check-links.py

# Written for Python 3. Although it runs on Python 2 as
# well, if that's a thing you're doing you might want to
# change items() to iteritems() and all that standard stuff.
#
# 2014 © ~kqr
# Licensed under the Apache License, Version 2.0 <LICENSE-APACHE or
# http://www.apache.org/licenses/LICENSE-2.0> or the MIT license
# <LICENSE-MIT or http://opensource.org/licenses/MIT>, at your
# option. This file may not be copied, modified, or distributed
# except according to those terms.

import sys
import re

id = re.compile('id="([^"]+)"')
href = re.compile('href="#([^"]+)"')


if __name__ == '__main__':
    for filename in sys.argv[1:]:
        anchors, references = scan_file(filename)

        for anchor, i in references.items():
            if anchor not in anchors:
                print("{file}:{i}: {anchor} referenced".format(file=filename, i=i, anchor=anchor))


def scan_file(filename):
    """Scans a HTML-like file for things that look like id and href attributes and
       returns all of their values coupled with the lines they appear in"""
    anchors = dict()
    references = dict()
  
    with open(filename, 'r') as file:
        for i, line in enumerate(file):
            anchors.update({ m.group(1): i for m in id.finditer(line) })
            references.update({ m.group(1): i for m in href.finditer(line) })
  
    return anchors, references