././@PaxHeader0000000000000000000000000000003300000000000010211 xustar0027 mtime=1744689734.577402 html2text-2025.4.15/0000755000175100001660000000000014777355107013410 5ustar00runnerdocker././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0 html2text-2025.4.15/.gitattributes0000644000175100001660000000010614777355103016274 0ustar00runnerdocker* text eol=lf *.bat text eol=crlf *.png -text *.pdf -text ././@PaxHeader0000000000000000000000000000003400000000000010212 xustar0028 mtime=1744689734.5434015 html2text-2025.4.15/.github/0000755000175100001660000000000014777355107014750 5ustar00runnerdocker././@PaxHeader0000000000000000000000000000003400000000000010212 xustar0028 mtime=1744689734.5464015 html2text-2025.4.15/.github/workflows/0000755000175100001660000000000014777355107017005 5ustar00runnerdocker././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0 html2text-2025.4.15/.github/workflows/main.yml0000644000175100001660000000503014777355103020446 0ustar00runnerdockername: CI # Controls when the action will run. on: # Triggers the workflow on push or pull request events but only for the master branch push: branches: [ master ] pull_request: branches: [ master ] # Allows you to run this workflow manually from the Actions tab workflow_dispatch: jobs: code-quality: runs-on: ubuntu-latest strategy: matrix: toxenv: - black - flake8 - mypy - isort env: TOXENV: ${{ matrix.toxenv }} name: "Tox ${{ matrix.toxenv }}" steps: # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it - uses: actions/checkout@v4 with: fetch-depth: 0 - name: setup python uses: actions/setup-python@v5 with: python-version: '3.13' - name: Install Requirements [${{ matrix.toxenv }}] run: pip install tox - name: Tox-${{ matrix.toxenv }} run: tox # This workflow contains a single job called "build" test: # The type of runner that the job will run on runs-on: ubuntu-latest strategy: matrix: toxenv: - py39 - py310 - py311 - py312 - py313 include: - toxenv: py39 python-version: '3.9' - toxenv: py310 python-version: '3.10' - toxenv: py311 python-version: '3.11' - toxenv: py312 python-version: '3.12' - toxenv: py313 python-version: '3.13' env: GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} TOXENV: ${{ matrix.toxenv }} name: "Python ${{ matrix.python-version }} | Tox ${{ matrix.toxenv }}" # Steps represent a sequence of tasks that will be executed as part of the job steps: # Checks-out your repository under $GITHUB_WORKSPACE, so your job can access it - uses: actions/checkout@v4 with: fetch-depth: 2 - name: setup python uses: actions/setup-python@v5 with: python-version: ${{ matrix.python-version }} - name: Install Requirements [Python-${{ matrix.python-version }}] run: pip install tox - name: Tox-${{ matrix.toxenv }} run: tox - name: Upload coverage to Codecov uses: codecov/codecov-action@v5 with: flags: unittests-${{ matrix.python-version }} token: ${{ secrets.CODECOV_TOKEN }} fail_ci_if_error: true # default = false verbose: true # default = false ././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0 html2text-2025.4.15/.github/workflows/pypi.yml0000644000175100001660000000124014777355103020502 0ustar00runnerdockername: Publish to PyPI on: release: types: [released] jobs: release: name: Release environment: name: pypi url: https://pypi.org/project/html2text permissions: id-token: write runs-on: ubuntu-latest steps: - name: Checkout code uses: actions/checkout@v4 - uses: actions/setup-python@v5 with: python-version: '3.13' - name: Build run: | python -m pip install build python -m build - name: Publish package distributions to PyPI uses: pypa/gh-action-pypi-publish@release/v1 with: verbose: true print-hash: true ././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0 html2text-2025.4.15/.gitignore0000644000175100001660000000022414777355103015372 0ustar00runnerdocker/html2text/_version.py *.py[co] *.bak build dist *.egg-info .idea .coverage .coverage.* coverage.xml env/ .c9/ .vscode .tox/ htmlcov/ .mypy_cache/ ././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0 html2text-2025.4.15/AUTHORS.rst0000644000175100001660000000256014777355103015266 0ustar00runnerdocker``html2text`` was originally written by Aaron Swartz. The AUTHORS/Contributors are (and/or have been): * Aaron Swartz * Yariv Barkan * Alex Musayev * Matěj Cepl * Stefano Rivera * Alireza Savand * Ivan Gromov * Jocelyn Delalande * Matt Dorn * Miguel Tavares * Scott Blackburn * Peter Wu * Arjoonn Sharma * Ali Mohammad * Albert Berger * Etienne Millon * John C F * Mikhail Melnik * Andres Rey * Ciprian Miclaus * Toshihiro Kamiya * Matt Dennewitz * Jonathan Sundqvist * Simon Meers * Kurt McKee * Germain Z. * Jacek Kołodziej * Jonathan Vanasco * Jon Dufresne * Edward Ross * Mike Borsetti * Gregory Anders * Maciej Podolski * Ludovic VAUGEOIS PEPIN * Ryan Barrett * Edward Ross * Gregory Anders * Alex Vandiver Maintainer: * Alireza Savand ././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0 html2text-2025.4.15/COPYING0000644000175100001660000010451314777355103014443 0ustar00runnerdocker 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 . ././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0 html2text-2025.4.15/ChangeLog.rst0000644000175100001660000002122114777355103015763 0ustar00runnerdocker2025.4.15 ========= ---- * Fix #418: Publishing wheels to PyPI. * Feature #386: Support tri-backquote style code block and fix ordered list indent. * Fix #310: Fix invalid character reference parsing. * #436 & #396: Modernization of wheel building process. 2024.2.26 ========= ---- * Fixes #409: IndexError on empty strong mark. 2024.2.25 ========= ---- * Fix #332: Insert at most one space for multiple emphasis * Feature #318: Make padded tables more similar to pandoc's pipe_tables. * Add support for Python 3.9. * Fix extra line breaks inside html link text (between '[' and ']') * Fix #344: indent ``
    `` inside ``
      `` three spaces instead of two to comply with CommonMark, GFM, etc. * Fix #324: unnecessary spaces around ````, ````, and ``strike`` tags. * Don't wrap tables by default and add a ``--wrap-tables`` config option. * Feature #198: Ignore ``

      `` tags inside table rows. * Don't wrap tables by default and add a ``--wrap-tables`` config option * Remove support for Python ≤ 3.5. Now requires Python 3.6+. * Support for Python 3.10+. * Fix #320 padding empty tables and tables with no ```` tags. * Add ``ignore_mailto_links`` config option to ignore ``mailto:`` style links. * Feature #407: Support the superscript and subscript tags. * Fix #373: ``\n`` inside text of a Markdown link. * Feature #406: Improve support for null atttibute values. 2020.1.16 ========= ---- * Add type annotations. * Add support for Python 3.8. * Performance improvements when ``wrap_links`` is ``False`` (the default). * Configure setuptools using setup.cfg. 2019.9.26 ========= ---- * Fix long blockquotes wrapping. * Remove the trailing whitespaces that were added after wrapping list items & blockquotes. * Remove support for Python ≤ 3.4. Now requires Python 3.5+. * Fix memory leak when processing a document containing a ```` tag. * Fix ``AttributeError`` when reading text from stdin. * Fix ``UnicodeEncodeError`` when writing output to stdout. 2019.8.11 ========= ---- * Add support for wrapping list items. * Fix #201: handle ‎/‏ marks mid-text within stressed tags or right after stressed tags. * Feature #213: ``images_as_html`` config option to always generate an ``img`` html tag. preserves "height", "width" and "alt" if possible. * Remove support for end-of-life Pythons. Now requires Python 2.7 or 3.4+. * Remove support for retrieving HTML over the network. * Add ``__main__.py`` module to allow running the CLI using ``python -m html2text ...``. * Fix #238: correct spacing when a HTML entity follows a non-stressed tags which follow a stressed tag. * Remove unused or deprecated: * ``html2text.compat.escape()`` * ``html2text.config.RE_UNESCAPE`` * ``html2text.HTML2Text.replaceEntities()`` * ``html2text.HTML2Text.unescape()`` * ``html2text.unescape()`` * Fix #208: handle LEFT-TO-RIGHT MARK after a stressed tag. 2018.1.9 ======== ---- * Fix #188: Non-ASCII in title attribute causes encode error. * Feature #194: Add support for the tag. * Feature #193: Add support for the tag. 2017.10.4 ========== ---- * Fix #157: Fix images link with div wrap * Fix #55: Fix error when empty title tags * Fix #160: The html2text tests are failing on Windows and on Cygwin due to differences in eol handling between windows/*nix * Feature #164: Housekeeping: Add flake8 to the travis build, cleanup existing flake8 violations, add py3.6 and pypy3 to the travis build * Fix #109: Fix for unexpanded < > & * Fix #143: Fix line wrapping for the lines starting with bold * Adds support for numeric bold text indication in ``font-weight``, as used by Google (and presumably others.) * Fix #173 and #142: Stripping whitespace in crucial markdown and adding whitespace as necessary * Don't drop any cell data on tables uneven row lengths (e.g. colspan in use) 2016.9.19 ========= ---- * Default image alt text option created and set to a default of empty string "" to maintain backward compatibility * Fix #136: --default-image-alt now takes a string as argument * Fix #113: Stop changing quiet levels on \/script tags. * Merge #126: Fix deprecation warning on py3 due to html.escape * Fix #145: Running test suite on Travis CI for Python 2.6. 2016.5.29 ========= ---- * Fix #125: --pad_tables now pads table cells to make them look nice. * Fix #114: Break does not interrupt blockquotes * Deprecation warnings for URL retrieval. 2016.4.2 ========= ---- * Fix #106: encoding by stdin * Fix #89: Python 3.5 support. * Fix #113: inplace baseurl substitution for and tags. * Feature #118: Update the badges to badge.kloud51.com * Fix #119: new-line after a list is inserted 2016.1.8 ========= ---- * Feature #99: Removed duplicated initialisation. * Fix #100: Get element style key error. * Fix #101: Fix error end tag pop exception * , , now rendered as ~~text~~. 2015.11.4 ========= ---- * Fix #38: Long links wrapping controlled by ``--no-wrap-links``. * Note: ``--no-wrap-links`` implies ``--reference-links`` * Feature #83: Add callback-on-tag. * Fix #87: Decode errors can be handled via command line. * Feature #95: Docs, decode errors spelling mistake. * Fix #84: Make bodywidth kwarg overridable using config. 2015.6.21 ========= ---- * Fix #31: HTML entities stay inside link. * Fix #71: Coverage detects command line tests. * Fix #39: Documentation update. * Fix #61: Functionality added for optional use of automatic links. * Feature #80: ``title`` attribute is preserved in both inline and reference links. * Feature #82: More command line options. See docs. 2015.6.12 ========= ---- * Feature #76: Making ``pre`` blocks clearer for further automatic formatting. * Fix #71: Coverage detects tests carried out in ``subprocesses`` 2015.6.6 ======== ---- * Fix #24: ``3.200.3`` vs ``2014.7.3`` output quirks. * Fix #61. Malformed links in markdown output. * Feature #62: Automatic version number. * Fix #63: Nested code, anchor bug. * Fix #64: Proper handling of anchors with content that starts with tags. * Feature #67: Documentation all over the module. * Feature #70: Adding tests for the module. * Fix #73: Typo in config documentation. 2015.4.14 ========= ---- * Feature #59: Write image tags with height and width attrs as raw html to retain dimensions 2015.4.13 ========= ---- * Feature #56: Treat '-' file parameter as stdin. * Feature #57: Retain escaping of html except within code or pre tags. 2015.2.18 ========= ---- * Fix #38: Anchor tags with empty text or with ```` tags inside are no longer stripped. 2014.12.29 ========== ---- * Feature #51: Add single line break option. This feature is useful for ensuring that lots of extra line breaks do not end up in the resulting Markdown file in situations like Evernote .enex exports. Note that this only works properly if ``body-width`` is set to ``0``. 2014.12.24 ========== ---- * Feature #49: Added an images_to_alt option to discard images and keep only their alt. * Feature #50: Protect links, surrounding them with angle brackets to avoid breaking... * Feature: Add ``setup.cfg`` file. 2014.12.5 ========= ---- * Feature: Update ``README.md`` with usage examples. * Fix #35: Remove ``py_modules`` from ``setup.py``. * Fix #36: Excludes tests from being installed as a separate module. * Fix #37: Don't hardcode the path to the installed binary. * Fix: Readme typo in running cli. * Feature #40: Extract cli part to ``cli`` module. * Feature #42: Bring python version compatibility to ``compat.py`` module. * Feature #41: Extract utility/helper methods to ``utils`` module. * Fix #45: Does not accept standard input when running under Python 3. * Feature: Clean up ``ChangeLog.rst`` for version and date numbers. 2014.9.25 ========= ---- * Feature #29, #27: Add simple table support with bypass option. * Fix #20: Replace project website with: https://alir3z4.github.io/html2text/ . 2014.9.8 ======== ---- * Fix #28: missing ``html2text`` package in installation. 2014.9.7 ======== ---- * Fix ``unicode``/``type`` error in memory leak unit-test. * Feature #16: Remove ``install_deps.py``. * Feature #17: Add status badges via pypin. * Feature #18: Add ``Python`` ``3.4`` to travis config file. * Feature #19: Bring ``html2text`` to a separate module and take out the ``conf``/``constant`` variables. * Feature #21: Remove meta vars from ``html2text.py`` file header. * Fix: Fix TypeError when parsing tags like . Fixed in #25. 2014.7.3 ======== ---- * Fix #8: Remove ``How to do a release`` section from README.md. * Fix #11: Include test directory markdown, html files. * Fix #13: memory leak in using ``handle`` while keeping the old instance of ``html2text``. 2014.4.5 ======== ---- * Fix #1: Add ``ChangeLog.rst`` file. * Fix #2: Add ``AUTHORS.rst`` file. ././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0 html2text-2025.4.15/ISSUE_TEMPLATE0000644000175100001660000000012714777355103015512 0ustar00runnerdocker - Version by `html2text --version` - Test script - Python version `python --version` ././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0 html2text-2025.4.15/MANIFEST.in0000644000175100001660000000020414777355103015136 0ustar00runnerdockerinclude COPYING include README.md include ChangeLog.rst include AUTHORS.rst include tox.ini recursive-include test *.html *.md *.py ././@PaxHeader0000000000000000000000000000003300000000000010211 xustar0027 mtime=1744689734.577402 html2text-2025.4.15/PKG-INFO0000644000175100001660000001006114777355107014503 0ustar00runnerdockerMetadata-Version: 2.4 Name: html2text Version: 2025.4.15 Summary: Turn HTML into equivalent Markdown-structured text. Author-email: Aaron Swartz Maintainer-email: Alireza Savand License-Expression: GPL-3.0-or-later Project-URL: Homepage, https://github.com/Alir3z4/html2text/ Platform: OS Independent Classifier: Development Status :: 5 - Production/Stable Classifier: Intended Audience :: Developers Classifier: Operating System :: OS Independent Classifier: Programming Language :: Python Classifier: Programming Language :: Python :: 3 Classifier: Programming Language :: Python :: 3.9 Classifier: Programming Language :: Python :: 3.10 Classifier: Programming Language :: Python :: 3.11 Classifier: Programming Language :: Python :: 3.12 Classifier: Programming Language :: Python :: 3.13 Classifier: Programming Language :: Python :: 3 :: Only Classifier: Programming Language :: Python :: Implementation :: CPython Classifier: Programming Language :: Python :: Implementation :: PyPy Requires-Python: >=3.9 Description-Content-Type: text/markdown License-File: COPYING License-File: AUTHORS.rst Dynamic: license-file # html2text [![CI](https://github.com/Alir3z4/html2text/actions/workflows/main.yml/badge.svg?branch=master)](https://github.com/Alir3z4/html2text/actions/workflows/main.yml) [![codecov](https://codecov.io/gh/Alir3z4/html2text/graph/badge.svg?token=OoxiyymjgU)](https://codecov.io/gh/Alir3z4/html2text) html2text is a Python script that converts a page of HTML into clean, easy-to-read plain ASCII text. Better yet, that ASCII also happens to be valid Markdown (a text-to-HTML format). Usage: `html2text [filename [encoding]]` | Option | Description |--------------------------------------------------------|--------------------------------------------------- | `--version` | Show program's version number and exit | `-h`, `--help` | Show this help message and exit | `--ignore-links` | Don't include any formatting for links |`--escape-all` | Escape all special characters. Output is less readable, but avoids corner case formatting issues. | `--reference-links` | Use reference links instead of links to create markdown | `--mark-code` | Mark preformatted and code blocks with [code]...[/code] For a complete list of options see the [docs](https://github.com/Alir3z4/html2text/blob/master/docs/usage.md) Or you can use it from within `Python`: ``` >>> import html2text >>> >>> print(html2text.html2text("

