main.py

import requests
from bs4 import BeautifulSoup
import re
import json
from urllib.parse import urljoin, quote
import time

class SoundgasmScraper:
    def __init__(self):
        self.base_url = "https://soundgasm.net"
        self.session = requests.Session()
        self.session.headers.update({
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
        })
    
    def search_audio(self, query, max_results=10):
        """
        Search for audio on Soundgasm.net
        Since Soundgasm doesn't have a built-in search, we'll use external search engines
        """
        results = []
        
        # Use Google to search for Soundgasm content
        search_query = f"site:soundgasm.net {query}"
        google_url = f"https://www.google.com/search?q={quote(search_query)}"
        
        try:
            response = self.session.get(google_url)
            soup = BeautifulSoup(response.content, 'html.parser')
            
            # Extract Soundgasm links from Google search results
            links = soup.find_all('a', href=True)
            soundgasm_links = []
            
            for link in links:
                href = link.get('href')
                if href and 'soundgasm.net/u/' in href:
                    # Clean up the URL
                    if href.startswith('/url?q='):
                        href = href.split('/url?q=')[1].split('&')[0]
                    if href.startswith('http') and 'soundgasm.net/u/' in href:
                        soundgasm_links.append(href)
            
            # Remove duplicates and limit results
            soundgasm_links = list(set(soundgasm_links))[:max_results]
            
            # Get details for each audio
            for link in soundgasm_links:
                audio_info = self.get_audio_info(link)
                if audio_info:
                    results.append(audio_info)
                    
        except Exception as e:
            print(f"Search error: {e}")
            
        return results
    
    def get_audio_info(self, url):
        """
        Extract audio information from a Soundgasm page
        """
        try:
            response = self.session.get(url)
            soup = BeautifulSoup(response.content, 'html.parser')
            
            # Extract title
            title_elem = soup.find('title')
            title = title_elem.text.strip() if title_elem else "Unknown Title"
            
            # Extract description
            description = ""
            desc_elem = soup.find('div', class_='jp-description')
            if desc_elem:
                description = desc_elem.get_text(strip=True)
            
            # Extract audio file URL from JavaScript
            audio_url = None
            scripts = soup.find_all('script')
            for script in scripts:
                if script.string:
                    # Look for the audio file URL in the JavaScript
                    match = re.search(r'["\']([^"\']*\.m4a)["\']', script.string)
                    if match:
                        audio_url = match.group(1)
                        if not audio_url.startswith('http'):
                            audio_url = urljoin(self.base_url, audio_url)
                        break
            
            # Extract username from URL
            username = ""
            url_match = re.search(r'/u/([^/]+)/', url)
            if url_match:
                username = url_match.group(1)
            
            # Extract audio title from URL
            audio_title = ""
            title_match = re.search(r'/u/[^/]+/(.+)$', url)
            if title_match:
                audio_title = title_match.group(1).replace('-', ' ').replace('_', ' ')
            
            return {
                'title': title,
                'audio_title': audio_title,
                'username': username,
                'description': description,
                'url': url,
                'audio_url': audio_url,
                'duration': None  # Would need to download file to get duration
            }
            
        except Exception as e:
            print(f"Error getting audio info for {url}: {e}")
            return None
    
    def search_by_username(self, username):
        """
        Get all audios from a specific user
        """
        user_url = f"{self.base_url}/u/{username}"
        try:
            response = self.session.get(user_url)
            soup = BeautifulSoup(response.content, 'html.parser')
            
            # Find all audio links on the user page
            audio_links = []
            links = soup.find_all('a', href=True)
            
            for link in links:
                href = link.get('href')
                if href and f'/u/{username}/' in href and href != f'/u/{username}':
                    full_url = urljoin(self.base_url, href)
                    audio_links.append(full_url)
            
            # Get info for each audio
            results = []
            for link in audio_links:
                audio_info = self.get_audio_info(link)
                if audio_info:
                    results.append(audio_info)
                    
            return results
            
        except Exception as e:
            print(f"Error searching by username {username}: {e}")
            return []

# Test the scraper
if __name__ == "__main__":
    scraper = SoundgasmScraper()
    
    # Test search
    print("Testing search functionality...")
    results = scraper.search_audio("ASMR", max_results=3)
    
    for i, result in enumerate(results, 1):
        print(f"\n--- Result {i} ---")
        print(f"Title: {result['title']}")
        print(f"Audio Title: {result['audio_title']}")
        print(f"Username: {result['username']}")
        print(f"URL: {result['url']}")
        print(f"Audio URL: {result['audio_url']}")
        print(f"Description: {result['description'][:100]}..." if result['description'] else "No description")