GHL Course Video Scraper

script.js

// Video URL Scraper for Course Platform
// WARNING: Only use this on content you have legal access to download

class VideoScraper {
    constructor() {
        this.videoUrls = [];
        this.currentPage = 1;
        this.isRunning = false;
        this.delay = 3000; // 3 seconds delay between actions
    }

    // Wait function for delays
    wait(ms) {
        return new Promise(resolve => setTimeout(resolve, ms));
    }

    // Find the next button (adjust selector as needed)
    findNextButton() {
        // Use the user's specific selector first
        try {
            const userButton = document.querySelectorAll(".max-w-8")[1];
            if (userButton && !userButton.disabled) {
                return userButton;
            }
        } catch (e) {
            console.log('User selector failed:', e.message);
        }
        
        // Try other possible selectors for the next button
        const selectors = [
            'button[data-v-646dd304]',
            '.plyr__control[data-plyr="next"]',
            '.next-button',
            '.navigation-next',
            'button[aria-label*="next"]',
            'button[aria-label*="Next"]'
        ];
        
        for (let selector of selectors) {
            try {
                const button = document.querySelector(selector);
                if (button && !button.disabled) {
                    return button;
                }
            } catch (e) {
                // Skip invalid selectors
                continue;
            }
        }
        
        // Look for buttons with arrow symbols or "next" text
        const allButtons = document.querySelectorAll('button');
        for (let button of allButtons) {
            const text = button.textContent.toLowerCase();
            if (text.includes('next') || text.includes('→') || text.includes('>') || text.includes('▶')) {
                return button;
            }
        }
        
        return null;
    }

    // Extract video URL from various sources
    getVideoUrl() {
        // Method 1: Check video element src
        const videoElement = document.querySelector('video');
        if (videoElement && videoElement.src && !videoElement.src.startsWith('blob:')) {
            return videoElement.src;
        }

        // Method 2: Check network requests for video files
        // This requires the script to monitor network activity
        return this.getVideoUrlFromNetwork();
    }

    // Monitor network requests for video URLs
    getVideoUrlFromNetwork() {
        // This is a simplified version - in practice, you'd need to set up
        // network monitoring before navigation
        const performanceEntries = performance.getEntriesByType('resource');
        
        for (let entry of performanceEntries) {
            if (entry.name.includes('.mp4') || 
                entry.name.includes('.m3u8') || 
                entry.name.includes('video') ||
                entry.name.includes('stream')) {
                if (!entry.name.startsWith('blob:')) {
                    return entry.name;
                }
            }
        }
        return null;
    }

    // Get current lesson/video title
    getCurrentTitle() {
        const titleSelectors = [
            'h1', 'h2', '.lesson-title', '.video-title',
            '[class*="title"]', '.course-title'
        ];
        
        for (let selector of titleSelectors) {
            const element = document.querySelector(selector);
            if (element) {
                return element.textContent.trim();
            }
        }
        
        return `Video ${this.currentPage}`;
    }

    // Log video information
    logVideoInfo(url, title) {
        const info = {
            page: this.currentPage,
            title: title,
            url: url,
            timestamp: new Date().toISOString()
        };
        
        this.videoUrls.push(info);
        console.log(`Found video ${this.currentPage}: ${title}`);
        console.log(`URL: ${url}`);
        console.log('---');
    }

    // Main scraping function
    async scrapeVideos() {
        if (this.isRunning) {
            console.log('Scraper is already running!');
            return;
        }

        this.isRunning = true;
        console.log('Starting video scraper...');
        console.log('WARNING: Make sure you have permission to download these videos!');
        
        try {
            while (this.isRunning) {
                console.log(`Processing page ${this.currentPage}...`);
                
                // Wait for page to load
                await this.wait(this.delay);
                
                // Get current video info
                const title = this.getCurrentTitle();
                const videoUrl = this.getVideoUrl();
                
                if (videoUrl) {
                    this.logVideoInfo(videoUrl, title);
                } else {
                    console.log(`No video URL found on page ${this.currentPage}`);
                }
                
                // Find and click next button
                const nextButton = this.findNextButton();
                
                if (!nextButton) {
                    console.log('No next button found. Scraping complete!');
                    break;
                }
                
                console.log('Clicking next button...');
                nextButton.click();
                
                this.currentPage++;
                
                // Wait for navigation
                await this.wait(this.delay);
            }
        } catch (error) {
            console.error('Error during scraping:', error);
        } finally {
            this.isRunning = false;
            this.showResults();
        }
    }

    // Stop the scraper
    stop() {
        console.log('Stopping scraper...');
        this.isRunning = false;
    }

    // Show all collected URLs
    showResults() {
        console.log('\n=== SCRAPING COMPLETE ===');
        console.log(`Found ${this.videoUrls.length} videos:`);
        console.log('\n');
        
        this.videoUrls.forEach((video, index) => {
            console.log(`${index + 1}. ${video.title}`);
            console.log(`   URL: ${video.url}`);
            console.log(`   Page: ${video.page}`);
            console.log('');
        });

        // Copy results to clipboard as JSON
        const jsonResults = JSON.stringify(this.videoUrls, null, 2);
        
        // Try to copy to clipboard
        if (navigator.clipboard) {
            navigator.clipboard.writeText(jsonResults).then(() => {
                console.log('Results copied to clipboard!');
            }).catch(() => {
                console.log('Could not copy to clipboard. Results logged above.');
            });
        }
        
        return this.videoUrls;
    }

    // Export URLs as downloadable file
    downloadResults() {
        const jsonResults = JSON.stringify(this.videoUrls, null, 2);
        const blob = new Blob([jsonResults], { type: 'application/json' });
        const url = URL.createObjectURL(blob);
        
        const a = document.createElement('a');
        a.href = url;
        a.download = 'video_urls.json';
        document.body.appendChild(a);
        a.click();
        document.body.removeChild(a);
        URL.revokeObjectURL(url);
        
        console.log('Results downloaded as video_urls.json');
    }
}

// Usage instructions
console.log('Video Scraper loaded! Usage:');
console.log('const scraper = new VideoScraper();');
console.log('scraper.scrapeVideos(); // Start scraping');
console.log('scraper.stop(); // Stop scraping');
console.log('scraper.showResults(); // Show collected URLs');
console.log('scraper.downloadResults(); // Download as JSON file');
console.log('');
console.log('IMPORTANT: Only use on content you have legal rights to download!');

// Auto-create instance
window.videoScraper = new VideoScraper();