      Zed's dead baby, Zed's dead.

      ")) **Zed's** dead baby, _Zed's_ dead. ``` Or with some configuration options: ``` >>> import html2text >>> >>> h = html2text.HTML2Text() >>> # Ignore converting links from HTML >>> h.ignore_links = True >>> print h.handle("

      Hello, world!") Hello, world! >>> print(h.handle("

      Hello, world!")) Hello, world! >>> # Don't Ignore links anymore, I like links >>> h.ignore_links = False >>> print(h.handle("

      Hello, world!")) Hello, [world](https://www.google.com/earth/)! ``` *Originally written by Aaron Swartz. This code is distributed under the GPLv3.* ## How to install `html2text` is available on pypi https://pypi.org/project/html2text/ ```shell $ pip install html2text ``` ## Development ### How to run unit tests ```shell $ tox ``` To see the coverage results: ```shell $ coverage html ``` then open the `./htmlcov/index.html` file in your browser. ### Code Quality & Pre Commit The CI runs several linting steps, including: - mypy - Flake8 - Black To make sure the code passes the CI linting steps, run: ```shell $ tox -e pre-commit ``` ## Documentation Documentation lives [here](https://github.com/Alir3z4/html2text/blob/master/docs/usage.md) ././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0 html2text-2025.4.15/README.md0000644000175100001660000000564114777355103014671 0ustar00runnerdocker# html2text [![CI](https://github.com/Alir3z4/html2text/actions/workflows/main.yml/badge.svg?branch=master)](https://github.com/Alir3z4/html2text/actions/workflows/main.yml) [![codecov](https://codecov.io/gh/Alir3z4/html2text/graph/badge.svg?token=OoxiyymjgU)](https://codecov.io/gh/Alir3z4/html2text) html2text is a Python script that converts a page of HTML into clean, easy-to-read plain ASCII text. Better yet, that ASCII also happens to be valid Markdown (a text-to-HTML format). Usage: `html2text [filename [encoding]]` | Option | Description |--------------------------------------------------------|--------------------------------------------------- | `--version` | Show program's version number and exit | `-h`, `--help` | Show this help message and exit | `--ignore-links` | Don't include any formatting for links |`--escape-all` | Escape all special characters. Output is less readable, but avoids corner case formatting issues. | `--reference-links` | Use reference links instead of links to create markdown | `--mark-code` | Mark preformatted and code blocks with [code]...[/code] For a complete list of options see the [docs](https://github.com/Alir3z4/html2text/blob/master/docs/usage.md) Or you can use it from within `Python`: ``` >>> import html2text >>> >>> print(html2text.html2text("

      Zed's dead baby, Zed's dead.

      ")) **Zed's** dead baby, _Zed's_ dead. ``` Or with some configuration options: ``` >>> import html2text >>> >>> h = html2text.HTML2Text() >>> # Ignore converting links from HTML >>> h.ignore_links = True >>> print h.handle("

      Hello, world!") Hello, world! >>> print(h.handle("

      Hello, world!")) Hello, world! >>> # Don't Ignore links anymore, I like links >>> h.ignore_links = False >>> print(h.handle("

      Hello, world!")) Hello, [world](https://www.google.com/earth/)! ``` *Originally written by Aaron Swartz. This code is distributed under the GPLv3.* ## How to install `html2text` is available on pypi https://pypi.org/project/html2text/ ```shell $ pip install html2text ``` ## Development ### How to run unit tests ```shell $ tox ``` To see the coverage results: ```shell $ coverage html ``` then open the `./htmlcov/index.html` file in your browser. ### Code Quality & Pre Commit The CI runs several linting steps, including: - mypy - Flake8 - Black To make sure the code passes the CI linting steps, run: ```shell $ tox -e pre-commit ``` ## Documentation Documentation lives [here](https://github.com/Alir3z4/html2text/blob/master/docs/usage.md) ././@PaxHeader0000000000000000000000000000003400000000000010212 xustar0028 mtime=1744689734.5474017 html2text-2025.4.15/docs/0000755000175100001660000000000014777355107014340 5ustar00runnerdocker././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0 html2text-2025.4.15/docs/about.md0000644000175100001660000000063214777355103015771 0ustar00runnerdockerAbout ----- html2text is a python package which converts a page of HTML into clean, easy-to-read plain ASCII text. Better yet, that ASCII also happens to be valid Markdown (a text-to-HTML format). It was originally written by Aaron Swartz. The code is under GPL v3. The module is based on the html parser in the python standard library and so any valid input for the parser is valid input for the library. ././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0 html2text-2025.4.15/docs/authors.md0000644000175100001660000000256014777355103016346 0ustar00runnerdocker``html2text`` was originally written by Aaron Swartz. The AUTHORS/Contributors are (and/or have been): * Aaron Swartz * Yariv Barkan * Alex Musayev * Matěj Cepl * Stefano Rivera * Alireza Savand * Ivan Gromov * Jocelyn Delalande * Matt Dorn * Miguel Tavares * Scott Blackburn * Peter Wu * Arjoonn Sharma * Ali Mohammad * Albert Berger * Etienne Millon * John C F * Mikhail Melnik * Andres Rey * Ciprian Miclaus * Toshihiro Kamiya * Matt Dennewitz * Jonathan Sundqvist * Simon Meers * Kurt McKee * Germain Z. * Jacek Kołodziej * Jonathan Vanasco * Jon Dufresne * Edward Ross * Mike Borsetti * Gregory Anders * Maciej Podolski * Ludovic VAUGEOIS PEPIN * Ryan Barrett * Edward Ross * Gregory Anders * Alex Vandiver Maintainer: * Alireza Savand ././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0 html2text-2025.4.15/docs/contributing.md0000644000175100001660000000051714777355103017370 0ustar00runnerdockerPull requests are welcome. The package is developed [here](https://github.com/Alir3z4/html2text) Pull guidelines --------------- - Make the changes modular. The usual method is one change per commit. - Add tests. (We love tests). - Update the ``ChangeLog.rst``. - Add yourself to ``AUTHORS.rst`` if you're not listed. - That is all ././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0 html2text-2025.4.15/docs/how_it_works.md0000644000175100001660000001460014777355103017375 0ustar00runnerdockerIntroduction ============ There are 5 components to the code. They are kept as separate files in the html2text directory. This part of the documentation explains them bit by bit. compat.py --------- This part exists only to test compatibility with the available python standard libraries. Python3 relocated some libraries and so this file makes sure that everything has a common interface. config.py --------- Used to provide various configuration settings to the converter. They are as follows: - UNICODE_SNOB for using unicode - ESCAPE_SNOB for escaping every special character - LINKS_EACH_PARAGRAPH for putting links after every paragraph - BODY_WIDTH for wrapping long lines - SKIP_INTERNAL_LINKS to skip #local-anchor things - INLINE_LINKS for formatting images and links - PROTECT_LINKS protect from line breaks - GOOGLE_LIST_INDENT no of pixels to indent nested lists - IGNORE_ANCHORS - IGNORE_IMAGES - IMAGES_AS_HTML always generate HTML tags for images; preserves `height`, `width`, `alt` if possible. - IMAGES_TO_ALT - IMAGES_WITH_SIZE - IGNORE_EMPHASIS - BYPASS_TABLES format tables in HTML rather than Markdown - IGNORE_TABLES ignore table-related tags (table, th, td, tr) while keeping rows - SINGLE_LINE_BREAK to use a single line break rather than two - UNIFIABLE is a dictionary which maps unicode abbreviations to ASCII values - RE_SPACE for finding space-only lines - RE_ORDERED_LIST_MATCHER for matching ordered lists in MD - RE_UNORDERED_LIST_MATCHER for matching unordered list matcher in MD - RE_MD_CHARS_MATCHER for matching Md \,[,],( and ) - RE_MD_CHARS_MATCHER_ALL for matching `,*,_,{,},[,],(,),#,! - RE_MD_DOT_MATCHER for matching lines starting with 1. - RE_MD_PLUS_MATCHER for matching lines starting with + - RE_MD_DASH_MATCHER for matching lines starting with (-) - RE_SLASH_CHARS a string of slash escapeable characters - RE_MD_BACKSLASH_MATCHER to match \char - USE_AUTOMATIC_LINKS to convert http://xyz to utils.py -------- Used to provide utility functions to html2text Some functions are: - name2cp :name to code point - hn :headings - dumb_property_dict :hash of css attrs - dumb_css_parser :returns a hash of css selectors, each containing a hash of css attrs - element_style :hash of final style of element - google_list_style :find out ordered?unordered - google_has_height :does element have height? - google_text_emphasis :a list of all emphasis modifiers - google_fixed_width_font :check for fixed width font - list_numbering_start :extract numbering from list elem attrs - skipwrap :skip wrap for give para or not? - escape_md :escape md sensitive within other md - escape_md_section :escape md sensitive across whole doc cli.py ------ Command line interface for the code. | Option | Description |--------------------------------------------------------|--------------------------------------------------- | `--version` | Show program version number and exit | `-h`, `--help` | Show this help message and exit | `--ignore-links` | Do not include any formatting for links |`--protect-links` | Protect links from line breaks surrounding them "+" with angle brackets |`--ignore-images` | Do not include any formatting for images |`--images-to-alt` | Discard image data, only keep alt text |`--images-with-size` | Write image tags with height and width attrs as raw html to retain dimensions |`--images-as-html` | Always write image tags as raw html; preserves "height", "width" and "alt" if possible. |`-g`, `--google-doc` | Convert an html-exported Google Document |`-d`, `--dash-unordered-list` | Use a dash rather than a star for unordered list items |`-b` `BODY_WIDTH`, `--body-width`=`BODY_WIDTH` | Number of characters per output line, `0` for no wrap |`-i` `LIST_INDENT`, `--google-list-indent`=`LIST_INDENT`| Number of pixels Google indents nested lists |`-s`, `--hide-strikethrough` | Hide strike-through text. only relevant when `-g` is specified as well |`--escape-all` | Escape all special characters. Output is less readable, but avoids corner case formatting issues. | `--bypass-tables` | Format tables in HTML rather than Markdown syntax. | `--ignore-tables` | Ignore table-related tags (table, th, td, tr) while keeping rows. | `--single-line-break` | Use a single line break after a block element rather than two. | `--reference-links` | Use reference links instead of inline links to create markdown *A complete list is available [here](usage.md)* __init__.py ----------- This is where everything comes together. This is the glue for all the things we have described above. This file describes a single HTML2Text class which is itself a subclass of the HTMLParser in python Upon initialization it sets various config variables necessary for processing the given html in a certain manner necessary to create valid markdown text. The class defines methods: - feed - handle - outtextf - close - handle_charref - handle_entityref - handle_starttag - handle_endtag - previousIndex - handle_emphasis - handle_tag - pbr - p - soft_br - o - handle_data - charref - entityref - google_nest_count - optwrap Besides this there are 2 more methods defined: - html2text :calls the HTML2Text class with .handle() method - unescape :calls the HTML2Text class with .unescape() method What they do is provide methods to make the HTML parser in python parse the HTML and convert to markdown. ././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0 html2text-2025.4.15/docs/index.md0000644000175100001660000000037314777355103015770 0ustar00runnerdockerHtml2Text ========= 1. [About](about.md) 2. [Authors](../AUTHORS.rst) 3. [What is markdown](https://daringfireball.net/projects/markdown/) 4. [How it works](how_it_works.md) 5. [Usage](usage.md) 6. [Contributing](contributing.md) 7. [Tests](test.md) ././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0 html2text-2025.4.15/docs/test.md0000644000175100001660000000044614777355103015641 0ustar00runnerdockerTests ===== Testing is essential. Run the tests ------------- `tox` Coverage results can be seen with `coverage html` and then opening the `./htmlcov/index.html` file with your browser. New tests --------- New tests are always welcome see [contributing](contributing.md) for guidelines. ././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0 html2text-2025.4.15/docs/usage.md0000644000175100001660000002010514777355103015760 0ustar00runnerdockerUsage ===== The module is simple enough to use. This tutorial will get you started. Installing ---------- These are the methods you can get the module installed:- ### PIP For those who have pip, we got your back. ``` $ pip install html2text ``` ### Clone from Git Repository Clone the repository from https://github.com/Alir3z4/html2text ``` $ git clone --depth 50 https://github.com/Alir3z4/html2text.git $ python -m build -nwx $ python -m pip install --upgrade ./dist/*.whl ``` Basic Usage ----------- Once installed the module can be used as follows. import html2text html = function_to_get_some_html() text = html2text.html2text(html) print(text) This converts the provided html to text( Markdown text) with all the options set to default. Using Options -------------- To customize the options provided by the module the usage is as follows: import html2text text_maker = html2text.HTML2Text() text_maker.ignore_links = True text_maker.bypass_tables = False html = function_to_get_some_html() text = text_maker.handle(html) print(text) Available Options ----------------- All options exist in the config.py file. A list is provided here with simple indications of their function. - UNICODE_SNOB for using unicode - ESCAPE_SNOB for escaping every special character - LINKS_EACH_PARAGRAPH for putting links after every paragraph - BODY_WIDTH for wrapping long lines - SKIP_INTERNAL_LINKS to skip #local-anchor things - INLINE_LINKS for formatting images and links - PROTECT_LINKS protect from line breaks - GOOGLE_LIST_INDENT no of pixels to indent nested lists - IGNORE_ANCHORS - IGNORE_IMAGES - IMAGES_AS_HTML always generate HTML tags for images; preserves `height`, `width`, `alt` if possible. - IMAGES_TO_ALT - IMAGES_WITH_SIZE - IGNORE_EMPHASIS - BYPASS_TABLES format tables in HTML rather than Markdown - IGNORE_TABLES ignore table-related tags (table, th, td, tr) while keeping rows - SINGLE_LINE_BREAK to use a single line break rather than two - UNIFIABLE is a dictionary which maps unicode abbreviations to ASCII values - RE_SPACE for finding space-only lines - RE_ORDERED_LIST_MATCHER for matching ordered lists in MD - RE_UNORDERED_LIST_MATCHER for matching unordered list matcher in MD - RE_MD_CHARS_MATCHER for matching Md \,[,],( and ) - RE_MD_CHARS_MATCHER_ALL for matching `,*,_,{,},[,],(,),#,! - RE_MD_DOT_MATCHER for matching lines starting with 1. - RE_MD_PLUS_MATCHER for matching lines starting with + - RE_MD_DASH_MATCHER for matching lines starting with (-) - RE_SLASH_CHARS a string of slash escapeable characters - RE_MD_BACKSLASH_MATCHER to match \char - USE_AUTOMATIC_LINKS to convert http://xyz to - MARK_CODE to wrap 'pre' blocks with [code]...[/code] tags - WRAP_LINKS to decide if links have to be wrapped during text wrapping (implies INLINE_LINKS = False) - WRAP_LIST_ITEMS to decide if list items have to be wrapped during text wrapping - WRAP_TABLES to decide if tables have to be wrapped during text wrapping - DECODE_ERRORS to handle decoding errors. 'strict', 'ignore', 'replace' are the acceptable values. - DEFAULT_IMAGE_ALT takes a string as value and is used whenever an image tag is missing an `alt` value. The default for this is an empty string '' to avoid backward breakage - OPEN_QUOTE is the character used to open a quote when replacing the `` tag. It defaults to `"`. - CLOSE_QUOTE is the character used to close a quote when replacing the `` tag. It defaults to `"`. Options that are not in the config.py file: - emphasis_mark is the character used when replacing the `` tag. It defaults to `_`. - strong_mark is the characer used when replacing the `` tag. It defaults to `**`. To alter any option the procedure is to create a parser with `parser = html2text.HTML2Text()` and to set the option on the parser. example: `parser.unicode_snob = True` to set the UNICODE_SNOB option. Command line options -------------------- | Option | Description |--------------------------------------------------------|--------------------------------------------------- | `--version` | Show program version number and exit | `-h`, `--help` | Show this help message and exit | `--ignore-links` | Do not include any formatting for links |`--protect-links` | Protect links from line breaks surrounding them "+" with angle brackets |`--ignore-images` | Do not include any formatting for images |`--images-as-html` | Always write image tags as raw html; preserves "height", "width" and "alt" if possible. |`--images-to-alt` | Discard image data, only keep alt text |`--images-with-size` | Write image tags with height and width attrs as raw html to retain dimensions |`-g`, `--google-doc` | Convert an html-exported Google Document |`-d`, `--dash-unordered-list` | Use a dash rather than a star for unordered list items |`-b` `BODY_WIDTH`, `--body-width`=`BODY_WIDTH` | Number of characters per output line, `0` for no wrap |`-i` `LIST_INDENT`, `--google-list-indent`=`LIST_INDENT`| Number of pixels Google indents nested lists |`-s`, `--hide-strikethrough` | Hide strike-through text. only relevant when `-g` is specified as well |`--escape-all` | Escape all special characters. Output is less readable, but avoids corner case formatting issues. | `--bypass-tables` | Format tables in HTML rather than Markdown syntax. | `--ignore-tables` | Ignore table-related tags (table, th, td, tr) while keeping rows. | `--single-line-break` | Use a single line break after a block element rather than two. | `--reference-links` | Use reference links instead of inline links to create markdown | `--ignore-emphasis` | Ignore all emphasis formatting in the html. | `--include-sup-sub` | Include `` and `` tags. | `-e`, `--asterisk-emphasis` | Use asterisk rather than underscore to emphasize text | `--unicode-snob` | Use unicode throughout instead of ASCII | `--no-automatic-links` | Do not use automatic links like | `--no-skip-internal-links` | Turn off skipping of internal links | `--links-after-para` | Put the links after the paragraph and not at end of document | `--mark-code` | Mark code with [code]...[/code] blocks | `--no-wrap-links` | Do not wrap links during text wrapping. Implies `--reference-links` | `--wrap-list-items` | Wrap list items during text wrapping. | `--wrap-tables` | Wrap tables during text wrapping. | `--decode-errors`=`HANDLER` | What to do in case an error is encountered. `ignore`, `strict`, `replace` etc. | `--pad-tables` | Use padding to make tables look good. | `--default-image-alt`=`Image_Here` | Inserts the given `alt` text whenever images are missing `alt` values. | `--open-quote`=`"` | Inserts the given text when opening a quote. Defaults to `"`. | `--close-quote`=`"` | Inserts the given text when closing a quote. Defaults to `"`. ././@PaxHeader0000000000000000000000000000003400000000000010212 xustar0028 mtime=1744689734.5494015 html2text-2025.4.15/html2text/0000755000175100001660000000000014777355107015343 5ustar00runnerdocker././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0 html2text-2025.4.15/html2text/__init__.py0000644000175100001660000011177514777355103017464 0ustar00runnerdocker"""html2text: Turn HTML into equivalent Markdown-structured text.""" import html.entities import html.parser import re import string import urllib.parse as urlparse from textwrap import wrap from typing import Dict, List, Optional, Tuple, Union from . import config from ._typing import OutCallback from ._version import __version_tuple__ from .elements import AnchorElement, ListElement from .utils import ( control_character_replacements, dumb_css_parser, element_style, escape_md, escape_md_section, google_fixed_width_font, google_has_height, google_list_style, google_text_emphasis, hn, list_numbering_start, pad_tables_in_text, skipwrap, unifiable_n, ) __version__ = __version_tuple__ # TODO: # Support decoded entities with UNIFIABLE. class HTML2Text(html.parser.HTMLParser): def __init__( self, out: Optional[OutCallback] = None, baseurl: str = "", bodywidth: int = config.BODY_WIDTH, ) -> None: """ Input parameters: out: possible custom replacement for self.outtextf (which appends lines of text). baseurl: base URL of the document we process """ super().__init__(convert_charrefs=False) # Config options self.split_next_td = False self.td_count = 0 self.table_start = False self.unicode_snob = config.UNICODE_SNOB # covered in cli self.escape_snob = config.ESCAPE_SNOB # covered in cli self.links_each_paragraph = config.LINKS_EACH_PARAGRAPH self.body_width = bodywidth # covered in cli self.skip_internal_links = config.SKIP_INTERNAL_LINKS # covered in cli self.inline_links = config.INLINE_LINKS # covered in cli self.protect_links = config.PROTECT_LINKS # covered in cli self.google_list_indent = config.GOOGLE_LIST_INDENT # covered in cli self.ignore_links = config.IGNORE_ANCHORS # covered in cli self.ignore_mailto_links = config.IGNORE_MAILTO_LINKS # covered in cli self.ignore_images = config.IGNORE_IMAGES # covered in cli self.images_as_html = config.IMAGES_AS_HTML # covered in cli self.images_to_alt = config.IMAGES_TO_ALT # covered in cli self.images_with_size = config.IMAGES_WITH_SIZE # covered in cli self.ignore_emphasis = config.IGNORE_EMPHASIS # covered in cli self.bypass_tables = config.BYPASS_TABLES # covered in cli self.ignore_tables = config.IGNORE_TABLES # covered in cli self.google_doc = False # covered in cli self.ul_item_mark = "*" # covered in cli self.emphasis_mark = "_" # covered in cli self.strong_mark = "**" self.single_line_break = config.SINGLE_LINE_BREAK # covered in cli self.use_automatic_links = config.USE_AUTOMATIC_LINKS # covered in cli self.hide_strikethrough = False # covered in cli self.mark_code = config.MARK_CODE self.backquote_code_style = config.BACKQUOTE_CODE_STYLE self.wrap_list_items = config.WRAP_LIST_ITEMS # covered in cli self.wrap_links = config.WRAP_LINKS # covered in cli self.wrap_tables = config.WRAP_TABLES self.pad_tables = config.PAD_TABLES # covered in cli self.default_image_alt = config.DEFAULT_IMAGE_ALT # covered in cli self.tag_callback = None self.open_quote = config.OPEN_QUOTE # covered in cli self.close_quote = config.CLOSE_QUOTE # covered in cli self.include_sup_sub = config.INCLUDE_SUP_SUB # covered in cli if out is None: self.out = self.outtextf else: self.out = out # empty list to store output characters before they are "joined" self.outtextlist: List[str] = [] self.quiet = 0 self.p_p = 0 # number of newline character to print before next output self.outcount = 0 self.start = True self.space = False self.a: List[AnchorElement] = [] self.astack: List[Optional[Dict[str, Optional[str]]]] = [] self.maybe_automatic_link: Optional[str] = None self.empty_link = False self.absolute_url_matcher = re.compile(r"^[a-zA-Z+]+://") self.acount = 0 self.list: List[ListElement] = [] self.blockquote = 0 self.pre = False self.startpre = False self.pre_indent = "" self.list_code_indent = "" self.code = False self.quote = False self.br_toggle = "" self.lastWasNL = False self.lastWasList = False self.style = 0 self.style_def: Dict[str, Dict[str, str]] = {} self.tag_stack: List[Tuple[str, Dict[str, Optional[str]], Dict[str, str]]] = [] self.emphasis = 0 self.drop_white_space = 0 self.inheader = False # Current abbreviation definition self.abbr_title: Optional[str] = None # Last inner HTML (for abbr being defined) self.abbr_data: Optional[str] = None # Stack of abbreviations to write later self.abbr_list: Dict[str, str] = {} self.baseurl = baseurl self.stressed = False self.preceding_stressed = False self.preceding_data = "" self.current_tag = "" config.UNIFIABLE["nbsp"] = " _place_holder;" def feed(self, data: str) -> None: data = data.replace("", "") super().feed(data) def handle(self, data: str) -> str: self.start = True self.feed(data) self.feed("") markdown = self.optwrap(self.finish()) if self.pad_tables: return pad_tables_in_text(markdown) else: return markdown def outtextf(self, s: str) -> None: self.outtextlist.append(s) if s: self.lastWasNL = s[-1] == "\n" def finish(self) -> str: self.close() self.pbr() self.o("", force="end") outtext = "".join(self.outtextlist) if self.unicode_snob: nbsp = html.entities.html5["nbsp;"] else: nbsp = " " outtext = outtext.replace(" _place_holder;", nbsp) # Clear self.outtextlist to avoid memory leak of its content to # the next handling. self.outtextlist = [] return outtext def handle_charref(self, c: str) -> None: self.handle_data(self.charref(c), True) def handle_entityref(self, c: str) -> None: ref = self.entityref(c) # ref may be an empty string (e.g. for ‎/‏ markers that should # not contribute to the final output). # self.handle_data cannot handle a zero-length string right after a # stressed tag or mid-text within a stressed tag (text get split and # self.stressed/self.preceding_stressed gets switched after the first # part of that text). if ref: self.handle_data(ref, True) def handle_starttag(self, tag: str, attrs: List[Tuple[str, Optional[str]]]) -> None: self.handle_tag(tag, dict(attrs), start=True) def handle_endtag(self, tag: str) -> None: self.handle_tag(tag, {}, start=False) def previousIndex(self, attrs: Dict[str, Optional[str]]) -> Optional[int]: """ :type attrs: dict :returns: The index of certain set of attributes (of a link) in the self.a list. If the set of attributes is not found, returns None :rtype: int """ if "href" not in attrs: return None match = False for i, a in enumerate(self.a): if "href" in a.attrs and a.attrs["href"] == attrs["href"]: if "title" in a.attrs or "title" in attrs: if ( "title" in a.attrs and "title" in attrs and a.attrs["title"] == attrs["title"] ): match = True else: match = True if match: return i return None def handle_emphasis( self, start: bool, tag_style: Dict[str, str], parent_style: Dict[str, str] ) -> None: """ Handles various text emphases """ tag_emphasis = google_text_emphasis(tag_style) parent_emphasis = google_text_emphasis(parent_style) # handle Google's text emphasis strikethrough = "line-through" in tag_emphasis and self.hide_strikethrough # google and others may mark a font's weight as `bold` or `700` bold = False for bold_marker in config.BOLD_TEXT_STYLE_VALUES: bold = bold_marker in tag_emphasis and bold_marker not in parent_emphasis if bold: break italic = "italic" in tag_emphasis and "italic" not in parent_emphasis fixed = ( google_fixed_width_font(tag_style) and not google_fixed_width_font(parent_style) and not self.pre ) if start: # crossed-out text must be handled before other attributes # in order not to output qualifiers unnecessarily if bold or italic or fixed: self.emphasis += 1 if strikethrough: self.quiet += 1 if italic: self.o(self.emphasis_mark) self.drop_white_space += 1 if bold: self.o(self.strong_mark) self.drop_white_space += 1 if fixed: self.o("`") self.drop_white_space += 1 self.code = True else: if bold or italic or fixed: # there must not be whitespace before closing emphasis mark self.emphasis -= 1 self.space = False if fixed: if self.drop_white_space: # empty emphasis, drop it self.drop_white_space -= 1 else: self.o("`") self.code = False if bold: if self.drop_white_space: # empty emphasis, drop it self.drop_white_space -= 1 else: self.o(self.strong_mark) if italic: if self.drop_white_space: # empty emphasis, drop it self.drop_white_space -= 1 else: self.o(self.emphasis_mark) # space is only allowed after *all* emphasis marks if (bold or italic) and not self.emphasis: self.o(" ") if strikethrough: self.quiet -= 1 def handle_tag( self, tag: str, attrs: Dict[str, Optional[str]], start: bool ) -> None: self.current_tag = tag if self.tag_callback is not None: if self.tag_callback(self, tag, attrs, start) is True: return # first thing inside the anchor tag is another tag # that produces some output if ( start and self.maybe_automatic_link is not None and tag not in ["p", "div", "style", "dl", "dt"] and (tag != "img" or self.ignore_images) ): self.o("[") self.maybe_automatic_link = None self.empty_link = False if self.google_doc: # the attrs parameter is empty for a closing tag. in addition, we # need the attributes of the parent nodes in order to get a # complete style description for the current element. we assume # that google docs export well formed html. parent_style: Dict[str, str] = {} if start: if self.tag_stack: parent_style = self.tag_stack[-1][2] tag_style = element_style(attrs, self.style_def, parent_style) self.tag_stack.append((tag, attrs, tag_style)) else: dummy, attrs, tag_style = ( self.tag_stack.pop() if self.tag_stack else (None, {}, {}) ) if self.tag_stack: parent_style = self.tag_stack[-1][2] if hn(tag): # check if nh is inside of an 'a' tag (incorrect but found in the wild) if self.astack: if start: self.inheader = True # are inside link name, so only add '#' if it can appear before '[' if self.outtextlist and self.outtextlist[-1] == "[": self.outtextlist.pop() self.space = False self.o(hn(tag) * "#" + " ") self.o("[") else: self.p_p = 0 # don't break up link name self.inheader = False return # prevent redundant emphasis marks on headers else: self.p() if start: self.inheader = True self.o(hn(tag) * "#" + " ") else: self.inheader = False return # prevent redundant emphasis marks on headers if tag in ["p", "div"]: if self.google_doc: if start and google_has_height(tag_style): self.p() else: self.soft_br() elif self.astack: pass elif self.split_next_td: pass else: self.p() if tag == "br" and start: if self.blockquote > 0: self.o(" \n> ") else: self.o(" \n") if tag == "hr" and start: self.p() self.o("* * *") self.p() if tag in ["head", "style", "script"]: if start: self.quiet += 1 else: self.quiet -= 1 if tag == "style": if start: self.style += 1 else: self.style -= 1 if tag in ["body"]: self.quiet = 0 # sites like 9rules.com never close if tag == "blockquote": if start: self.p() self.o("> ", force=True) self.start = True self.blockquote += 1 else: self.blockquote -= 1 self.p() if tag in ["em", "i", "u"] and not self.ignore_emphasis: # Separate with a space if we immediately follow an alphanumeric # character, since otherwise Markdown won't render the emphasis # marks, and we'll be left with eg 'foo_bar_' visible. # (Don't add a space otherwise, though, since there isn't one in the # original HTML.) if ( start and self.preceding_data and self.preceding_data[-1] not in string.whitespace and self.preceding_data[-1] not in string.punctuation ): emphasis = " " + self.emphasis_mark self.preceding_data += " " else: emphasis = self.emphasis_mark self.o(emphasis) if start: self.stressed = True if tag in ["strong", "b"] and not self.ignore_emphasis: # Separate with space if we immediately follow an * character, since # without it, Markdown won't render the resulting *** correctly. # (Don't add a space otherwise, though, since there isn't one in the # original HTML.) if ( start and self.preceding_data # When `self.strong_mark` is set to empty, the next condition # will cause IndexError since it's trying to match the data # with the first character of the `self.strong_mark`. and len(self.strong_mark) > 0 and self.preceding_data[-1] == self.strong_mark[0] ): strong = " " + self.strong_mark self.preceding_data += " " else: strong = self.strong_mark self.o(strong) if start: self.stressed = True if tag in ["del", "strike", "s"]: if start and self.preceding_data and self.preceding_data[-1] == "~": strike = " ~~" self.preceding_data += " " else: strike = "~~" self.o(strike) if start: self.stressed = True if self.google_doc: if not self.inheader: # handle some font attributes, but leave headers clean self.handle_emphasis(start, tag_style, parent_style) if tag in ["kbd", "code", "tt"] and not self.pre: self.o("`") # TODO: `` `this` `` self.code = not self.code if tag == "abbr": if start: self.abbr_title = None self.abbr_data = "" if "title" in attrs: self.abbr_title = attrs["title"] else: if self.abbr_title is not None: assert self.abbr_data is not None self.abbr_list[self.abbr_data] = self.abbr_title self.abbr_title = None self.abbr_data = None if tag == "q": if not self.quote: self.o(self.open_quote) else: self.o(self.close_quote) self.quote = not self.quote def link_url(self: HTML2Text, link: str, title: str = "") -> None: url = urlparse.urljoin(self.baseurl, link) title = ' "{}"'.format(title) if title.strip() else "" self.o("]({url}{title})".format(url=escape_md(url), title=title)) if tag == "a" and not self.ignore_links: if start: if ( "href" in attrs and attrs["href"] is not None and not (self.skip_internal_links and attrs["href"].startswith("#")) and not ( self.ignore_mailto_links and attrs["href"].startswith("mailto:") ) ): self.astack.append(attrs) self.maybe_automatic_link = attrs["href"] self.empty_link = True if self.protect_links: attrs["href"] = "<" + attrs["href"] + ">" else: self.astack.append(None) else: if self.astack: a = self.astack.pop() if self.maybe_automatic_link and not self.empty_link: self.maybe_automatic_link = None elif a: assert a["href"] is not None if self.empty_link: self.o("[") self.empty_link = False self.maybe_automatic_link = None if self.inline_links: self.p_p = 0 title = a.get("title") or "" title = escape_md(title) link_url(self, a["href"], title) else: i = self.previousIndex(a) if i is not None: a_props = self.a[i] else: self.acount += 1 a_props = AnchorElement(a, self.acount, self.outcount) self.a.append(a_props) self.o("][" + str(a_props.count) + "]") if tag == "img" and start and not self.ignore_images: if "src" in attrs and attrs["src"] is not None: if not self.images_to_alt: attrs["href"] = attrs["src"] alt = attrs.get("alt") or self.default_image_alt # If we have images_with_size, write raw html including width, # height, and alt attributes if self.images_as_html or ( self.images_with_size and ("width" in attrs or "height" in attrs) ): self.o("") return # If we have a link to create, output the start if self.maybe_automatic_link is not None: href = self.maybe_automatic_link if ( self.images_to_alt and escape_md(alt) == href and self.absolute_url_matcher.match(href) ): self.o("<" + escape_md(alt) + ">") self.empty_link = False return else: self.o("[") self.maybe_automatic_link = None self.empty_link = False # If we have images_to_alt, we discard the image itself, # considering only the alt text. if self.images_to_alt: self.o(escape_md(alt)) else: self.o("![" + escape_md(alt) + "]") if self.inline_links: href = attrs.get("href") or "" self.o( "(" + escape_md(urlparse.urljoin(self.baseurl, href)) + ")" ) else: i = self.previousIndex(attrs) if i is not None: a_props = self.a[i] else: self.acount += 1 a_props = AnchorElement(attrs, self.acount, self.outcount) self.a.append(a_props) self.o("[" + str(a_props.count) + "]") if tag == "dl" and start: self.p() if tag == "dt" and not start: self.pbr() if tag == "dd" and start: self.o(" ") if tag == "dd" and not start: self.pbr() if tag in ["ol", "ul"]: # Google Docs create sub lists as top level lists if not self.list and not self.lastWasList: self.p() if start: if self.google_doc: list_style = google_list_style(tag_style) else: list_style = tag numbering_start = list_numbering_start(attrs) self.list.append(ListElement(list_style, numbering_start)) else: if self.list: self.list.pop() if not self.google_doc and not self.list: self.o("\n") self.lastWasList = True else: self.lastWasList = False if tag == "li": self.list_code_indent = "" self.pbr() if start: if self.list: li = self.list[-1] else: li = ListElement("ul", 0) if self.google_doc: self.o(" " * self.google_nest_count(tag_style)) else: # Indent two spaces per list, except use three spaces for an # unordered list inside an ordered list. # https://spec.commonmark.org/0.28/#motivation # TODO: line up

      1. s > 9 correctly. parent_list = None for list in self.list: self.list_code_indent += " " if parent_list == "ol" else " " parent_list = list.name self.o(self.list_code_indent) if li.name == "ul": self.list_code_indent += " " self.o(self.ul_item_mark + " ") elif li.name == "ol": li.num += 1 self.list_code_indent += " " self.o(str(li.num) + ". ") self.start = True if tag in ["table", "tr", "td", "th"]: if self.ignore_tables: if tag == "tr": if start: pass else: self.soft_br() else: pass elif self.bypass_tables: if start: self.soft_br() if tag in ["td", "th"]: if start: self.o("<{}>\n\n".format(tag)) else: self.o("\n".format(tag)) else: if start: self.o("<{}>".format(tag)) else: self.o("".format(tag)) else: if tag == "table": if start: self.table_start = True if self.pad_tables: self.o("<" + config.TABLE_MARKER_FOR_PAD + ">") self.o(" \n") else: if self.pad_tables: # add break in case the table is empty or its 1 row table self.soft_br() self.o("") self.o(" \n") if tag in ["td", "th"] and start: if self.split_next_td: self.o("| ") self.split_next_td = True if tag == "tr" and start: self.td_count = 0 if tag == "tr" and not start: self.split_next_td = False self.soft_br() if tag == "tr" and not start and self.table_start: # Underline table header self.o("|".join(["---"] * self.td_count)) self.soft_br() self.table_start = False if tag in ["td", "th"] and start: self.td_count += 1 if tag == "pre": if start: self.startpre = True self.pre = True self.pre_indent = "" else: self.pre = False if self.backquote_code_style: self.out("\n" + self.pre_indent + "```") if self.mark_code: self.out("\n[/code]") self.p() if tag in ["sup", "sub"] and self.include_sup_sub: if start: self.o("<{}>".format(tag)) else: self.o("".format(tag)) # TODO: Add docstring for these one letter functions def pbr(self) -> None: "Pretty print has a line break" if self.p_p == 0: self.p_p = 1 def p(self) -> None: "Set pretty print to 1 or 2 lines" self.p_p = 1 if self.single_line_break else 2 def soft_br(self) -> None: "Soft breaks" self.pbr() self.br_toggle = " " def o( self, data: str, puredata: bool = False, force: Union[bool, str] = False ) -> None: """ Deal with indentation and whitespace """ if self.abbr_data is not None: self.abbr_data += data if not self.quiet: if self.google_doc: # prevent white space immediately after 'begin emphasis' # marks ('**' and '_') lstripped_data = data.lstrip() if self.drop_white_space and not (self.pre or self.code): data = lstripped_data if lstripped_data != "": self.drop_white_space = 0 if puredata and not self.pre: # This is a very dangerous call ... it could mess up # all handling of   when not handled properly # (see entityref) data = re.sub(r"\s+", r" ", data) if data and data[0] == " ": self.space = True data = data[1:] if not data and not force: return if self.startpre: # self.out(" :") #TODO: not output when already one there if not data.startswith("\n") and not data.startswith("\r\n"): # 
        stuff...
                    data = "\n" + data
                if self.mark_code:
                    self.out("\n[code]")
                    self.p_p = 0

            bq = ">" * self.blockquote
            if not (force and data and data[0] == ">") and self.blockquote:
                bq += " "

            if self.pre:
                if self.list:
                    bq += self.list_code_indent

                if not self.backquote_code_style:
                    bq += "    "

                data = data.replace("\n", "\n" + bq)
                self.pre_indent = bq

            if self.startpre:
                self.startpre = False
                if self.backquote_code_style:
                    self.out("\n" + self.pre_indent + "```")
                    self.p_p = 0
                elif self.list:
                    # use existing initial indentation
                    data = data.lstrip("\n" + self.pre_indent)

            if self.start:
                self.space = False
                self.p_p = 0
                self.start = False

            if force == "end":
                # It's the end.
                self.p_p = 0
                self.out("\n")
                self.space = False

            if self.p_p:
                self.out((self.br_toggle + "\n" + bq) * self.p_p)
                self.space = False
                self.br_toggle = ""

            if self.space:
                if not self.lastWasNL:
                    self.out(" ")
                self.space = False

            if self.a and (
                (self.p_p == 2 and self.links_each_paragraph) or force == "end"
            ):
                if force == "end":
                    self.out("\n")

                newa = []
                for link in self.a:
                    if self.outcount > link.outcount:
                        self.out(
                            "   ["
                            + str(link.count)
                            + "]: "
                            + urlparse.urljoin(self.baseurl, link.attrs["href"])
                        )
                        if "title" in link.attrs and link.attrs["title"] is not None:
                            self.out(" (" + link.attrs["title"] + ")")
                        self.out("\n")
                    else:
                        newa.append(link)

                # Don't need an extra line when nothing was done.
                if self.a != newa:
                    self.out("\n")

                self.a = newa

            if self.abbr_list and force == "end":
                for abbr, definition in self.abbr_list.items():
                    self.out("  *[" + abbr + "]: " + definition + "\n")

            self.p_p = 0
            self.out(data)
            self.outcount += 1

    def handle_data(self, data: str, entity_char: bool = False) -> None:
        if not data:
            # Data may be empty for some HTML entities. For example,
            # LEFT-TO-RIGHT MARK.
            return

        if self.stressed:
            data = data.strip()
            self.stressed = False
            self.preceding_stressed = True
        elif self.preceding_stressed:
            if (
                re.match(r"[^][(){}\s.!?]", data[0])
                and not hn(self.current_tag)
                and self.current_tag not in ["a", "code", "pre"]
            ):
                # should match a letter or common punctuation
                data = " " + data
            self.preceding_stressed = False

        if self.style:
            self.style_def.update(dumb_css_parser(data))

        if self.maybe_automatic_link is not None:
            href = self.maybe_automatic_link
            if (
                href == data
                and self.absolute_url_matcher.match(href)
                and self.use_automatic_links
            ):
                self.o("<" + data + ">")
                self.empty_link = False
                return
            else:
                self.o("[")
                self.maybe_automatic_link = None
                self.empty_link = False

        if not self.code and not self.pre and not entity_char:
            data = escape_md_section(data, snob=self.escape_snob)
        self.preceding_data = data
        self.o(data, puredata=True)

    def charref(self, name: str) -> str:
        if name[0] in ["x", "X"]:
            c = int(name[1:], 16)
        else:
            c = int(name)

        if not 0 < c < 0x110000 or 0xD800 <= c < 0xE000:  # invalid or surrogate
            c = 0xFFFD  # REPLACEMENT CHARACTER
        c = control_character_replacements.get(c, c)

        if not self.unicode_snob and c in unifiable_n:
            return unifiable_n[c]
        else:
            return chr(c)

    def entityref(self, c: str) -> str:
        if not self.unicode_snob and c in config.UNIFIABLE:
            return config.UNIFIABLE[c]
        try:
            ch = html.entities.html5[c + ";"]
        except KeyError:
            return "&" + c + ";"
        return config.UNIFIABLE[c] if c == "nbsp" else ch

    def google_nest_count(self, style: Dict[str, str]) -> int:
        """
        Calculate the nesting count of google doc lists

        :type style: dict

        :rtype: int
        """
        nest_count = 0
        if "margin-left" in style:
            nest_count = int(style["margin-left"][:-2]) // self.google_list_indent

        return nest_count

    def optwrap(self, text: str) -> str:
        """
        Wrap all paragraphs in the provided text.

        :type text: str

        :rtype: str
        """
        if not self.body_width:
            return text

        result = ""
        newlines = 0
        # I cannot think of a better solution for now.
        # To avoid the non-wrap behaviour for entire paras
        # because of the presence of a link in it
        if not self.wrap_links:
            self.inline_links = False
        start_code = False
        for para in text.split("\n"):
            # If the text is between tri-backquote pairs, it's a code block;
            # don't wrap
            if self.backquote_code_style and para.lstrip().startswith("```"):
                start_code = not start_code
            if start_code:
                result += para + "\n"
            elif len(para) > 0:
                if not skipwrap(
                    para, self.wrap_links, self.wrap_list_items, self.wrap_tables
                ):
                    indent = ""
                    if para.startswith("  " + self.ul_item_mark):
                        # list item continuation: add a double indent to the
                        # new lines
                        indent = "    "
                    elif para.startswith("> "):
                        # blockquote continuation: add the greater than symbol
                        # to the new lines
                        indent = "> "
                    wrapped = wrap(
                        para,
                        self.body_width,
                        break_long_words=False,
                        subsequent_indent=indent,
                    )
                    result += "\n".join(wrapped)
                    if para.endswith("  "):
                        result += "  \n"
                        newlines = 1
                    elif indent:
                        result += "\n"
                        newlines = 1
                    else:
                        result += "\n\n"
                        newlines = 2
                else:
                    # Warning for the tempted!!!
                    # Be aware that obvious replacement of this with
                    # line.isspace()
                    # DOES NOT work! Explanations are welcome.
                    if not config.RE_SPACE.match(para):
                        result += para + "\n"
                        newlines = 1
            else:
                if newlines < 2:
                    result += "\n"
                    newlines += 1
        return result


def html2text(html: str, baseurl: str = "", bodywidth: Optional[int] = None) -> str:
    if bodywidth is None:
        bodywidth = config.BODY_WIDTH
    h = HTML2Text(baseurl=baseurl, bodywidth=bodywidth)

    return h.handle(html)
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/html2text/__main__.py0000644000175100001660000000003614777355103017430 0ustar00runnerdockerfrom .cli import main

main()
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/html2text/_typing.py0000644000175100001660000000007714777355103017366 0ustar00runnerdockerclass OutCallback:
    def __call__(self, s: str) -> None: ...
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689734.0
html2text-2025.4.15/html2text/_version.py0000644000175100001660000000100714777355106017536 0ustar00runnerdocker# file generated by setuptools-scm
# don't change, don't track in version control

__all__ = ["__version__", "__version_tuple__", "version", "version_tuple"]

TYPE_CHECKING = False
if TYPE_CHECKING:
    from typing import Tuple
    from typing import Union

    VERSION_TUPLE = Tuple[Union[int, str], ...]
else:
    VERSION_TUPLE = object

version: str
__version__: str
__version_tuple__: VERSION_TUPLE
version_tuple: VERSION_TUPLE

__version__ = version = '2025.4.15'
__version_tuple__ = version_tuple = (2025, 4, 15)
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/html2text/cli.py0000644000175100001660000002407414777355103016467 0ustar00runnerdockerimport argparse
import sys

from . import HTML2Text, config
from ._version import __version_tuple__ as __version__


def main() -> None:
    baseurl = ""

    class bcolors:
        HEADER = "\033[95m"
        OKBLUE = "\033[94m"
        OKGREEN = "\033[92m"
        WARNING = "\033[93m"
        FAIL = "\033[91m"
        ENDC = "\033[0m"
        BOLD = "\033[1m"
        UNDERLINE = "\033[4m"

    p = argparse.ArgumentParser()
    p.add_argument(
        "--default-image-alt",
        dest="default_image_alt",
        default=config.DEFAULT_IMAGE_ALT,
        help="The default alt string for images with missing ones",
    )
    p.add_argument(
        "--pad-tables",
        dest="pad_tables",
        action="store_true",
        default=config.PAD_TABLES,
        help="pad the cells to equal column width in tables",
    )
    p.add_argument(
        "--no-wrap-links",
        dest="wrap_links",
        action="store_false",
        default=config.WRAP_LINKS,
        help="don't wrap links during conversion",
    )
    p.add_argument(
        "--wrap-list-items",
        dest="wrap_list_items",
        action="store_true",
        default=config.WRAP_LIST_ITEMS,
        help="wrap list items during conversion",
    )
    p.add_argument(
        "--wrap-tables",
        dest="wrap_tables",
        action="store_true",
        default=config.WRAP_TABLES,
        help="wrap tables",
    )
    p.add_argument(
        "--ignore-emphasis",
        dest="ignore_emphasis",
        action="store_true",
        default=config.IGNORE_EMPHASIS,
        help="don't include any formatting for emphasis",
    )
    p.add_argument(
        "--reference-links",
        dest="inline_links",
        action="store_false",
        default=config.INLINE_LINKS,
        help="use reference style links instead of inline links",
    )
    p.add_argument(
        "--ignore-links",
        dest="ignore_links",
        action="store_true",
        default=config.IGNORE_ANCHORS,
        help="don't include any formatting for links",
    )
    p.add_argument(
        "--ignore-mailto-links",
        action="store_true",
        dest="ignore_mailto_links",
        default=config.IGNORE_MAILTO_LINKS,
        help="don't include mailto: links",
    )
    p.add_argument(
        "--protect-links",
        dest="protect_links",
        action="store_true",
        default=config.PROTECT_LINKS,
        help="protect links from line breaks surrounding them with angle brackets",
    )
    p.add_argument(
        "--ignore-images",
        dest="ignore_images",
        action="store_true",
        default=config.IGNORE_IMAGES,
        help="don't include any formatting for images",
    )
    p.add_argument(
        "--images-as-html",
        dest="images_as_html",
        action="store_true",
        default=config.IMAGES_AS_HTML,
        help=(
            "Always write image tags as raw html; preserves `height`, `width` and "
            "`alt` if possible."
        ),
    )
    p.add_argument(
        "--images-to-alt",
        dest="images_to_alt",
        action="store_true",
        default=config.IMAGES_TO_ALT,
        help="Discard image data, only keep alt text",
    )
    p.add_argument(
        "--images-with-size",
        dest="images_with_size",
        action="store_true",
        default=config.IMAGES_WITH_SIZE,
        help=(
            "Write image tags with height and width attrs as raw html to retain "
            "dimensions"
        ),
    )
    p.add_argument(
        "-g",
        "--google-doc",
        action="store_true",
        dest="google_doc",
        default=False,
        help="convert an html-exported Google Document",
    )
    p.add_argument(
        "-d",
        "--dash-unordered-list",
        action="store_true",
        dest="ul_style_dash",
        default=False,
        help="use a dash rather than a star for unordered list items",
    )
    p.add_argument(
        "-e",
        "--asterisk-emphasis",
        action="store_true",
        dest="em_style_asterisk",
        default=False,
        help="use an asterisk rather than an underscore for emphasized text",
    )
    p.add_argument(
        "-b",
        "--body-width",
        dest="body_width",
        type=int,
        default=config.BODY_WIDTH,
        help="number of characters per output line, 0 for no wrap",
    )
    p.add_argument(
        "-i",
        "--google-list-indent",
        dest="list_indent",
        type=int,
        default=config.GOOGLE_LIST_INDENT,
        help="number of pixels Google indents nested lists",
    )
    p.add_argument(
        "-s",
        "--hide-strikethrough",
        action="store_true",
        dest="hide_strikethrough",
        default=False,
        help="hide strike-through text. only relevant when -g is " "specified as well",
    )
    p.add_argument(
        "--escape-all",
        action="store_true",
        dest="escape_snob",
        default=False,
        help=(
            "Escape all special characters.  Output is less readable, but avoids "
            "corner case formatting issues."
        ),
    )
    p.add_argument(
        "--bypass-tables",
        action="store_true",
        dest="bypass_tables",
        default=config.BYPASS_TABLES,
        help="Format tables in HTML rather than Markdown syntax.",
    )
    p.add_argument(
        "--ignore-tables",
        action="store_true",
        dest="ignore_tables",
        default=config.IGNORE_TABLES,
        help="Ignore table-related tags (table, th, td, tr) " "while keeping rows.",
    )
    p.add_argument(
        "--single-line-break",
        action="store_true",
        dest="single_line_break",
        default=config.SINGLE_LINE_BREAK,
        help=(
            "Use a single line break after a block element rather than two line "
            "breaks. NOTE: Requires --body-width=0"
        ),
    )
    p.add_argument(
        "--unicode-snob",
        action="store_true",
        dest="unicode_snob",
        default=config.UNICODE_SNOB,
        help="Use unicode throughout document",
    )
    p.add_argument(
        "--no-automatic-links",
        action="store_false",
        dest="use_automatic_links",
        default=config.USE_AUTOMATIC_LINKS,
        help="Do not use automatic links wherever applicable",
    )
    p.add_argument(
        "--no-skip-internal-links",
        action="store_false",
        dest="skip_internal_links",
        default=config.SKIP_INTERNAL_LINKS,
        help="Do not skip internal links",
    )
    p.add_argument(
        "--links-after-para",
        action="store_true",
        dest="links_each_paragraph",
        default=config.LINKS_EACH_PARAGRAPH,
        help="Put links after each paragraph instead of document",
    )
    p.add_argument(
        "--mark-code",
        action="store_true",
        dest="mark_code",
        default=config.MARK_CODE,
        help="Mark program code blocks with [code]...[/code]",
    )
    p.add_argument(
        "--backquote-code-style",
        action="store_true",
        dest="backquote_code_style",
        default=config.BACKQUOTE_CODE_STYLE,
        help="Multi line code block using tri-backquote style",
    )
    p.add_argument(
        "--decode-errors",
        dest="decode_errors",
        default=config.DECODE_ERRORS,
        help=(
            "What to do in case of decode errors.'ignore', 'strict' and 'replace' are "
            "acceptable values"
        ),
    )
    p.add_argument(
        "--open-quote",
        dest="open_quote",
        default=config.OPEN_QUOTE,
        help="The character used to open quotes",
    )
    p.add_argument(
        "--close-quote",
        dest="close_quote",
        default=config.CLOSE_QUOTE,
        help="The character used to close quotes",
    )
    p.add_argument(
        "--version", action="version", version=".".join(map(str, __version__))
    )
    p.add_argument("filename", nargs="?")
    p.add_argument("encoding", nargs="?", default="utf-8")
    p.add_argument(
        "--include-sup-sub",
        dest="include_sup_sub",
        action="store_true",
        default=config.INCLUDE_SUP_SUB,
        help="Include the sup and sub tags",
    )
    args = p.parse_args()

    if args.filename and args.filename != "-":
        with open(args.filename, "rb") as fp:
            data = fp.read()
    else:
        data = sys.stdin.buffer.read()

    try:
        html = data.decode(args.encoding, args.decode_errors)
    except UnicodeDecodeError as err:
        warning = bcolors.WARNING + "Warning:" + bcolors.ENDC
        warning += " Use the " + bcolors.OKGREEN
        warning += "--decode-errors=ignore" + bcolors.ENDC + " flag."
        print(warning)
        raise err

    h = HTML2Text(baseurl=baseurl)
    # handle options
    if args.ul_style_dash:
        h.ul_item_mark = "-"
    if args.em_style_asterisk:
        h.emphasis_mark = "*"
        h.strong_mark = "__"

    h.body_width = args.body_width
    h.google_list_indent = args.list_indent
    h.ignore_emphasis = args.ignore_emphasis
    h.ignore_links = args.ignore_links
    h.ignore_mailto_links = args.ignore_mailto_links
    h.protect_links = args.protect_links
    h.ignore_images = args.ignore_images
    h.images_as_html = args.images_as_html
    h.images_to_alt = args.images_to_alt
    h.images_with_size = args.images_with_size
    h.google_doc = args.google_doc
    h.hide_strikethrough = args.hide_strikethrough
    h.escape_snob = args.escape_snob
    h.bypass_tables = args.bypass_tables
    h.ignore_tables = args.ignore_tables
    h.single_line_break = args.single_line_break
    h.inline_links = args.inline_links
    h.unicode_snob = args.unicode_snob
    h.use_automatic_links = args.use_automatic_links
    h.skip_internal_links = args.skip_internal_links
    h.links_each_paragraph = args.links_each_paragraph
    h.mark_code = args.mark_code
    h.backquote_code_style = args.backquote_code_style
    h.wrap_links = args.wrap_links
    h.wrap_list_items = args.wrap_list_items
    h.wrap_tables = args.wrap_tables
    h.pad_tables = args.pad_tables
    h.default_image_alt = args.default_image_alt
    h.open_quote = args.open_quote
    h.close_quote = args.close_quote
    h.include_sup_sub = args.include_sup_sub

    sys.stdout.write(h.handle(html))
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/html2text/config.py0000644000175100001660000000772414777355103017170 0ustar00runnerdockerimport re

# Use Unicode characters instead of their ascii pseudo-replacements
UNICODE_SNOB = False

# Marker to use for marking tables for padding post processing
TABLE_MARKER_FOR_PAD = "special_marker_for_table_padding"
# Escape all special characters.  Output is less readable, but avoids
# corner case formatting issues.
ESCAPE_SNOB = False

# Put the links after each paragraph instead of at the end.
LINKS_EACH_PARAGRAPH = False

# Wrap long lines at position. 0 for no wrapping.
BODY_WIDTH = 78

# Don't show internal links (href="#local-anchor") -- corresponding link
# targets won't be visible in the plain text file anyway.
SKIP_INTERNAL_LINKS = True

# Use inline, rather than reference, formatting for images and links
INLINE_LINKS = True

# Protect links from line breaks surrounding them with angle brackets (in
# addition to their square brackets)
PROTECT_LINKS = False
# WRAP_LINKS = True
WRAP_LINKS = True

# Wrap list items.
WRAP_LIST_ITEMS = False

# Wrap tables
WRAP_TABLES = False

# Number of pixels Google indents nested lists
GOOGLE_LIST_INDENT = 36

# Values Google and others may use to indicate bold text
BOLD_TEXT_STYLE_VALUES = ("bold", "700", "800", "900")

IGNORE_ANCHORS = False
IGNORE_MAILTO_LINKS = False
IGNORE_IMAGES = False
IMAGES_AS_HTML = False
IMAGES_TO_ALT = False
IMAGES_WITH_SIZE = False
IGNORE_EMPHASIS = False
MARK_CODE = False
BACKQUOTE_CODE_STYLE = False
DECODE_ERRORS = "strict"
DEFAULT_IMAGE_ALT = ""
PAD_TABLES = False

# Convert links with same href and text to  format
# if they are absolute links
USE_AUTOMATIC_LINKS = True

# For checking space-only lines on line 771
RE_SPACE = re.compile(r"\s\+")

RE_ORDERED_LIST_MATCHER = re.compile(r"\d+\.\s")
RE_UNORDERED_LIST_MATCHER = re.compile(r"[-\*\+]\s")
RE_MD_CHARS_MATCHER = re.compile(r"([\\\[\]\(\)])")
RE_MD_CHARS_MATCHER_ALL = re.compile(r"([`\*_{}\[\]\(\)#!])")

# to find links in the text
RE_LINK = re.compile(r"(\[.*?\] ?\(.*?\))|(\[.*?\]:.*?)")

# to find table separators
RE_TABLE = re.compile(r" \| ")

RE_MD_DOT_MATCHER = re.compile(
    r"""
    ^             # start of line
    (\s*\d+)      # optional whitespace and a number
    (\.)          # dot
    (?=\s)        # lookahead assert whitespace
    """,
    re.MULTILINE | re.VERBOSE,
)
RE_MD_PLUS_MATCHER = re.compile(
    r"""
    ^
    (\s*)
    (\+)
    (?=\s)
    """,
    flags=re.MULTILINE | re.VERBOSE,
)
RE_MD_DASH_MATCHER = re.compile(
    r"""
    ^
    (\s*)
    (-)
    (?=\s|\-)     # followed by whitespace (bullet list, or spaced out hr)
                  # or another dash (header or hr)
    """,
    flags=re.MULTILINE | re.VERBOSE,
)
RE_SLASH_CHARS = r"\`*_{}[]()#+-.!"
RE_MD_BACKSLASH_MATCHER = re.compile(
    r"""
    (\\)          # match one slash
    (?=[%s])      # followed by a char that requires escaping
    """
    % re.escape(RE_SLASH_CHARS),
    flags=re.VERBOSE,
)

UNIFIABLE = {
    "rsquo": "'",
    "lsquo": "'",
    "rdquo": '"',
    "ldquo": '"',
    "copy": "(C)",
    "mdash": "--",
    "nbsp": " ",
    "rarr": "->",
    "larr": "<-",
    "middot": "*",
    "ndash": "-",
    "oelig": "oe",
    "aelig": "ae",
    "agrave": "a",
    "aacute": "a",
    "acirc": "a",
    "atilde": "a",
    "auml": "a",
    "aring": "a",
    "egrave": "e",
    "eacute": "e",
    "ecirc": "e",
    "euml": "e",
    "igrave": "i",
    "iacute": "i",
    "icirc": "i",
    "iuml": "i",
    "ograve": "o",
    "oacute": "o",
    "ocirc": "o",
    "otilde": "o",
    "ouml": "o",
    "ugrave": "u",
    "uacute": "u",
    "ucirc": "u",
    "uuml": "u",
    "lrm": "",
    "rlm": "",
}

# Format tables in HTML rather than Markdown syntax
BYPASS_TABLES = False
# Ignore table-related tags (table, th, td, tr) while keeping rows
IGNORE_TABLES = False


# Use a single line break after a block element rather than two line breaks.
# NOTE: Requires body width setting to be 0.
SINGLE_LINE_BREAK = False


# Use double quotation marks when converting the  tag.
OPEN_QUOTE = '"'
CLOSE_QUOTE = '"'

# Include the  and  tags
INCLUDE_SUP_SUB = False
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/html2text/elements.py0000644000175100001660000000064714777355103017534 0ustar00runnerdockerfrom typing import Dict, Optional


class AnchorElement:
    __slots__ = ["attrs", "count", "outcount"]

    def __init__(self, attrs: Dict[str, Optional[str]], count: int, outcount: int):
        self.attrs = attrs
        self.count = count
        self.outcount = outcount


class ListElement:
    __slots__ = ["name", "num"]

    def __init__(self, name: str, num: int):
        self.name = name
        self.num = num
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/html2text/py.typed0000644000175100001660000000000014777355103017024 0ustar00runnerdocker././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/html2text/utils.py0000644000175100001660000002305014777355103017051 0ustar00runnerdockerimport html.entities
from typing import Dict, List, Optional

from . import config

unifiable_n = {
    html.entities.name2codepoint[k]: v
    for k, v in config.UNIFIABLE.items()
    if k != "nbsp"
}

# https://html.spec.whatwg.org/multipage/parsing.html#character-reference-code
control_character_replacements = {
    0x80: 0x20AC,  # EURO SIGN (€)
    0x82: 0x201A,  # SINGLE LOW-9 QUOTATION MARK (‚)
    0x83: 0x0192,  # LATIN SMALL LETTER F WITH HOOK (ƒ)
    0x84: 0x201E,  # DOUBLE LOW-9 QUOTATION MARK („)
    0x85: 0x2026,  # HORIZONTAL ELLIPSIS (…)
    0x86: 0x2020,  # DAGGER (†)
    0x87: 0x2021,  # DOUBLE DAGGER (‡)
    0x88: 0x02C6,  # MODIFIER LETTER CIRCUMFLEX ACCENT (ˆ)
    0x89: 0x2030,  # PER MILLE SIGN (‰)
    0x8A: 0x0160,  # LATIN CAPITAL LETTER S WITH CARON (Š)
    0x8B: 0x2039,  # SINGLE LEFT-POINTING ANGLE QUOTATION MARK (‹)
    0x8C: 0x0152,  # LATIN CAPITAL LIGATURE OE (Œ)
    0x8E: 0x017D,  # LATIN CAPITAL LETTER Z WITH CARON (Ž)
    0x91: 0x2018,  # LEFT SINGLE QUOTATION MARK (‘)
    0x92: 0x2019,  # RIGHT SINGLE QUOTATION MARK (’)
    0x93: 0x201C,  # LEFT DOUBLE QUOTATION MARK (“)
    0x94: 0x201D,  # RIGHT DOUBLE QUOTATION MARK (”)
    0x95: 0x2022,  # BULLET (•)
    0x96: 0x2013,  # EN DASH (–)
    0x97: 0x2014,  # EM DASH (—)
    0x98: 0x02DC,  # SMALL TILDE (˜)
    0x99: 0x2122,  # TRADE MARK SIGN (™)
    0x9A: 0x0161,  # LATIN SMALL LETTER S WITH CARON (š)
    0x9B: 0x203A,  # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK (›)
    0x9C: 0x0153,  # LATIN SMALL LIGATURE OE (œ)
    0x9E: 0x017E,  # LATIN SMALL LETTER Z WITH CARON (ž)
    0x9F: 0x0178,  # LATIN CAPITAL LETTER Y WITH DIAERESIS (Ÿ)
}


def hn(tag: str) -> int:
    if tag[0] == "h" and len(tag) == 2:
        n = tag[1]
        if "0" < n <= "9":
            return int(n)
    return 0


def dumb_property_dict(style: str) -> Dict[str, str]:
    """
    :returns: A hash of css attributes
    """
    return {
        x.strip().lower(): y.strip().lower()
        for x, y in [z.split(":", 1) for z in style.split(";") if ":" in z]
    }


def dumb_css_parser(data: str) -> Dict[str, Dict[str, str]]:
    """
    :type data: str

    :returns: A hash of css selectors, each of which contains a hash of
    css attributes.
    :rtype: dict
    """
    # remove @import sentences
    data += ";"
    importIndex = data.find("@import")
    while importIndex != -1:
        data = data[0:importIndex] + data[data.find(";", importIndex) + 1 :]
        importIndex = data.find("@import")

    # parse the css. reverted from dictionary comprehension in order to
    # support older pythons
    pairs = [x.split("{") for x in data.split("}") if "{" in x.strip()]
    try:
        elements = {a.strip(): dumb_property_dict(b) for a, b in pairs}
    except ValueError:
        elements = {}  # not that important

    return elements


def element_style(
    attrs: Dict[str, Optional[str]],
    style_def: Dict[str, Dict[str, str]],
    parent_style: Dict[str, str],
) -> Dict[str, str]:
    """
    :type attrs: dict
    :type style_def: dict
    :type style_def: dict

    :returns: A hash of the 'final' style attributes of the element
    :rtype: dict
    """
    style = parent_style.copy()
    if "class" in attrs:
        assert attrs["class"] is not None
        for css_class in attrs["class"].split():
            css_style = style_def.get("." + css_class, {})
            style.update(css_style)
    if "style" in attrs:
        assert attrs["style"] is not None
        immediate_style = dumb_property_dict(attrs["style"])
        style.update(immediate_style)

    return style


def google_list_style(style: Dict[str, str]) -> str:
    """
    Finds out whether this is an ordered or unordered list

    :type style: dict

    :rtype: str
    """
    if "list-style-type" in style:
        list_style = style["list-style-type"]
        if list_style in ["disc", "circle", "square", "none"]:
            return "ul"

    return "ol"


def google_has_height(style: Dict[str, str]) -> bool:
    """
    Check if the style of the element has the 'height' attribute
    explicitly defined

    :type style: dict

    :rtype: bool
    """
    return "height" in style


def google_text_emphasis(style: Dict[str, str]) -> List[str]:
    """
    :type style: dict

    :returns: A list of all emphasis modifiers of the element
    :rtype: list
    """
    emphasis = []
    if "text-decoration" in style:
        emphasis.append(style["text-decoration"])
    if "font-style" in style:
        emphasis.append(style["font-style"])
    if "font-weight" in style:
        emphasis.append(style["font-weight"])

    return emphasis


def google_fixed_width_font(style: Dict[str, str]) -> bool:
    """
    Check if the css of the current element defines a fixed width font

    :type style: dict

    :rtype: bool
    """
    font_family = ""
    if "font-family" in style:
        font_family = style["font-family"]
    return "courier new" == font_family or "consolas" == font_family


def list_numbering_start(attrs: Dict[str, Optional[str]]) -> int:
    """
    Extract numbering from list element attributes

    :type attrs: dict

    :rtype: int or None
    """
    if "start" in attrs:
        assert attrs["start"] is not None
        try:
            return int(attrs["start"]) - 1
        except ValueError:
            pass

    return 0


def skipwrap(
    para: str, wrap_links: bool, wrap_list_items: bool, wrap_tables: bool
) -> bool:
    # If it appears to contain a link
    # don't wrap
    if not wrap_links and config.RE_LINK.search(para):
        return True
    # If the text begins with four spaces or one tab, it's a code block;
    # don't wrap
    if para[0:4] == "    " or para[0] == "\t":
        return True

    # If the text begins with only two "--", possibly preceded by
    # whitespace, that's an emdash; so wrap.
    stripped = para.lstrip()
    if stripped[0:2] == "--" and len(stripped) > 2 and stripped[2] != "-":
        return False

    # I'm not sure what this is for; I thought it was to detect lists,
    # but there's a 
        -inside- case in one of the tests that
    # also depends upon it.
    if stripped[0:1] in ("-", "*") and not stripped[0:2] == "**":
        return not wrap_list_items

    # If text contains a pipe character it is likely a table
    if not wrap_tables and config.RE_TABLE.search(para):
        return True

    # If the text begins with a single -, *, or +, followed by a space,
    # or an integer, followed by a ., followed by a space (in either
    # case optionally proceeded by whitespace), it's a list; don't wrap.
    return bool(
        config.RE_ORDERED_LIST_MATCHER.match(stripped)
        or config.RE_UNORDERED_LIST_MATCHER.match(stripped)
    )


def escape_md(text: str) -> str:
    """
    Escapes markdown-sensitive characters within other markdown
    constructs.
    """
    return config.RE_MD_CHARS_MATCHER.sub(r"\\\1", text)


def escape_md_section(text: str, snob: bool = False) -> str:
    """
    Escapes markdown-sensitive characters across whole document sections.
    """
    text = config.RE_MD_BACKSLASH_MATCHER.sub(r"\\\1", text)

    if snob:
        text = config.RE_MD_CHARS_MATCHER_ALL.sub(r"\\\1", text)

    text = config.RE_MD_DOT_MATCHER.sub(r"\1\\\2", text)
    text = config.RE_MD_PLUS_MATCHER.sub(r"\1\\\2", text)
    text = config.RE_MD_DASH_MATCHER.sub(r"\1\\\2", text)

    return text


def reformat_table(lines: List[str], right_margin: int) -> List[str]:
    """
    Given the lines of a table
    padds the cells and returns the new lines
    """
    # find the maximum width of the columns
    max_width = [len(x.rstrip()) + right_margin for x in lines[0].split("|")]
    max_cols = len(max_width)
    for line in lines:
        cols = [x.rstrip() for x in line.split("|")]
        num_cols = len(cols)

        # don't drop any data if colspan attributes result in unequal lengths
        if num_cols < max_cols:
            cols += [""] * (max_cols - num_cols)
        elif max_cols < num_cols:
            max_width += [len(x) + right_margin for x in cols[-(num_cols - max_cols) :]]
            max_cols = num_cols

        max_width = [
            max(len(x) + right_margin, old_len) for x, old_len in zip(cols, max_width)
        ]

    # reformat
    new_lines = []
    for line in lines:
        cols = [x.rstrip() for x in line.split("|")]
        if set(line.strip()) == set("-|"):
            filler = "-"
            new_cols = [
                x.rstrip() + (filler * (M - len(x.rstrip())))
                for x, M in zip(cols, max_width)
            ]
            new_lines.append("|-" + "|".join(new_cols) + "|")
        else:
            filler = " "
            new_cols = [
                x.rstrip() + (filler * (M - len(x.rstrip())))
                for x, M in zip(cols, max_width)
            ]
            new_lines.append("| " + "|".join(new_cols) + "|")
    return new_lines


def pad_tables_in_text(text: str, right_margin: int = 1) -> str:
    """
    Provide padding for tables in the text
    """
    lines = text.split("\n")
    table_buffer = []  # type: List[str]
    table_started = False
    new_lines = []
    for line in lines:
        # Toggle table started
        if config.TABLE_MARKER_FOR_PAD in line:
            table_started = not table_started
            if not table_started:
                table = reformat_table(table_buffer, right_margin)
                new_lines.extend(table)
                table_buffer = []
                new_lines.append("")
            continue
        # Process lines
        if table_started:
            table_buffer.append(line)
        else:
            new_lines.append(line)
    return "\n".join(new_lines)
././@PaxHeader0000000000000000000000000000003300000000000010211 xustar0027 mtime=1744689734.577402
html2text-2025.4.15/html2text.egg-info/0000755000175100001660000000000014777355107017035 5ustar00runnerdocker././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689734.0
html2text-2025.4.15/html2text.egg-info/PKG-INFO0000644000175100001660000001006114777355106020127 0ustar00runnerdockerMetadata-Version: 2.4
Name: html2text
Version: 2025.4.15
Summary: Turn HTML into equivalent Markdown-structured text.
Author-email: Aaron Swartz 
Maintainer-email: Alireza Savand 
License-Expression: GPL-3.0-or-later
Project-URL: Homepage, https://github.com/Alir3z4/html2text/
Platform: OS Independent
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: Implementation :: CPython
Classifier: Programming Language :: Python :: Implementation :: PyPy
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: COPYING
License-File: AUTHORS.rst
Dynamic: license-file

# html2text

[![CI](https://github.com/Alir3z4/html2text/actions/workflows/main.yml/badge.svg?branch=master)](https://github.com/Alir3z4/html2text/actions/workflows/main.yml)
[![codecov](https://codecov.io/gh/Alir3z4/html2text/graph/badge.svg?token=OoxiyymjgU)](https://codecov.io/gh/Alir3z4/html2text)



html2text is a Python script that converts a page of HTML into clean, easy-to-read plain ASCII text. Better yet, that ASCII also happens to be valid Markdown (a text-to-HTML format).


Usage: `html2text [filename [encoding]]`

| Option                                                 | Description
|--------------------------------------------------------|---------------------------------------------------
| `--version`                                            | Show program's version number and exit
| `-h`, `--help`                                         | Show this help message and exit
| `--ignore-links`                                       | Don't include any formatting for links
|`--escape-all`                                          | Escape all special characters.  Output is less readable, but avoids corner case formatting issues.
| `--reference-links`                                    | Use reference links instead of links to create markdown
| `--mark-code`                                          | Mark preformatted and code blocks with [code]...[/code]

For a complete list of options see the [docs](https://github.com/Alir3z4/html2text/blob/master/docs/usage.md)


Or you can use it from within `Python`:

```
>>> import html2text
>>>
>>> print(html2text.html2text("
        Zed's dead baby, Zed's dead.
        "))
**Zed's** dead baby, _Zed's_ dead.

```


Or with some configuration options:
```
>>> import html2text
>>>
>>> h = html2text.HTML2Text()
>>> # Ignore converting links from HTML
>>> h.ignore_links = True
>>> print h.handle("
        Hello, world!")
Hello, world!

>>> print(h.handle("
        Hello, world!"))

Hello, world!

>>> # Don't Ignore links anymore, I like links
>>> h.ignore_links = False
>>> print(h.handle("
        Hello, world!"))
Hello, [world](https://www.google.com/earth/)!

```

*Originally written by Aaron Swartz. This code is distributed under the GPLv3.*


## How to install

`html2text` is available on pypi
https://pypi.org/project/html2text/

```shell
$ pip install html2text
```

##  Development

### How to run unit tests

```shell
$ tox
```

To see the coverage results:

```shell
$ coverage html
```

then open the `./htmlcov/index.html` file in your browser.


### Code Quality & Pre Commit

The CI runs several linting steps, including:

- mypy
- Flake8
- Black

To make sure the code passes the CI linting steps, run:

```shell
$ tox -e pre-commit
```

## Documentation

Documentation lives [here](https://github.com/Alir3z4/html2text/blob/master/docs/usage.md)
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689734.0
html2text-2025.4.15/html2text.egg-info/SOURCES.txt0000644000175100001660000001071514777355106020724 0ustar00runnerdocker.gitattributes
.gitignore
AUTHORS.rst
COPYING
ChangeLog.rst
ISSUE_TEMPLATE
MANIFEST.in
README.md
pyproject.toml
tox.ini
.github/workflows/main.yml
.github/workflows/pypi.yml
docs/about.md
docs/authors.md
docs/contributing.md
docs/how_it_works.md
docs/index.md
docs/test.md
docs/usage.md
html2text/__init__.py
html2text/__main__.py
html2text/_typing.py
html2text/_version.py
html2text/cli.py
html2text/config.py
html2text/elements.py
html2text/py.typed
html2text/utils.py
html2text.egg-info/PKG-INFO
html2text.egg-info/SOURCES.txt
html2text.egg-info/dependency_links.txt
html2text.egg-info/entry_points.txt
html2text.egg-info/not-zip-safe
html2text.egg-info/top_level.txt
test/GoogleDocMassDownload.html
test/GoogleDocMassDownload.md
test/GoogleDocSaved.html
test/GoogleDocSaved.md
test/GoogleDocSaved_two.html
test/GoogleDocSaved_two.md
test/__init__.py
test/abbr_tag.html
test/abbr_tag.md
test/anchors.html
test/anchors.md
test/apos_element.html
test/apos_element.md
test/backquote_code_style.html
test/backquote_code_style.md
test/blockquote_example.html
test/blockquote_example.md
test/bodywidth_newline.html
test/bodywidth_newline.md
test/bold_inside_link.html
test/bold_inside_link.md
test/bold_long_line.html
test/bold_long_line.md
test/br_inside_a.md
test/break_preserved_in_blockquote.html
test/break_preserved_in_blockquote.md
test/css_import_no_semicolon.html
test/css_import_no_semicolon.md
test/decript_tage.html
test/decript_tage.md
test/default_image_alt.html
test/default_image_alt.md
test/doc_with_table.html
test/doc_with_table.md
test/doc_with_table_bypass.html
test/doc_with_table_bypass.md
test/emdash-para.html
test/emdash-para.md
test/emphasis_preserved_whitespace.html
test/emphasis_preserved_whitespace.md
test/emphasis_whitespace.html
test/emphasis_whitespace.md
test/empty-img-src.html
test/empty-img-src.md
test/empty-link.html
test/empty-link.md
test/empty-title-tag.html
test/empty-title-tag.md
test/flip_emphasis.html
test/flip_emphasis.md
test/google-like_font-properties.html
test/google-like_font-properties.md
test/header_tags.html
test/header_tags.md
test/horizontal_rule.html
test/horizontal_rule.md
test/html-escaping.html
test/html-escaping.md
test/html_entities_out_of_text.html
test/html_entities_out_of_text.md
test/images_as_html.html
test/images_as_html.md
test/images_to_alt.html
test/images_to_alt.md
test/images_with_div_wrap.html
test/images_with_div_wrap.md
test/images_with_size.html
test/images_with_size.md
test/img-tag-with-link.html
test/img-tag-with-link.md
test/inplace_baseurl_substitution.html
test/inplace_baseurl_substitution.md
test/invalid_start.html
test/invalid_start.md
test/invalid_unicode.html
test/invalid_unicode.md
test/kbd_tag.html
test/kbd_tag.md
test/link_titles.html
test/link_titles.md
test/list_tags_example.html
test/list_tags_example.md
test/long_lines.html
test/long_lines.md
test/lrm_after_b.html
test/lrm_after_b.md
test/lrm_after_i.html
test/lrm_after_i.md
test/lrm_inside_i.html
test/lrm_inside_i.md
test/mark_code.html
test/mark_code.md
test/mixed_nested_lists.html
test/mixed_nested_lists.md
test/nbsp.html
test/nbsp.md
test/nbsp_unicode.html
test/nbsp_unicode.md
test/no_inline_links_example.html
test/no_inline_links_example.md
test/no_inline_links_images_to_alt.html
test/no_inline_links_images_to_alt.md
test/no_inline_links_nested.html
test/no_inline_links_nested.md
test/no_mailto_links.html
test/no_mailto_links.md
test/no_p_in_table.html
test/no_p_in_table.md
test/no_wrap_links.html
test/no_wrap_links.md
test/no_wrap_links_no_inline_links.html
test/no_wrap_links_no_inline_links.md
test/normal.html
test/normal.md
test/normal_escape_snob.html
test/normal_escape_snob.md
test/pad_table.html
test/pad_table.md
test/pad_table_empty.html
test/pad_table_empty.md
test/pad_table_no_closed_tr.html
test/pad_table_no_closed_tr.md
test/pre.html
test/pre.md
test/preformatted_in_list.html
test/preformatted_in_list.md
test/protect_links.html
test/protect_links.md
test/q_tag.html
test/q_tag.md
test/rlm_inside_strong.html
test/rlm_inside_strong.md
test/single_line_break.html
test/single_line_break.md
test/stressed_with_html_entities.html
test/stressed_with_html_entities.md
test/sub_tag.html
test/sub_tag.md
test/sup_tag.html
test/sup_tag.md
test/table_ignore.html
test/table_ignore.md
test/test_html2text.py
test/test_memleak.py
test/test_newlines_on_multiple_calls.py
test/text_after_list.html
test/text_after_list.md
test/url-escaping.html
test/url-escaping.md
test/wrap_list_items_example.html
test/wrap_list_items_example.md
test/wrap_tables.html
test/wrap_tables.md././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689734.0
html2text-2025.4.15/html2text.egg-info/dependency_links.txt0000644000175100001660000000000114777355106023102 0ustar00runnerdocker
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689734.0
html2text-2025.4.15/html2text.egg-info/entry_points.txt0000644000175100001660000000006114777355106022327 0ustar00runnerdocker[console_scripts]
html2text = html2text.cli:main
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689734.0
html2text-2025.4.15/html2text.egg-info/not-zip-safe0000644000175100001660000000000114777355106021262 0ustar00runnerdocker
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689734.0
html2text-2025.4.15/html2text.egg-info/top_level.txt0000644000175100001660000000001214777355106021557 0ustar00runnerdockerhtml2text
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/pyproject.toml0000644000175100001660000000337114777355103016324 0ustar00runnerdocker[build-system]
requires = ["setuptools>=61.2", "setuptools_scm[toml]>=3.4.3"]
build-backend = "setuptools.build_meta"

[project]
name = "html2text"
description = "Turn HTML into equivalent Markdown-structured text."
readme = "README.md"
authors = [{name = "Aaron Swartz", email = "me@aaronsw.com"}]
maintainers = [{name = "Alireza Savand", email = "alireza.savand@gmail.com"}]
license = "GPL-3.0-or-later"
classifiers = [
    "Development Status :: 5 - Production/Stable",
    "Intended Audience :: Developers",
    "Operating System :: OS Independent",
    "Programming Language :: Python",
    "Programming Language :: Python :: 3",
    "Programming Language :: Python :: 3.9",
    "Programming Language :: Python :: 3.10",
    "Programming Language :: Python :: 3.11",
    "Programming Language :: Python :: 3.12",
    "Programming Language :: Python :: 3.13",
    "Programming Language :: Python :: 3 :: Only",
    "Programming Language :: Python :: Implementation :: CPython",
    "Programming Language :: Python :: Implementation :: PyPy",
]
urls = {Homepage = "https://github.com/Alir3z4/html2text/"}
requires-python = ">=3.9"
dynamic = ["version"]

[project.scripts]
html2text = "html2text.cli:main"

[tool.setuptools]
zip-safe = false
packages = ["html2text"]
platforms = ["OS Independent"]
include-package-data = false

[tool.setuptools.package-data]
html2text = ["py.typed"]

[tool.setuptools_scm]
write_to = "html2text/_version.py"

[tool.black]
line-length = 88
target-version = ['py313']
extend-exclude = '''
/(
  html2text/_version.py
)
'''

[tool.flake8]  # you will need Flake8-pyproject
max_line_length = "88"
extend-ignore = "E203"

[tool.isort]
profile = "black"
combine_as_imports = true
extend_skip = ["html2text/_version.py"]

[tool.mypy]
python_version = "3.9"
././@PaxHeader0000000000000000000000000000003300000000000010211 xustar0027 mtime=1744689734.577402
html2text-2025.4.15/setup.cfg0000644000175100001660000000004614777355107015231 0ustar00runnerdocker[egg_info]
tag_build = 
tag_date = 0

././@PaxHeader0000000000000000000000000000003300000000000010211 xustar0027 mtime=1744689734.577402
html2text-2025.4.15/test/0000755000175100001660000000000014777355107014367 5ustar00runnerdocker././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/GoogleDocMassDownload.html0000644000175100001660000001352114777355103021431 0ustar00runnerdocker
  
    
    Sandbox
    
  
  
    
        
      
      
      
      test doc
    
        
    
        
    
    first issue
    
        
    
        
    
    
    
        
    
          
      
        1. 
      
      bit
      
          2. 
      
