> Hello, please port chm2pdf to Python3 and/or drop the python 2 > package. This will help the goal of removing Python 2 from Debian, > and would also (more immediately) allow to remove packages currently > dependencies of this one.
I tried a brutal port to py3k: 2to3 + fixing some encoding/decoding issue + port to html.parser but chm2pdf is still not working. not sure it's worth the effort, so i'm gonna go ahead and ask for its removal (replying here to leave some info if someone will pick up the work)
--- a/chm2pdf +++ b/chm2pdf @@ -1,4 +1,4 @@ -#!/usr/bin/python +#!/usr/bin/python3 ''' CHM2PDF v. 0.9.1 http://code.google.com/p/chm2pdf @@ -23,7 +23,7 @@ A script that converts a CHM compiled HT import chm.chm as chm import sys -import sgmllib +import html.parser import os, os.path import re, glob import getopt @@ -49,13 +49,13 @@ CHM2PDF_TEMP_ORIG_DIR=tempfile.mkdtemp() # YOU DON'T NEED TO CHANGE ANYTHING BELOW THIS LINE! -class PageLister(sgmllib.SGMLParser): +class PageLister(html.parser.HTMLParser): ''' parser of the chm.chm GetTopicsTree() method that retrieves the URL of the HTML page embedded in the CHM file. ''' def reset(self): - sgmllib.SGMLParser.reset(self) + html.parser.HTMLParser.reset(self) self.pages=[] def start_param(self,attrs): @@ -66,12 +66,12 @@ class PageLister(sgmllib.SGMLParser): if urlparam_flag and key=='value': self.pages.append('/'+value) -class ImageCatcher(sgmllib.SGMLParser): +class ImageCatcher(html.parser.HTMLParser): ''' finds image urls in the current html page, so to take them out from the chm file. ''' def reset(self): - sgmllib.SGMLParser.reset(self) + html.parser.HTMLParser.reset(self) self.imgurls=[] def start_img(self,attrs): @@ -81,12 +81,12 @@ class ImageCatcher(sgmllib.SGMLParser): if not self.imgurls.count(value): self.imgurls.append(value) -class CssCatcher(sgmllib.SGMLParser): +class CssCatcher(html.parser.HTMLParser): ''' finds CSS urls in the current html page, so to take them out from the chm file. ''' def reset(self): - sgmllib.SGMLParser.reset(self) + html.parser.HTMLParser.reset(self) self.cssurls=[] def start_link(self,attrs): @@ -101,7 +101,7 @@ def get_html_list(cfile): retrieves the list of HTML files contained into the CHM file, **in order** (that's the important bit). (actually performed by the PageLister class) ''' - topicstree=cfile.GetTopicsTree() + topicstree=cfile.GetTopicsTree().decode('utf-8', errors='replace') lister=PageLister() lister.feed(topicstree) #print 'lister pages',lister.pages @@ -338,10 +338,10 @@ def convert_to_pdf(cfile, filename, outp output_titlefile = CHM2PDF_WORK_DIR + os.sep + options['titlefile'] if not options['titlefile']=='' and not output_titlefile: - print '### WARNING: ' + options['titlefile'] + ' not found inside ' + filename + ' - possible spelling error.' - print '### You can check it if you do \'' + sys.argv[0] + ' --extract-only\',' - print '### then have a look at the files in ' + CHM2PDF_ORIG_DIR + '.' - print '### Option \'--titlefile ' + options['titlefile'] + '\' ignored' + print('### WARNING: ' + options['titlefile'] + ' not found inside ' + filename + ' - possible spelling error.') + print('### You can check it if you do \'' + sys.argv[0] + ' --extract-only\',') + print('### then have a look at the files in ' + CHM2PDF_ORIG_DIR + '.') + print('### Option \'--titlefile ' + options['titlefile'] + '\' ignored') options['titlefile'] = '' @@ -373,7 +373,7 @@ def convert_to_pdf(cfile, filename, outp page_filename = re.sub('%20',' ',page_filename) if options['verbose']=='--verbose' and options['verbositylevel']=='high' and options['dontextract'] == '': - print "Correcting " + page_filename + print("Correcting " + page_filename) if os.path.exists(page_filename) and (options['titlefile'] == '' or not options['titlefile'] in url): @@ -425,25 +425,25 @@ def convert_to_pdf(cfile, filename, outp if options['dontextract'] == '': # Correct links to files in the local collection. if options['verbose']=='--verbose' and options['verbositylevel']=='low': - print 'Correcting links in the HTML files...' + print('Correcting