Download raw (1.4 KB)

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import re
import glob
import codecs
import os.path
import argparse

parser = argparse.ArgumentParser("Insert image references")
parser.add_argument('folder', help="Stories folder, with HTML files")
args = parser.parse_args()

def insert_image_references (m):
  src = m.group(1)
  alt = m.group(2)
  className = m.group(3)
  num = re.search("[\d|\w]+$", alt).group(0)
  return '<span class="img_ref" data-for="figure_{3}">{3}</span><img src="{0}" alt="{1}" class="{2}" id="figure_{3}" />'.format(src, alt, className, num)

for bookfolder in glob.glob("{0}/book*".format(os.path.normpath(args.folder))):
  print "{0}".format(bookfolder)
  for htmlpath in glob.glob("{0}/*.html".format(os.path.normpath(bookfolder))):
    print "\t{0}".format(htmlpath)
    htmlstring = None

    with codecs.open(htmlpath, mode='r', encoding='utf-8') as htmlfile:
      htmlstring = htmlfile.read()
      htmlstring = re.sub('\<img src="(.[^\"]+)" alt="(.[^\"]+)" (?:class="(.[^\"]+)" )?/\>', insert_image_references, htmlstring)
      
      # matches = re.finditer('\<img src="(.[^\"]+)" alt="(.[^\"]+)" (?:class="(.[^\"]+)" )?/\>', htmlstring)
      # if matches:
      #   for m in matches:
      #     print m.group(1), m.group(2), m.group(3)

    if htmlstring:
      with codecs.open(htmlpath, mode='w', encoding='utf-8') as htmlfile:
        htmlfile.write(htmlstring)