def add_news(request):
website_urls=['http://rss.cnn.com/rss/edition.rss','https://news.ycombinator.com/rss ','http://economictimes.indiatimes.com/rssfeedsdefault.cms','http://yourstory.com/feed/',]
#request_recvd = request.POST.get('data')
for website_url in website_urls:
parsed_uri = urlparse( website_url )
domain = '{uri.scheme}://{uri.netloc}/'.format(uri=parsed_uri)
print website_url
feeds=feedparser.parse(website_url)
print feeds
for loop in feeds.entries :
print loop.published
print loop.summary_detail.value
print domain
print website_url
print loop.title
news = News(time_stamp = json.dumps(list(loop.published_parsed)),website = domain, url = website_url,title = loop.title,content = loop.summary_detail.value)
news.save()
# if len([News.objects.get(link = link)]) == 0 :
return redirect('/api/')
def test_update_news(mock_model, client, admin):
# Given
news = News(name='News', text='coucou')
news.create()
update_obj = {
"_id": "news",
"name": "Super News",
"text": "<b>coucou</b> <script>lol()</script>"
}
# When
res = client.put(url_for('api.update_news', news_id='news'),
data=json.dumps(update_obj),
content_type='application/json')
data = res.json
assert res.status_code == 200
assert data['data']['name'] == 'Super News'
assert data['data']['_id'] == 'news'
assert data['data'][
'text'] == '<b>coucou</b> <script>lol()</script>'
assert dateutil.parser.parse(
data['data']['created_at']) < dateutil.parser.parse(
data['data']['updated_at'])
def test_pairs(self):
saver = HackerNewsSaver()
flag = {'value': False}
news_items = {
'title0': News(title='title0', url='url0'),
'title1': News(title='title1', url='url1'),
}
for item in news_items.values():
item.save()
item.created = timezone.now() - datetime.timedelta(days=30)
item.save()
setattr(saver, '_get_content', lambda *args: self._get_content(flag, """\
<table class="itemlist">
<tr class="athing">
<td class="title">
<a href="url1" class="storylink">
title1
</a>
</td>
</tr>
<tr class="athing">
<td class="title">
<a href="url2" class="storylink">
title2
</a>
</td>
</tr>
</table>"""))
now = timezone.now()
saver.save()
self.assertTrue(flag['value'], 'Function _get_content was not called')
now_exists = News.objects.all()
self.assertLessEqual(len(now_exists), 3, 'Redundant news items were added')
self.assertEqual(3, len(now_exists), 'News item was not added')
for item in now_exists:
if item.title in news_items:
self.assertEqual(item.created, news_items[item.title].created,
'created for existed row was updated')
else:
self.assertGreaterEqual(item.created, now, 'New item has invalid created time')
self.assertEqual(item.title, 'title2', 'New item has invalid title')
self.assertEqual(item.url, 'url2', 'New item has invalid url')
setattr(saver, '_get_content', lambda *args: self._get_content(flag, ''))
self.assertRaises(RuntimeError, saver.save)
def setUp(self):
now = timezone.make_aware(timezone.datetime(2019, 1, 1, 0, 0, 0),
timezone.get_default_timezone())
self._posts = []
for i in range(10):
now += timezone.timedelta(minutes=i)
post = {
'url': f'url{i}',
'title': f'title{i}',
'created': now.isoformat()
}
self._posts.append(post)
n = News(**post)
n.save()
post['id'] = n.id
n.created = now
n.save()
def news():
return News(name='Super News', text='<p>Youpi !</p>')
def seed_data():
"""
seed isl teams data from file
:return:
"""
with open(file_name, encoding='utf-8') as fp:
contents_of_file = json.load(fp)
for data in contents_of_file:
news_date = data['news_date']
content = data['content']
source = data['source']
title = data['title']
news_tags = data['news_tags']
sport = data['sport']
is_trending = data['is_trending']
trend_scale = data['trend_scale']
display_order = data['display_order']
image = data['image']
identifier = data['identifier']
try:
news = News.objects.get(identifier=identifier)
except News.DoesNotExist:
news = News()
news.news_date = datetime.datetime.strptime(news_date,
"%Y-%m-%d").date()
news.content = content
news.source = source
news.title = title
news.news_tags = news_tags
news.sport = sport
news.is_trending = is_trending
news.trend_scale = trend_scale
news.display_order = display_order
news.identifier = identifier
news.save()
print('added news')
lowPrice=0,
closePrice=0)
db.session.add(s1)
db.session.add(s2)
db.session.add(s3)
db.session.add(s4)
db.session.add(s5)
db.session.commit()
for stock in ['BAJAJ', 'HDFC', 'ICICI', 'TCS', 'INFY']:
r = requests.get(
f"https://newsapi.org/v2/everything?q={stock}&apiKey=b49814b3a46e428d9b99b40c568ef6fc"
)
json_obj = r.json()
for news in json_obj['articles']:
save_news = News(name=stock,
newsURL=news['url'],
text=news['description'],
title=news['title'])
db.session.add(save_news)
db.session.commit()
f1 = Favourites(user_id=1, stock_name="BAJAJ")
f2 = Favourites(user_id=1, stock_name="TCS")
f3 = Favourites(user_id=2, stock_name="HDFC")
db.session.add(f1)
db.session.add(f2)
db.session.commit()
else:
cover = headline["cover"]["thumbnailUrl"]
date = datetime.datetime.fromtimestamp(headline["date"])
author = headline["author"]["name"]
intro = headline["intro"]
htmlText = html.fromstring(headline['entryContent']['html'])
paragraphs = htmlText.xpath('//p/text()')
text = ""
for par in paragraphs:
text = text + par + "\n\n"
print(text)
n1 = positiver.evalute(Api.cleanText(text))
n2 = checker.evalute(Api.cleanText(text))
if len(News.objects.all().filter(article_id=article_id)) == 0:
article = News(article_id=article_id,
title=title,
intro=intro,
date=date,
author=author,
cover=cover,
article=text,
authorPosition=n1,
concrete=n2)
article.save()
time.sleep(10)
time.sleep(400)