links in the HTML files...') if options['verbose']=='--verbose' and options['verbositylevel']=='high': - print '############### 1st pass ###############' + print('############### 1st pass ###############') for match_string in match_strings: replace_string = replace_garbled_strings[match_strings.index(match_string)] if options['verbose']=='--verbose' and options['verbositylevel']=='high': - print "match " + match_string + ' ' + "and replace it with " + replace_string + print("match " + match_string + ' ' + "and replace it with " + replace_string) if options['verbose']=='--verbose' and options['verbositylevel']=='high': - print + print() if options['verbose']=='--verbose' and options['verbositylevel']=='high': - print '############### 2nd pass ###############' + print('############### 2nd pass ###############') for match_string in replace_garbled_strings: replace_string = replace_strings[replace_garbled_strings.index(match_string)] if options['verbose']=='--verbose' and options['verbositylevel']=='high': - print "match " + match_string + ' ' + "and replace it with " + replace_string + print("match " + match_string + ' ' + "and replace it with " + replace_string) if options['verbose']=='--verbose' and options['verbositylevel']=='high': - print + print() for filename in htmlout_filenames: @@ -487,11 +487,11 @@ def convert_to_pdf(cfile, filename, outp # ...otherwise continue with PDF generation. if options['verbose']=='--verbose' and options['verbositylevel']=='low': - print 'Producing the PDF from the '+str(c)+' individual HTML files...' + print('Producing the PDF from the '+str(c)+' individual HTML files...') htmldoc_opts = '' # print options - for key in options.keys(): + for key in list(options.keys()): value = options[key] if not value == '': if key=='bodycolor': htmldoc_opts += ' --bodycolor ' + value @@ -582,136 +582,136 @@ def convert_to_pdf(cfile, filename, outp elif key=='webpage': htmldoc_opts += ' ' + value if options['verbose']=='--verbose' and options['verbositylevel']=='high': - print 'htmldoc' + htmldoc_opts + ' ' + htmlout_filename_list + " -f "+ outputfilename + " > /dev/null" + print('htmldoc' + htmldoc_opts + ' ' + htmlout_filename_list + " -f "+ outputfilename + " > /dev/null") exit_value=os.system ('htmldoc' + htmldoc_opts + ' ' + htmlout_filename_list + " -f "+ outputfilename + " > /dev/null") if exit_value != 0: - print 'Something wrong happened when launching htmldoc.' - print 'exit value: ',exit_value - print 'Check if output exists or if it is good.' + print('Something wrong happened when launching htmldoc.') + print('exit value: ',exit_value) + print('Check if output exists or if it is good.') else: - print 'Written file ' + outputfilename - print 'Done.' + print('Written file ' + outputfilename) + print('Done.') def usage (name): - print 'Usage:' - print "\t%s [options] input_filename [output_filename]" % name - print - print 'Options:' - print - print '\t--beautifulsoup\n\t\tCorrect the HTML code of the pages before converting them to PDF. The BeautifulSoup package (see http://www.crummy.com/software/BeautifulSoup/) needs to be installed.' - print '\t--bodycolor color\n\t\tSpecifies the background color for all pages.' - print '\t--bodyfont {courier,helvetica,monospace,sans,serif,times}. Default is times.' - print '\t--bodyimage filename.{bmp,gif,jpg,png}' - print '\t--book\n\t\tSpecifies that the HTML sources are structured (headings, chapters, etc.).' - print '\t--bottom margin{in,cm,mm}\n\t\tSpecifies the bottom margin in points (no suffix or ##pt), inches (##in), centimeters (##cm), or millimeters (##mm).' - print '\t--browserwidth pixels\n\t\tSee http://www.htmldoc.org/newsgroups.php?ghtmldoc.general+v:3465' - print '\t--charset {cp-874...1258,iso-8859-1...8859-15,koi8-r}\n\t\tSpecifies the ISO character set to use for the output.' - print '\t--color\n\t\tSpecifies that PDF output should be in color.' - print '\t--compression[=level]\n\t\t' - print '\t--continuous\n\t\tSpecifies that the HTML sources are unstructured (plain web pages).