def test_get_urls(self):
"""Test getting urls from the database."""
self.assertEqual(set(database_reader.get_urls()), set())
groups = classifier.group_articles(test_utils.SIMILAR_ARTICLES)
database_writer.write_groups(groups)
self.assertEqual(
set(database_reader.get_urls()),
set(model.get_url() for model in test_utils.SIMILAR_ARTICLES))
def test_remove_grouping_from_database(self):
"""Test remove grouping from database."""
database_writer.write_groups([self.grouping])
self.assertTrue(self.grouping.in_database())
self.assertEqual(1, len(database_reader.get_urls()))
database_writer.remove_grouping_from_database(self.grouping)
self.assertFalse(self.grouping.in_database())
self.assertEqual(0, len(database_reader.get_urls()))
def test_clean_database(self):
"""Test clean database."""
database_writer.write_groups([self.grouping])
self.assertEqual(1, len(database_reader.get_urls()))
database_writer.clean_database()
self.assertEqual(1, len(database_reader.get_urls()))
grouping = models.Grouping(
models.Article(url="google.com",
publishedAt="2016-10-11T23:41:34Z",
keywords=["a"]))
database_writer.write_groups([grouping])
self.assertEqual(2, len(database_reader.get_urls()))
database_writer.clean_database()
self.assertEqual(1, len(database_reader.get_urls()))
def test_write_topics_to_database_grouping_in_database(self):
"""Test remove grouping from database."""
self.grouping.set_in_database(True)
for article in self.grouping.get_articles():
article.set_in_database(True)
database_writer.write_groups([self.grouping])
self.assertTrue(self.grouping.in_database())
self.assertEqual(0, len(database_reader.get_urls()))
def update_database():
"""Update the database with all the headlines from get_top_headlines."""
database_writer.clean_database()
articles = get_top_headlines(add_category_information=True)
urls_in_database = database_reader.get_urls()
articles = [article for article in articles if article.get_url() not in urls_in_database]
database_writer.write_articles(articles, )
grouped = classifier.group_articles()
database_writer.write_groups(grouped)
database_writer.write_group_fits()
database_writer.write_overall_fits()
if database_reader.get_number_articles_without_overall_fit() > constants.ARTICLES_NEEDED_BEFORE_ALL_FIT_UPDATED:
print "Not enough new articles"
database_writer.update_topic_pictures()
@app.route("/keywords")
def get_top_keywords():
"""Get the most used keywords in the database."""
return json.dumps(
database_reader.get_top_keywords(
int(request.args.get("n", constants.DEFAULT_NUM_KEYWORDS))))
@app.route("/getStories")
def get_stories_for_topic():
"""Get the stories for a topic id."""
topic_id = request.args.get("topic_id")
return json.dumps(database_reader.get_stories_for_topic(topic_id))
@app.route("/userClick", methods=['POST'])
def user_click():
"""Update the popularity when the user clicks on an article."""
data = json.loads(request.data)
if "url" in data:
database_writer.mark_item_as_clicked(data["url"])
return ""
if __name__ == "__main__": # pragma: no cover
if not database_reader.get_urls():
# If there is nothing in the database, update it
print "Nothing in database. Populating..."
news_fetcher.update_database()
app.run(host="localhost", port=80, threaded=True)