#!/usr/bin/python '''A script that converts a CHM compiled HTML file into a single PDF file. (c) 2012 Neil Schemenauer Losely based on a version of a script with the same name: (c) 2007 Massimo Sandal (c) 2007 Chris Karakas ''' # This program is free software: you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation, either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see . import sys import os import optparse import subprocess import shutil import sgmllib import tempfile import urllib import chm.chm as chm USAGE = 'Usage: %prog [options] ' VERSION = '1.0' class PageLister(sgmllib.SGMLParser): def reset(self): sgmllib.SGMLParser.reset(self) self.pages = [] def start_param(self,attrs): attrs = dict(attrs) if attrs.get('name') == 'Local': self.pages.append(attrs['value']) def list_topics(cfile): """List the URLs in the CHM topics tree. """ page = cfile.GetTopicsTree() if not page: return [] lister = PageLister() lister.feed(page) return lister.pages class UrlCatcher(sgmllib.SGMLParser): def reset(self): sgmllib.SGMLParser.reset(self) self.urls = set() def start_img(self,attrs): for key, value in attrs: if key.lower() == 'src': self.urls.add(value) def start_link(self,attrs): for key, value in attrs: if key.lower() == 'href': self.urls.add(value) def list_urls(page_data): """Return a set of URLs referenced in a HTML document. """ c = UrlCatcher() c.feed(page_data) return c.urls def fix_abs_urls(base_dir, filename): with open(filename, 'rU') as fp: page = fp.read() change = {} for url in list_urls(page): if url.startswith('/'): # absolute path, make relative to temp directory change['"%s"' % url] = '"%s%s"' % (urllib.quote(base_dir), url) if change: for old, new in change.items(): if VERBOSE: print old, '->', new # this is a hack since it might change content that is no actually # a reference page = page.replace(old, new) with open(filename, 'w') as fp: fp.write(page) def convert_pdf_wk(options, pages, outputfilename): pdf_opts = ['--page-size', options.page_size] if options.grayscale: pdf_opts.append('-g') if not VERBOSE: pdf_opts.append('--quiet') cmd = ['wkhtmltopdf'] + pdf_opts + pages + [outputfilename] if VERBOSE: print ' '.join(cmd) if not options.extract_only: subprocess.call(cmd) def convert_pdf_htmldoc(options, pages, outputfilename): cmd = ['htmldoc', '--continuous', '--duplex', '--format', 'pdf14', '--outfile', outputfilename, '--jpeg=90', #'--header', 'c C', '--footer', 'c C', #'--bodyfont', 'times', '--linkstyle', 'plain', '--size', options.page_size.lower()] if options.grayscale: cmd.append('--gray') else: cmd.append('--color') if not VERBOSE: cmd.append('--quiet') cmd.extend(pages) if VERBOSE: print ' '.join(cmd) if not options.extract_only: subprocess.call(cmd) def main(argv): global VERBOSE parser = optparse.OptionParser(USAGE, version=VERSION) parser.add_option('--output', '-o', default=None) parser.add_option('-v', '--verbose', action='store_true', dest='verbose', default=0, help="enable extra status output") parser.add_option('-k', '--keep', action='store_true', help="keep temporary directory of extracted content") parser.add_option('-e', '--extract-only', action='store_true', dest='extract_only', help="extract content but do not create PDF") parser.add_option('-s', '--page-size', default='A4', help="Set paper size to : A4, Letter, etc") parser.add_option('-g', '--grayscale', action='store_true', help="PDF will be generated in grayscale") parser.add_option('--htmldoc', action='store_true', help="use htmldoc create PDF (default " "is to use wkhtmltopdf)") options, args = parser.parse_args() VERBOSE = options.verbose if options.extract_only: options.keep = True if len(args) != 1: parser.print_usage() raise SystemExit filename = os.path.abspath(args[0]) if not os.path.exists(filename): raise SystemExit('CHM file "' + filename + '" not found!') cfile = chm.CHMFile() cfile.LoadCHM(filename) basename, ext = os.path.splitext(os.path.basename(filename)) dirname = os.path.dirname(filename) if options.output: outputfilename = os.path.abspath(options.output) else: outputfilename = os.path.join(dirname, basename +'.pdf') base_dir = tempfile.mkdtemp(prefix='chm2pdf.') try: os.chdir(base_dir) if VERBOSE: print 'extracting to', base_dir cmd = ['extract_chmLib', filename, '.'] p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT) out, err = p.communicate() if VERBOSE: sys.stdout.write(out) urls = list_topics(cfile) if not urls: raise SystemExit('No pages found.') pages = [] for url in urls: filename = urllib.unquote(url) if filename.startswith('/'): filename = filename[1:] if os.path.exists(filename): pages.append(filename) fix_abs_urls(base_dir, filename) else: if VERBOSE: print 'cannot find %r, ignoring' % filename if options.htmldoc: convert_pdf_htmldoc(options, pages, outputfilename) else: convert_pdf_wk(options, pages, outputfilename) finally: if options.keep: print 'keeping extracted content as %r' % base_dir else: shutil.rmtree(base_dir) if __name__ == '__main__': main(sys.argv)