Script is useful for creating the advanced HTML newsletter. It reads the file with the email message created by Mozilla Thunderbird (variable filename) with attached images. It replaces image filenames (it uses MD5 checksum; variables fileImages, ...

repair_email_images.py

#!/usr/bin/env python2.7
#          Copyright Martin Mevald 2011.
# Distributed under the Boost Software License, Version 1.0.
#    (See accompanying file LICENSE_1_0.txt or copy at
#          http://www.boost.org/LICENSE_1_0.txt)

# settings
fileImages = ['hl1.png','Afrika_party_212px.jpg','vlnovka.png','f.png','distribuce.jpg','teachers_first round_demonstration180px.jpg','vlnovka0.png','rusinga_island_rustinga_1_180px.jpg','IMG_0075_180px.jpg','3_180px.jpg','afrika_nevsednima_ocima_program_partnerstvi_partnerstvi_180px.jpg','zapati.png']
imagesPath = 'C:\\Users\Martin\\Documents\\Bulletin\\'
filename='C:\\Users\\Martin\\Documents\\Bulletin Centra Narovinu.eml'

"""
Script is useful for creating the advanced HTML newsletter.
It reads the file with the email message created by Mozilla Thunderbird (variable filename) with attached images.
It replaces image filenames (it uses MD5 checksum; variables fileImages, imagesPath) with their Content-ID.
Script writes the output to [filename].output .
"""

import md5
import base64

md5Images = {}

#force
#md5Images['95e735cd48776c326967a722e2517abd']='x.jpg'

# load images
for fileImage in fileImages:
    f = open(imagesPath+fileImage,"rb")
    image = f.read()
    f.close()
    digest = md5.md5(image).hexdigest()
    print fileImage,digest
    md5Images[digest] = fileImage
#endfor

f = open(filename,"r")
lines = []
for line in f.readlines():
    lines.append(line.replace('\n','').replace('\r',''))
#endfor
f.close()



#print len(lines)
readingImage = False

images = []

for line in lines:
    if not readingImage:
        img = ''
        contentId = ''
        if line[0:11] == 'Content-ID:':
            contentId=line.split(' ')[1].replace('<','').replace('>','')
            readingImage = True
            print contentId
        #endif
    else:
        if line[0:5]=='-----':
            # complete image
            image=base64.b64decode(img)
            digest = md5.md5(image).hexdigest()
            if not md5Images.has_key(digest):
                raise(Warning("Digest: %s, no image for Content-ID: %s, img: %s" % (digest,contentId,img)))
            #endif
            images.append((contentId,md5Images[digest]))
            readingImage = False
        elif line=='' or (line.find('Content-Disposition:')>=0) or (line.find(' filename')>=0):
            continue
        else:
            img+=line
        #endif
    #endif
#endfor

print
print
print images

# write
f = open(filename+".output","w")

for line in lines:
    for image in images:
        output = line.replace(image[1],'cid:'+image[0])
        if line!=output:
            break
        #endif
    #endif
    f.write(output+'\n')
#endfor

f.close()