I have a database on PythonAnywhere and credentials in place.
The aim is to scrape a whole load of news websites and chuck the data into a new website using Flask.
Here's my code for a section of my website. (I've ignored the imports because it runs)
@app.route("/nationals")def scrape_nationals(): feeds = [{"type": "news","title": "BBC", "url": "http://feeds.bbci.co.uk/news/uk/rss.xml"}, {"type": "news","title": "The Economist", "url": "https://www.economist.com/international/rss.xml"}, {"type": "news","title": "The New Statesman", "url": "https://www.newstatesman.com/feed"}, {"type": "news","title": "The New York Times", "url": "https://rss.nytimes.com/services/xml/rss/nyt/HomePage.xml"}, {"type": "news","title": "Metro UK","url": "https://metro.co.uk/feed/"}, {"type": "news", "title": "Evening Standard", "url": "https://www.standard.co.uk/rss.xml"}, {"type": "news","title": "Daily Mail", "url": "https://www.dailymail.co.uk/articles.rss"}, {"type": "news","title": "Sky News", "url": "https://news.sky.com/feeds/rss/home.xml"}, {"type": "news", "title": "The Mirror", "url": "https://www.mirror.co.uk/news/?service=rss"}, {"type": "news", "title": "The Sun", "url": "https://www.thesun.co.uk/news/feed/"}, {"type": "news", "title": "Sky News", "url": "https://news.sky.com/feeds/rss/home.xml"}, {"type": "news", "title": "The Guardian", "url": "https://www.theguardian.com/uk/rss"}, {"type": "news", "title": "The Independent", "url": "https://www.independent.co.uk/news/uk/rss"}, #{"type": "news", "title": "The Telegraph", "url": "https://www.telegraph.co.uk/news/rss.xml"}, {"type": "news", "title": "The Times", "url": "https://www.thetimes.co.uk/?service=rss"}] print(feeds) data = [] # <---- initialize empty list here for feed in feeds: parsed_feed = feedparser.parse(feed['url']) #print("Title:", feed['title']) #print("Number of Articles:", len(parsed_feed.entries)) #print("\n") for entry in parsed_feed.entries: title = entry.title print(title) url = entry.link #print(entry.summary) try: summary = entry.summary[:400] or "No summary available" # I simplified the ternary operators here except: #print("no summary") summary = "none" try: date = pd.to_datetime(entry.published)# #or "No data available" # I simplified the ternary operators here except: #print("date") date = pd.to_datetime("01-01-1970") data.append([title, url, summary, date]) # <---- append data from each entry here df = pd.DataFrame(data, columns = ['title', 'url', 'summary', 'date']) articles = pd.read_sql('nationals', con = engine) articles = articles.drop_duplicates() df = df.append(articles) df = df.drop_duplicates() df.to_sql('nationals', con = engine, if_exists = 'replace', index = False)It works in VSCode locally, but I can't work out why my table on PythonAnywhere won't populate. What have I got wrong?