\n\t\tNo page breaks are inserted between each file or URL in the output.' - print '\t--cookies \'name="value with space"; name=value\'\n\t\t' - print '\t--datadir directory\n\t\tSpecifies the location of the HTMLDOC data files, usually /usr/share/htmldoc or C:\Program Files\HTMLDOC ' + print('Usage:') + print("\t%s [options] input_filename [output_filename]" % name) + print() + print('Options:') + print() + print('\t--beautifulsoup\n\t\tCorrect the HTML code of the pages before converting them to PDF. The BeautifulSoup package (see http://www.crummy.com/software/BeautifulSoup/) needs to be installed.') + print('\t--bodycolor color\n\t\tSpecifies the background color for all pages.') + print('\t--bodyfont {courier,helvetica,monospace,sans,serif,times}. Default is times.') + print('\t--bodyimage filename.{bmp,gif,jpg,png}') + print('\t--book\n\t\tSpecifies that the HTML sources are structured (headings, chapters, etc.).') + print('\t--bottom margin{in,cm,mm}\n\t\tSpecifies the bottom margin in points (no suffix or ##pt), inches (##in), centimeters (##cm), or millimeters (##mm).') + print('\t--browserwidth pixels\n\t\tSee http://www.htmldoc.org/newsgroups.php?ghtmldoc.general+v:3465') + print('\t--charset {cp-874...1258,iso-8859-1...8859-15,koi8-r}\n\t\tSpecifies the ISO character set to use for the output.') + print('\t--color\n\t\tSpecifies that PDF output should be in color.') + print('\t--compression[=level]\n\t\t') + print('\t--continuous\n\t\tSpecifies that the HTML sources are unstructured (plain web pages).\n\t\tNo page breaks are inserted between each file or URL in the output.') + print('\t--cookies \'name="value with space"; name=value\'\n\t\t') + print('\t--datadir directory\n\t\tSpecifies the location of the HTMLDOC data files, usually /usr/share/htmldoc or C:\Program Files\HTMLDOC ') # print "\t--dontextract \n\t\tIf given, %s will not extract the HTML files from the given CHM file, but will use previously extracted copies from the temporary directory " %name + '(i.e. ' + CHM2PDF_TEMP_ORIG_DIR + ' and ' + CHM2PDF_TEMP_WORK_DIR + '). Usually you will use this option after you have used the \'--extract-only\' option to extract the files in order to correct them manually (in ' + CHM2PDF_TEMP_WORK_DIR + '). After the correction, a call with \'--dontextract\' will not overwrite your changes, but will use the corrected files instead.' - print '\t--duplex\n\t\tSpecifies that the output should be formatted for double-sided printing.' - print '\t--effectduration {0.1..10.0}\n\t\tSpecifies the duration in seconds of PDF page transition effects.' - print '\t--embedfonts\n\t\tSpecifies that fonts should be embedded in PDF output.' - print '\t--encryption\n\t\tEnables encryption of PDF files.' - print '\t--extract-only\n\t\tExtract the HTML files from the CHM file and stop.\n\t\tThe extracted files will be found in CHM2PDF_WORK_DIR/input_filename_without_extension.' - print '\t--firstpage {p1,toc,c1}\n\t\t' - print '\t--fontsize {4.0..24.0}\n\t\tSpecifies the default font size for body text.' - print '\t--fontspacing {1.0..3.0}\n\t\tSpecifies the default line spacing for body text.\n\t\tThe line spacing is a multiplier for the font size, so a value of 1.2 \n\t\twill provide an additional 20% of space between the lines.' - print '\t--footer fff\n\t\t' - print '\t{--format, -t} {pdf11,pdf12,pdf13,pdf14}\n\t\tSpecifies the output format: pdf11\n\t\tpdf11 (PDF 1.1/Acrobat 2.0), pdf12 (PDF 1.2/Acrobat 3.0), \n\t\tpdf or pdf13 (PDF 1.3/Acrobat 4.0), or pdf14 (PDF 1.4/Acrobat 5.0)' - print '\t--gray\n\t\t' - print '\t--header fff\n\t\t' - print '\t--header1 fff\n\t\t' - print '\t--headfootfont {courier{-bold,-oblique,-boldoblique}, \n\t\thelvetica{-bold,-oblique,-boldoblique}, \n\t\tmonospace{-bold,-oblique,-boldoblique}, \n\t\tsans{-bold,-oblique,-boldoblique}, \n\t\tserif{-bold,-italic,-bolditalic}, \n\t\ttimes{-roman,-bold,-italic,-bolditalic}} \n\t\t\tSets the font to use on headers and footers.' - print '\t--headfootsize {6.0..24.0}\n\t\tSets the size of the font to use on headers and footers.' - print '\t--headingfont {courier,helvetica,monospace,sans,serif,times}\n\t\tSets the typeface to use for headings.' - print '\t--help\n\t\tDisplays a summary of command-line options.' - print '\t--hfimage0 filename.