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 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 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')
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)