├── requirements.txt ├── PKG-INFO ├── .gitignore ├── setup.py ├── README.md ├── README ├── LICENSE └── chm2pdf /requirements.txt: -------------------------------------------------------------------------------- 1 | pychm 2 | sgmllib3k 3 | -------------------------------------------------------------------------------- /PKG-INFO: -------------------------------------------------------------------------------- 1 | Metadata-Version: 1.0 2 | Name: chm2pdf 3 | Version: 0.9.1 4 | Summary: A script to convert CHM files into PDF 5 | Home-page: http://code.google.com/p/chm2pdf/ 6 | Author: Massimo Sandal, Chris Karakas 7 | Author-email: devicerandom@gmail.com, chris@karakas-online.de 8 | License: GPL v.2. 9 | Description: A script to convert CHM files into PDF. Requires chmlib, pychm, htmldoc. 10 | Platform: UNKNOWN 11 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | *.py[cod] 2 | 3 | # C extensions 4 | *.so 5 | 6 | # Packages 7 | *.egg 8 | *.egg-info 9 | dist 10 | build 11 | eggs 12 | parts 13 | bin 14 | var 15 | sdist 16 | develop-eggs 17 | .installed.cfg 18 | lib 19 | lib64 20 | __pycache__ 21 | 22 | # Installer logs 23 | pip-log.txt 24 | 25 | # Unit test / coverage reports 26 | .coverage 27 | .tox 28 | nosetests.xml 29 | 30 | # Translations 31 | *.mo 32 | 33 | # Mr Developer 34 | .mr.developer.cfg 35 | .project 36 | .pydevproject 37 | -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | 3 | from distutils.core import setup 4 | 5 | setup(name = "chm2pdf", 6 | version = "0.9", 7 | description = "A script to convert CHM files into PDF", 8 | author = "Massimo Sandal, Chris Karakas, Suleyman Poyraz", 9 | author_email = "devicerandom@gmail.com, chris@karakas-online.de", 10 | url = "http://code.google.com/p/chm2pdf/", 11 | scripts = ["chm2pdf"], 12 | long_description = "A script to convert CHM files into PDF. Requires chmlib, pychm, htmldoc." 13 | ) 14 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | chm2pdf 2 | ======= 3 | A Python script that converts a CHM file into a single PDF file. 4 | 5 | (c) 2007 Massimo Sandal 6 | 7 | (c) 2007-2008 Chris Karakas and 8 | 9 | Usage: 10 | `chm2pdf [options] input_filename [output_filename]` 11 | 12 | For all options, see 13 | `chm2pdf --help` 14 | 15 | RECOMMENDED READING: 16 | - http://www.karakas-online.de/forum/viewtopic.php?t=10275 17 | - http://www.karakas-online.de/forum/viewtopic.php?t=10969 18 | 19 | Installation: 20 | - download the .tar.gz 21 | - unzip it: "tar -xzvf chm2pdf-a.b.c.tar.gz" 22 | - enter the newly created directory 23 | - acquire root privileges 24 | - type "python setup.py install" 25 | 26 | Requires: 27 | - python 28 | - chmlib. NOTE: chmlib *must* be configured with ./configure --enable-examples 29 | - pychm 30 | - htmldoc 31 | - BeautifulSoup (optional) 32 | 33 | All of these should be in your Linux/Unix distribution repository :) 34 | -------------------------------------------------------------------------------- /README: -------------------------------------------------------------------------------- 1 | CHM2PDF 2 | 3 | (c) 2007 Massimo Sandal 4 | (c) 2007-2008 Chris Karakas 5 | (c) 2020 Suleyman Poyraz 6 | 7 | A Python script that converts a CHM file into a single PDF file. 8 | 9 | Usage: 10 | chm2pdf [options] input_filename [output_filename] 11 | 12 | See 13 | 14 | chm2pdf --help 15 | 16 | for all options. 17 | 18 | RECOMMENDED READING: 19 | - http://www.karakas-online.de/forum/viewtopic.php?t=10275 20 | - http://www.karakas-online.de/forum/viewtopic.php?t=10969 21 | 22 | 23 | Installation: 24 | - download the .tar.gz 25 | - unzip it: "tar -xzvf chm2pdf-a.b.c.tar.gz" 26 | - enter the newly created directory 27 | - acquire root privileges 28 | - type "python setup.py install" 29 | 30 | Requires: 31 | - python 32 | - chmlib 33 | NOTE: chmlib *must* be configured with ./configure --enable-examples 34 | - pychm 35 | - htmldoc 36 | 37 | Optional: 38 | - BeautifulSoup 39 | 40 | All of these should be in your Linux/Unix distribution repository :) 41 | 42 | To contact Massimo: devicerandom@gmail.com 43 | To contact Chris: chris@karakas-online.de 44 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | GNU GENERAL PUBLIC LICENSE 2 | Version 2, June 1991 3 | 4 | Copyright (C) 1989, 1991 Free Software Foundation, Inc., 5 | 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA 6 | Everyone is permitted to copy and distribute verbatim copies 7 | of this license document, but changing it is not allowed. 8 | 9 | Preamble 10 | 11 | The licenses for most software are designed to take away your 12 | freedom to share and change it. By contrast, the GNU General Public 13 | License is intended to guarantee your freedom to share and change free 14 | software--to make sure the software is free for all its users. This 15 | General Public License applies to most of the Free Software 16 | Foundation's software and to any other program whose authors commit to 17 | using it. (Some other Free Software Foundation software is covered by 18 | the GNU Lesser General Public License instead.) You can apply it to 19 | your programs, too. 20 | 21 | When we speak of free software, we are referring to freedom, not 22 | price. Our General Public Licenses are designed to make sure that you 23 | have the freedom to distribute copies of free software (and charge for 24 | this service if you wish), that you receive source code or can get it 25 | if you want it, that you can change the software or use pieces of it 26 | in new free programs; and that you know you can do these things. 27 | 28 | To protect your rights, we need to make restrictions that forbid 29 | anyone to deny you these rights or to ask you to surrender the rights. 30 | These restrictions translate to certain responsibilities for you if you 31 | distribute copies of the software, or if you modify it. 32 | 33 | For example, if you distribute copies of such a program, whether 34 | gratis or for a fee, you must give the recipients all the rights that 35 | you have. You must make sure that they, too, receive or can get the 36 | source code. And you must show them these terms so they know their 37 | rights. 38 | 39 | We protect your rights with two steps: (1) copyright the software, and 40 | (2) offer you this license which gives you legal permission to copy, 41 | distribute and/or modify the software. 42 | 43 | Also, for each author's protection and ours, we want to make certain 44 | that everyone understands that there is no warranty for this free 45 | software. If the software is modified by someone else and passed on, we 46 | want its recipients to know that what they have is not the original, so 47 | that any problems introduced by others will not reflect on the original 48 | authors' reputations. 49 | 50 | Finally, any free program is threatened constantly by software 51 | patents. We wish to avoid the danger that redistributors of a free 52 | program will individually obtain patent licenses, in effect making the 53 | program proprietary. To prevent this, we have made it clear that any 54 | patent must be licensed for everyone's free use or not licensed at all. 55 | 56 | The precise terms and conditions for copying, distribution and 57 | modification follow. 58 | 59 | GNU GENERAL PUBLIC LICENSE 60 | TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION 61 | 62 | 0. This License applies to any program or other work which contains 63 | a notice placed by the copyright holder saying it may be distributed 64 | under the terms of this General Public License. The "Program", below, 65 | refers to any such program or work, and a "work based on the Program" 66 | means either the Program or any derivative work under copyright law: 67 | that is to say, a work containing the Program or a portion of it, 68 | either verbatim or with modifications and/or translated into another 69 | language. (Hereinafter, translation is included without limitation in 70 | the term "modification".) Each licensee is addressed as "you". 71 | 72 | Activities other than copying, distribution and modification are not 73 | covered by this License; they are outside its scope. The act of 74 | running the Program is not restricted, and the output from the Program 75 | is covered only if its contents constitute a work based on the 76 | Program (independent of having been made by running the Program). 77 | Whether that is true depends on what the Program does. 78 | 79 | 1. You may copy and distribute verbatim copies of the Program's 80 | source code as you receive it, in any medium, provided that you 81 | conspicuously and appropriately publish on each copy an appropriate 82 | copyright notice and disclaimer of warranty; keep intact all the 83 | notices that refer to this License and to the absence of any warranty; 84 | and give any other recipients of the Program a copy of this License 85 | along with the Program. 86 | 87 | You may charge a fee for the physical act of transferring a copy, and 88 | you may at your option offer warranty protection in exchange for a fee. 89 | 90 | 2. You may modify your copy or copies of the Program or any portion 91 | of it, thus forming a work based on the Program, and copy and 92 | distribute such modifications or work under the terms of Section 1 93 | above, provided that you also meet all of these conditions: 94 | 95 | a) You must cause the modified files to carry prominent notices 96 | stating that you changed the files and the date of any change. 