{bmp,gif,jpg,png}\n\t\t ' - print '\t--hfimage1 filename.{bmp,gif,jpg,png}\n\t\t ' - print '\t--hfimage2 filename.{bmp,gif,jpg,png}\n\t\t ' - print '\t--hfimage3 filename.{bmp,gif,jpg,png}\n\t\t ' - print '\t--hfimage4 filename.{bmp,gif,jpg,png}\n\t\t ' - print '\t--hfimage5 filename.{bmp,gif,jpg,png}\n\t\t ' - print '\t--hfimage6 filename.{bmp,gif,jpg,png}\n\t\t ' - print '\t--hfimage7 filename.{bmp,gif,jpg,png}\n\t\t ' - print '\t--hfimage8 filename.{bmp,gif,jpg,png}\n\t\t ' - print '\t--hfimage9 filename.{bmp,gif,jpg,png}\n\t\t ' - print '\t--jpeg quality\n\t\tSets the JPEG compression level to use for large images. A value of 0 disables JPEG compression.' - print '\t--landscape\n\t\t' - print '\t--left margin{in,cm,mm}\n\t\tSpecifies the left margin in points (no suffix or ##pt), inches (##in), centimeters (##cm), or millimeters (##mm).' - print '\t--linkcolor color\n\t\tSets the color of links. You can use well-known color names like blue, or the usual #RRGGBB notation.' - print '\t--links\n\t\tEnables generation of links in PDF files (default).' - print '\t--linkstyle {plain,underline}\n\t\tSets the style of links.' - print '\t--logoimage filename.{bmp,gif,jpg,png}\n\t\tSpecifies an image to be used as a logo in the header or footer in a PDF document.' - print '\t--logoimage filename.{bmp,gif,jpg,png}\n\t\tNote that you need to use the --header and/or --footer options with the l parameter.' - print '\t--no-compression\n\t\tDisables compression of PDF file.' - print '\t--no-duplex\n\t\tDisables double-sided printing.' - print '\t--no-embedfonts\n\t\tSpecifies that fonts should not be embedded in PDF and PostScript output.' - print '\t--no-encryption\n\t\tDisables document encryption.' - print '\t--no-links\n\t\tDisables generation of links in a PDF document. ' - print '\t--no-localfiles\n\t\t' - print '\t--no-numbered\n\t\tDisables automatic heading numbering.' - print '\t--no-overflow\n\t\t' - print '\t--no-strict\n\t\tDisables strict HTML input checking.' - print '\t--no-title\n\t\tDisables generation of a title page.' - print '\t--no-toc\n\t\tDisables generation of a table of contents.' - print '\t--numbered\n\t\tNumbers all headings in a document.' - print '\t--nup {1,2,4,6,9,16}\n\t\tSets the number of pages that are placed on each output page. Valid values are 1, 2, 4, 6, 9, and 16.' - print '\t{--outfile, -f} filename{.pdf}\n\t\tSpecifies the name of the output file. If no ending is given, ".pdf" is used.' - print '\t--overflow\n\t\t' - print '\t--owner-password password\n\t\tSets the owner password for encrypted PDF files.' - print '\t--pageduration {1.0..60.0}\n\t\tSets the view duration of a page in a PDF document.' - print '\t--pageeffect {none,bi,bo,d,gd,gdr,gr,hb,hsi,hso,vb,vsi,vso,wd,wl,wr,wu}\n\t\tSpecifies the page transition effect for all pages; this attribute is ignored by all Adobe PDF viewers.. ' - print '\t--pagelayout {single,one,twoleft,tworight}\n\t\tSpecifies the initial layout of pages for a PDF file.' - print '\t--pagemode {document,outline,fullscreen}\n\t\tSpecifies the initial viewing mode for a PDF file.' - print '\t--path "dir1;dir2;dir3;...;dirN"\n\t\tSpecifies a search path for files in a document.' - print '\t--permissions {all,annotate,copy,modify,print,no-annotate,no-copy,no-modify,no-print,none}\n\t\tSpecifies document permissions for encrypted PDF files. Separate multiple permissions with commas. ' - print '\t--portrait\n\t\t' - print '\t--prefontsize {4.0..24.0, small, normal, big, huge, +1, +2, -1, -2,...whatever}\n\t\tSpecifies the font size for text inside <pre> tags. Whatever you pass here will be used as font size inside preformatted pieces of text (usually code snippets, console output, program messages...). Effective only together with the \'--beautifulsoup\' option.' - print '\t--quiet\n\t\tSuppresses all messages, even error messages.' - print '\t--right margin{in,cm,mm}\n\t\tSpecifies the right margin in points (no suffix or ##pt), inches (##in), centimeters (##cm), or millimeters (##mm).' - print '\t--size {letter,a4,WxH{in,cm,mm},etc}\n\t\tSpecifies the page size using a standard name or in points (no suffix or ##x##pt), inches (##x##in),\n\t\tcentimeters (##x##cm), or millimeters (##x##mm). The standard sizes that are currently recognized\n\t\tare "letter" (8.5x11in), "legal" (8.5x14in), "a4" (210x297mm), and "universal" (8.27x11in).' - print '\t--strict\n\t\tEnables strict HTML input checking.' - print '\t--textcolor color\n\t\tSpecifies the default color of all text.' - print '\t--textfont {courier,helvetica,monospace,sans,serif,times}\n\t\t' - print '\t--title\n\t\tEnables the generation of a title page.' - print '\t--titlefile filename.{htm,html,shtml}\n\t\tSpecifies the file to use for the title page. If the file is an image then the title page\n\t\tis automatically generated using the document meta data and image title.' - print '\t--titleimage filename.{bmp,gif,jpg,png}\n\t\tSpecifies the image to use for the title page. The title page is automatically \n\t\tgenerated using the document meta data and title image.' - print '\t--tocfooter fff\n\t\tSets the page footer to use on table-of-contents pages. See below for the format of fff.' - print '\t--tocheader fff\n\t\tSets the page header to use on table-of-contents pages. See below for the format of fff.' - print '\t--toclevels levels\n\t\tSets the number of levels in the table-of-contents.' - print '\t--toctitle string\n\t\tSets the title for the table-of-contents.' - print '\t--top margin{in,cm,mm}\n\t\tSpecifies the top margin in points (no suffix or ##pt), inches (##in), centimeters (##cm), or millimeters (##mm).' - print '\t--user-password password\n\t\tSpecifies the user password for encryption of PDF files.' - print '\t--verbose\n\t\tDisplays various messages indicating the progress of the conversion process. The verbosity depends on --verbositylevel. If --verbose is not set, almost no messages will be printed. The default is \'not set\', so if you want the minimum amount of messages, just don\' use this option.' - print '\t--verbositylevel\n\t\tSpecifies the verbosity level of the messages. Can be either \'low\' or \'high\'. Default is low. The --verbose option must be set, otherwise this option will have no effect.' - print '\t--version\n\t\tDisplays the current version number.' - print '\t--webpage\n\t\tSpecifies that the HTML sources are unstructured (plain web pages).\n\t\tA page break is inserted between each file or URL in the output.' - print - print '\tfff\n\t\tHeading format string; each \'f\' can be one of:' - print - print '\t\t\t. = blank' - print '\t\t\t/ = n/N arabic page numbers (1/3, 2/3, 3/3)' - print '\t\t\t: = c/C arabic chapter page numbers (1/2, 2/2, 1/4, 2/4, ...)' - print '\t\t\t1 = arabic numbers (1, 2, 3, ...)' - print '\t\t\ta = lowercase letters' - print '\t\t\tA = uppercase letters' - print '\t\t\tc = current chapter heading' - print '\t\t\tC = current chapter page number (arabic)' - print '\t\t\td = current date' - print '\t\t\tD = current date and time' - print '\t\t\th = current heading' - print '\t\t\ti = lowercase roman numerals' - print '\t\t\tI = uppercase roman numerals' - print '\t\t\tl = logo image' - print '\t\t\tt = title text' - print '\t\t\tT = current time' - print - print '### See also: http://www.karakas-online.de/forum/viewtopic.php?t=10275' + print('\t--duplex\n\t\tSpecifies that the output should be formatted for double-sided printing.') + print('\t--effectduration {0.1..10.0}\n\t\tSpecifies the duration in seconds of PDF page transition effects.') + print('\t--embedfonts\n\t\tSpecifies that fonts should be embedded in PDF output.') + print('\t--encryption\n\t\tEnables encryption of PDF files.') + print('\t--extract-only\n\t\tExtract the HTML files from the CHM file and stop.