Just want to scrape news feeds from RSS.
import feedparserimport pandas as pdfrom datetime import datetimearchive = pd.read_csv("national_news_scrape.csv")# Your list of feedsfeeds = [{"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"}]# Create an empty DataFrame to store the newsnews_df = pd.DataFrame(columns=['source', 'title', 'date', 'summary', "url"])# For each feed, parse it and add the news to the DataFramefor feed in feeds: print(f"Scraping: {feed['title']}") d = feedparser.parse(feed['url']) for entry in d.entries: # Some feeds do not have 'summary' field, handle this case summary = entry.summary if hasattr(entry, 'summary') else '' url = entry.link # Add the news to the DataFrame news_df = news_df.append({'source': feed['title'],'title': entry.title,"url": url,'date': datetime(*entry.published_parsed[:6]),'summary': summary, }, ignore_index=True)combined = pd.concat([news_df, archive]).drop_duplicates()# Save the DataFrame to a CSV filenews_df.to_csv('national_news_scrape.csv', index=False)Why doesn't it read the URL of an individual article?
