PDF Checking

PDF-Testing.md

PDF Testing Gist

These two files, pdf_linkchecker.py and pdf_fontchecker.py are code examples to go along with a blog article: http://reachtim.com/articles/PDF-Testing.html

See the article for details on how to test your PDFs for broken internal and external links and for unembedded fonts.

pdf_fontchecker.py

'''
Gist to accompany blog artice:
http://reachtim.com/articles/PDF-Testing.html
'''

from PyPDF2 import PdfFileReader
from pprint import pprint
import sys

fontkeys = set(['/FontFile', '/FontFile2', '/FontFile3'])

def walk(obj, fnt, emb):
    if '/BaseFont' in obj:
        fnt.add(obj['/BaseFont'])

    elif '/FontName' in obj and fontkeys.intersection(set(obj)):
        emb.add(obj['/FontName'])

    for k in obj:
        if hasattr(obj[k], 'keys'):
            walk(obj[k], fnt, emb)

    return fnt, emb

if __name__ == '__main__':
    fname = sys.argv[1]
    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(list(fonts)))

    if unembedded:
        print '\nUnembedded Fonts'
        pprint(unembedded)

pdf_linkchecker.py

'''
Gist to accompany blog artice:
http://reachtim.com/PDF-Testing.html
'''

from PyPDF2 import PdfFileReader
import requests
import sys
import urllib

def check_ftp(url):
    try:
        response = urllib.urlopen(url)
    except IOError as e:
        result, reason = False, e
    else:
        if response.read():
            result, reason = True, 'okay'
        else:
            result, reason = False, 'Empty Page'
    return result, reason
    
def check_url(url, auth=None):
    headers = {'User-Agent': 'Mozilla/5.0', 'Accept': '*/*'}
    if url.startswith('ftp://'):
        result, reason = check_ftp(url)
    else:
        try:
            response = requests.get(url, timeout=6, auth=auth, headers=headers)
        except (requests.ConnectionError,
                requests.HTTPError,
                requests.Timeout,
                requests.exceptions.MissingSchema) as e:
            result, reason = False, e
        else:
            if response.text:
                result, reason = response.status_code, response.reason
            else:
                result, reason = False, 'Empty Page'

    return result, reason
        
def check_pdf(pdf):
    links = list()
    urls = list()
    badurls = list()

    for page in pdf.pages:
        obj = page.getObject()
        for annot in [x.getObject() for x in obj.get('/Annots', [])]:
            if '/A' in annot:
                dst = annot['/A'].get('/D')
                url = annot['/A'].get('/URI')
                if dst:
                    links.append(dst)
                elif url:
                    urls.append(url)
                    result, reason = check_url(url)
                    if not result:
                        badurls.append({'url':url, 'reason': '%r' % reason})
            elif '/Dest' in annot:
                links.append(annot['/Dest'])
                

    anchors = pdf.namedDestinations.keys()
    superfluous_anchors = [x for x in anchors if x not in links]
    badlinks = [x for x in links if x not in anchors]
    return anchors, links, superfluous_anchors, badlinks, urls, badurls
        
if __name__ == '__main__':
    fname = sys.argv[1]
    print 'Checking %s' % fname
    pdf = PdfFileReader(fname)
    anchors, links, superfluous_anchors, badlinks, urls, badurls = check_pdf(pdf)
    print 'urls: ', ', '.join(urls)
    print
    print 'anchors: ', ', '.join(anchors)
    print
    print 'superfluous_anchors: ', ', '.join(superfluous_anchors)
    print
    print 'links: ', ', '.join(links)
    print
    print 'bad links: ', ', '.join(badlinks)
    print
    print 'bad urls:'
    for item in badurls:
        for key, value in item.items():
            print '  {}: {}'.format(key, value) 

It's a great resource, and to be very honest, conversations like these help me to remember why I adore the IT community. Everyone is willing to provide a hand and share priceless advice at all times. Speaking of advice, I recently had a little experience with PDFs of my own. My phone was inundated with paperwork as I was leaving for a client presentation—proposals, contracts, you name it. Finding the correct PDF at the right moment became a mini-nightmare among the confusion. Subsequently, I discovered something that gave me hope for the future. This post http://www.techguide.com.au/news/internet-news/adding-pdf-to-apple-wallet-a-travelers-guide-for-safe-pdf-document-storage/ about adding PDFs to Apple Wallet caught my attention; although it seems straightforward, it was enlightening. Take a look at TechGuide for yourself.For me, it's proven invaluable, particularly in circumstances where I need to quickly access my documents without having to go through emails or folders.