\n\t\tThe extracted files will be found in CHM2PDF_WORK_DIR/input_filename_without_extension.') + print('\t--firstpage {p1,toc,c1}\n\t\t') + print('\t--fontsize {4.0..24.0}\n\t\tSpecifies the default font size for body text.') + print('\t--fontspacing {1.0..3.0}\n\t\tSpecifies the default line spacing for body text.\n\t\tThe line spacing is a multiplier for the font size, so a value of 1.2 \n\t\twill provide an additional 20% of space between the lines.') + print('\t--footer fff\n\t\t') + print('\t{--format, -t} {pdf11,pdf12,pdf13,pdf14}\n\t\tSpecifies the output format: pdf11\n\t\tpdf11 (PDF 1.1/Acrobat 2.0), pdf12 (PDF 1.2/Acrobat 3.0), \n\t\tpdf or pdf13 (PDF 1.3/Acrobat 4.0), or pdf14 (PDF 1.4/Acrobat 5.0)') + print('\t--gray\n\t\t') + print('\t--header fff\n\t\t') + print('\t--header1 fff\n\t\t') + print('\t--headfootfont {courier{-bold,-oblique,-boldoblique}, \n\t\thelvetica{-bold,-oblique,-boldoblique}, \n\t\tmonospace{-bold,-oblique,-boldoblique}, \n\t\tsans{-bold,-oblique,-boldoblique}, \n\t\tserif{-bold,-italic,-bolditalic}, \n\t\ttimes{-roman,-bold,-italic,-bolditalic}} \n\t\t\tSets the font to use on headers and footers.') + print('\t--headfootsize {6.0..24.0}\n\t\tSets the size of the font to use on headers and footers.') + print('\t--headingfont {courier,helvetica,monospace,sans,serif,times}\n\t\tSets the typeface to use for headings.') + print('\t--help\n\t\tDisplays a summary of command-line options.') + print('\t--hfimage0 filename.{bmp,gif,jpg,png}\n\t\t ') + print('\t--hfimage1 filename.{bmp,gif,jpg,png}\n\t\t ') + print('\t--hfimage2 filename.{bmp,gif,jpg,png}\n\t\t ') + print('\t--hfimage3 filename.{bmp,gif,jpg,png}\n\t\t ') + print('\t--hfimage4 filename.{bmp,gif,jpg,png}\n\t\t ') + print('\t--hfimage5 filename.{bmp,gif,jpg,png}\n\t\t ') + print('\t--hfimage6 filename.{bmp,gif,jpg,png}\n\t\t ') + print('\t--hfimage7 filename.{bmp,gif,jpg,png}\n\t\t ') + print('\t--hfimage8 filename.{bmp,gif,jpg,png}\n\t\t ') + print('\t--hfimage9 filename.{bmp,gif,jpg,png}\n\t\t ') + print('\t--jpeg quality\n\t\tSets the JPEG compression level to use for large images. A value of 0 disables JPEG compression.') + print('\t--landscape\n\t\t') + print('\t--left margin{in,cm,mm}\n\t\tSpecifies the left margin in points (no suffix or ##pt), inches (##in), centimeters (##cm), or millimeters (##mm).') + print('\t--linkcolor color\n\t\tSets the color of links. You can use well-known color names like blue, or the usual #RRGGBB notation.') + print('\t--links\n\t\tEnables generation of links in PDF files (default).') + print('\t--linkstyle {plain,underline}\n\t\tSets the style of links.') + print('\t--logoimage filename.{bmp,gif,jpg,png}\n\t\tSpecifies an image to be used as a logo in the header or footer in a PDF document.') + print('\t--logoimage filename.{bmp,gif,jpg,png}\n\t\tNote that you need to use the --header and/or --footer options with the l parameter.') + print('\t--no-compression\n\t\tDisables compression of PDF file.') + print('\t--no-duplex\n\t\tDisables double-sided printing.') + print('\t--no-embedfonts\n\t\tSpecifies that fonts should not be embedded in PDF and PostScript output.') + print('\t--no-encryption\n\t\tDisables document encryption.') + print('\t--no-links\n\t\tDisables generation of links in a PDF document. ') + print('\t--no-localfiles\n\t\t') + print('\t--no-numbered\n\t\tDisables automatic heading numbering.') + print('\t--no-overflow\n\t\t') + print('\t--no-strict\n\t\tDisables strict HTML input checking.') + print('\t--no-title\n\t\tDisables generation of a title page.') + print('\t--no-toc\n\t\tDisables generation of a table of contents.') + print('\t--numbered\n\t\tNumbers all headings in a document.') + print('\t--nup {1,2,4,6,9,16}\n\t\tSets the number of pages that are placed on each output page. Valid values are 1, 2, 4, 6, 9, and 16.') + print('\t{--outfile, -f} filename{.pdf}\n\t\tSpecifies the name of the output file. If no ending is given, ".pdf" is used.') + print('\t--overflow\n\t\t') + print('\t--owner-password password\n\t\tSets the owner password for encrypted PDF files.') + print('\t--pageduration {1.0..60.0}\n\t\tSets the view duration of a page in a PDF document.') + print('\t--pageeffect {none,bi,bo,d,gd,gdr,gr,hb,hsi,hso,vb,vsi,vso,wd,wl,wr,wu}\n\t\tSpecifies the page transition effect for all pages; this attribute is ignored by all Adobe PDF viewers.. ') + print('\t--pagelayout {single,one,twoleft,tworight}\n\t\tSpecifies the initial layout of pages for a PDF file.') + print('\t--pagemode {document,outline,fullscreen}\n\t\tSpecifies the initial viewing mode for a PDF file.') + print('\t--path "dir1;dir2;dir3;...;dirN"\n\t\tSpecifies a search path for files in a document.') + print('\t--permissions {all,annotate,copy,modify,print,no-annotate,no-copy,no-modify,no-print,none}\n\t\tSpecifies document permissions for encrypted PDF files. Separate multiple permissions with commas. ') + print('\t--portrait\n\t\t') + print('\t--prefontsize {4.0..24.0, small, normal, big, huge, +1, +2, -1, -2,...whatever}\n\t\tSpecifies the font size for text inside <pre> tags. Whatever you pass here will be used as font size inside preformatted pieces of text (usually code snippets, console output, program messages...). Effective only together with the \'--beautifulsoup\' option.') + print('\t--quiet\n\t\tSuppresses all messages, even error messages.') + print('\t--right margin{in,cm,mm}\n\t\tSpecifies the right margin in points (no suffix or ##pt), inches (##in), centimeters (##cm), or millimeters (##mm).') + print('\t--size {letter,a4,WxH{in,cm,mm},etc}\n\t\tSpecifies the page size using a standard name or in points (no suffix or ##x##pt), inches (##x##in),\n\t\tcentimeters (##x##cm), or millimeters (##x##mm). The standard sizes that are currently recognized\n\t\tare "letter" (8.5x11in), "legal" (8.5x14in), "a4" (210x297mm), and "universal" (8.27x11in).') + print('\t--strict\n\t\tEnables strict HTML input checking.') + print('\t--textcolor color\n\t\tSpecifies the default color of all text.') + print('\t--textfont {courier,helvetica,monospace,sans,serif,times}\n\t\t') + print('\t--title\n\t\tEnables the generation of a title page.') + print('\t--titlefile filename.{htm,html,shtml}\n\t\tSpecifies the file to use for the title page. If the file is an image then the title page\n\t\tis automatically generated using the document meta data and image title.') + print('\t--titleimage filename.{bmp,gif,jpg,png}\n\t\tSpecifies the image to use for the title page. The title page is automatically \n\t\tgenerated using the document meta data and title image.') + print('\t--tocfooter fff\n\t\tSets the page footer to use on table-of-contents pages. See below for the format of fff.') + print('\t--tocheader fff\n\t\tSets the page header to use on table-of-contents pages. See below for the format of fff.') + print('\t--toclevels levels\n\t\tSets the number of levels in the table-of-contents.') + print('\t--toctitle string\n\t\tSets the title for the table-of-contents.') + print('\t--top margin{in,cm,mm}\n\t\tSpecifies the top margin in points (no suffix or ##pt), inches (##in), centimeters (##cm), or millimeters (##mm).') + print('\t--user-password password\n\t\tSpecifies the user password for encryption of PDF files.') + print('\t--verbose\n\t\tDisplays various messages indicating the progress of the conversion process. The verbosity depends on --verbositylevel. If --verbose is not set, almost no messages will be printed. The default is \'not set\', so if you want the minimum amount of messages, just don\' use this option.') + print('\t--verbositylevel\n\t\tSpecifies the verbosity level of the messages. Can be either \'low\' or \'high\'. Default is low. The --verbose option must be set, otherwise this option will have no effect.') + print('\t--version\n\t\tDisplays the current version number.') + print('\t--webpage\n\t\tSpecifies that the HTML sources are unstructured (plain web pages).