Spaces:
Sleeping
Sleeping
| """ | |
| This script downloads the top 30 most read books from Project Gutenberg in EPUB format. | |
| The script performs the following steps: | |
| 1. Fetches the list of the most read books from Project Gutenberg. | |
| 2. Parses the list to extract the top 30 books. | |
| 3. Downloads the EPUB files of the top 30 books. | |
| 4. Saves the EPUB files locally with titles formatted to replace whitespace with underscores. | |
| Modules required: | |
| - requests: For making HTTP requests to Project Gutenberg. | |
| - BeautifulSoup (bs4): For parsing HTML content. | |
| - tqdm: For displaying a progress bar. | |
| - re: For regular expression operations. | |
| Usage: | |
| Run the script directly to start the download process. | |
| """ | |
| import requests | |
| from bs4 import BeautifulSoup | |
| from tqdm import tqdm | |
| import re | |
| def get_top_books(): | |
| """ | |
| Fetches the list of most read books from Project Gutenberg. | |
| Returns: | |
| list: A list of BeautifulSoup tag objects containing the top 30 most read books. | |
| """ | |
| # Get the list of most read books | |
| response = requests.get("http://www.gutenberg.org/browse/scores/top") | |
| soup = BeautifulSoup(response.content, 'html.parser') | |
| # Find the top 30 most read books | |
| top_books = soup.select('ol li a[href^="/ebooks/"]')[:30] | |
| return top_books | |
| def download_epub(book_id, title, directory): | |
| """ | |
| Downloads the EPUB file of a book from Project Gutenberg. | |
| Args: | |
| book_id (str): The ID of the book on Project Gutenberg. | |
| title (str): The title of the book. | |
| Returns: | |
| None | |
| """ | |
| epub_url = f"http://www.gutenberg.org/ebooks/{book_id}.epub.noimages" | |
| epub_response = requests.get(epub_url) | |
| # Check if the request was successful | |
| if epub_response.status_code == 200: | |
| # Replace whitespace in the title with underscores | |
| formatted_title = re.sub(r'\s+', '_', title) | |
| filename = f"{directory}{formatted_title}.epub" | |
| # Save the EPUB file | |
| with open(filename, 'wb') as file: | |
| file.write(epub_response.content) | |
| print(f"Downloaded: {filename}") | |
| else: | |
| print(f"EPUB not available for book ID: {book_id}") | |
| def main(): | |
| """ | |
| Main function to download the top 30 most read books from Project Gutenberg in EPUB format. | |
| Returns: | |
| None | |
| """ | |
| top_books = get_top_books() | |
| # Loop through the top books and download EPUB files | |
| for book in tqdm(top_books, desc='Downloading books...'): | |
| book_url = book['href'] | |
| book_id = book_url.split('/')[-1] | |
| title = book.get_text().strip().replace('/', '-') | |
| download_epub(book_id, title, directory="data/self_scraped/books_epub/") | |
| if __name__ == "__main__": | |
| main() | |