🔍📰🤖 This project utilizes Selenium and BeautifulSoup libraries to scrape Google search results for URLs based on specified keywords. It also extracts article details from the obtained URLs.
🚀 To run the script, ensure you have Python installed along with necessary libraries. You'll also need to download ChromeDriver and set the path accordingly.
pip install selenium beautifulsoup4 newspaper3k wordcloud pandas transformers matplotlib nltk langdetect googletrans- 🔍 Scrapes Google search results for URLs containing specified keywords.
- 📰 Extracts article details from obtained URLs.
- 📊 Generates word cloud visualization of article texts.
- 🔧 Ensure ChromeDriver is installed and its path is set correctly.
- 🛠️ Adjust Chrome options such as headless mode as needed.
- 🌍 The script may require additional setup for non-English languages.