Multiple YouTube Video Analyzer

Overview

The YouTube Video Analyzer is a powerful tool designed to help educators, content creators, and learners analyze and compare educational videos on YouTube. It provides in-depth insights into video performance, content quality, and audience engagement through various metrics and AI-powered analysis.

Features

• Multiple video comparison (2–10 videos)
• Content analysis: subject and subtopic identification
• Content analysis: difficulty level assessment
• Content analysis: target audience identification
• Content analysis: prerequisites detection
• Content analysis: key concepts extraction
• Performance metrics: views, likes, and comments statistics
• Performance metrics: engagement metrics
• Performance metrics: comment sentiment analysis
• Domain compatibility checking
• Video recommendations based on multiple factors

Features in detail

• Content Analysis — identifies the main subject and subtopic of each video, assesses difficulty level and target audience, and lists prerequisites and key concepts covered.
• Performance Metrics — total views, likes, and comments for each video, comparative analysis across videos, and engagement metrics calculation.
• Sentiment Analysis — analyzes video comments for sentiment, provides positive/negative sentiment distribution, and calculates an overall sentiment score.
• Domain Compatibility — ensures videos being compared are from related educational domains, preventing misleading comparisons across unrelated subjects.
• Video Recommendations — data-driven recommendations considering content quality, engagement metrics, audience response, and sentiment analysis.

Architecture / project structure

• youtube_analyzer.py — main application file with the Streamlit interface
• api_client.py — handles API interactions with YouTube and Google AI
• content_analyzer.py — processes video content analysis using AI
• video_analyzer.py — core video analysis functionality
• requirements.txt — project dependencies
• .env — API configuration (needs to be created)

Prerequisites

• Python 3.11
• YouTube Data API key
• Google API key (for Gemini AI)

Setup

• Clone the repository and change into the project directory.
• Install required packages: pip install -r requirements.txt
• Create a .env file in the project root with YOUTUBE_API_KEY and GOOGLE_API_KEY.

Usage

• Start the application: streamlit run youtube_analyzer.py
• Select the number of videos to analyze (2–10) and enter the YouTube video URLs.
• Click "Analyze Videos" to start the analysis.
• Review the results: content analysis, metrics summary, sentiment analysis, and the recommended video.

Notes

• The application requires valid API keys to function.
• Analysis quality depends on video metadata and comment availability.
• For educational videos only; not designed for entertainment content.
• Rate limits apply based on your API quota.

Error handling

The application includes comprehensive error handling for invalid YouTube URLs, API failures, domain mismatches, and missing or incorrect API keys.