def test_basic(): print "start scraping: " news = scraper.extract_news(CNN_NEWS_URL) print news assert EXPECTED_NEWS in news print 'test_basic passed!'
def test_basic(): """Basic Test""" news = scraper.extract_news(CNN_NEWS_URL) print(news) assert EXPECTED_NEWS in news print("Test Passed!")
def handle_message(msg): if msg is None or not isinstance(msg, dict): print 'message is broken' return task = msg text = None # We support CNN only now if task['source'] == 'cnn': print 'Scraping CNN news' text = cnn_news_scraper.extract_news(task['url']) else: print 'News source [%s] is not suppport.' % task['source'] task['text'] = text # article = Article(task['url']) # article.download() # article.parse() # print article.text # task['text'] = article.text dedupe_news_queue_client.sendMessage(task)
def test_basic(): news = scraper.extract_news(CNN_NEWS_URL) print(news) assert EXPECTED_NEWS in news print('test_basic passed!')
def test_basic(): news = scraper.extract_news(CNN_NEWS_URL) print news assert EXPECTED_STRING in news print 'test_basic passed!'
def test_basic(): """Test CNN news scraper basically""" news = scraper.extract_news(CNN_NEWS_URL) print(news) assert EXPECTED_NEWS in news print('test_basic passed!')
def handle_message(msg): if msg is None or not isinstance(msg, dict): logger.warning('message is broken') return text = None if (msg['source'] == 'cnn'): text = cnn_news_scraper.extract_news(msg['url']) msg['text'] = text #to do:re_connect is lost dedupe_news_queue_client.sendMessage(msg)
def handle_message_old(msg): # if the msg is not json format if not isinstance(msg, dict): logger.warning('message is broken') return text = None if msg['source'] == 'cnn': text = cnn_news_scraper.extract_news(msg['url']) if text is not None and len(text) > 0: msg['text'] = text dedupe_queue_client.sendMessage(msg)
def test_basic(url=NEWS_URL): news = cnn_news_scraper.extract_news(url) print news assert EXPECTED_RESULT in news print 'test_basic passed'
def test_basic(): news = extract_news(url) assert some_content in news print('extract_new trivial case passed')
def basic_test(): news = cnn_news_scraper.extract_news(CNN_NEWS_URL) assert EXPECTED_NEWS in news print("basic test passed!")
def test_basic(): news = scraper.extract_news(CNN_NEWS_URL) print news assert EXPECTED_STRING in news print 'test_basic passed!'
def test_basic(): news = cnn_news_scraper.extract_news(URL) print(news) assert EXPECTED_CONTENT in news print("CNN scraper works!")
def test_basic(): news = scraper.extract_news(CNN_NEWS_URL) print news print 'test_basic passed!'