\n\t\tA page break is inserted between each file or URL in the output.') + print() + print('\tfff\n\t\tHeading format string; each \'f\' can be one of:') + print() + print('\t\t\t. = blank') + print('\t\t\t/ = n/N arabic page numbers (1/3, 2/3, 3/3)') + print('\t\t\t: = c/C arabic chapter page numbers (1/2, 2/2, 1/4, 2/4, ...)') + print('\t\t\t1 = arabic numbers (1, 2, 3, ...)') + print('\t\t\ta = lowercase letters') + print('\t\t\tA = uppercase letters') + print('\t\t\tc = current chapter heading') + print('\t\t\tC = current chapter page number (arabic)') + print('\t\t\td = current date') + print('\t\t\tD = current date and time') + print('\t\t\th = current heading') + print('\t\t\ti = lowercase roman numerals') + print('\t\t\tI = uppercase roman numerals') + print('\t\t\tl = logo image') + print('\t\t\tt = title text') + print('\t\t\tT = current time') + print() + print('### See also: http://www.karakas-online.de/forum/viewtopic.php?t=10275') def split(path): if path[-1] == os.sep : @@ -1015,9 +1015,9 @@ def main(argv): elif o in ('-v', '--verbose'): options['verbose'] = '--verbose' elif o == '--verbositylevel': options['verbositylevel'] = a elif o == '--version': - print sys.argv[0] + ' version ' + version - print 'This is free software; see the source for copying conditions. There is NO' - print 'warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.' + print(sys.argv[0] + ' version ' + version) + print('This is free software; see the source for copying conditions. There is NO') + print('warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.') return elif o == '--webpage': options['webpage'] = '--webpage' @@ -1026,10 +1026,10 @@ def main(argv): # Only one of '--extract-only' and '--dontextract' may be given! if options['dontextract'] == '--dontextract' and options['extract-only'] == '--extract-only': usage(sys.argv[0]) - print - print '### Either \'--dontextract\' or \'extract-only\' may be given!' - print '### Only one of the two options can be present, not both!' - print '### See above or try \'' + sys.argv[0] + ' --help | less\' to view the help contents in less.' + print() + print('### Either \'--dontextract\' or \'extract-only\' may be given!') + print('### Only one of the two options can be present, not both!') + print('### See above or try \'' + sys.argv[0] + ' --help | less\' to view the help contents in less.') return # # One of '--book' or '--webpage' MUST be given! @@ -1038,10 +1038,10 @@ def main(argv): (options['book'] == '--book' and options['continuous'] == '--continuous') or (options['webpage'] == '--webpage' and options['continuous'] == '--continuous')): usage(sys.argv[0]) - print - print '### Either \'--book\' or \'--webpage\' or \'--continuous\' MUST be given!' - print '### Only one of the three options can be present, not two, or even all three of them!' - print '### See above or try \'' + sys.argv[0] + ' --help | less\' to view the help contents in less.' + print() + print('### Either \'--book\' or \'--webpage\' or \'--continuous\' MUST be given!') + print('### Only one of the three options can be present, not two, or even all three of them!') + print('### See above or try \'' + sys.argv[0] + ' --help | less\' to view the help contents in less.') return if len(args)==0: @@ -1069,11 +1069,11 @@ def main(argv): CHM2PDF_ORIG_DIR = CHM2PDF_TEMP_ORIG_DIR + os.sep + basename if options['verbose']=='--verbose' and options['verbositylevel']=='low': - print 'CHM2PDF_WORK_DIR = ' + CHM2PDF_WORK_DIR - print 'CHM2PDF_ORIG_DIR = ' + CHM2PDF_ORIG_DIR + print('CHM2PDF_WORK_DIR = ' + CHM2PDF_WORK_DIR) + print('CHM2PDF_ORIG_DIR = ' + CHM2PDF_ORIG_DIR) if not os.path.exists(filename): - print 'CHM file "' + filename + '" not found!' + print('CHM file "' + filename + '" not found!') return cfile = chm.CHMFile() @@ -1081,8 +1081,8 @@ def main(argv): if options['dontextract'] == '--dontextract': if options['verbose'] == '--verbose': - print '\'--dontextract\' option was given. No files will be extracted from CHM.' - print 'Will use the files in ' + CHM2PDF_ORIG_DIR + ' and ' + CHM2PDF_WORK_DIR + '.' + print('\'--dontextract\' option was given. No files will be extracted from CHM.') + print('Will use the files in ' + CHM2PDF_ORIG_DIR + ' and ' + CHM2PDF_WORK_DIR + '.') else: if options['verbose'] == '--verbose' and options['verbositylevel'] == 'high': os.system('extract_chmLib ' + filename + ' ' + CHM2PDF_ORIG_DIR)
