Tech Watch News Aggregator & Summarizer

This project is an automated Python script designed to scrape, summarize, and archive news articles from specific online sources related to a company and its key topics. It provides a comprehensive solution for generating daily reports without manual work.

Features ✨

• Targeted Scraping: Utilizes the SerpAPI to find relevant news articles from a predefined list of sources and topics.
• AI-Powered Summaries: Integrates the Google Gemini API to generate a concise summary for each news article, highlighting the most important information.
• Dual Output: With each run, the script creates a new, timestamped Google Sheet and a text file containing all the summarized news.
• Automated Cloud Storage: The generated Google Sheet and the summary text file are automatically saved to a specified folder in your Google Drive.

Prerequisites 🛠️

Before running this script, you will need the following:

1. Python 3.x installed on your system.
2. A Google Cloud Project with the following APIs enabled:
   • Google Sheets API
   • Google Drive API
   • Google Gemini API
3. A SerpAPI API key.
4. A Service Account with access to your Google Cloud Project. You will need to download the JSON key file for this account.
5. A designated folder on your Google Drive to save the output files.

Setup and Installation 🚀

1. Clone the repository to your local machine:

   git clone [https://github.com/your-username/your-repository.git](https://github.com/your-username/your-repository.git)
   cd your-repository

2. Install the required Python libraries:

   pip install pandas requests gspread google-generativeai gspread_dataframe google-auth google-auth-oauthlib google-api-python-client beautifulsoup4

3. Place your authentication files:

   • Save your Google Service Account JSON key file as client_secret.json in the project directory.
   • The script will automatically generate a token.json file on the first run.
   • Ensure your Google Drive folder is shared with the service account's email address (found in the client_secret.json file).

4. Configure the script: Open the Python script and fill in the configuration variables at the top of the file:

   • SERPAPI_API_KEY: Paste your SerpAPI key here.
   • GEMINI_API_KEY: Paste your Gemini API key here.
   • PARENT_FOLDER_ID: Paste the ID of your Google Drive folder.

5. Run the script: Execute the script from your terminal. The first time you run it, it will open a browser window for you to authorize access to your Google account.

   python your_script_name.py

   Upon successful completion, a new folder will appear in your Google Drive containing a new Google Sheet and a text file with the news summaries.