Project Description:
This Python-based news scraper automatically extracts the latest news articles from specified websites and uses AI-powered summarization to condense long articles into shorter summaries. It also analyzes the sentiment of each article, categorizing it as positive, negative, or neutral.
Libraries Used:
- BeautifulSoup: For web scraping and parsing HTML.
- Requests: For making HTTP requests to fetch web pages.
- Transformers (HuggingFace): For AI-powered summarization and sentiment analysis.
- TextBlob: For sentiment analysis.
Key Logic:
- Scrapes news articles from a given website using BeautifulSoup and Requests.
- Summarizes each article using a pre-trained transformer model.
- Analyzes sentiment using TextBlob or HuggingFace sentiment analysis models.
- Stores the results in a readable format with summaries and sentiment categorization.
How It Works:
- The script crawls selected news websites to gather article data.
- Each article is passed through a summarization AI model to condense the content.
- Sentiment analysis is performed to categorize the article as positive, negative, or neutral.
- The output is displayed with the article summary and sentiment result.
Outcome:
This tool automates the process of keeping up with the news, offering summarized and sentiment-analyzed articles that save time and effort for users.