find PDF font info with PyPDF2, example code

gistfile1.txt

from PyPDF2 import PdfFileReader
from pprint import pprint

def walk(obj, fnt, emb):
    '''
    If there is a key called 'BaseFont', that is a font that is used in the document.
    If there is a key called 'FontName' and another key in the same dictionary object
    that is called 'FontFilex' (where x is null, 2, or 3), then that fontname is 
    embedded.
    
    We create and add to two sets, fnt = fonts used and emb = fonts embedded.
    '''
    if not hasattr(obj, 'keys'):
        return None, None
    fontkeys = set(['/FontFile', '/FontFile2', '/FontFile3'])
    if '/BaseFont' in obj:
        fnt.add(obj['/BaseFont'])
    if '/FontName' in obj:
        if [x for x in fontkeys if x in obj]:# test to see if there is FontFile
            emb.add(obj['/FontName'])

    for k in obj.keys():
        walk(obj[k], fnt, emb)

    return fnt, emb# return the sets for each page

if __name__ == '__main__':
    import sys
    try:
        fname = sys.argv[1]
    except:
        print("Usage:\n{0} filename.pdf".format(sys.argv[0]))
        sys.exit(0)
    pdf = PdfFileReader(fname)
    fonts = set()
    embedded = set()
    for page in pdf.pages:
        obj = page.getObject()
        f, e = walk(obj['/Resources'], fonts, embedded)
        fonts = fonts.union(f)
        embedded = embedded.union(e)

    unembedded = fonts - embedded
    print( 'Font List')
    pprint(sorted(fonts))
    if unembedded:
        print( '\nUnembedded Fonts')
        pprint(sorted(unembedded))