Get a PDF by its DOI

get_pdf.py

"""
Module to download a PDF from Sci-Hub using a provided DOI.

This script uses curl to fetch a PDF from Sci-Hub based on the provided DOI and
saves it to a specified output path.

Example usage:
    python get_pdf.py "10.1038/s41586-020-2649-2" "output.pdf"

If no output path is specified, the DOI will be used as the filename with invalid
characters replaced.
"""

import subprocess
import re
import sys

def sanitize_filename(doi: str) -> str:
    """
    Sanitize the DOI to create a valid filename.

    Args:
        doi (str): The DOI to sanitize.

    Returns:
        str: A sanitized filename.
    """
    return re.sub(r'[\\/*?:"<>|]', '_', doi) + ".pdf"

def get_pdf_by_doi(doi: str, output_path: str) -> None:
    """
    Download a PDF from Sci-Hub using the provided DOI.

    Args:
        doi (str): The DOI of the paper to download.
        output_path (str): The path to save the downloaded PDF.

    Raises:
        RuntimeError: If the download fails.
    """
    # Construct the Sci-Hub URL
    sci_hub_url = f"https://sci-hub.se/{doi}"
    
    # Use curl to fetch the Sci-Hub page
    result = subprocess.run(['curl', '-sL', sci_hub_url], capture_output=True, text=True)
    
    if result.returncode != 0:
        raise RuntimeError(f"Failed to fetch the Sci-Hub page: {result.stderr}")
    
    # Extract the PDF URL from the Sci-Hub page
    pdf_url_match = re.search(r'src="([^"]+\.pdf[^"]*)"', result.stdout)
    
    if not pdf_url_match:
        raise RuntimeError("Failed to find the PDF URL on the Sci-Hub page.")
    
    pdf_url = pdf_url_match.group(1)
    
    # Ensure the PDF URL is complete
    if not pdf_url.startswith("http"):
        pdf_url = "https://sci-hub.se" + pdf_url
    
    # Download the PDF using curl
    download_result = subprocess.run(['curl', '-o', output_path, pdf_url])
    
    if download_result.returncode != 0:
        raise RuntimeError(f"Failed to download the PDF: {download_result.stderr}")

    print(f"Saved to {output_path}")

def main() -> None:
    """
    Main function to download a PDF by DOI using Sci-Hub.

    Command-line Args:
        doi (str): The DOI of the paper to download.
        output_path (str, optional): The path to save the downloaded PDF. Defaults to using the DOI as filename.
    """
    if len(sys.argv) < 2:
        print("Usage: python get_pdf.py <DOI> [output_path]")
        sys.exit(1)

    doi = sys.argv[1]
    output_path = sys.argv[2] if len(sys.argv) > 2 else sanitize_filename(doi)

    get_pdf_by_doi(doi, output_path)

if __name__ == "__main__":
    main()