Converting presentation slides to HTML blog post with images

Here is a Python script to convert a PDF to series of HTML <img> tags with alt texts. It makes the presentation suitable embedded for a blog post and reading on a mobile device and such.

The motivation for creating this script is that services creating embedded slideshow viewers (SlideShare, Speaker Deck) create <iframe> based output that is not RSS reader friendly. For example, blog aggregation services and soon defunct Google Reader may strip out the presentations <iframe> from RSS feeds. Also, generated <iframe> viewers are not mobile friendly. If you want to share your slides in a blog post using plain old HTML and images is the most bullet-proof way of doing it.

The script also shows the power of Python scripting, when combined with UNIX command line tools like Ghostscript PDF renderer and high availability of ready-made Python libraries from PyPi repository.

Example Workflow:

  • Export presentation from Apple Keynote to PDF file. On Export dialog untick include date and add borders around slides.
  • Run the script against generated PDF file to convert it to a series of JPEG files and a HTML snippet with <img> tags
  • Optionally, the scripts adds a full URL prefix to <img src>, so you don’t need to manually link images to your hosting service absolute URL
  • Copy-paste generated HTML to your blog post

Tested with Apple Keynote exported PDFs, but the approach should work for any PDF content.

See example blog post and presentation.


Source code below. The full source code with README and usage instructions is available on Github.

    PDF to HTML converter.


import os
import sys

import pyPdf
from pyPdf.pdf import ContentStream
from pyPdf.pdf import TextStringObject

SLIDE_TEMPLATE = u'<p><img src="{prefix}{src}" alt="{alt}" /></p>'

# You can pass Ghostscript binary to the script as an environment variable.
GHOSTSCRIPT = os.environ.get("GHOSTSCRIPT", "gs")

def create_images(src, target, width=620, height=480):
    """ Create series of images from slides.

    :param src: Source PDF file

    :param target: Target folder

    if target.endswith("/"):
        target = target[0:-1]

    # Generated filenames
    ftemplate = "%(target)s/slide%%d.jpg" % locals()

    # gs binary
    ghostscript = GHOSTSCRIPT

    # Export magic of doing
    # Note: Ghostscript 9.06 crashed for me
    # had to upgrade 9.07
    # This command does magic of anti-aliasing text and settings output JPEG dimensions correctly
    cmd = "%(ghostscript)s -dNOPAUSE -dPDFFitPage -dTextAlphaBits=4 -sDEVICE=jpeg -sOutputFile=%(ftemplate)s -dJPEGQ=80 -dDEVICEWIDTH=%(width)d -dDEVICEHEIGHT=%(height)d  %(src)s -c quit"
    cmd = cmd % locals()  # Apply templating

    if os.system(cmd):
        raise RuntimeError("Command failed: %s" % cmd)

def extract_text(self):
    """ Patched extractText() from pyPdf to put spaces between different text snippets.
    text = u""
    content = self["/Contents"].getObject()
    if not isinstance(content, ContentStream):
        content = ContentStream(content, self.pdf)
    # Note: we check all strings are TextStringObjects.  ByteStringObjects
    # are strings where the byte->string encoding was unknown, so adding
    # them to the text here would be gibberish.
    for operands, operator in content.operations:
        if operator == "Tj":
            _text = operands[0]
            if isinstance(_text, TextStringObject):
                text += _text
        elif operator == "T*":
            text += "\n"
        elif operator == "'":
            text += "\n"
            _text = operands[0]
            if isinstance(_text, TextStringObject):
                text += operands[0]
        elif operator == '"':
            _text = operands[2]
            if isinstance(_text, TextStringObject):
                text += "\n"
                text += _text
        elif operator == "TJ":
            for i in operands[0]:
                if isinstance(i, TextStringObject):
                    text += i

        if text and not text.endswith(" "):
            text += " "  # Don't let words concatenate

    return text

def scrape_text(src):
    """ Read a PDF file and return plain text of each page.

    :return: List of plain text unicode strings

    pages = []

    pdf = pyPdf.PdfFileReader(open(src, "rb"))
    for page in pdf.pages:
        text = extract_text(page)

    return pages

def create_index_html(target, slides, prefix):
    """ Generate HTML code for `<img>` tags.

    out = open(target, "wt")

    print >> out, "<!doctype html>"
    for i in xrange(0, len(slides)):
        alt = slides[i]  # ALT text for this slide
        params = dict(src=u"slide%d.jpg" % (i+1), prefix=prefix, alt=alt)
        line = SLIDE_TEMPLATE.format(**params)
        print >> out, line.encode("utf-8")


def main():
    """ Entry point. """

    if len(sys.argv) < 3:
        sys.exit("Usage: mypresentation.pdf targetfolder [image path prefix]")

    src = sys.argv[1]
    folder = sys.argv[2]

    if len(sys.argv) > 3:
        prefix = sys.argv[3]
        prefix = ""

    if not os.path.exists(folder):

    alt_texts = scrape_text(src)

    target_html = os.path.join(folder, "index.html")

    create_index_html(target_html, alt_texts, prefix)

    create_images(src, folder)

if __name__ == "__main__":

\"\" Subscribe to RSS feed Follow me on Twitter Follow me on Facebook Follow me Google+

Leave a Reply

Your email address will not be published. Required fields are marked *