat_schedule = {
    # executes every 1 minute
    'scraping-task-one-min': {
        'task': 'rss_feed_scraper.tasks.prnewswire_rss',
        'schedule': crontab(),
    },
    # # executes every 15 minutes
    # 'scraping-task-fifteen-min': {
    #     'task': 'tasks.hackernews_rss',
    #     'schedule': crontab(minute='*/15')
    # },
    # # executes daily at midnight
    # 'scraping-task-midnight-daily': {
    #     'task': 'tasks.hackernews_rss',
    #     'schedule': crontab(minute=0, hour=0)
    # }
}

models.py
---------
from django.db import models


# Create your models here.
class PressReleases(models.Model):
    title = models.CharField(max_length=200, unique=True)
    description = models.CharField(max_length=500)
    link = models.CharField(max_length=2083, default="")
    image_url = models.CharField(max_length=2083, default="", null=True)
    published = models.DateTimeField()
    created_at = models.DateTimeField(auto_now_add=True)
    updated_at = models.DateTimeField(auto_now=True)
    source = models.CharField(max_length=30, default="", blank=True, null=True)

Вернуться на верх