Explore the manifest file

10.08.2018.3.py

from bs4 import BeautifulSoup

def explore_metadata():
    """Explores arxiv bucket metadata."""

    print('\narxiv bucket metadata:')

    with open('src/arXiv_src_manifest.xml', 'r') as manifest:
        soup = BeautifulSoup(manifest, 'xml')

        # Print last time the manifest was edited
        timestamp = soup.arXivSRC.find('timestamp', recursive=False).string
        print('Manifest was last edited on ' + timestamp)

        # Print number of files in bucket
        numOfFiles = len(soup.find_all('file'))
        print('arxiv bucket contains ' + str(numOfFiles) + ' tars')

        # Print total size
        total_size = 0
        for size in soup.find_all('size'):
            total_size = total_size + int(size.string)
        print('Total size: ' + str(total_size/1000000000) + ' GB')

    print('')

if __name__ == '__main__':
    """Runs if script is called on command line"""

    # Explore bucket metadata 
    explore_metadata()