def testDifficultyOfFeedItems(self):
feed = RSSFeedRule().feed1
download_from_feed(feed, zeeguu.db.session, 3)
articles = feed.get_articles(limit=2)
assert len(articles) == 2
assert articles[0].fk_difficulty
def setUp(self):
super().setUp()
self.spiegel = RSSFeedRule().feed1
download_from_feed(self.spiegel, self.db.session, 3)
self.telegraaf = RSSFeedRule().feed2
download_from_feed(self.telegraaf, self.db.session, 3)
def test_get_feed_items_with_metrics(self):
download_from_feed(self.feed1, zeeguu.db.session, 3)
feed_items = self.json_from_api_get(
f"get_feed_items_with_metrics/{self.feed1.id}")
assert len(feed_items) > 0
assert feed_items[0]["title"]
assert feed_items[0]["summary"]
assert feed_items[0]["published"]
assert feed_items[0]['metrics']
def test_recommended(self):
self.feed1 = RSSFeedRule().feed1
self.feed2 = RSSFeedRule().feed2
download_from_feed(self.feed1, zeeguu.db.session, 2)
download_from_feed(self.feed2, zeeguu.db.session, 3)
RSSFeedRegistration.find_or_create(zeeguu.db.session, self.user,
self.feed1)
RSSFeedRegistration.find_or_create(zeeguu.db.session, self.user,
self.feed2)
feed_items = self.json_from_api_get(f"/user_articles/recommended/5")
assert (len(feed_items) == 5)
def testDownloadWithTopic(self):
feed = RSSFeedRule().feed1
topic = Topic("Spiegel")
zeeguu.db.session.add(topic)
zeeguu.db.session.commit()
loc_topic = LocalizedTopic(topic, self.lan, "spiegelDE", "spiegel")
zeeguu.db.session.add(loc_topic)
zeeguu.db.session.commit()
download_from_feed(feed, zeeguu.db.session, 3)
article = feed.get_articles(limit=2)[0]
assert (topic in article.topics)
def testDownloadWithWords(self):
feed = RSSFeedRule().feed1
download_from_feed(feed, zeeguu.db.session, 3)
article = feed.get_articles(limit=2)[0]
# Try two words, as one might be filtered out
word = strip_article_title_word(article.title.split()[0])
article_word = ArticleWord.find_by_word(word)
if word in ['www', ''
] or word.isdigit() or len(word) < 3 or len(word) > 25:
assert (article_word is None)
else:
assert (article in article_word.articles)
#!/usr/bin/env python
"""
Script that goes through all the feeds that are
available in the DB and retrieves the newest articles
in order to populate the DB with them.
The DB is populated by saving Article objects in the
articles table.
Before this script checking whether there were new items
in a given feed was done while serving the request for
items to read. That was too slow.
To be called from a cron job.
"""
import zeeguu
from zeeguu.content_retriever.article_downloader import download_from_feed
from zeeguu.model import RSSFeed
session = zeeguu.db.session
counter = 0
for feed in RSSFeed.query.all():
counter += 1
print(f"{counter}: DOWNLOADING {feed.title}".encode('utf-8'))
download_from_feed(feed, zeeguu.db.session)
print(f"{counter}: FINISHED DOWNLOADING {feed.title}".encode('utf-8'))