paroles-net-scraper/paroles_net_scraper/paroles_net_scraper.py

#!/usr/bin/env python3
"""
Module to fetch song lyrics from paroles.net
"""

import requests
from bs4 import BeautifulSoup
import argparse
import re


def get_song_lyrics(artist, song_title):
    """
    Fetch song lyrics from paroles.net
    
    Args:
        artist (str): Name of the artist
        song_title (str): Title of the song
        
    Returns:
        str: Song lyrics or error message
    """
    # Format the URL
    # Convert artist and song to lowercase and replace spaces with hyphens
    formatted_artist = artist.lower().replace(' ', '-').replace('$', 's').replace('&', 'and')
    formatted_song = song_title.lower().replace(' ', '-').replace('\'', '').replace('"', '')
    
    url = f"https://www.paroles.net/{formatted_artist}/paroles-{formatted_song}"
    
    try:
        # Set headers to mimic a browser request
        headers = {
            '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'
        }
        
        # Send GET request
        response = requests.get(url, headers=headers)
        response.raise_for_status()  # Raise exception for bad status codes
        
        # Parse HTML content
        soup = BeautifulSoup(response.content, 'html.parser')
        
        # Find the lyrics container
        # Looking for the div with class 'song-text'
        lyrics_div = soup.find('div', class_='song-text')
        
        if not lyrics_div:
            return "Lyrics not found on the page"
        
        # Extract text content
        # Get all text from the div but preserve line breaks
        lyrics_parts = []
        for element in lyrics_div.descendants:
            if element.name == 'br':
                lyrics_parts.append('\n')
            elif element.string and element.string.strip():
                # Skip the heading that repeats the song info
                if 'Paroles de la chanson' not in element.string:
                    lyrics_parts.append(element.string)
        
        # Join the parts and clean up
        lyrics = ''.join(lyrics_parts).strip()
        
        # Clean up extra whitespace while preserving verse structure
        lines = lyrics.split('\n')
        cleaned_lines = []
        for line in lines:
            stripped_line = line.strip()
            # Skip empty lines and ad content
            if stripped_line and not re.match(r'^(Content_\d+|.*Advertisement.*|\d+\s*)$', stripped_line):
                # Also remove inline ad markers
                cleaned_line = re.sub(r'^Content_\d+\s*', '', stripped_line)
                if cleaned_line:  # Only add non-empty lines
                    cleaned_lines.append(cleaned_line)
        
        lyrics = '\n'.join(cleaned_lines).strip()
        
        if not lyrics:
            return "Could not extract lyrics from the page"
            
        return lyrics
        
    except requests.exceptions.RequestException as e:
        return f"Error fetching lyrics: {str(e)}"
    except Exception as e:
        return f"Error parsing lyrics: {str(e)}"


def search_song(artist, song_title):
    """
    Search for a song on paroles.net and return the first result
    
    Args:
        artist (str): Name of the artist
        song_title (str): Title of the song
        
    Returns:
        str: URL of the first search result or error message
    """
    # Format search URL
    search_query = f"{artist} {song_title}"
    search_url = f"https://www.paroles.net/recherche?q={requests.utils.quote(search_query)}"
    
    try:
        headers = {
            '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'
        }
        
        response = requests.get(search_url, headers=headers)
        response.raise_for_status()
        
        soup = BeautifulSoup(response.content, 'html.parser')
        
        # Find the first search result link
        first_result = soup.find('a', href=lambda x: x and '/paroles-' in x)
        
        if first_result:
            return f"https://www.paroles.net{first_result['href']}"
        else:
            return "No search results found"
            
    except requests.exceptions.RequestException as e:
        return f"Error searching for song: {str(e)}"


def main():
    parser = argparse.ArgumentParser(description='Fetch song lyrics from paroles.net')
    parser.add_argument('query', help='Artist and song in format "ARTIST - SONG TITLE" or separate artist and song arguments')
    parser.add_argument('song', nargs='?', help='Song title (optional if using ARTIST - SONG format)')
    parser.add_argument('--search', action='store_true', help='Use search functionality instead of direct URL construction')
    
    args = parser.parse_args()
    
    # Handle both input formats:
    # 1. Single argument: "ARTIST - SONG TITLE"
    # 2. Two arguments: ARTIST SONG_TITLE
    if args.song is None:
        # Single argument format: split on " - "
        if " - " in args.query:
            artist, song = args.query.split(" - ", 1)
        else:
            print("Error: Please provide artist and song in format 'ARTIST - SONG TITLE'")
            return
    else:
        # Two argument format: artist and song provided separately
        artist = args.query
        song = args.song
    
    # Strip any leading/trailing whitespace
    artist = artist.strip()
    song = song.strip()
    
    if args.search:
        # First search for the song to get the correct URL
        search_result = search_song(artist, song)
        if search_result.startswith("http"):
            # Extract artist and song from the URL
            print(f"Found song at: {search_result}")
            # For simplicity, we'll still call get_song_lyrics with original params
            lyrics = get_song_lyrics(artist, song)
            print(lyrics)
        else:
            print(search_result)  # Print error message
    else:
        lyrics = get_song_lyrics(artist, song)
        print(lyrics)


if __name__ == "__main__":
    main()