97 | 98 | b) You must cause any work that you distribute or publish, that in 99 | whole or in part contains or is derived from the Program or any 100 | part thereof, to be licensed as a whole at no charge to all third 101 | parties under the terms of this License. 102 | 103 | c) If the modified program normally reads commands interactively 104 | when run, you must cause it, when started running for such 105 | interactive use in the most ordinary way, to print or display an 106 | announcement including an appropriate copyright notice and a 107 | notice that there is no warranty (or else, saying that you provide 108 | a warranty) and that users may redistribute the program under 109 | these conditions, and telling the user how to view a copy of this 110 | License. (Exception: if the Program itself is interactive but 111 | does not normally print such an announcement, your work based on 112 | the Program is not required to print an announcement.) 113 | 114 | These requirements apply to the modified work as a whole. If 115 | identifiable sections of that work are not derived from the Program, 116 | and can be reasonably considered independent and separate works in 117 | themselves, then this License, and its terms, do not apply to those 118 | sections when you distribute them as separate works. But when you 119 | distribute the same sections as part of a whole which is a work based 120 | on the Program, the distribution of the whole must be on the terms of 121 | this License, whose permissions for other licensees extend to the 122 | entire whole, and thus to each and every part regardless of who wrote it. 123 | 124 | Thus, it is not the intent of this section to claim rights or contest 125 | your rights to work written entirely by you; rather, the intent is to 126 | exercise the right to control the distribution of derivative or 127 | collective works based on the Program. 128 | 129 | In addition, mere aggregation of another work not based on the Program 130 | with the Program (or with a work based on the Program) on a volume of 131 | a storage or distribution medium does not bring the other work under 132 | the scope of this License. 133 | 134 | 3. You may copy and distribute the Program (or a work based on it, 135 | under Section 2) in object code or executable form under the terms of 136 | Sections 1 and 2 above provided that you also do one of the following: 137 | 138 | a) Accompany it with the complete corresponding machine-readable 139 | source code, which must be distributed under the terms of Sections 140 | 1 and 2 above on a medium customarily used for software interchange; or, 141 | 142 | b) Accompany it with a written offer, valid for at least three 143 | years, to give any third party, for a charge no more than your 144 | cost of physically performing source distribution, a complete 145 | machine-readable copy of the corresponding source code, to be 146 | distributed under the terms of Sections 1 and 2 above on a medium 147 | customarily used for software interchange; or, 148 | 149 | c) Accompany it with the information you received as to the offer 150 | to distribute corresponding source code. (This alternative is 151 | allowed only for noncommercial distribution and only if you 152 | received the program in object code or executable form with such 153 | an offer, in accord with Subsection b above.) 154 | 155 | The source code for a work means the preferred form of the work for 156 | making modifications to it. For an executable work, complete source 157 | code means all the source code for all modules it contains, plus any 158 | associated interface definition files, plus the scripts used to 159 | control compilation and installation of the executable. However, as a 160 | special exception, the source code distributed need not include 161 | anything that is normally distributed (in either source or binary 162 | form) with the major components (compiler, kernel, and so on) of the 163 | operating system on which the executable runs, unless that component 164 | itself accompanies the executable. 165 | 166 | If distribution of executable or object code is made by offering 167 | access to copy from a designated place, then offering equivalent 168 | access to copy the source code from the same place counts as 169 | distribution of the source code, even though third parties are not 170 | compelled to copy the source along with the object code. 171 | 172 | 4. You may not copy, modify, sublicense, or distribute the Program 173 | except as expressly provided under this License. Any attempt 174 | otherwise to copy, modify, sublicense or distribute the Program is 175 | void, and will automatically terminate your rights under this License. 176 | However, parties who have received copies, or rights, from you under 177 | this License will not have their licenses terminated so long as such 178 | parties remain in full compliance. 179 | 180 | 5. You are not required to accept this License, since you have not 181 | signed it. However, nothing else grants you permission to modify or 182 | distribute the Program or its derivative works. These actions are 183 | prohibited by law if you do not accept this License. Therefore, by 184 | modifying or distributing the Program (or any work based on the 185 | Program), you indicate your acceptance of this License to do so, and 186 | all its terms and conditions for copying, distributing or modifying 187 | the Program or works based on it. 188 | 189 | 6. Each time you redistribute the Program (or any work based on the 190 | Program), the recipient automatically receives a license from the 191 | original licensor to copy, distribute or modify the Program subject to 192 | these terms and conditions. You may not impose any further 193 | restrictions on the recipients' exercise of the rights granted herein. 194 | You are not responsible for enforcing compliance by third parties to 195 | this License. 196 | 197 | 7. If, as a consequence of a court judgment or allegation of patent 198 | infringement or for any other reason (not limited to patent issues), 199 | conditions are imposed on you (whether by court order, agreement or 200 | otherwise) that contradict the conditions of this License, they do not 201 | excuse you from the conditions of this License. If you cannot 202 | distribute so as to satisfy simultaneously your obligations under this 203 | License and any other pertinent obligations, then as a consequence you 204 | may not distribute the Program at all. For example, if a patent 205 | license would not permit royalty-free redistribution of the Program by 206 | all those who receive copies directly or indirectly through you, then 207 | the only way you could satisfy both it and this License would be to 208 | refrain entirely from distribution of the Program. 209 | 210 | If any portion of this section is held invalid or unenforceable under 211 | any particular circumstance, the balance of the section is intended to 212 | apply and the section as a whole is intended to apply in other 213 | circumstances. 214 | 215 | It is not the purpose of this section to induce you to infringe any 216 | patents or other property right claims or to contest validity of any 217 | such claims; this section has the sole purpose of protecting the 218 | integrity of the free software distribution system, which is 219 | implemented by public license practices. Many people have made 220 | generous contributions to the wide range of software distributed 221 | through that system in reliance on consistent application of that 222 | system; it is up to the author/donor to decide if he or she is willing 223 | to distribute software through any other system and a licensee cannot 224 | impose that choice. 225 | 226 | This section is intended to make thoroughly clear what is believed to 227 | be a consequence of the rest of this License. 228 | 229 | 8. If the distribution and/or use of the Program is restricted in 230 | certain countries either by patents or by copyrighted interfaces, the 231 | original copyright holder who places the Program under this License 232 | may add an explicit geographical distribution limitation excluding 233 | those countries, so that distribution is permitted only in or among 234 | countries not thus excluded. In such case, this License incorporates 235 | the limitation as if written in the body of this License. 236 | 237 | 9. The Free Software Foundation may publish revised and/or new versions 238 | of the General Public License from time to time. Such new versions will 239 | be similar in spirit to the present version, but may differ in detail to 240 | address new problems or concerns. 241 | 242 | Each version is given a distinguishing version number. If the Program 243 | specifies a version number of this License which applies to it and "any 244 | later version", you have the option of following the terms and conditions 245 | either of that version or of any later version published by the Free 246 | Software Foundation. If the Program does not specify a version number of 247 | this License, you may choose any version ever published by the Free Software 248 | Foundation. 249 | 250 | 10. If you wish to incorporate parts of the Program into other free 251 | programs whose distribution conditions are different, write to the author 252 | to ask for permission. For software which is copyrighted by the Free 253 | Software Foundation, write to the Free Software Foundation; we sometimes 254 | make exceptions for this. Our decision will be guided by the two goals 255 | of preserving the free status of all derivatives of our free software and 256 | of promoting the sharing and reuse of software generally. 257 | 258 | NO WARRANTY 259 | 260 | 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY 261 | FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN 262 | OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES 263 | PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED 264 | OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF 265 | MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS 266 | TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE 267 | PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, 268 | REPAIR OR CORRECTION. 269 | 270 | 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 271 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR 272 | REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, 273 | INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING 274 | OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED 275 | TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY 276 | YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER 277 | PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE 278 | POSSIBILITY OF SUCH DAMAGES. 279 | 280 | END OF TERMS AND CONDITIONS 281 | 282 | How to Apply These Terms to Your New Programs 283 | 284 | If you develop a new program, and you want it to be of the greatest 285 | possible use to the public, the best way to achieve this is to make it 286 | free software which everyone can redistribute and change under these terms. 287 | 288 | To do so, attach the following notices to the program. It is safest 289 | to attach them to the start of each source file to most effectively 290 | convey the exclusion of warranty; and each file should have at least 291 | the "copyright" line and a pointer to where the full notice is found. 292 | 293 | {description} 294 | Copyright (C) {year} {fullname} 295 | 296 | This program is free software; you can redistribute it and/or modify 297 | it under the terms of the GNU General Public License as published by 298 | the Free Software Foundation; either version 2 of the License, or 299 | (at your option) any later version. 300 | 301 | This program is distributed in the hope that it will be useful, 302 | but WITHOUT ANY WARRANTY; without even the implied warranty of 303 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 304 | GNU General Public License for more details. 305 | 306 | You should have received a copy of the GNU General Public License along 307 | with this program; if not, write to the Free Software Foundation, Inc., 308 | 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. 309 | 310 | Also add information on how to contact you by electronic and paper mail. 311 | 312 | If the program is interactive, make it output a short notice like this 313 | when it starts in an interactive mode: 314 | 315 | Gnomovision version 69, Copyright (C) year name of author 316 | Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'. 317 | This is free software, and you are welcome to redistribute it 318 | under certain conditions; type `show c' for details. 319 | 320 | The hypothetical commands `show w' and `show c' should show the appropriate 321 | parts of the General Public License. Of course, the commands you use may 322 | be called something other than `show w' and `show c'; they could even be 323 | mouse-clicks or menu items--whatever suits your program. 324 | 325 | You should also get your employer (if you work as a programmer) or your 326 | school, if any, to sign a "copyright disclaimer" for the program, if 327 | necessary. Here is a sample; alter the names: 328 | 329 | Yoyodyne, Inc., hereby disclaims all copyright interest in the program 330 | `Gnomovision' (which makes passes at compilers) written by James Hacker. 331 | 332 | {signature of Ty Coon}, 1 April 1989 333 | Ty Coon, President of Vice 334 | 335 | This General Public License does not permit incorporating your program into 336 | proprietary programs. If your program is a subroutine library, you may 337 | consider it more useful to permit linking proprietary applications with the 338 | library. If this is what you want to do, use the GNU Lesser General 339 | Public License instead of this License. 340 | -------------------------------------------------------------------------------- /chm2pdf: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | ''' 3 | CHM2PDF v. 0.9.2 4 | http://code.google.com/p/chm2pdf 5 | 6 | A script that converts a CHM compiled HTML file into a single PDF file. 7 | (c) 2007 Massimo Sandal 8 | (c) 2007 Chris Karakas 9 | (c) 2020 Suleyman Poyraz 10 | 11 | This program is free software: you can redistribute it and/or modify 12 | 13 | it under the terms of the GNU General Public License as published by 14 | the Free Software Foundation, either version 2 of the License, or 15 | (at your option) any later version. 16 | 17 | This program is distributed in the hope that it will be useful, 18 | but WITHOUT ANY WARRANTY; without even the implied warranty of 19 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 20 | GNU General Public License for more details. 21 | 22 | You should have received a copy of the GNU General Public License 23 | along with this program. If not, see . 24 | ''' 25 | 26 | 27 | from __future__ import print_function # (at top of module) 28 | 29 | import chm.chm as chm 30 | import sys 31 | import sgmllib 32 | import os, os.path 33 | import re, glob 34 | import getopt 35 | # from BeautifulSoup import BeautifulSoup 36 | 37 | global version 38 | 39 | global CHM2PDF_TEMP_WORK_DIR #where conversions etc. take place 40 | global CHM2PDF_TEMP_ORIG_DIR #where the chm file is exploded 41 | global CHM2PDF_WORK_DIR 42 | global CHM2PDF_ORIG_DIR 43 | 44 | global filename #the input filename 45 | 46 | version = '0.9.2' 47 | CHM2PDF_TEMP_WORK_DIR='/tmp/chm2pdf/work' 48 | CHM2PDF_TEMP_ORIG_DIR='/tmp/chm2pdf/orig' 49 | 50 | # YOU DON'T NEED TO CHANGE ANYTHING BELOW THIS LINE! 51 | 52 | 53 | class PageLister(sgmllib.SGMLParser): 54 | ''' 55 | parser of the chm.chm GetTopicsTree() method that retrieves the URL of the HTML 56 | page embedded in the CHM file. 57 | ''' 58 | def reset(self): 59 | sgmllib.SGMLParser.reset(self) 60 | self.pages=[] 61 | 62 | def start_param(self,attrs): 63 | urlparam_flag=False 64 | for key,value in attrs: 65 | if key=='name' and value=='Local': 66 | urlparam_flag=True 67 | if urlparam_flag and key=='value': 68 | self.pages.append('/'+value) 69 | 70 | class ImageCatcher(sgmllib.SGMLParser): 71 | ''' 72 | finds image urls in the current html page, so to take them out from the chm file. 73 | ''' 74 | def reset(self): 75 | sgmllib.SGMLParser.reset(self) 76 | self.imgurls=[] 77 | 78 | def start_img(self,attrs): 79 | for key,value in attrs: 80 | if key=='src' or key=='SRC': 81 | # Avoid duplicates in the list of image URLs. 82 | if not self.imgurls.count(value): 83 | self.imgurls.append(value) 84 | 85 | class CssCatcher(sgmllib.SGMLParser): 86 | ''' 87 | finds CSS urls in the current html page, so to take them out from the chm file. 88 | ''' 89 | def reset(self): 90 | sgmllib.SGMLParser.reset(self) 91 | self.cssurls=[] 92 | 93 | def start_link(self,attrs): 94 | for key,value in attrs: 95 | if key=='href' or key=='HREF': 96 | # Avoid duplicates in the list of CSS URLs. 97 | if not self.cssurls.count(value): 98 | self.cssurls.append(value) 99 | 100 | def get_html_list(cfile): 101 | ''' 102 | retrieves the list of HTML files contained into the CHM file, **in order** (that's the important bit). 103 | (actually performed by the PageLister class) 104 | ''' 105 | if sys.version_info[0] == 2: 106 | topicstree=cfile.GetTopicsTree() 107 | else: 108 | topicstree=cfile.GetTopicsTree().decode("utf-8") 109 | #print(type(topicstree)) 110 | 111 | lister=PageLister() 112 | lister.feed(topicstree) 113 | #print 'lister pages',lister.pages 114 | return lister.pages 115 | 116 | def get_objective_urls_list(filename): 117 | ''' 118 | takes the list of files inside the chm archive, with the correct urls of each one. 119 | ''' 120 | 121 | os.system('enum_chmLib '+filename+' > '+CHM2PDF_WORK_DIR+'/urlslist.txt') 122 | if sys.version_info[0] == 2: 123 | flist=open(CHM2PDF_WORK_DIR+'/urlslist.txt','rU') 124 | else: 125 | flist=open(CHM2PDF_WORK_DIR+'/urlslist.txt','r', newline=None) 126 | 127 | urls_list=[] 128 | for line in flist.readlines()[3:]: 129 | #print 'line',line 130 | spline=line.split() 131 | urls_list.append(spline[5]) 132 | flist.close() 133 | # os.remove(CHM2PDF_WORK_DIR+'/urlslist.txt') 134 | 135 | return urls_list 136 | 137 | 138 | def correct_file(input_file, output_file, html_list, objective_urls, options): 139 | 140 | # Correct image links in file 141 | if sys.version_info[0] == 2: 142 | pf=open(input_file,'rU') 143 | else: 144 | pf=open(input_file,'r', newline=None) 145 | 146 | page=pf.read() 147 | pf.close() 148 | 149 | # Correct the HTML markup of the page, if the --beautifulsoup was passed. 150 | if options['beautifulsoup']=='--beautifulsoup': 151 | from BeautifulSoup import BeautifulSoup, Tag 152 | soup = BeautifulSoup(page) 153 | page = str(soup) 154 | 155 | image_catcher=ImageCatcher() 156 | image_catcher.feed(page) 157 | 158 | css_catcher=CssCatcher() 159 | css_catcher.feed(page) 160 | 161 | # We substitute the image URLs of input_file with the *actual* URLs on the CHM2PDF_ORIG_DIR directory 162 | for iurl in image_catcher.imgurls: 163 | # print 'iurl = ' + iurl 164 | 165 | img_filename = '' 166 | for item in objective_urls: 167 | if iurl in item: 168 | img_filename=CHM2PDF_ORIG_DIR+item 169 | if ';' in img_filename: #hack to get rid of mysterious ; in filenames and urls... 170 | img_filename=img_filename.split(';')[0] 171 | # substitute the new image filenames - but only if an img_filename was found! 172 | if img_filename: 173 | page=re.sub(iurl,img_filename,page) 174 | 175 | 176 | # We substitute the CSS URLs of input_file with the *actual* URLs on the CHM2PDF_ORIG_DIR directory 177 | for curl in css_catcher.cssurls: 178 | # print 'curl = ' + curl 179 | 180 | css_filename = '' 181 | for item in objective_urls: 182 | if curl in item: 183 | css_filename=CHM2PDF_ORIG_DIR+item 184 | if ';' in css_filename: #hack to get rid of mysterious ; in filenames and urls... 185 | css_filename=img_filename.split(';')[0] 186 | # substitute the new image filenames - but only if a css_filename was found! 187 | if css_filename: 188 | page=re.sub(curl,css_filename,page) 189 | 190 | # Fontsize hack: 191 | # Since htmldoc ignores the --fontsize option, we have to do something about it... 192 | # If --fontsize xxx was given on the command line, 193 | # insert and tags between

and

. 194 | # While doing so, use xxx as the value of the size attribute of the font tag. 195 | if options['fontsize']: 196 | # page=re.sub('(]*>)','\\1' + os.linesep + '' + os.linesep, page) 197 | # page=re.sub('(<\/p[^>]*>)', os.linesep + '' + os.linesep + '\\1' + os.linesep, page) 198 | 199 | # page=re.sub('(]*>)','\\1' + '',page) 200 | # page=re.sub('(<\/body[^>]*>)','' + '\\1',page) 201 | 202 | # page=re.sub('(]*>)','\\1' + os.linesep + '' + os.linesep, page) 203 | # page=re.sub('(<\/table[^>]*>)', os.linesep + '' + os.linesep + '\\1' + os.linesep, page) 204 | 205 | # page=re.sub('(]*>)','\\1' + ' ',page) 206 | page=re.sub('(]*>)','\\1' + '',page) 207 | page=re.sub('(<\/body[^>]*>)','' + '\\1',page) 208 | 209 | # Delete unwanted HTML elements. 210 | page=re.sub('
','', page) 211 | page=re.sub(']*><\/a>','' ,page) 212 | page=re.sub(']*><\/a>','', page) 213 | page=re.sub(']*><\/a>','', page) 214 | page=re.sub('"[^"]*previous\.gif"','""', page) 215 | page=re.sub('"[^"]*prev\.gif"','""', page) 216 | page=re.sub('"[^"]*next\.gif"','""', page) 217 | 218 | # Delete CSS markup (]*>','', page) 225 | 226 | # Change font size between 
 and
to the value given by the '--prefontsize' option. 227 | if options['prefontsize'] != '': 228 | page=re.sub('
','
', page)
 229 |         page=re.sub('<\/pre>','
', page)
 230 | 
 231 | 
 232 |     # Correct the HTML markup of the page, if the --beautifulsoup was passed.
 233 |     if options['beautifulsoup']=='--beautifulsoup':
 234 |         # from BeautifulSoup import BeautifulSoup
 235 |         soup = BeautifulSoup(page)
 236 |         # page = soup.prettify()
 237 | 
 238 |         # top_vevel_table = soup.table
 239 |         # top_vevel_table.extract()
 240 |         # top_vevel_table['width'] = options['browserwidth']
 241 | 
 242 | #         tables=soup.findAll('table')
 243 | #         for table in tables:
 244 | #             # table['cellpadding'] = '0.15in'
 245 | #             table['border'] = '1'
 246 | #             table['width'] = '95%'
 247 | #             # table['width'] = options['browserwidth']
 248 | 
 249 | #             trs=table.findAll('tr')
 250 | #             for tr in trs:
 251 | #                 tds=tr.findAll('td')
 252 | #                 for td in tds:
 253 | #                     # print td.find(text=True)
 254 | #                     # td['cellpadding'] = '0.15in'
 255 | #                     # td['nowrap'] = 'false'
 256 | #                     # if td.content != None:
 257 | #                     for tag in td.contents:
 258 | #                         if tag.__class__.__name__ == 'NavigableString' and (tag == "\n" or tag == ''):
 259 | #                             print 'The following is of class ' + tag.__class__.__name__ + ' and is empty: '
 260 | #                             print '-->' + tag + '<--'
 261 | #                             tag.extract
 262 | #                             # print td.content
 263 | #                             # td.string = re.sub('^[\n\t\r ]*$', '', td.string)
 264 | #                             # if td.string == '':
 265 | #                             #     td.extract()
 266 | 
 267 | #         pixelimgs=soup.findAll('img', {"width" : "1", "height" : "1"})
 268 | #         for pixelimg in pixelimgs:
 269 | #             pixelimg.extract()
 270 | 
 271 | #         divs=soup.findAll('div')
 272 | #         for div in divs:
 273 | #             if div.string == None or div.string == os.linesep:
 274 | #                 div.extract()
 275 | #             # else:
 276 | #             #     print '-->"' + div.string + '"'
 277 | 
 278 | 
 279 |         pres = soup.findAll('pre')
 280 |         line_regex = re.compile(r'^.*$', re.MULTILINE)
 281 |         for pre in pres:
 282 | 
 283 |             pre['width'] = '50'
 284 | 
 285 | #             font_tag = Tag(BeautifulSoup(), 'font')
 286 | #             font_tag['size'] = '-1'
 287 | #             pre.insert(0, font_tag)
 288 | 
 289 |             texts_with_linesep = pre.findAll(text=line_regex, recursive=True)
 290 |             for text in texts_with_linesep:
 291 |                 newtext=re.sub(os.linesep,'
',text.string)
 292 | #                 print "#########################################################################"
 293 | #                 print text
 294 | #                 print "#########################################################################"
 295 | #                 print
 296 | #                 print
 297 |                 text.replaceWith(newtext)
 298 | 
 299 | 
 300 |         # page = soup.prettify()
 301 |         page = str(soup)
 302 | 
 303 | 
 304 |     f=open(output_file,'w')
 305 |     f.write(page)
 306 |     f.close()
 307 | 
 308 | 
 309 | def convert_to_pdf(cfile, filename, outputfilename, options):
 310 |     '''
 311 |     Performs actual converting.
 312 |     '''
 313 | 
 314 |     # Extract the files from the CHM archive and correct them ONLY IF '--dontextract' was NOT given!
 315 |     # ########################### File extraction and correction: START ############################
 316 |     #
 317 |     if options['dontextract'] == '':
 318 | 
 319 |         try:
 320 |             os.mkdir(CHM2PDF_TEMP_WORK_DIR)
 321 |         except OSError: # The directory already exists.
 322 |             pass
 323 | 
 324 |         try:
 325 |             os.mkdir(CHM2PDF_TEMP_ORIG_DIR)
 326 |         except OSError: # The directory already exists.
 327 |             pass
 328 | 
 329 |         try:
 330 |             os.mkdir(CHM2PDF_ORIG_DIR)
 331 |         except OSError: # The directory already exists.
 332 |             pass
 333 | 
 334 |         try:
 335 |             os.mkdir(CHM2PDF_WORK_DIR)
 336 |         except OSError: # The directory already exists.
 337 |             pass
 338 | 
 339 |     # Compute filenames and lists. This is needed no matter if '--dontextract' was given or not!
 340 | 
 341 |     html_list=get_html_list(cfile)
 342 |     objective_urls=get_objective_urls_list(filename)
 343 | 
 344 |     # print 'objective_urls'
 345 |     # print '=============='
 346 |     # print objective_urls
 347 |     # print
 348 |     # print 'html_list'
 349 |     # print '========='
 350 |     # print html_list
 351 | 
 352 |     true_html_list=[] #Should mostly coincide with html_list, but...
 353 | 
 354 |     input_titlefile = ''
 355 |     output_titlefile = ''
 356 |     for html_file in html_list:
 357 |         for item in objective_urls:
 358 |             if html_file in item:
 359 |                 true_html_list.append(CHM2PDF_ORIG_DIR+item)
 360 |             if not options['titlefile']=='' and options['titlefile'] in item:
 361 |                 input_titlefile = CHM2PDF_ORIG_DIR+item
 362 |                 output_titlefile = CHM2PDF_WORK_DIR + os.sep + options['titlefile']
 363 | 
 364 |     if not options['titlefile']=='' and not output_titlefile:
 365 |         print('### WARNING: ' + options['titlefile'] + ' not found inside ' + filename + ' - possible spelling error.')
 366 |         print('### You can check it if you do  \'' + sys.argv[0] + ' --extract-only\',')
 367 |         print('### then have a look at the files in  ' + CHM2PDF_ORIG_DIR + '.')
 368 |         print('### Option \'--titlefile ' + options['titlefile'] + '\' ignored')
 369 |         options['titlefile'] = ''
 370 | 
 371 | 
 372 |     # Process toc file. This depends on the '--dontextract' option.
 373 | 
 374 |     if options['dontextract'] == '':
 375 |         # Correct image links in toc file.
 376 |         if not options['titlefile']=='' and os.path.exists(input_titlefile):
 377 |             correct_file(input_titlefile, output_titlefile, html_list, objective_urls, options)
 378 | 
 379 | 
 380 |     # Now process the rest of HTML files.
 381 | 
 382 |     # Compute some lists. Again, this is independent of the '--dontextract' option.
 383 | 
 384 |     c=0
 385 |     htmlout_filename_list=''
 386 |     htmlout_filenames = []
 387 |     if output_titlefile:
 388 |         htmlout_filenames.append(output_titlefile)
 389 |     match_strings = []
 390 |     replace_strings = []
 391 |     replace_garbled_strings = []
 392 |     for url in html_list:
 393 |         c+=1
 394 |         page_filename=CHM2PDF_ORIG_DIR + url
 395 |         # Some names contain a '%20' (an HTML code for a space). We substitute with a "real space"
 396 |         # otherwise a 'File not found' error will occur.
 397 |         page_filename = re.sub('%20',' ',page_filename)
 398 | 
 399 |         if options['verbose']=='--verbose' and options['verbositylevel']=='high' and options['dontextract'] == '':
 400 |             print("Correcting " + page_filename)
 401 | 
 402 | 
 403 |         if os.path.exists(page_filename) and (options['titlefile'] == '' or not options['titlefile'] in url):
 404 |             htmlout_filename=CHM2PDF_WORK_DIR+'/temp'+'%(#)04d' %{"#":c}+'.html'
 405 |             htmlout_filename_list+=' '+ htmlout_filename
 406 |             htmlout_filenames.append(htmlout_filename)
 407 | 
 408 |             if options['dontextract'] == '':
 409 |                 # Correct image links in file page_filename.
 410 |                 correct_file(page_filename, htmlout_filename, html_list, objective_urls, options)
 411 | 
 412 |             # Escape slashes in url.
 413 |             url_filename_escaped = re.sub('/', '\/', os.path.basename(url))
 414 |             # Escape dots in url.
 415 |             url_filename_escaped = re.sub('\.', '\.', url_filename_escaped)
 416 |             # Escape slashes in htmlout_filename.
 417 |             htmlout_filename_escaped = re.sub('/', '\/', os.path.basename(htmlout_filename))
 418 |             # Compute a "garbled" htmlout_filename, where dots are simply replaced with underscores.
 419 |             htmlout_filename_escaped_garbled = re.sub('\.', '_', htmlout_filename_escaped)
 420 | 
 421 |             # Build a list for each of the three strings (the original URL, the output filename and the garbled one).
 422 |             # The idea is that we want to replace the match_strings with the corresponding replace_garbled_strings first.
 423 |             # Then, in a second pass, we will replace the garbled strings with the "real" replace_strings.
 424 |             # This trick is necessary to avoid problems in cases where the original URLs look like
 425 |             #
 426 |             # 0001.html, 0002.html, 0003.html...
 427 |             #
 428 |             # and we want to replace as follows:
 429 |             #
 430 |             # toc.html	-> temp0001.html
 431 |             # 0001.html	-> temp0002.html
 432 |             # 0002.html -> temp0003.html
 433 |             # 0003.html -> temp0004.html
 434 |             #
 435 |             # If we try it "directly", i.e. without the "garbled" names first, we will end up changing:
 436 |             #
 437 |             # tol.html	-> temp0001.html -> temptemp0002.html -> temptemptemp0003.html ...
 438 |             # 0001.html	-> temp0002.html -> temptemp0003.html -> temptemptemp0004.html ...
 439 |             # ...
 440 |             #
 441 |             # which is not what we want.
 442 |             match_strings.append(url_filename_escaped)
 443 |             replace_strings.append(htmlout_filename_escaped)
 444 |             replace_garbled_strings.append(htmlout_filename_escaped_garbled)
 445 | 
 446 |     # Now we've got the lists computed. We proceed with the actual correction,
 447 |     # which IS dependent on the '--dontextract' option:
 448 | 
 449 |     if options['dontextract'] == '':
 450 |         # Correct links to files in the local collection.
 451 |         if options['verbose']=='--verbose' and options['verbositylevel']=='low':
 452 |             print('Correcting links in the HTML files...')
 453 | 
 454 |         if options['verbose']=='--verbose' and options['verbositylevel']=='high':
 455 |             print('############### 1st pass ###############')
 456 |         for match_string in  match_strings:
 457 |             replace_string = replace_garbled_strings[match_strings.index(match_string)]
 458 |             if options['verbose']=='--verbose' and options['verbositylevel']=='high':
 459 |                 print("match " + match_string + ' ' + "and replace it with " + replace_string)
 460 |         if options['verbose']=='--verbose' and options['verbositylevel']=='high':
 461 |             print()
 462 | 
 463 |         if options['verbose']=='--verbose' and options['verbositylevel']=='high':
 464 |             print('############### 2nd pass ###############')
 465 |         for match_string in  replace_garbled_strings:
 466 |             replace_string = replace_strings[replace_garbled_strings.index(match_string)]
 467 |             if options['verbose']=='--verbose' and options['verbositylevel']=='high':
 468 |                 print("match " + match_string + ' ' + "and replace it with " + replace_string)
 469 |         if options['verbose']=='--verbose' and options['verbositylevel']=='high':
 470 |             print()
 471 | 
 472 |         for filename in htmlout_filenames:
 473 | 
 474 |             if sys.version_info[0] == 2:
 475 |                 pf=open(filename,'rU')
 476 |             else:
 477 |                 pf=open(filename, 'r', newline=None)
 478 | 
 479 |             page=pf.read()
 480 |             pf.close()
 481 | 
 482 |             # Substitutions in 1st pass: we replace the original filenames with their corresponding "garbled" equivalents.
 483 |             for match_string in  match_strings:
 484 |                 replace_string = replace_garbled_strings[match_strings.index(match_string)]
 485 |                 page = re.sub(match_string, replace_string, page)
 486 | 
 487 | 
 488 |             # Substitutuions in the 2nd pass: we replace the garbled filenames with the correct ones.
 489 |             for match_string in  replace_garbled_strings:
 490 |                 replace_string = replace_strings[replace_garbled_strings.index(match_string)]
 491 |                 page = re.sub(match_string, replace_string, page)
 492 | 
 493 |             # Replace links of the form "somefile.html#894" with "somefile0206.html"
 494 |             # The following will match anchors like ' /dev/null")
 614 |     exit_value=os.system ('htmldoc' + htmldoc_opts + ' ' + htmlout_filename_list + " -f "+ outputfilename + " > /dev/null")
 615 | 
 616 |     if exit_value != 0:
 617 |         print('Something wrong happened when launching htmldoc.')
 618 |         print('exit value: ',exit_value)
 619 |         print('Check if output exists or if it is good.')
 620 |     else:
 621 |         print('Written file ' + outputfilename)
 622 |     print('Done.')
 623 | 
 624 | def usage (name):
 625 |     print('Usage:')
 626 |     print("\t%s [options] input_filename [output_filename]" % name)
 627 |     print()
 628 |     print('Options:')
 629 |     print()
 630 |     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.')
 631 |     print('\t--bodycolor color\n\t\tSpecifies the background color for all pages.')
 632 |     print('\t--bodyfont {courier,helvetica,monospace,sans,serif,times}. Default is times.')
 633 |     print('\t--bodyimage filename.{bmp,gif,jpg,png}')
 634 |     print('\t--book\n\t\tSpecifies that the HTML sources are structured (headings, chapters, etc.).')
 635 |     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).')
 636 |     print('\t--browserwidth pixels\n\t\tSee http://www.htmldoc.org/newsgroups.php?ghtmldoc.general+v:3465')
 637 |     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.')
 638 |     print('\t--color\n\t\tSpecifies that PDF output should be in color.')
 639 |     print('\t--compression[=level]\n\t\t')
 640 |     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.')
 641 |     print('\t--cookies \'name="value with space"; name=value\'\n\t\t')
 642 |     print('\t--datadir directory\n\t\tSpecifies the  location  of  the  HTMLDOC  data  files,  usually  /usr/share/htmldoc  or  C:\Program Files\HTMLDOC ')
 643 |     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.')
 644 |     print('\t--duplex\n\t\tSpecifies that the output should be formatted for double-sided printing.')
 645 |     print('\t--effectduration {0.1..10.0}\n\t\tSpecifies the duration in seconds of PDF page transition effects.')
 646 |     print('\t--embedfonts\n\t\tSpecifies that fonts should be embedded in PDF output.')
 647 |     print('\t--encryption\n\t\tEnables encryption of PDF files.')
 648 |     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.')
 649 |     print('\t--firstpage {p1,toc,c1}\n\t\t')
 650 |     print('\t--fontsize {4.0..24.0}\n\t\tSpecifies the default font size for body text.')
 651 |     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.')
 652 |     print('\t--footer fff\n\t\t')
 653 |     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)')
 654 |     print('\t--gray\n\t\t')
 655 |     print('\t--header fff\n\t\t')
 656 |     print('\t--header1 fff\n\t\t')
 657 |     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.')
 658 |     print('\t--headfootsize {6.0..24.0}\n\t\tSets the size of the font to use on headers and footers.')
 659 |     print('\t--headingfont {courier,helvetica,monospace,sans,serif,times}\n\t\tSets the typeface to use for headings.')
 660 |     print('\t--help\n\t\tDisplays a summary of command-line options.')
 661 |     print('\t--hfimage0 filename.{bmp,gif,jpg,png}\n\t\t ')
 662 |     print('\t--hfimage1 filename.{bmp,gif,jpg,png}\n\t\t ')
 663 |     print('\t--hfimage2 filename.{bmp,gif,jpg,png}\n\t\t ')
 664 |     print('\t--hfimage3 filename.{bmp,gif,jpg,png}\n\t\t ')
 665 |     print('\t--hfimage4 filename.{bmp,gif,jpg,png}\n\t\t ')
 666 |     print('\t--hfimage5 filename.{bmp,gif,jpg,png}\n\t\t ')
 667 |     print('\t--hfimage6 filename.{bmp,gif,jpg,png}\n\t\t ')
 668 |     print('\t--hfimage7 filename.{bmp,gif,jpg,png}\n\t\t ')
 669 |     print('\t--hfimage8 filename.{bmp,gif,jpg,png}\n\t\t ')
 670 |     print('\t--hfimage9 filename.{bmp,gif,jpg,png}\n\t\t ')
 671 |     print('\t--jpeg quality\n\t\tSets the JPEG compression level to use for large images. A value of 0 disables JPEG compression.')
 672 |     print('\t--landscape\n\t\t')
 673 |     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).')
 674 |     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.')
 675 |     print('\t--links\n\t\tEnables generation of links in PDF files (default).')
 676 |     print('\t--linkstyle {plain,underline}\n\t\tSets the style of links.')
 677 |     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.')
 678 |     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.')
 679 |     print('\t--no-compression\n\t\tDisables compression of PDF file.')
 680 |     print('\t--no-duplex\n\t\tDisables double-sided printing.')
 681 |     print('\t--no-embedfonts\n\t\tSpecifies that fonts should not be embedded in PDF and PostScript output.')
 682 |     print('\t--no-encryption\n\t\tDisables document encryption.')
 683 |     print('\t--no-links\n\t\tDisables generation of links in a PDF document. ')
 684 |     print('\t--no-localfiles\n\t\t')
 685 |     print('\t--no-numbered\n\t\tDisables automatic heading numbering.')
 686 |     print('\t--no-overflow\n\t\t')
 687 |     print('\t--no-strict\n\t\tDisables strict HTML input checking.')
 688 |     print('\t--no-title\n\t\tDisables generation of a title page.')
 689 |     print('\t--no-toc\n\t\tDisables generation of a table of contents.')
 690 |     print('\t--numbered\n\t\tNumbers all headings in a document.')
 691 |     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.')
 692 |     print('\t{--outfile, -f} filename{.pdf}\n\t\tSpecifies the name of the output file. If no ending is given, ".pdf" is used.')
 693 |     print('\t--overflow\n\t\t')
 694 |     print('\t--owner-password password\n\t\tSets the owner password for encrypted PDF files.')
 695 |     print('\t--pageduration {1.0..60.0}\n\t\tSets the view duration of a page in a PDF document.')
 696 |     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.. ')
 697 |     print('\t--pagelayout {single,one,twoleft,tworight}\n\t\tSpecifies the initial layout of pages for a PDF file.')
 698 |     print('\t--pagemode {document,outline,fullscreen}\n\t\tSpecifies the initial viewing mode for a PDF file.')
 699 |     print('\t--path "dir1;dir2;dir3;...;dirN"\n\t\tSpecifies a search path for files in a document.')
 700 |     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. ')
 701 |     print('\t--portrait\n\t\t')
 702 |     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 
 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.')
 703 |     print('\t--quiet\n\t\tSuppresses all messages, even error messages.')
 704 |     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).')
 705 |     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).')
 706 |     print('\t--strict\n\t\tEnables strict HTML input checking.')
 707 |     print('\t--textcolor color\n\t\tSpecifies the default color of all text.')
 708 |     print('\t--textfont {courier,helvetica,monospace,sans,serif,times}\n\t\t')
 709 |     print('\t--title\n\t\tEnables the generation of a title page.')
 710 |     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.')
 711 |     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.')
 712 |     print('\t--tocfooter fff\n\t\tSets the page footer to use on table-of-contents pages. See below for the format of fff.')
 713 |     print('\t--tocheader fff\n\t\tSets the page header to use on table-of-contents pages. See below for the format of fff.')
 714 |     print('\t--toclevels levels\n\t\tSets the number of levels in the table-of-contents.')
 715 |     print('\t--toctitle string\n\t\tSets the title for the table-of-contents.')
 716 |     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).')
 717 |     print('\t--user-password password\n\t\tSpecifies the user password for encryption of PDF files.')
 718 |     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.')
 719 |     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.')
 720 |     print('\t--version\n\t\tDisplays the current version number.')
 721 |     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.')
 722 |     print()
 723 |     print('\tfff\n\t\tHeading format string; each \'f\' can be one of:')
 724 |     print()
 725 |     print('\t\t\t. = blank')
 726 |     print('\t\t\t/ = n/N arabic page numbers (1/3, 2/3, 3/3)')
 727 |     print('\t\t\t: = c/C arabic chapter page numbers (1/2, 2/2, 1/4, 2/4, ...)')
 728 |     print('\t\t\t1 = arabic numbers (1, 2, 3, ...)')
 729 |     print('\t\t\ta = lowercase letters')
 730 |     print('\t\t\tA = uppercase letters')
 731 |     print('\t\t\tc = current chapter heading')
 732 |     print('\t\t\tC = current chapter page number (arabic)')
 733 |     print('\t\t\td = current date')
 734 |     print('\t\t\tD = current date and time')
 735 |     print('\t\t\th = current heading')
 736 |     print('\t\t\ti = lowercase roman numerals')
 737 |     print('\t\t\tI = uppercase roman numerals')
 738 |     print('\t\t\tl = logo image')
 739 |     print('\t\t\tt = title text')
 740 |     print('\t\t\tT = current time')
 741 |     print()
 742 |     print('### See also: http://www.karakas-online.de/forum/viewtopic.php?t=10275')
 743 | 
 744 | def split(path):
 745 |     if path[-1] == os.sep :
 746 |         path, fname = path[:-1], ''
 747 |     else:
 748 |         path, fname = os.path.split( path )
 749 |         fname, ext = os.path.splitext( fname )
 750 |     return ( path, fname, ext[1:] )
 751 | 
 752 | 
 753 | 
 754 | def main(argv):
 755 | 
 756 |     global CHM2PDF_WORK_DIR
 757 |     global CHM2PDF_ORIG_DIR
 758 | 
 759 |     # Defaults
 760 |     options={}
 761 |     options['beautifulsoup'] = ''
 762 |     options['bodycolor'] = ''
 763 |     options['bodyfont'] = 'times'
 764 |     options['bodyimage'] = ''
 765 |     options['book'] = ''
 766 |     options['bottom'] = ''
 767 |     options['browserwidth'] = ''
 768 |     options['charset'] = ''
 769 |     options['color'] = ''
 770 |     options['compression'] = ''
 771 |     options['continuous'] = ''
 772 |     options['cookies'] = ''
 773 |     options['datadir'] = ''
 774 |     options['dontextract'] = ''
 775 |     options['duplex'] = '--duplex'
 776 |     options['effectduration'] = ''
 777 |     options['embedfonts'] = '--embedfonts'
 778 |     options['encryption'] = ''
 779 |     options['extract-only'] = ''
 780 |     options['firstpage'] = ''
 781 |     options['fontsize'] = ''
 782 |     options['fontspacing'] = ''
 783 |     options['footer'] = '\'c C\''
 784 |     options['format'] = '\'pdf14\''
 785 |     options['gray'] = ''
 786 |     options['header'] = '\'c C\''
 787 |     options['header1'] = ''
 788 |     options['headfootfont'] = ''
 789 |     options['headfootsize'] = ''
 790 |     options['headingfont'] = ''
 791 |     options['help'] = ''
 792 |     options['hfimage0'] = ''
 793 |     options['hfimage1'] = ''
 794 |     options['hfimage2'] = ''
 795 |     options['hfimage3'] = ''
 796 |     options['hfimage4'] = ''
 797 |     options['hfimage5'] = ''
 798 |     options['hfimage6'] = ''
 799 |     options['hfimage7'] = ''
 800 |     options['hfimage8'] = ''
 801 |     options['hfimage9'] = ''
 802 |     options['jpeg'] = '\'100\''
 803 |     options['landscape'] = ''
 804 |     options['left'] = ''
 805 |     options['linkcolor'] = '\'blue\''
 806 |     options['links'] = ''
 807 |     options['linkstyle'] = '\'plain\''
 808 |     options['logoimage'] = ''
 809 |     options['logoimage'] = ''
 810 |     options['no-compression'] = ''
 811 |     options['no-duplex'] = ''
 812 |     options['no-embedfonts'] = ''
 813 |     options['no-encryption'] = ''
 814 |     options['no-links'] = ''
 815 |     options['no-localfiles'] = ''
 816 |     options['no-numbered'] = ''
 817 |     options['no-overflow'] = ''
 818 |     options['no-strict'] = ''
 819 |     options['no-title'] = ''
 820 |     options['no-toc'] = ''
 821 |     options['numbered'] = ''
 822 |     options['nup'] = ''
 823 |     options['outfile'] = ''
 824 |     options['overflow'] = ''
 825 |     options['owner-password'] = ''
 826 |     options['pageduration'] = ''
 827 |     options['pageeffect'] = ''
 828 |     options['pagelayout'] = ''
 829 |     options['pagemode'] = ''
 830 |     options['path'] = ''
 831 |     options['permissions'] = ''
 832 |     options['portrait'] = ''
 833 |     options['prefontsize'] = ''
 834 |     options['quiet'] = ''
 835 |     options['right'] = ''
 836 |     options['size'] = '\'a4\''
 837 |     options['strict'] = ''
 838 |     options['textcolor'] = ''
 839 |     options['textfont'] = ''
 840 |     options['title'] = ''
 841 |     options['titlefile'] = ''
 842 |     options['titleimage'] = ''
 843 |     options['tocfooter'] = ''
 844 |     options['tocheader'] = ''
 845 |     options['toclevels'] = ''
 846 |     options['toctitle'] = ''
 847 |     options['top'] = ''
 848 |     options['user-password'] = ''
 849 |     options['verbose'] = ''
 850 |     options['verbositylevel'] = 'low'
 851 |     options['version'] = ''
 852 |     options['webpage'] = ''
 853 | 
 854 |     try:
 855 |         opts, args = getopt.getopt(sys.argv[1:], "f:t:v:",
 856 |                      [
 857 |                       "beautifulsoup",
 858 |                       "bodycolor=",
 859 |                       "bodyfont=",
 860 |                       "bodyimage=",
 861 |                       "book",
 862 |                       "bottom=",
 863 |                       "browserwidth=",
 864 |                       "charset=",
 865 |                       "color",
 866 |                       "compression=",
 867 |                       "continuous",
 868 |                       "cookies=",
 869 |                       "datadir=",
 870 |                       "dontextract",
 871 |                       "duplex",
 872 |                       "effectduration=",
 873 |                       "embedfonts",
 874 |                       "encryption",
 875 |                       "extract-only",
 876 |                       "firstpage=",
 877 |                       "fontsize=",
 878 |                       "fontspacing=",
 879 |                       "footer=",
 880 |                       "format=",
 881 |                       "gray",
 882 |                       "header=",
 883 |                       "header1=",
 884 |                       "headfootfont=",
 885 |                       "headfootsize=",
 886 |                       "headingfont=",
 887 |                       "help",
 888 |                       "hfimage0=",
 889 |                       "hfimage1=",
 890 |                       "hfimage2=",
 891 |                       "hfimage3=",
 892 |                       "hfimage4=",
 893 |                       "hfimage5=",
 894 |                       "hfimage6=",
 895 |                       "hfimage7=",
 896 |                       "hfimage8=",
 897 |                       "hfimage9=",
 898 |                       "jpeg=",
 899 |                       "landscape",
 900 |                       "left=",
 901 |                       "linkcolor=",
 902 |                       "links",
 903 |                       "linkstyle=",
 904 |                       "logoimage=",
 905 |                       "logoimage=",
 906 |                       "no-compression",
 907 |                       "no-duplex",
 908 |                       "no-embedfonts",
 909 |                       "no-encryption",
 910 |                       "no-links",
 911 |                       "no-localfiles",
 912 |                       "no-numbered",
 913 |                       "no-overflow",
 914 |                       "no-strict",
 915 |                       "no-title",
 916 |                       "no-toc",
 917 |                       "numbered",
 918 |                       "nup=",
 919 |                       "outfile=",
 920 |                       "overflow",
 921 |                       "owner-password=",
 922 |                       "pageduration=",
 923 |                       "pageeffect=",
 924 |                       "pagelayout=",
 925 |                       "pagemode=",
 926 |                       "path=",
 927 |                       "permissions=",
 928 |                       "portrait",
 929 |                       "prefontsize=",
 930 |                       "quiet",
 931 |                       "right=",
 932 |                       "size=",
 933 |                       "strict",
 934 |                       "textcolor=",
 935 |                       "textfont=",
 936 |                       "title",
 937 |                       "titlefile=",
 938 |                       "titleimage=",
 939 |                       "tocfooter=",
 940 |                       "tocheader=",
 941 |                       "toclevels=",
 942 |                       "toctitle=",
 943 |                       "top=",
 944 |                       "user-password=",
 945 |                       "verbose",
 946 |                       "verbositylevel=",
 947 |                       "version",
 948 |                       "webpage"
 949 |                      ])
 950 |     except getopt.GetoptError:
 951 |         usage(sys.argv[0])
 952 |         sys.exit(1)
 953 | 
 954 |     for o, a in opts:
 955 |         if   o == '--beautifulsoup': options['beautifulsoup'] = '--beautifulsoup'
 956 |         elif o == '--bodycolor': options['bodycolor'] = a
 957 |         elif o == '--bodyfont': options['bodyfont'] = a
 958 |         elif o == '--bodyimage': options['bodyimage'] = a
 959 |         elif o == '--book': options['book'] = '--book'
 960 |         elif o == '--bottom': options['bottom'] = a
 961 |         elif o == '--browserwidth': options['browserwidth'] = a
 962 |         elif o == '--charset': options['charset'] = a
 963 |         elif o == '--color': options['color'] = '--color'
 964 |         elif o == '--compression': options['compression'] = a
 965 |         elif o == '--continuous': options['continuous'] = '--continuous'
 966 |         elif o == '--cookies': options['cookies'] = a
 967 |         elif o == '--datadir': options['datadir'] = a
 968 |         elif o == '--dontextract': options['dontextract'] = '--dontextract'
 969 |         elif o == '--duplex': options['duplex'] = '--duplex'
 970 |         elif o == '--effectduration': options['effectduration'] = a
 971 |         elif o == '--embedfonts': options['embedfonts'] = '--embedfonts'
 972 |         elif o == '--encryption': options['encryption'] = '--encryption'
 973 |         elif o == '--extract-only': options['extract-only'] = '--extract-only'
 974 |         elif o == '--firstpage': options['firstpage'] = a
 975 |         elif o == '--fontsize': options['fontsize'] = a
 976 |         elif o == '--fontspacing': options['fontspacing'] = a
 977 |         elif o == '--footer': options['footer'] = a
 978 |         elif o in ('-t', '--format'): options['format'] = a
 979 |         elif o == '--gray': options['gray'] = '--gray'
 980 |         elif o == '--header': options['header'] = a
 981 |         elif o == '--header1': options['header1'] = a
 982 |         elif o == '--headfootfont': options['headfootfont'] = a
 983 |         elif o == '--headfootsize': options['headfootsize'] = a
 984 |         elif o == '--headingfont': options['headingfont'] = a
 985 |         elif o == '--help': options['help'] = '--help'
 986 |         elif o == '--hfimage0': options['hfimage0'] = a
 987 |         elif o == '--hfimage1': options['hfimage1'] = a
 988 |         elif o == '--hfimage2': options['hfimage2'] = a
 989 |         elif o == '--hfimage3': options['hfimage3'] = a
 990 |         elif o == '--hfimage4': options['hfimage4'] = a
 991 |         elif o == '--hfimage5': options['hfimage5'] = a
 992 |         elif o == '--hfimage6': options['hfimage6'] = a
 993 |         elif o == '--hfimage7': options['hfimage7'] = a
 994 |         elif o == '--hfimage8': options['hfimage8'] = a
 995 |         elif o == '--hfimage9': options['hfimage9'] = a
 996 |         elif o == '--jpeg': options['jpeg'] = a
 997 |         elif o == '--landscape': options['landscape'] = '--landscape'
 998 |         elif o == '--left': options['left'] = a
 999 |         elif o == '--linkcolor': options['linkcolor'] = a
1000 |         elif o == '--links': options['links'] = '--links'
1001 |         elif o == '--linkstyle': options['linkstyle'] = a
1002 |         elif o == '--logoimage': options['logoimage'] = a
1003 |         elif o == '--logoimage': options['logoimage'] = a
1004 |         elif o == '--no-compression': options['no-compression'] = '--no-compression'
1005 |         elif o == '--no-duplex': options['no-duplex'] = '--no-duplex'
1006 |         elif o == '--no-embedfonts': options['no-embedfonts'] = '--no-embedfonts'
1007 |         elif o == '--no-encryption': options['no-encryption'] = '--no-encryption'
1008 |         elif o == '--no-links': options['no-links'] = '--no-links'
1009 |         elif o == '--no-localfiles': options['no-localfiles'] = '--no-localfiles'
1010 |         elif o == '--no-numbered': options['no-numbered'] = '--no-numbered'
1011 |         elif o == '--no-overflow': options['no-overflow'] = '--no-overflow'
1012 |         elif o == '--no-strict': options['no-strict'] = '--no-strict'
1013 |         elif o == '--no-title': options['no-title'] = '--no-title'
1014 |         elif o == '--no-toc': options['no-toc'] = '--no-toc'
1015 |         elif o == '--numbered': options['numbered'] = '--numbered'
1016 |         elif o == '--nup': options['nup'] = a
1017 |         elif o in ('-f', '--outfile'): options['outfile'] = a
1018 |         elif o == '--overflow': options['overflow'] = '--overflow'
1019 |         elif o == '--owner-password': options['owner-password'] = a
1020 |         elif o == '--pageduration': options['pageduration'] = a
1021 |         elif o == '--pageeffect': options['pageeffect'] = a
1022 |         elif o == '--pagelayout': options['pagelayout'] = a
1023 |         elif o == '--pagemode': options['pagemode'] = a
1024 |         elif o == '--path': options['path'] = a
1025 |         elif o == '--permissions': options['permissions'] = a
1026 |         elif o == '--portrait': options['portrait'] = '--portrait'
1027 |         elif o == '--prefontsize': options['prefontsize'] = a
1028 |         elif o == '--quiet': options['quiet'] = '--quiet'
1029 |         elif o == '--right': options['right'] = a
1030 |         elif o == '--size': options['size'] = a
1031 |         elif o == '--strict': options['strict'] = '--strict'
1032 |         elif o == '--textcolor': options['textcolor'] = a
1033 |         elif o == '--textfont': options['textfont'] = a
1034 |         elif o == '--title': options['title'] = '--title'
1035 |         elif o == '--titlefile': options['titlefile'] = a
1036 |         elif o == '--titleimage': options['titleimage'] = a
1037 |         elif o == '--tocfooter': options['tocfooter'] = a
1038 |         elif o == '--tocheader': options['tocheader'] = a
1039 |         elif o == '--toclevels': options['toclevels'] = a
1040 |         elif o == '--toctitle': options['toctitle'] = a
1041 |         elif o == '--top': options['top'] = a
1042 |         elif o == '--user-password': options['user-password'] = a
1043 |         elif o in ('-v', '--verbose'): options['verbose'] = '--verbose'
1044 |         elif o == '--verbositylevel': options['verbositylevel'] = a
1045 |         elif o == '--version':
1046 |             print(sys.argv[0] + ' version ' + version)
1047 |             print('This is free software; see the source for copying conditions.  There is NO')
1048 |             print('warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.')
1049 |             return
1050 |         elif o == '--webpage': options['webpage'] = '--webpage'
1051 | 
1052 |     # Option validation checks
1053 |     #
1054 |     # Only one of '--extract-only' and '--dontextract' may be given!
1055 |     if options['dontextract'] == '--dontextract' and options['extract-only'] == '--extract-only':
1056 |         usage(sys.argv[0])
1057 |         print()
1058 |         print('### Either \'--dontextract\' or \'extract-only\' may be given!')
1059 |         print('### Only one of the two options can be present, not both!')
1060 |         print('### See above or try \'' + sys.argv[0] + ' --help | less\' to view the help contents in less.')
1061 |         return
1062 |     #
1063 |     # One of '--book' or '--webpage' MUST be given!
1064 |     if options['extract-only'] == '' and ((options['book'] == '' and options['webpage'] == '' and options['continuous'] == '') or
1065 |                                           (options['book'] == '--book' and options['webpage'] == '--webpage') or
1066 |                                           (options['book'] == '--book' and options['continuous'] == '--continuous') or
1067 |                                           (options['webpage'] == '--webpage' and options['continuous'] == '--continuous')):
1068 |         usage(sys.argv[0])
1069 |         print()
1070 |         print('### Either \'--book\' or \'--webpage\' or \'--continuous\' MUST be given!')
1071 |         print('### Only one of the three options can be present, not two, or even all three of them!')
1072 |         print('### See above or try \'' + sys.argv[0] + ' --help | less\' to view the help contents in less.')
1073 |         return
1074 | 
1075 |     if len(args)==0:
1076 |         usage(sys.argv[0])
1077 |         return
1078 |     elif len(args)==1:
1079 |         filename = args[0]
1080 |         dirname, basename, suffix = split(filename)
1081 |         if dirname:
1082 |             outputfilename = dirname + os.sep + basename +'.pdf'
1083 |         else:
1084 |             outputfilename = dirname + basename +'.pdf'
1085 |         # print 'outputfilename = ' + outputfilename
1086 | 
1087 |     elif len(args)==2:
1088 |         filename = args[0]
1089 |         dirname, basename, suffix = split(filename)
1090 |         outputfilename = args[1]
1091 |         # print 'outputfilename = ' + outputfilename
1092 |     else:
1093 |         usage(sys.argv[0])
1094 |         return
1095 | 
1096 |     CHM2PDF_WORK_DIR = CHM2PDF_TEMP_WORK_DIR + os.sep + basename
1097 |     CHM2PDF_ORIG_DIR = CHM2PDF_TEMP_ORIG_DIR + os.sep + basename
1098 | 
1099 |     if options['verbose']=='--verbose' and options['verbositylevel']=='low':
1100 |         print('CHM2PDF_WORK_DIR = ' + CHM2PDF_WORK_DIR)
1101 |         print('CHM2PDF_ORIG_DIR = ' + CHM2PDF_ORIG_DIR)
1102 | 
1103 |     if not os.path.exists(filename):
1104 |         print('CHM file "' + filename + '" not found!')
1105 |         return
1106 | 
1107 |     #remove temporary files
1108 |     if options['dontextract'] == '':
1109 |         if options['verbose']=='--verbose' and options['verbositylevel']=='high':
1110 |             print('Removing any previous temporary files...')
1111 |         os.system('rm -r '+CHM2PDF_ORIG_DIR+'/*')
1112 |         os.system('rm -r '+CHM2PDF_WORK_DIR+'/*')
1113 | 
1114 |     cfile = chm.CHMFile()
1115 |     cfile.LoadCHM(filename)
1116 | 
1117 |     if options['dontextract'] == '--dontextract':
1118 |         if options['verbose'] == '--verbose':
1119 |             print('\'--dontextract\' option was given. No files will be extracted from CHM.')
1120 |             print('Will use the files in ' + CHM2PDF_ORIG_DIR + ' and ' + CHM2PDF_WORK_DIR + '.')
1121 |     else:
1122 |         if options['verbose'] == '--verbose' and options['verbositylevel'] == 'high':
1123 |             os.system('extract_chmLib ' + filename + ' ' + CHM2PDF_ORIG_DIR)
1124 |         else:
1125 |             os.system('extract_chmLib ' + filename + ' ' + CHM2PDF_ORIG_DIR + '&> /dev/null')
1126 | 
1127 |     convert_to_pdf(cfile, filename, outputfilename, options)
1128 | 
1129 | 
1130 | if __name__ == '__main__':
1131 |     main(sys.argv)
1132 | 


--------------------------------------------------------------------------------