def get_flats_info(url): response = requests.get(url) soup = BeautifulSoup(response.content, 'html.parser') db_file = "flats_olx.db" # Search all novostroys and add them into the list all_flats = soup.find_all("tr", class_="wrap") list_of_novostroys = [] for td in all_flats: current_title = td.h3 title_text = td.h3.get_text() if ("новостр" in title_text or "Новостр" in title_text): # formated_title_text = ' '.join(title_text.split()) # list_of_flats.append((formated_title_text,)) link_of_novostroy = current_title.a['href'] list_of_novostroys.append(link_of_novostroy) # Then check DB. Delete links from list if they are already in the list # and add in DB new links db_connection = create_connection(db_file) # Get headers from all novostroys flats_info = get_headlines(list_of_novostroys) # actual_list = update_list(list_of_novostroys) unique_flats = input_new_titles(db_connection, flats_info) db_connection.close() return unique_flats
def show_bbc_hl(newssource): """ to get the Headline news from BBC,CNN,API,Google or New York Times""" bbc_dict = get_headlines(newssource) if newssource == 'bbc-news': headline_string = "BBC Headline News" elif newssource == 'bloomberg': headline_string = "Bloomberg Headline News" elif newssource == 'cnn': headline_string = "CNN Headline News" elif newssource == 'associated-press': headline_string = 'Associated Press Headline News' elif newssource =='google-news': headline_string = "Google Headline News" url = bbc_dict['url'] title = bbc_dict['title'] description = bbc_dict['description'] return render_template("headlines.html",headline_string=headline_string,url=url,title=title,description=description)
print("I was built by Ashwin Kumar Ramaswamy") elif "open stackoverflow" in statement: webbrowser.open_new_tab("https://stackoverflow.com/login") speak("Here is stackoverflow") elif 'news' in statement: news = webbrowser.open_new_tab( "https://timesofindia.indiatimes.com/home/headlines") speak( 'Here are some headlines from the Times of India,Happy reading' ) speak( 'If you like the headline, say "visit" to open the page and read details' ) headlines = headlines.get_headlines( "https://timesofindia.indiatimes.com/home/headlines") for i in range(15): speak(headlines['text'][i]) command = takeCommand() if 'visit' in command: webbrowser.open_new_tab(headlines['link'][i]) break elif 'stop' in command: break time.sleep(5) time.sleep(6) elif "camera" in statement or "take a photo" in statement: ec.capture(0, "robo camera", "img.jpg") elif 'search' in statement: