From 8cb99955160750b7a85e3bd84ae1bfdbf7c1c9d1 Mon Sep 17 00:00:00 2001 From: Arjan Date: Sun, 2 Oct 2022 09:04:45 +0200 Subject: [PATCH 1/5] Ready for release --- LICENSE | 674 +++++++++++++++++++++++++++++++++++++++++++++++++++ README.rst | 38 ++- config.yaml | 3 + exitwp.py | 114 +++++---- html2text.py | 34 ++- 5 files changed, 783 insertions(+), 80 deletions(-) create mode 100644 LICENSE diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..f288702 --- /dev/null +++ b/LICENSE @@ -0,0 +1,674 @@ + GNU GENERAL PUBLIC LICENSE + Version 3, 29 June 2007 + + Copyright (C) 2007 Free Software Foundation, Inc. + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The GNU General Public License is a free, copyleft license for +software and other kinds of works. + + The licenses for most software and other practical works are designed +to take away your freedom to share and change the works. By contrast, +the GNU General Public License is intended to guarantee your freedom to +share and change all versions of a program--to make sure it remains free +software for all its users. We, the Free Software Foundation, use the +GNU General Public License for most of our software; it applies also to +any other work released this way by its authors. You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +them if you wish), that you receive source code or can get it if you +want it, that you can change the software or use pieces of it in new +free programs, and that you know you can do these things. + + To protect your rights, we need to prevent others from denying you +these rights or asking you to surrender the rights. Therefore, you have +certain responsibilities if you distribute copies of the software, or if +you modify it: responsibilities to respect the freedom of others. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must pass on to the recipients the same +freedoms that you received. You must make sure that they, too, receive +or can get the source code. And you must show them these terms so they +know their rights. + + Developers that use the GNU GPL protect your rights with two steps: +(1) assert copyright on the software, and (2) offer you this License +giving you legal permission to copy, distribute and/or modify it. + + For the developers' and authors' protection, the GPL clearly explains +that there is no warranty for this free software. For both users' and +authors' sake, the GPL requires that modified versions be marked as +changed, so that their problems will not be attributed erroneously to +authors of previous versions. + + Some devices are designed to deny users access to install or run +modified versions of the software inside them, although the manufacturer +can do so. This is fundamentally incompatible with the aim of +protecting users' freedom to change the software. The systematic +pattern of such abuse occurs in the area of products for individuals to +use, which is precisely where it is most unacceptable. Therefore, we +have designed this version of the GPL to prohibit the practice for those +products. If such problems arise substantially in other domains, we +stand ready to extend this provision to those domains in future versions +of the GPL, as needed to protect the freedom of users. + + Finally, every program is threatened constantly by software patents. +States should not allow patents to restrict development and use of +software on general-purpose computers, but in those that do, we wish to +avoid the special danger that patents applied to a free program could +make it effectively proprietary. To prevent this, the GPL assures that +patents cannot be used to render the program non-free. + + The precise terms and conditions for copying, distribution and +modification follow. + + TERMS AND CONDITIONS + + 0. Definitions. + + "This License" refers to version 3 of the GNU General Public License. + + "Copyright" also means copyright-like laws that apply to other kinds of +works, such as semiconductor masks. + + "The Program" refers to any copyrightable work licensed under this +License. Each licensee is addressed as "you". "Licensees" and +"recipients" may be individuals or organizations. + + To "modify" a work means to copy from or adapt all or part of the work +in a fashion requiring copyright permission, other than the making of an +exact copy. The resulting work is called a "modified version" of the +earlier work or a work "based on" the earlier work. + + A "covered work" means either the unmodified Program or a work based +on the Program. + + To "propagate" a work means to do anything with it that, without +permission, would make you directly or secondarily liable for +infringement under applicable copyright law, except executing it on a +computer or modifying a private copy. Propagation includes copying, +distribution (with or without modification), making available to the +public, and in some countries other activities as well. + + To "convey" a work means any kind of propagation that enables other +parties to make or receive copies. Mere interaction with a user through +a computer network, with no transfer of a copy, is not conveying. + + An interactive user interface displays "Appropriate Legal Notices" +to the extent that it includes a convenient and prominently visible +feature that (1) displays an appropriate copyright notice, and (2) +tells the user that there is no warranty for the work (except to the +extent that warranties are provided), that licensees may convey the +work under this License, and how to view a copy of this License. If +the interface presents a list of user commands or options, such as a +menu, a prominent item in the list meets this criterion. + + 1. Source Code. + + The "source code" for a work means the preferred form of the work +for making modifications to it. "Object code" means any non-source +form of a work. + + A "Standard Interface" means an interface that either is an official +standard defined by a recognized standards body, or, in the case of +interfaces specified for a particular programming language, one that +is widely used among developers working in that language. + + The "System Libraries" of an executable work include anything, other +than the work as a whole, that (a) is included in the normal form of +packaging a Major Component, but which is not part of that Major +Component, and (b) serves only to enable use of the work with that +Major Component, or to implement a Standard Interface for which an +implementation is available to the public in source code form. A +"Major Component", in this context, means a major essential component +(kernel, window system, and so on) of the specific operating system +(if any) on which the executable work runs, or a compiler used to +produce the work, or an object code interpreter used to run it. + + The "Corresponding Source" for a work in object code form means all +the source code needed to generate, install, and (for an executable +work) run the object code and to modify the work, including scripts to +control those activities. However, it does not include the work's +System Libraries, or general-purpose tools or generally available free +programs which are used unmodified in performing those activities but +which are not part of the work. For example, Corresponding Source +includes interface definition files associated with source files for +the work, and the source code for shared libraries and dynamically +linked subprograms that the work is specifically designed to require, +such as by intimate data communication or control flow between those +subprograms and other parts of the work. + + The Corresponding Source need not include anything that users +can regenerate automatically from other parts of the Corresponding +Source. + + The Corresponding Source for a work in source code form is that +same work. + + 2. Basic Permissions. + + All rights granted under this License are granted for the term of +copyright on the Program, and are irrevocable provided the stated +conditions are met. This License explicitly affirms your unlimited +permission to run the unmodified Program. The output from running a +covered work is covered by this License only if the output, given its +content, constitutes a covered work. This License acknowledges your +rights of fair use or other equivalent, as provided by copyright law. + + You may make, run and propagate covered works that you do not +convey, without conditions so long as your license otherwise remains +in force. You may convey covered works to others for the sole purpose +of having them make modifications exclusively for you, or provide you +with facilities for running those works, provided that you comply with +the terms of this License in conveying all material for which you do +not control copyright. Those thus making or running the covered works +for you must do so exclusively on your behalf, under your direction +and control, on terms that prohibit them from making any copies of +your copyrighted material outside their relationship with you. + + Conveying under any other circumstances is permitted solely under +the conditions stated below. Sublicensing is not allowed; section 10 +makes it unnecessary. + + 3. Protecting Users' Legal Rights From Anti-Circumvention Law. + + No covered work shall be deemed part of an effective technological +measure under any applicable law fulfilling obligations under article +11 of the WIPO copyright treaty adopted on 20 December 1996, or +similar laws prohibiting or restricting circumvention of such +measures. + + When you convey a covered work, you waive any legal power to forbid +circumvention of technological measures to the extent such circumvention +is effected by exercising rights under this License with respect to +the covered work, and you disclaim any intention to limit operation or +modification of the work as a means of enforcing, against the work's +users, your or third parties' legal rights to forbid circumvention of +technological measures. + + 4. Conveying Verbatim Copies. + + You may convey verbatim copies of the Program's source code as you +receive it, in any medium, provided that you conspicuously and +appropriately publish on each copy an appropriate copyright notice; +keep intact all notices stating that this License and any +non-permissive terms added in accord with section 7 apply to the code; +keep intact all notices of the absence of any warranty; and give all +recipients a copy of this License along with the Program. + + You may charge any price or no price for each copy that you convey, +and you may offer support or warranty protection for a fee. + + 5. Conveying Modified Source Versions. + + You may convey a work based on the Program, or the modifications to +produce it from the Program, in the form of source code under the +terms of section 4, provided that you also meet all of these conditions: + + a) The work must carry prominent notices stating that you modified + it, and giving a relevant date. + + b) The work must carry prominent notices stating that it is + released under this License and any conditions added under section + 7. This requirement modifies the requirement in section 4 to + "keep intact all notices". + + c) You must license the entire work, as a whole, under this + License to anyone who comes into possession of a copy. This + License will therefore apply, along with any applicable section 7 + additional terms, to the whole of the work, and all its parts, + regardless of how they are packaged. This License gives no + permission to license the work in any other way, but it does not + invalidate such permission if you have separately received it. + + d) If the work has interactive user interfaces, each must display + Appropriate Legal Notices; however, if the Program has interactive + interfaces that do not display Appropriate Legal Notices, your + work need not make them do so. + + A compilation of a covered work with other separate and independent +works, which are not by their nature extensions of the covered work, +and which are not combined with it such as to form a larger program, +in or on a volume of a storage or distribution medium, is called an +"aggregate" if the compilation and its resulting copyright are not +used to limit the access or legal rights of the compilation's users +beyond what the individual works permit. Inclusion of a covered work +in an aggregate does not cause this License to apply to the other +parts of the aggregate. + + 6. Conveying Non-Source Forms. + + You may convey a covered work in object code form under the terms +of sections 4 and 5, provided that you also convey the +machine-readable Corresponding Source under the terms of this License, +in one of these ways: + + a) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by the + Corresponding Source fixed on a durable physical medium + customarily used for software interchange. + + b) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by a + written offer, valid for at least three years and valid for as + long as you offer spare parts or customer support for that product + model, to give anyone who possesses the object code either (1) a + copy of the Corresponding Source for all the software in the + product that is covered by this License, on a durable physical + medium customarily used for software interchange, for a price no + more than your reasonable cost of physically performing this + conveying of source, or (2) access to copy the + Corresponding Source from a network server at no charge. + + c) Convey individual copies of the object code with a copy of the + written offer to provide the Corresponding Source. This + alternative is allowed only occasionally and noncommercially, and + only if you received the object code with such an offer, in accord + with subsection 6b. + + d) Convey the object code by offering access from a designated + place (gratis or for a charge), and offer equivalent access to the + Corresponding Source in the same way through the same place at no + further charge. You need not require recipients to copy the + Corresponding Source along with the object code. If the place to + copy the object code is a network server, the Corresponding Source + may be on a different server (operated by you or a third party) + that supports equivalent copying facilities, provided you maintain + clear directions next to the object code saying where to find the + Corresponding Source. Regardless of what server hosts the + Corresponding Source, you remain obligated to ensure that it is + available for as long as needed to satisfy these requirements. + + e) Convey the object code using peer-to-peer transmission, provided + you inform other peers where the object code and Corresponding + Source of the work are being offered to the general public at no + charge under subsection 6d. + + A separable portion of the object code, whose source code is excluded +from the Corresponding Source as a System Library, need not be +included in conveying the object code work. + + A "User Product" is either (1) a "consumer product", which means any +tangible personal property which is normally used for personal, family, +or household purposes, or (2) anything designed or sold for incorporation +into a dwelling. In determining whether a product is a consumer product, +doubtful cases shall be resolved in favor of coverage. For a particular +product received by a particular user, "normally used" refers to a +typical or common use of that class of product, regardless of the status +of the particular user or of the way in which the particular user +actually uses, or expects or is expected to use, the product. A product +is a consumer product regardless of whether the product has substantial +commercial, industrial or non-consumer uses, unless such uses represent +the only significant mode of use of the product. + + "Installation Information" for a User Product means any methods, +procedures, authorization keys, or other information required to install +and execute modified versions of a covered work in that User Product from +a modified version of its Corresponding Source. The information must +suffice to ensure that the continued functioning of the modified object +code is in no case prevented or interfered with solely because +modification has been made. + + If you convey an object code work under this section in, or with, or +specifically for use in, a User Product, and the conveying occurs as +part of a transaction in which the right of possession and use of the +User Product is transferred to the recipient in perpetuity or for a +fixed term (regardless of how the transaction is characterized), the +Corresponding Source conveyed under this section must be accompanied +by the Installation Information. But this requirement does not apply +if neither you nor any third party retains the ability to install +modified object code on the User Product (for example, the work has +been installed in ROM). + + The requirement to provide Installation Information does not include a +requirement to continue to provide support service, warranty, or updates +for a work that has been modified or installed by the recipient, or for +the User Product in which it has been modified or installed. Access to a +network may be denied when the modification itself materially and +adversely affects the operation of the network or violates the rules and +protocols for communication across the network. + + Corresponding Source conveyed, and Installation Information provided, +in accord with this section must be in a format that is publicly +documented (and with an implementation available to the public in +source code form), and must require no special password or key for +unpacking, reading or copying. + + 7. Additional Terms. + + "Additional permissions" are terms that supplement the terms of this +License by making exceptions from one or more of its conditions. +Additional permissions that are applicable to the entire Program shall +be treated as though they were included in this License, to the extent +that they are valid under applicable law. If additional permissions +apply only to part of the Program, that part may be used separately +under those permissions, but the entire Program remains governed by +this License without regard to the additional permissions. + + When you convey a copy of a covered work, you may at your option +remove any additional permissions from that copy, or from any part of +it. (Additional permissions may be written to require their own +removal in certain cases when you modify the work.) You may place +additional permissions on material, added by you to a covered work, +for which you have or can give appropriate copyright permission. + + Notwithstanding any other provision of this License, for material you +add to a covered work, you may (if authorized by the copyright holders of +that material) supplement the terms of this License with terms: + + a) Disclaiming warranty or limiting liability differently from the + terms of sections 15 and 16 of this License; or + + b) Requiring preservation of specified reasonable legal notices or + author attributions in that material or in the Appropriate Legal + Notices displayed by works containing it; or + + c) Prohibiting misrepresentation of the origin of that material, or + requiring that modified versions of such material be marked in + reasonable ways as different from the original version; or + + d) Limiting the use for publicity purposes of names of licensors or + authors of the material; or + + e) Declining to grant rights under trademark law for use of some + trade names, trademarks, or service marks; or + + f) Requiring indemnification of licensors and authors of that + material by anyone who conveys the material (or modified versions of + it) with contractual assumptions of liability to the recipient, for + any liability that these contractual assumptions directly impose on + those licensors and authors. + + All other non-permissive additional terms are considered "further +restrictions" within the meaning of section 10. If the Program as you +received it, or any part of it, contains a notice stating that it is +governed by this License along with a term that is a further +restriction, you may remove that term. If a license document contains +a further restriction but permits relicensing or conveying under this +License, you may add to a covered work material governed by the terms +of that license document, provided that the further restriction does +not survive such relicensing or conveying. + + If you add terms to a covered work in accord with this section, you +must place, in the relevant source files, a statement of the +additional terms that apply to those files, or a notice indicating +where to find the applicable terms. + + Additional terms, permissive or non-permissive, may be stated in the +form of a separately written license, or stated as exceptions; +the above requirements apply either way. + + 8. Termination. + + You may not propagate or modify a covered work except as expressly +provided under this License. Any attempt otherwise to propagate or +modify it is void, and will automatically terminate your rights under +this License (including any patent licenses granted under the third +paragraph of section 11). + + However, if you cease all violation of this License, then your +license from a particular copyright holder is reinstated (a) +provisionally, unless and until the copyright holder explicitly and +finally terminates your license, and (b) permanently, if the copyright +holder fails to notify you of the violation by some reasonable means +prior to 60 days after the cessation. + + Moreover, your license from a particular copyright holder is +reinstated permanently if the copyright holder notifies you of the +violation by some reasonable means, this is the first time you have +received notice of violation of this License (for any work) from that +copyright holder, and you cure the violation prior to 30 days after +your receipt of the notice. + + Termination of your rights under this section does not terminate the +licenses of parties who have received copies or rights from you under +this License. If your rights have been terminated and not permanently +reinstated, you do not qualify to receive new licenses for the same +material under section 10. + + 9. Acceptance Not Required for Having Copies. + + You are not required to accept this License in order to receive or +run a copy of the Program. Ancillary propagation of a covered work +occurring solely as a consequence of using peer-to-peer transmission +to receive a copy likewise does not require acceptance. However, +nothing other than this License grants you permission to propagate or +modify any covered work. These actions infringe copyright if you do +not accept this License. Therefore, by modifying or propagating a +covered work, you indicate your acceptance of this License to do so. + + 10. Automatic Licensing of Downstream Recipients. + + Each time you convey a covered work, the recipient automatically +receives a license from the original licensors, to run, modify and +propagate that work, subject to this License. You are not responsible +for enforcing compliance by third parties with this License. + + An "entity transaction" is a transaction transferring control of an +organization, or substantially all assets of one, or subdividing an +organization, or merging organizations. If propagation of a covered +work results from an entity transaction, each party to that +transaction who receives a copy of the work also receives whatever +licenses to the work the party's predecessor in interest had or could +give under the previous paragraph, plus a right to possession of the +Corresponding Source of the work from the predecessor in interest, if +the predecessor has it or can get it with reasonable efforts. + + You may not impose any further restrictions on the exercise of the +rights granted or affirmed under this License. For example, you may +not impose a license fee, royalty, or other charge for exercise of +rights granted under this License, and you may not initiate litigation +(including a cross-claim or counterclaim in a lawsuit) alleging that +any patent claim is infringed by making, using, selling, offering for +sale, or importing the Program or any portion of it. + + 11. Patents. + + A "contributor" is a copyright holder who authorizes use under this +License of the Program or a work on which the Program is based. The +work thus licensed is called the contributor's "contributor version". + + A contributor's "essential patent claims" are all patent claims +owned or controlled by the contributor, whether already acquired or +hereafter acquired, that would be infringed by some manner, permitted +by this License, of making, using, or selling its contributor version, +but do not include claims that would be infringed only as a +consequence of further modification of the contributor version. For +purposes of this definition, "control" includes the right to grant +patent sublicenses in a manner consistent with the requirements of +this License. + + Each contributor grants you a non-exclusive, worldwide, royalty-free +patent license under the contributor's essential patent claims, to +make, use, sell, offer for sale, import and otherwise run, modify and +propagate the contents of its contributor version. + + In the following three paragraphs, a "patent license" is any express +agreement or commitment, however denominated, not to enforce a patent +(such as an express permission to practice a patent or covenant not to +sue for patent infringement). To "grant" such a patent license to a +party means to make such an agreement or commitment not to enforce a +patent against the party. + + If you convey a covered work, knowingly relying on a patent license, +and the Corresponding Source of the work is not available for anyone +to copy, free of charge and under the terms of this License, through a +publicly available network server or other readily accessible means, +then you must either (1) cause the Corresponding Source to be so +available, or (2) arrange to deprive yourself of the benefit of the +patent license for this particular work, or (3) arrange, in a manner +consistent with the requirements of this License, to extend the patent +license to downstream recipients. "Knowingly relying" means you have +actual knowledge that, but for the patent license, your conveying the +covered work in a country, or your recipient's use of the covered work +in a country, would infringe one or more identifiable patents in that +country that you have reason to believe are valid. + + If, pursuant to or in connection with a single transaction or +arrangement, you convey, or propagate by procuring conveyance of, a +covered work, and grant a patent license to some of the parties +receiving the covered work authorizing them to use, propagate, modify +or convey a specific copy of the covered work, then the patent license +you grant is automatically extended to all recipients of the covered +work and works based on it. + + A patent license is "discriminatory" if it does not include within +the scope of its coverage, prohibits the exercise of, or is +conditioned on the non-exercise of one or more of the rights that are +specifically granted under this License. You may not convey a covered +work if you are a party to an arrangement with a third party that is +in the business of distributing software, under which you make payment +to the third party based on the extent of your activity of conveying +the work, and under which the third party grants, to any of the +parties who would receive the covered work from you, a discriminatory +patent license (a) in connection with copies of the covered work +conveyed by you (or copies made from those copies), or (b) primarily +for and in connection with specific products or compilations that +contain the covered work, unless you entered into that arrangement, +or that patent license was granted, prior to 28 March 2007. + + Nothing in this License shall be construed as excluding or limiting +any implied license or other defenses to infringement that may +otherwise be available to you under applicable patent law. + + 12. No Surrender of Others' Freedom. + + If conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot convey a +covered work so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you may +not convey it at all. For example, if you agree to terms that obligate you +to collect a royalty for further conveying from those to whom you convey +the Program, the only way you could satisfy both those terms and this +License would be to refrain entirely from conveying the Program. + + 13. Use with the GNU Affero General Public License. + + Notwithstanding any other provision of this License, you have +permission to link or combine any covered work with a work licensed +under version 3 of the GNU Affero General Public License into a single +combined work, and to convey the resulting work. The terms of this +License will continue to apply to the part which is the covered work, +but the special requirements of the GNU Affero General Public License, +section 13, concerning interaction through a network will apply to the +combination as such. + + 14. Revised Versions of this License. + + The Free Software Foundation may publish revised and/or new versions of +the GNU General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + + Each version is given a distinguishing version number. If the +Program specifies that a certain numbered version of the GNU General +Public License "or any later version" applies to it, you have the +option of following the terms and conditions either of that numbered +version or of any later version published by the Free Software +Foundation. If the Program does not specify a version number of the +GNU General Public License, you may choose any version ever published +by the Free Software Foundation. + + If the Program specifies that a proxy can decide which future +versions of the GNU General Public License can be used, that proxy's +public statement of acceptance of a version permanently authorizes you +to choose that version for the Program. + + Later license versions may give you additional or different +permissions. However, no additional obligations are imposed on any +author or copyright holder as a result of your choosing to follow a +later version. + + 15. Disclaimer of Warranty. + + THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY +APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT +HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY +OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, +THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR +PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM +IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF +ALL NECESSARY SERVICING, REPAIR OR CORRECTION. + + 16. Limitation of Liability. + + IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS +THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY +GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE +USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF +DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD +PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), +EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF +SUCH DAMAGES. + + 17. Interpretation of Sections 15 and 16. + + If the disclaimer of warranty and limitation of liability provided +above cannot be given local legal effect according to their terms, +reviewing courts shall apply local law that most closely approximates +an absolute waiver of all civil liability in connection with the +Program, unless a warranty or assumption of liability accompanies a +copy of the Program in return for a fee. + + END OF TERMS AND CONDITIONS + + How to Apply These Terms to Your New Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. It is safest +to attach them to the start of each source file to most effectively +state the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + + Copyright (C) + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . + +Also add information on how to contact you by electronic and paper mail. + + If the program does terminal interaction, make it output a short +notice like this when it starts in an interactive mode: + + Copyright (C) + This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, your program's commands +might be different; for a GUI interface, you would use an "about box". + + You should also get your employer (if you work as a programmer) or school, +if any, to sign a "copyright disclaimer" for the program, if necessary. +For more information on this, and how to apply and follow the GNU GPL, see +. + + The GNU General Public License does not permit incorporating your program +into proprietary programs. If your program is a subroutine library, you +may consider it more useful to permit linking proprietary applications with +the library. If this is what you want to do, use the GNU Lesser General +Public License instead of this License. But first, please read +. diff --git a/README.rst b/README.rst index cdaeb1a..64d0343 100644 --- a/README.rst +++ b/README.rst @@ -1,26 +1,31 @@ -###### -Exitwp -###### +############### +ExitWP for Hugo +############### -Exitwp is tool for making migration from one or more wordpress blogs to the `jekyll blog engine `_ as easy as possible. +This is a port of Thomas Frössman's ExitWP tool (for Jekyll). + +You can find also a howto and background information here on my website: https://arjan.wooning.cz/conversion-tools-from-wordpress-to-hugo/#final-solution-exitwp-for-hugo + + +Exitwp is tool for making migration from one or more wordpress blogs to the `hugo blog engine `_ as easy as possible. By default it will try to convert as much information as possible from wordpress but can also be told to filter the amount of data it converts. -The latest version of these docs should always be available at https://github.com/thomasf/exitwp +The latest version of these docs should always be available at https://github.com/wooni005/exitwp-for-hugo Getting started =============== - * `Download `_ or clone using ``git clone https://github.com/thomasf/exitwp.git`` + * `Download `_ or clone using ``git clone https://github.com/wooni005/exitwp-for-hugo.git`` * Export one or more wordpress blogs using the wordpress exporter under tools/export in wordpress admin. * Put all wordpress xml files in the ``wordpress-xml`` directory * Special note for Wordpress 3.1, you need to add a missing namespace in rss tag : ``xmlns:atom="http://www.w3.org/2005/Atom"`` * Run xmllint on your export file and fix errors if there are. - * Run the converter by typing ``python exitwp.py`` in the console from the directory of the unzipped archive + * Run the converter by typing ``./exitwp.py`` in the console from the directory of the unzipped archive * You should now have all the blogs converted into separate directories under the ``build`` directory Runtime dependencies ==================== - * `Python `_ 2.6, 2.7, ??? + * `Python `_: Python 2 * `html2text `_ : converts HTML to markdown (python) * `PyYAML `_ : Reading configuration files and writing YAML headers (python) * `Beautiful soup `_ : Parsing and downloading of post images/attachments (python) @@ -42,26 +47,13 @@ Note that PyYAML will require other packages to compile correctly under ubuntu/d ``sudo apt-get install libyaml-dev python-dev build-essential`` -Using Vagrant for dependency management ---------------------------------------- - -In the event your local system is incompatible with the dependencies listed (or you'd rather not install them), you can use the included Vagrantfile to start a VM with all necessary dependencies installed. - -1. Lint and place all wordpress xml files in the ``wordpress-xml`` directory as mentioned above -2. In the directory of the unzipped archive, run ``vagrant up``. -3. SSH to your Vagrant VM using ``vagrant ssh`` -4. Run ``cd /vagrant`` to open the VM's shared folder -5. Run the converter from the VM by typing ``python exitwp.py`` -6. After the converter completes, exit the SSH session using ``exit`` -7. You should now have all the blogs converted into separate directories under the ``build`` directory -8. **Important:** Once satisfied with the results, run ``vagrant destroy -f`` to shut down the VM and remove the virtual drive from your local machine Configuration/Customization =========================== -See the `configuration file `_ for all configurable options. +See the `configuration file `_ for all configurable options. -Some things like custom handling of non standard post types is not fully configurable through the config file. You might have to modify the `source code `_ to add custom parsing behaviour. +Some things like custom handling of non standard post types is not fully configurable through the config file. You might have to modify the `source code `_ to add custom parsing behaviour. Known issues ============ diff --git a/config.yaml b/config.yaml index aa03275..43fe840 100644 --- a/config.yaml +++ b/config.yaml @@ -1,3 +1,6 @@ +# Tell me what's going on.. can also pass command line argument -v +verbose: False + # The directory where exitwp looks for wordpress export xml files. wp_exports: wordpress-xml diff --git a/exitwp.py b/exitwp.py index 17127d3..f18ecbc 100755 --- a/exitwp.py +++ b/exitwp.py @@ -1,4 +1,4 @@ -#!/usr/bin/env python +#!/usr/bin/python2 import codecs import os @@ -9,6 +9,7 @@ from urllib import urlretrieve from urlparse import urljoin, urlparse from xml.etree.ElementTree import ElementTree, XMLTreeBuilder +from urlparse import urlparse #AW!! import yaml from bs4 import BeautifulSoup @@ -24,7 +25,7 @@ ###################################################### # Configration ###################################################### -config = yaml.load(file('config.yaml', 'r')) +config = yaml.safe_load(file('config.yaml', 'r')) wp_exports = config['wp_exports'] build_dir = config['build_dir'] download_images = config['download_images'] @@ -36,12 +37,17 @@ item_field_filter = config['item_field_filter'] date_fmt = config['date_format'] body_replace = config['body_replace'] +verbose = config['verbose'] # Time definitions ZERO = timedelta(0) HOUR = timedelta(hours=1) +# Logging +def log(msg): + if verbose: + print(msg) # UTC support class UTC(tzinfo): @@ -81,7 +87,7 @@ def html2fmt(html, target_format): def parse_wp_xml(file): parser = ns_tracker_tree_builder() tree = ElementTree() - print 'reading: ' + wpe + log('reading: ' + wpe) root = tree.parse(file, parser) ns = parser.namespaces ns[''] = '' @@ -122,8 +128,8 @@ def gi(q, unicode_wrap=True, empty=False): else: tag = q try: - result = (i.find(q, ns) or i.find(tag) or i.find(ns[namespace] + tag)).text.strip() - print result.encode('utf-8') + result = i.find(ns[namespace] + tag).text + #print result.encode('utf-8') except AttributeError: result = 'No Content Found' if empty: @@ -140,12 +146,12 @@ def gi(q, unicode_wrap=True, empty=False): img_srcs = [] if body is not None: try: - soup = BeautifulSoup(body) + soup = BeautifulSoup(body, features="lxml") img_tags = soup.find_all('img') for img in img_tags: img_srcs.append(img['src']) except: - print 'could not parse html: ' + body + print('could not parse html: ' + body) # print img_srcs excerpt = gi('excerpt:encoded', empty=True) @@ -166,7 +172,7 @@ def gi(q, unicode_wrap=True, empty=False): 'excerpt': excerpt, 'img_srcs': img_srcs } - + log(' item/' + export_item['wp_id'] + ': ' + export_item['title']) export_items.append(export_item) return export_items @@ -179,11 +185,14 @@ def gi(q, unicode_wrap=True, empty=False): def write_jekyll(data, target_format): - sys.stdout.write('writing') + if verbose: + log('writing..') + else: + sys.stdout.write('writing') item_uids = {} attachments = {} - def get_blog_path(data, path_infix='jekyll'): + def get_blog_path(data, path_infix='hugo'): #AW!! Changed jekyll path into hugo name = data['header']['link'] name = re.sub('^https?', '', name) name = re.sub('[^A-Za-z0-9_.-]', '', name) @@ -193,7 +202,7 @@ def get_blog_path(data, path_infix='jekyll'): def get_full_dir(dir): full_dir = os.path.normpath(blog_dir + '/' + dir) - if (not os.path.exists(full_dir)): + if not os.path.exists(full_dir): os.makedirs(full_dir) return full_dir @@ -210,12 +219,8 @@ def get_item_uid(item, date_prefix=False, namespace=''): result = item_uids[namespace][item['wp_id']] else: uid = [] - if (date_prefix): - try: - dt = datetime.strptime(item['date'], date_fmt) - except: - dt = datetime.today() - print 'Wrong date in', item['title'] + if date_prefix: + dt = datetime.strptime(item['date'], date_fmt) uid.append(dt.strftime('%Y-%m-%d')) uid.append('-') s_title = item['slug'] @@ -237,10 +242,9 @@ def get_item_uid(item, date_prefix=False, namespace=''): def get_item_path(item, dir=''): full_dir = get_full_dir(dir) - filename_parts = [full_dir, '/'] - filename_parts.append(item['uid']) + filename_parts = [full_dir, '/', item['uid']] if item['type'] == 'page': - if (not os.path.exists(''.join(filename_parts))): + if not os.path.exists(''.join(filename_parts)): os.makedirs(''.join(filename_parts)) filename_parts.append('/index') filename_parts.append('.') @@ -271,7 +275,7 @@ def get_attachment_path(src, dir, dir_prefix='images'): target_dir = os.path.normpath(blog_dir + '/' + dir_prefix + '/' + dir) target_file = os.path.normpath(target_dir + '/' + filename) - if (not os.path.exists(target_dir)): + if not os.path.exists(target_dir): os.makedirs(target_dir) # if src not in attachments[dir]: @@ -279,43 +283,45 @@ def get_attachment_path(src, dir, dir_prefix='images'): return target_file for i in data['items']: - skip_item = False + skip_item = None for field, value in item_field_filter.iteritems(): - if(i[field] == value): - skip_item = True + if i[field] == value: + skip_item = value break - if(skip_item): + if skip_item: + log(' skipped(field=' + skip_item + ')/' + i['wp_id'] + ': ' + i['title']) continue - sys.stdout.write('.') - sys.stdout.flush() + if not verbose: + sys.stdout.write('.') + sys.stdout.flush() out = None - try: - date = datetime.strptime(i['date'], '%Y-%m-%d %H:%M:%S').replace(tzinfo=UTC()) - except: - date = datetime.today() - print 'Wrong date in', i['title'] + + item_url = urlparse(i['link']) # AW!!: Store item url for later url path relative yaml_header = { 'title': i['title'], - 'link': i['link'], + 'url': item_url.path, # AW!!: Renamed: link (Jekykll) -> url and and make url path relative 'author': i['author'], - 'date': date, - 'slug': i['slug'], - 'wordpress_id': int(i['wp_id']), - 'comments': i['comments'], + 'date': datetime.strptime( + i['date'], '%Y-%m-%d %H:%M:%S').replace(tzinfo=UTC()) + #'slug': i['slug'], # AW!!: can be used + #'wordpress_id': int(i['wp_id']), # AW!!: not used + #'comments': i['comments'], # AW!!: Via Disqus } - if len(i['excerpt']) > 0: - yaml_header['excerpt'] = i['excerpt'] - if i['status'] != u'publish': - yaml_header['published'] = False + #if len(i['excerpt']) > 0: + # yaml_header['excerpt'] = i['excerpt'] # AW!!: can be used + if i['status'] == u'publish': + yaml_header['draft'] = False + #else: + # yaml_header['draft'] = True if i['type'] == 'post': i['uid'] = get_item_uid(i, date_prefix=True) fn = get_item_path(i, dir='_posts') out = open_file(fn) - yaml_header['layout'] = 'post' + yaml_header['type'] = 'post' # AW!!: Changed from layout into type elif i['type'] == 'page': i['uid'] = get_item_uid(i) # Chase down parent path, if any @@ -330,11 +336,12 @@ def get_attachment_path(src, dir, dir_prefix='images'): break fn = get_item_path(i, parentpath) out = open_file(fn) - yaml_header['layout'] = 'page' + yaml_header['type'] = 'page' # AW!!: Changed from layout into type elif i['type'] in item_type_filter: + log(' skipped(type=' + i['type'] + ')/' + i['wp_id']+ ': ' + i['title']) pass else: - print 'Unknown item type :: ' + i['type'] + print('Unknown item type :: ' + i['type']) if download_images: for img in i['img_srcs']: @@ -343,8 +350,7 @@ def get_attachment_path(src, dir, dir_prefix='images'): img.encode('utf-8')), get_attachment_path(img, i['uid'])) except: - print '\n unable to download ' + urljoin( - data['header']['link'], img.encode('utf-8')) + print('\n unable to download ' + urljoin(data['header']['link'], img.encode('utf-8'))) if out is not None: def toyaml(data): @@ -371,14 +377,22 @@ def toyaml(data): try: out.write(html2fmt(i['body'], target_format)) except: - print '\n Parse error on: ' + i['title'] + print('\n Parse error on: ' + i['title']) out.close() - print '\n' - + log(' written/' + i['wp_id'] + ': ' + i['title']) + print( '\n') + +for arg in range(1, len(sys.argv)): + if sys.argv[arg] == '-v': + verbose = True + elif sys.argv[arg] == '-h': + print('usage: ' + sys.argv[0] + ' [-h(elp)] [-v(erbose)]') + sys.exit(0) +print('starting..') wp_exports = glob(wp_exports + '/*.xml') for wpe in wp_exports: data = parse_wp_xml(wpe) write_jekyll(data, target_format) -print 'done' +print('done') diff --git a/html2text.py b/html2text.py index 77178f0..9609289 100755 --- a/html2text.py +++ b/html2text.py @@ -413,14 +413,23 @@ def handle_tag(self, tag, attrs, start): else: attrs = dict(attrs) + # AW!! This part is used for tags nested within a 
 tag
+		# For my website I decided to remove the  and  tags, but you can fill it in
         if self.pre and not tag == "pre":
             if start:
-                attrs_string = ""
-                for k, v in attrs.items():
-                    attrs_string += " " + k + "=\"" + v + "\""
-                self.o("<"+tag+attrs_string+">")
+				if tag in ['em', 'i', 'u']: self.o("")    # "_"
+				elif tag in ['strong', 'b']: self.o("")   # "**"
+				else:
+					attrs_string = ""
+					for k, v in attrs.items():
+						attrs_string += " " + k + "=\"" + v + "\""
+					self.o("<"+tag+attrs_string+">")
             else:
-                self.o("")
+				if tag in ['em', 'i', 'u']: self.o("")
+				elif tag in ['strong', 'b']: self.o("")
+				else:
+					self.o("")
+					
             return None
 
         if options.google_doc:
@@ -448,6 +457,17 @@ def handle_tag(self, tag, attrs, start):
                 self.inheader = False
                 return # prevent redundant emphasis marks on headers
 
+        if tag in ['iframe', 'object', 'embed']:
+            if start:
+                attrs_string = ""
+                for k, v in attrs.items():
+                    if v == None:
+                       v = "None"
+                    attrs_string += " " + k + "=\"" + v + "\""
+                self.o("<"+tag+attrs_string+">")
+            else:
+                self.o("")
+
         if tag in ['p', 'div']:
             if options.google_doc:
                 if start and google_has_height(tag_style):
@@ -542,7 +562,7 @@ def handle_tag(self, tag, attrs, start):
                 if INLINE_LINKS:
                     self.o("![")
                     self.o(alt)
-                    self.o("]("+ attrs['href'] +")")
+                    self.o("]("+ attrs['href'] +")" +"\n") #AW!!: Added newline after image tag
                 else:
                     i = self.previousIndex(attrs)
                     if i is not None:
@@ -579,7 +599,7 @@ def handle_tag(self, tag, attrs, start):
             self.lastWasList = False
 
         if tag == 'li':
-            self.pbr()
+            self.p_p = 0  #AW!! Remove newlines and spaces within bullet or numbered list
             if start:
                 if self.list: li = self.list[-1]
                 else: li = {'name':'ul', 'num':0}

From 7d64037994f525bb7f645c9993f2b307753ea927 Mon Sep 17 00:00:00 2001
From: Arjan 
Date: Sun, 2 Oct 2022 09:44:28 +0200
Subject: [PATCH 2/5] Python3

---
 README.rst   |  2 +-
 config.yaml  |  2 +-
 exitwp.py    | 85 ++++++++++++++++++++++++++--------------------------
 html2text.py | 31 ++++++++++---------
 4 files changed, 60 insertions(+), 60 deletions(-)

diff --git a/README.rst b/README.rst
index 64d0343..6c3377c 100644
--- a/README.rst
+++ b/README.rst
@@ -25,7 +25,7 @@ Getting started
 
 Runtime dependencies
 ====================
- * `Python `_: Python 2
+ * `Python `_ 2.6, 2.7, ???
  * `html2text `_ :  converts HTML to markdown (python)
  * `PyYAML `_ : Reading configuration files and writing YAML headers (python)
  * `Beautiful soup `_ : Parsing and downloading of post images/attachments (python)
diff --git a/config.yaml b/config.yaml
index 43fe840..3afd815 100644
--- a/config.yaml
+++ b/config.yaml
@@ -16,7 +16,7 @@ target_format: markdown
 date_format: '%Y-%m-%d %H:%M:%S'
 
 # Try to download and reloacate all images locally to the blog.
-download_images: False
+download_images: True
 
 # Item types we don't want to import.
 item_type_filter: {attachment, nav_menu_item}
diff --git a/exitwp.py b/exitwp.py
index f18ecbc..d993d67 100755
--- a/exitwp.py
+++ b/exitwp.py
@@ -1,15 +1,15 @@
-#!/usr/bin/python2
+#!/usr/bin/env python3
 
 import codecs
 import os
 import re
 import sys
+import urllib.parse
 from datetime import datetime, timedelta, tzinfo
 from glob import glob
-from urllib import urlretrieve
-from urlparse import urljoin, urlparse
-from xml.etree.ElementTree import ElementTree, XMLTreeBuilder
-from urlparse import urlparse #AW!!
+from urllib.request import urlretrieve
+from urllib.parse import urljoin, urlparse
+from xml.etree.ElementTree import ElementTree, TreeBuilder, XMLParser
 
 import yaml
 from bs4 import BeautifulSoup
@@ -17,15 +17,15 @@
 from html2text import html2text_file
 
 '''
-exitwp - Wordpress xml exports to Jekykll blog format conversion
+exitwp - Wordpress xml exports to Hugo blog format conversion
 
-Tested with Wordpress 3.3.1 and jekyll 0.11.2
+Tested with Wordpress 3.3.1 and hugo 0.69
 
 '''
 ######################################################
 # Configration
 ######################################################
-config = yaml.safe_load(file('config.yaml', 'r'))
+config = yaml.safe_load(open('config.yaml', 'r'))
 wp_exports = config['wp_exports']
 build_dir = config['build_dir']
 download_images = config['download_images']
@@ -62,17 +62,14 @@ def tzname(self, dt):
     def dst(self, dt):
         return ZERO
 
-
-class ns_tracker_tree_builder(XMLTreeBuilder):
+class ns_tracker_tree_builder(TreeBuilder):
 
     def __init__(self):
-        XMLTreeBuilder.__init__(self)
-        self._parser.StartNamespaceDeclHandler = self._start_ns
+        TreeBuilder.__init__(self)
         self.namespaces = {}
 
-    def _start_ns(self, prefix, ns):
-        self.namespaces[prefix] = '{' + ns + '}'
-
+    def start_ns(self, prefix, uri):
+        self.namespaces[prefix] = '{' + uri + '}'
 
 def html2fmt(html, target_format):
     #   html = html.replace("\n\n", '

')
@@ -85,20 +82,21 @@ def html2fmt(html, target_format):
 
 
 def parse_wp_xml(file):
-    parser = ns_tracker_tree_builder()
+    tree_builder = ns_tracker_tree_builder()
+    parser = XMLParser(target=tree_builder)
     tree = ElementTree()
     log('reading: ' + wpe)
     root = tree.parse(file, parser)
-    ns = parser.namespaces
+    ns = tree_builder.namespaces
     ns[''] = ''
 
     c = root.find('channel')
 
     def parse_header():
         return {
-            'title': unicode(c.find('title').text),
-            'link': unicode(c.find('link').text),
-            'description': unicode(c.find('description').text)
+            'title': str(c.find('title').text),
+            'link': str(c.find('link').text),
+            'description': str(c.find('description').text)
         }
 
     def parse_items():
@@ -110,8 +108,8 @@ def parse_items():
             for tax in taxanomies:
                 if 'domain' not in tax.attrib:
                     continue
-                t_domain = unicode(tax.attrib['domain'])
-                t_entry = unicode(tax.text)
+                t_domain = str(tax.attrib['domain'])
+                t_entry = str(tax.text)
                 if (not (t_domain in taxonomy_filter) and
                     not (t_domain
                          in taxonomy_entry_filter and
@@ -129,13 +127,13 @@ def gi(q, unicode_wrap=True, empty=False):
                     tag = q
                 try:
                     result = i.find(ns[namespace] + tag).text
-                    #print result.encode('utf-8')
+                    #print(result.encode('utf-8'))
                 except AttributeError:
                     result = 'No Content Found'
                     if empty:
                         result = ''
                 if unicode_wrap:
-                    result = unicode(result)
+                    result = str(result)
                 return result
 
             body = gi('content:encoded')
@@ -152,7 +150,7 @@ def gi(q, unicode_wrap=True, empty=False):
                         img_srcs.append(img['src'])
                 except:
                     print('could not parse html: ' + body)
-            # print img_srcs
+            # print(img_srcs)
 
             excerpt = gi('excerpt:encoded', empty=True)
 
@@ -183,7 +181,7 @@ def gi(q, unicode_wrap=True, empty=False):
     }
 
 
-def write_jekyll(data, target_format):
+def write_hugo(data, target_format):
 
     if verbose:
         log('writing..')
@@ -202,7 +200,7 @@ def get_blog_path(data, path_infix='hugo'): #AW!! Changed jekyll path into hugo
 
     def get_full_dir(dir):
         full_dir = os.path.normpath(blog_dir + '/' + dir)
-        if not os.path.exists(full_dir):
+        if (not os.path.exists(full_dir)):
             os.makedirs(full_dir)
         return full_dir
 
@@ -219,7 +217,7 @@ def get_item_uid(item, date_prefix=False, namespace=''):
             result = item_uids[namespace][item['wp_id']]
         else:
             uid = []
-            if date_prefix:
+            if (date_prefix):
                 dt = datetime.strptime(item['date'], date_fmt)
                 uid.append(dt.strftime('%Y-%m-%d'))
                 uid.append('-')
@@ -242,9 +240,10 @@ def get_item_uid(item, date_prefix=False, namespace=''):
 
     def get_item_path(item, dir=''):
         full_dir = get_full_dir(dir)
-        filename_parts = [full_dir, '/', item['uid']]
+        filename_parts = [full_dir, '/']
+        filename_parts.append(item['uid'])
         if item['type'] == 'page':
-            if not os.path.exists(''.join(filename_parts)):
+            if (not os.path.exists(''.join(filename_parts))):
                 os.makedirs(''.join(filename_parts))
             filename_parts.append('/index')
         filename_parts.append('.')
@@ -275,22 +274,22 @@ def get_attachment_path(src, dir, dir_prefix='images'):
         target_dir = os.path.normpath(blog_dir + '/' + dir_prefix + '/' + dir)
         target_file = os.path.normpath(target_dir + '/' + filename)
 
-        if not os.path.exists(target_dir):
+        if (not os.path.exists(target_dir)):
             os.makedirs(target_dir)
 
         # if src not in attachments[dir]:
-        #     print target_name
+        #     print(target_name)
         return target_file
 
     for i in data['items']:
         skip_item = None
 
-        for field, value in item_field_filter.iteritems():
-            if i[field] == value:
+        for field, value in item_field_filter.items():
+            if(i[field] == value):
                 skip_item = value
                 break
 
-        if skip_item:
+        if(skip_item):
             log('  skipped(field=' + skip_item + ')/' + i['wp_id'] + ': ' + i['title'])
             continue
 
@@ -345,17 +344,19 @@ def get_attachment_path(src, dir, dir_prefix='images'):
 
         if download_images:
             for img in i['img_srcs']:
+                comp = urllib.parse.urlparse(img)
+                if comp[1] == '':
+                    comp._replace(netloc = data['header']['link'])
+                newurl = urllib.parse.urlunparse(comp)
                 try:
-                    urlretrieve(urljoin(data['header']['link'],
-                                        img.encode('utf-8')),
-                                get_attachment_path(img, i['uid']))
+                    urlretrieve(newurl,get_attachment_path(img, i['uid']))
                 except:
-                    print('\n unable to download ' + urljoin(data['header']['link'], img.encode('utf-8')))
+                    print( f'\n unable to download {newurl}')
 
         if out is not None:
             def toyaml(data):
                 return yaml.safe_dump(data, allow_unicode=True,
-                                      default_flow_style=False).decode('utf-8')
+                                      default_flow_style=False)
 
             tax_out = {}
             for taxonomy in i['taxanomies']:
@@ -381,7 +382,7 @@ def toyaml(data):
 
             out.close()
             log('  written/' + i['wp_id'] + ': ' + i['title'])
-    print( '\n')
+    print('\n')
 
 for arg in range(1, len(sys.argv)):
     if sys.argv[arg] == '-v':
@@ -393,6 +394,6 @@ def toyaml(data):
 wp_exports = glob(wp_exports + '/*.xml')
 for wpe in wp_exports:
     data = parse_wp_xml(wpe)
-    write_jekyll(data, target_format)
+    write_hugo(data, target_format)
 
 print('done')
diff --git a/html2text.py b/html2text.py
index 9609289..cc3d3fc 100755
--- a/html2text.py
+++ b/html2text.py
@@ -124,8 +124,8 @@ def unescape(s):
 def onlywhite(line):
     """Return true if the line does only consist of whitespace characters."""
     for c in line:
-        if c is not ' ' and c is not '  ':
-            return c is ' '
+        if (c != ' ') and (c != '  '):
+            return c == ' '
     return line
 
 def optwrap(text):
@@ -413,23 +413,22 @@ def handle_tag(self, tag, attrs, start):
         else:
             attrs = dict(attrs)
 
-		# AW!! This part is used for tags nested within a 
 tag
-		# For my website I decided to remove the  and  tags, but you can fill it in
+        # AW!! This part is used for tags nested within a 
 tag
+        # For my website I decided to remove the  and  tags, but you can fill it in
         if self.pre and not tag == "pre":
             if start:
-				if tag in ['em', 'i', 'u']: self.o("")    # "_"
-				elif tag in ['strong', 'b']: self.o("")   # "**"
-				else:
-					attrs_string = ""
-					for k, v in attrs.items():
-						attrs_string += " " + k + "=\"" + v + "\""
-					self.o("<"+tag+attrs_string+">")
+                if tag in ['em', 'i', 'u']: self.o("")    # "_"
+                elif tag in ['strong', 'b']: self.o("")   # "**"
+                else:
+                    attrs_string = ""
+                    for k, v in attrs.items():
+                        attrs_string += " " + k + "=\"" + v + "\""
+                    self.o("<"+tag+attrs_string+">")
             else:
-				if tag in ['em', 'i', 'u']: self.o("")
-				elif tag in ['strong', 'b']: self.o("")
-				else:
-					self.o("")
-					
+                if tag in ['em', 'i', 'u']: self.o("")
+                elif tag in ['strong', 'b']: self.o("")
+                else:
+                    self.o("")
             return None
 
         if options.google_doc:

From a4dae5d50060e39023f7e5d2c4650952856b0cc0 Mon Sep 17 00:00:00 2001
From: Hugo Schotman 
Date: Thu, 22 Aug 2024 13:47:10 +0200
Subject: [PATCH 3/5] Adaptations to include in the pull-request

---
 README.md            |  78 +++++
 README.rst           |  66 ----
 RELEASE_NOTES.md     |  60 ++++
 Vagrantfile          |  19 -
 config.yaml          |  71 +++-
 exitwp.py            | 376 +++++++++++++++-----
 html2text.py         | 811 -------------------------------------------
 pip_requirements.txt |  12 +-
 8 files changed, 504 insertions(+), 989 deletions(-)
 create mode 100644 README.md
 delete mode 100644 README.rst
 create mode 100644 RELEASE_NOTES.md
 delete mode 100644 Vagrantfile
 delete mode 100755 html2text.py

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..8fb301a
--- /dev/null
+++ b/README.md
@@ -0,0 +1,78 @@
+# ExitWP for Hugo
+
+This is an updated version of the ExitWP tool, originally created by Thomas Frössman for Jekyll and later adapted for Hugo by Arjan Wooning.
+
+For a detailed guide and background information, visit [Arjan Wooning's website](https://arjan.wooning.cz/conversion-tools-from-wordpress-to-hugo/#final-solution-exitwp-for-hugo).
+
+ExitWP is a tool designed to simplify the migration process from one or more WordPress blogs to the [Hugo static site generator](https://gohugo.io/). It aims to convert as much information as possible from WordPress, with options to filter the converted data.
+
+## Features
+
+- Converts WordPress export XML to Hugo-compatible Markdown or HTML
+- Downloads and processes images within posts
+- Supports inclusion of comments from WordPress posts
+- Handles tags and categories for Hugo
+- Flexible configuration options via `config.yaml`
+
+Please refer to the [Release notes](RELEASE_NOTES.md) (RELEASE_NOTES.md) for an overview of changes and updates.
+
+## Getting Started
+
+1. Clone the repository: `git clone https://github.com/wooni005/exitwp-for-hugo.git`
+2. Export your WordPress blog(s) using the WordPress exporter (Tools > Export in WordPress admin). Other website hosting sites, like [SquareSpace](https://squarespace.com/) also offer the option to export your site as WordPress formatted XML file(s).
+3. Place all WordPress XML files in the `wordpress-xml` directory
+4. Configure the tool by editing `config.yaml`
+5. Run the converter: `python3 exitwp.py`
+6. Optionally, if the script runs into issues, or the output does not appear to be correct, run `xmllint` [part of Libxml2](https://en.wikipedia.org/wiki/Libxml2) on your export file(s) and fix any errors.
+7. Your converted blog(s) will be in separate directories under the `build` directory, specified in `config.yaml`.
+
+## Dependencies
+
+- Python 3.x
+- markdownify
+- PyYAML
+- Beautiful Soup 4
+
+## Installing Dependencies
+
+```bash
+pip3 install -r requirements.txt
+```
+
+## Configuration
+
+Refer to the `config.yaml` file for all configurable options. Key settings include:
+
+- `wp_exports`: Directory containing WordPress export XML files
+- `build_dir`: Target directory for output
+- `download_images`: Whether to download and relocate images
+- `include_comments`: Option to include comments in the exported content
+- `target_format`: Choose between 'markdown' or 'html' output
+- `image_settings`: Configure image processing behavior
+
+## Usage
+
+Basic usage:
+
+```bash
+python3 exitwp.py
+```
+
+For verbose output:
+
+```bash
+python3 exitwp.py -v
+```
+
+## Known Issues and Limitations
+
+- Potential issues with non-UTF-8 encoded WordPress dump files
+- Image downloading may fail for some URLs due to various reasons (404 errors, timeouts, etc.)
+
+## Support
+
+This tool is not actively maintained. For support or custom modifications, consider using AI chatbots like ChatGPT or Claude.
+
+## Contributing
+
+If you've made significant improvements to the tool, feel free to submit a pull request.
diff --git a/README.rst b/README.rst
deleted file mode 100644
index 6c3377c..0000000
--- a/README.rst
+++ /dev/null
@@ -1,66 +0,0 @@
-###############
-ExitWP for Hugo
-###############
-
-This is a port of Thomas Frössman's ExitWP tool (for Jekyll).
-
-You can find also a howto and background information here on my website: https://arjan.wooning.cz/conversion-tools-from-wordpress-to-hugo/#final-solution-exitwp-for-hugo
-
-
-Exitwp is tool for making migration from one or more wordpress blogs to the `hugo blog engine `_ as easy as possible.
-
-By default it will try to convert as much information as possible from wordpress but can also be told to filter the amount of data it converts.
-
-The latest version of these docs should always be available at https://github.com/wooni005/exitwp-for-hugo
-
-Getting started
-===============
- * `Download `_ or clone using ``git clone https://github.com/wooni005/exitwp-for-hugo.git``
- * Export one or more wordpress blogs using the wordpress exporter under tools/export in wordpress admin.
- * Put all wordpress xml files in the ``wordpress-xml`` directory
- * Special note for Wordpress 3.1, you need to add a missing namespace in rss tag : ``xmlns:atom="http://www.w3.org/2005/Atom"``
- * Run xmllint on your export file and fix errors if there are.
- * Run the converter by typing ``./exitwp.py`` in the console from the directory of the unzipped archive
- * You should now have all the blogs converted into separate directories under the ``build`` directory
-
-Runtime dependencies
-====================
- * `Python `_ 2.6, 2.7, ???
- * `html2text `_ :  converts HTML to markdown (python)
- * `PyYAML `_ : Reading configuration files and writing YAML headers (python)
- * `Beautiful soup `_ : Parsing and downloading of post images/attachments (python)
-
-
-Installing dependencies in ubuntu/debian
-----------------------------------------
-
-   ``sudo apt-get install python-yaml python-bs4 python-html2text``
-
-Installing Python dependencies using python package installer (pip)
--------------------------------------------------------------------
-
-From the checked out root for this project, type:
-
-   ``sudo pip install --upgrade  -r pip_requirements.txt``
-
-Note that PyYAML will require other packages to compile correctly under ubuntu/debian, these are installed by typing:
-
-   ``sudo apt-get install libyaml-dev python-dev build-essential``
-
-
-Configuration/Customization
-===========================
-
-See the `configuration file `_ for all configurable options.
-
-Some things like custom handling of non standard post types is not fully configurable through the config file. You might have to modify the `source code `_ to add custom parsing behaviour.
-
-Known issues
-============
- * Target file names are some times less than optimal.
- * Rewriting of image/attachment links if they are downloaded would be a good feature
- * There will probably be issues when migrating non utf-8 encoded wordpress dump files (if they exist).
-
-Other Tools
-===========
- * A Gist to convert WP-Footnotes style footnotes to PHP Markdown Extra style footnotes: https://gist.github.com/1246047
diff --git a/RELEASE_NOTES.md b/RELEASE_NOTES.md
new file mode 100644
index 0000000..8871ba8
--- /dev/null
+++ b/RELEASE_NOTES.md
@@ -0,0 +1,60 @@
+# Changelog and Release Notes
+
+# August 2024
+
+## exitwp.py
+
+### Major Changes
+- Replaced html2text_file with markdownify for HTML to Markdown conversion
+- Added support for downloading and processing images within posts
+- Implemented comment extraction and inclusion in the output
+- Added support for tags and categories handling
+- Improved error handling and logging
+
+### New Features
+- Image processing: Downloads images, saves them locally, and updates image URLs in the content
+- Comment handling: Extracts and includes comments in the output markdown files
+- Tags and categories: Properly handles WordPress tags and categories, mapping them to Hugo format
+- Timezone handling: Added support for CET timezone
+
+### Improvements
+- Enhanced YAML header generation for Hugo compatibility
+- Improved date parsing and handling
+- Better error logging and verbose output options
+- Refactored code for better readability and maintainability
+
+### Bug Fixes
+- Fixed issues with Unicode handling
+- Addressed potential errors in parsing XML and HTML content
+
+## config.yaml
+
+### New Options
+- Added `tags_label` option to specify the label for tags/categories in the output
+- Introduced `include_comments` option to control whether comments are included in the export
+
+### Changes
+- Refined `taxonomies` configuration to better handle tags and categories
+- Updated `body_replace` patterns for improved content transformation
+
+### Improvements
+- Added more detailed comments and explanations for configuration options
+
+## Overall Improvements
+
+1. Better Hugo Compatibility: The updated script now generates output more closely aligned with Hugo's expectations.
+2. Enhanced Image Handling: Improved downloading and processing of images within posts.
+3. Comment Support: Added the ability to include WordPress comments in the exported content.
+4. Improved Taxonomy Handling: Better management of tags and categories for Hugo.
+5. More Flexible Configuration: Additional options in config.yaml for finer control over the export process.
+
+## Upgrade Notes
+
+When upgrading to this new version:
+
+1. Review the new configuration options in config.yaml and adjust as needed for your use case.
+2. Be aware of the change from html2text to markdownify for HTML to Markdown conversion.
+3. Test the script with a small subset of your content first to ensure compatibility with your specific WordPress export.
+4. Pay attention to the new image handling and comment inclusion features, adjusting settings as necessary.
+
+This update significantly improves the WordPress to Hugo migration process, offering more features and better compatibility with Hugo's content structure.
diff --git a/Vagrantfile b/Vagrantfile
deleted file mode 100644
index bdd2794..0000000
--- a/Vagrantfile
+++ /dev/null
@@ -1,19 +0,0 @@
-# -*- mode: ruby -*-
-# vi: set ft=ruby :
-
-$script = <