        2. 
      
      bold italic
      
          3. 
    
        
    
          
      
        1. 
      
      orange
      
          2. 
      
        2. 
      
      apple
      
          3. 
    
        
    
          
      
        1. 
      
      final
      
          2. 
    
        
    
        
    
    
    
        
    
        
    
    text to separate lists
    
        
    
        
    
    
    
        
    
          
      
        1. 
      
      now with numbers
      
          2. 
      
        2. 
      
      the prisoner
      
          3. 
    
        
    
          
      
        1. 
      
      not an 
      
      italic number
      
          2. 
      
        2. 
      
      a 
      
      bold human
      
       being
      
          3. 
    
        
    
          
      
        1. 
      
      end
      
          2. 
    
        
    
        
    
    
    
        
    
        
    
    bold
    
        
    
        
    
    italic
    
        
    
        
    
    
    
        
    
        
    
    def func(x):
    
        
    
        
    
      if x < 1:
    
        
    
        
    
        return 'a'
    
        
    
        
    
      return 'b'
    
        
    
        
    
    
    
        
    
        
    
    Some 
    
    fixed width text
    
     here
    
        
    
        
    
    italic fixed width text
    
        
    
        
    
    
    
        
  


././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/GoogleDocMassDownload.md0000644000175100001660000000064314777355103021066 0ustar00runnerdocker#  test doc  
  
first issue  
  
  - bit
  - _**bold italic**_ 
    - orange
    - apple
  - final  
  
text to separate lists  
  
  1. now with numbers
  2. the prisoner
    1. not an  _italic number_ 
    2. a  **bold human**   being
  3. end  
  
**bold**   
_italic_   
  
` def func(x):`  
`   if x < 1:`  
`     return 'a'`  
`   return 'b'`  
  
Some  ` fixed width text`  here  
_` italic fixed width text`_ 
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/GoogleDocSaved.html0000644000175100001660000000743014777355103020102 0ustar00runnerdocker
  
    
    Sandbox
    
  
  
    
        
      
      
      
      test doc
    
        
    
        
    
    first issue
    
        
    
        
    
    
    
        
    
          
      
        1. 
      
      bit
      
          2. 
      
        2. 
      
      bold italic
      
          3. 
    
        
    
          
      
        1. 
      
      orange
      
          2. 
      
        2. 
      
      apple
      
          3. 
    
        
    
          
      
        1. 
      
      final
      
          2. 
    
        
    
        
    
    
    
        
    
        
    
    text to separate lists
    
        
    
        
    
    
    
        
    
          
      
        1. 
      
      now with numbers
      
          2. 
      
        2. 
      
      the prisoner
      
          3. 
    
        
    
          
      
        1. 
      
      not an 
      
      italic number
      
          2. 
      
        2. 
      
      a 
      
      bold human
      
       being
      
          3. 
    
        
    
          
      
        1. 
      
      end
      
          2. 
    
        
    
        
    
    
    
        
    
        
    
    bold
    
        
    
        
    
    italic
    
        
    
        
    
    
    
        
    
        
    
    def func(x):
    
        
    
        
    
      if x < 1:
    
        
    
        
    
        return 'a'
    
        
    
        
    
      return 'b'
    
        
    
        
    
    
    
        
    
        
    
    Some 
    
    fixed width text
    
     here
    
        
    
        
    
    italic fixed width text
    
        
    
        
    
    
    
        
  


././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/GoogleDocSaved.md0000644000175100001660000000064314777355103017535 0ustar00runnerdocker#  test doc  
  
first issue  
  
  - bit
  - _**bold italic**_ 
    - orange
    - apple
  - final  
  
text to separate lists  
  
  1. now with numbers
  2. the prisoner
    1. not an  _italic number_ 
    2. a  **bold human**   being
  3. end  
  
**bold**   
_italic_   
  
` def func(x):`  
`   if x < 1:`  
`     return 'a'`  
`   return 'b'`  
  
Some  ` fixed width text`  here  
_` italic fixed width text`_ 
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/GoogleDocSaved_two.html0000644000175100001660000000746514777355103021003 0ustar00runnerdocker
  
    
    Sandbox
    
  
  
    
        
      
      
      
      test doc
    
        
    
        
    
    first issue
    
        
    
        
    
    
    
        
    
          
      
        1. 
      
      bit
      
          2. 
      
        2. 
      
      bold italic
      
          3. 
    
        
    
          
      
        1. 
      
      orange
      
          2. 
      
        2. 
      
      apple
      
          3. 
    
        
    
          
      
        1. 
      
      final
      
          2. 
    
        
    
        
    
    
    
        
    
        
    
    text to separate lists
    
        
    
        
    
    
    
        
    
          
      
        1. 
      
      now with numbers
      
          2. 
      
        2. 
      
      the prisoner
      
          3. 
    
        
    
          
      
        1. 
      
      not an 
      
      italic number
      
          2. 
      
        2. 
      
      a 
      
      bold human
      
       being
      
          3. 
    
        
    
          
      
        1. 
      
      end
      
          2. 
    
        
    
        
    
    
    
        
    
        
    
    bold
    
        
    
        
    
    italic
    
        
    
        
    
    
    
        
    
        
    
    def func(x):
    
        
    
        
    
      if x < 1:
    
        
    
        
    
        return 'a'
    
        
    
        
    
      return 'b'
    
        
    
        
    
    
    
        
    
        
    
    Some 
    
    fixed width text
    
     here
    
        
    
        
    
    italic fixed width text
    
        
    
        
    
    
    
        
  


././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/GoogleDocSaved_two.md0000644000175100001660000000000014777355103020411 0ustar00runnerdocker././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/__init__.py0000644000175100001660000000000014777355103016462 0ustar00runnerdocker././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/abbr_tag.html0000644000175100001660000000007714777355103017016 0ustar00runnerdockerTLA
xyz
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/abbr_tag.md0000644000175100001660000000005014777355103016441 0ustar00runnerdockerTLA xyz

  *[TLA]: Three Letter Acronym
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/anchors.html0000644000175100001660000000042714777355103016711 0ustar00runnerdocker
        Processing hyperlinks
        


        Additional hyperlink tests!
        

Bold Link
filename.py
The source code is called magic.py
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/anchors.md0000644000175100001660000000031714777355103016343 0ustar00runnerdocker# Processing hyperlinks

Additional hyperlink tests!

[**Bold Link**](http://some.link)
[`filename.py`](http://some.link/filename.py) [The source code is called
`magic.py`](http://some.link/magicsources.py)
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/apos_element.html0000644000175100001660000000006514777355103017725 0ustar00runnerdocker
    
        '
    

././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/apos_element.md0000644000175100001660000000000214777355103017350 0ustar00runnerdocker'
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/backquote_code_style.html0000644000175100001660000000056214777355103021444 0ustar00runnerdocker
        def func(x):
  if x < 1:
    return 'a'
  return 'b'

        


          
  
        • unordered
          • 
  
        • ...
          • 
  
            
    
          1. ordered
            2. 
    
          2. code:
      
            a
b
c
            
    
            3. 
    
          3. ...
            4. 
    
              
      
            1. ordered
              2. 
      
            2. code:
        
              d
e
f
              
      
              3. 
      
            3. ...
              4. 
    
            
    
          4. end
            5. 
  
          
  
        • end
          • 

        
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/backquote_code_style.md0000644000175100001660000000046614777355103021103 0ustar00runnerdocker
```
def func(x):
  if x < 1:
    return 'a'
  return 'b'

```

  * unordered
  * ...
    1. ordered
    2. code: 
       ```
       a
       b
       c
       ```

    3. ...
       1. ordered
       2. code: 
          ```
          d
          e
          f
          ```

       3. ...
    4. end
  * end

././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/blockquote_example.html0000644000175100001660000000033314777355103021133 0ustar00runnerdocker
        
"The time has come", the Walrus said, "To talk of many things: Of shoes - and ships - and sealing wax - Of cabbages - and kings- And why the sea is boiling hot - And whether pigs have wings."

        
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/blockquote_example.md0000644000175100001660000000030614777355103020567 0ustar00runnerdocker> "The time has come", the Walrus said, "To talk of many things: Of shoes -
> and ships - and sealing wax - Of cabbages - and kings- And why the sea is
> boiling hot - And whether pigs have wings."
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/bodywidth_newline.html0000644000175100001660000000055714777355103020776 0ustar00runnerdocker
        Another theory is that magician and occultist Aliester Crowley created the beast while
    attempting to summon evil spirits at his house on the edge of the
    lake in the early 1900′s. I met a local woman who
        prefers this explanation.
        
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/bodywidth_newline.md0000644000175100001660000000043414777355103020424 0ustar00runnerdockerAnother theory is that magician and occultist [Aliester Crowley](http://en.wikipedia.org/wiki/Aleister_Crowley) created the beast while attempting to summon evil spirits at his house on the edge of the lake in the early 1900′s. **I met a local woman who prefers this explanation.**
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/bold_inside_link.html0000644000175100001660000000011114777355103020532 0ustar00runnerdockerText
sample
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/bold_inside_link.md0000644000175100001660000000005614777355103020176 0ustar00runnerdocker[**Text**](link.htm) [**sample**](/nothing/)

././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/bold_long_line.html0000644000175100001660000000021114777355103020211 0ustar00runnerdocker
        
text and a very long long long long long long long long long long long long long long long long long long long long line

        
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/bold_long_line.md0000644000175100001660000000017514777355103017656 0ustar00runnerdocker**text** and a very long long long long long long long long long long long
long long long long long long long long long line
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/br_inside_a.md0000644000175100001660000000004714777355103017144 0ustar00runnerdocker[This is a test](https://example.org/)
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/break_preserved_in_blockquote.html0000644000175100001660000000004114777355103023325 0ustar00runnerdockera
        b
        c
        
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/break_preserved_in_blockquote.md0000644000175100001660000000001514777355103022762 0ustar00runnerdockera

> b  
> c
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/css_import_no_semicolon.html0000644000175100001660000000066214777355103022203 0ustar00runnerdocker
  
    NBSP handling test #1
    
  
  
    
        CSS @import statement without semicolon handling test
        
    
        Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
        
  


././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/css_import_no_semicolon.md0000644000175100001660000000026614777355103021637 0ustar00runnerdocker# CSS @import statement without semicolon handling test

Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua.
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/decript_tage.html0000644000175100001660000000010114777355103017673 0ustar00runnerdockersomething
something
something
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/decript_tage.md0000644000175100001660000000005214777355103017334 0ustar00runnerdocker~~something~~ ~~something~~ ~~something~~
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/default_image_alt.html0000644000175100001660000000007614777355103020702 0ustar00runnerdocker
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/default_image_alt.md0000644000175100001660000000006114777355103020330 0ustar00runnerdocker[![Image](images/google.png)](http://google.com)
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/doc_with_table.html0000644000175100001660000000131314777355103020216 0ustar00runnerdocker


    
    




        This is a test document
        

With some text, code, bolds and italics.


        This is second header
        


        Displaynone text
        


        
    
        
        Header 1
        Header 2
        Header 3
    
        
    
        
        Content 1
        Content 2
        200 Image!
    
        
    
        
        Content 1
        Content 2
        200 Image!
    
        

        


././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/doc_with_table.md0000644000175100001660000000046414777355103017660 0ustar00runnerdocker# This is a test document

With some text, `code`, **bolds** and _italics_.

## This is second header

Displaynone text

Header 1 | Header 2 | Header 3  
---|---|---  
Content 1 | Content 2 | ![200](http://lorempixel.com/200/200) Image!  
Content 1 | Content 2 | ![200](http://lorempixel.com/200/200) Image!
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/doc_with_table_bypass.html0000644000175100001660000000106614777355103021604 0ustar00runnerdocker


    
    




        This is a test document
        

With some text, code, bolds and italics.


        This is second header
        


        Displaynone text
        


        
    
        
        Header 1
        Header 2
        Header 3
    
        
    
        
        Content 1
        Content 2
        200 Image!
    
        


        


././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/doc_with_table_bypass.md0000644000175100001660000000053614777355103021241 0ustar00runnerdocker# This is a test document

With some text, `code`, **bolds** and _italics_.

## This is second header

Displaynone text  
  

          

          


Header 1

  


Header 2

  


Header 3

 
          

          


Content 1

  


Content 2

  


![200](http://lorempixel.com/200/200) Image!

 
         
        
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/emdash-para.html0000644000175100001660000000143714777355103017440 0ustar00runnerdocker
        Bacon ipsum dolor sit amet pork chop id pork belly ham hock, sed meatloaf eu exercitation flank quis veniam officia. Chuck dolor esse, occaecat est elit drumstick ground round tri-tip nisi. Eu fugiat drumstick leberkas magna. Turducken frankfurter nisi aute shank—
        

        —irure ex esse id, ham commodo meatloaf pig pariatur ut cow. Officia salami in fatback voluptate boudin ullamco beef ribs shank. Duis spare ribs pork chop, ad leberkas reprehenderit id voluptate salami ham ut in ut cillum turducken. Nisi ribeye tail capicola dolore andouille. Short ribs id beef ribs, et nulla ground round do sunt dolore. Dolore nisi ullamco veniam sunt. Duis brisket drumstick, dolor fatback filet mignon meatloaf laboris tri-tip speck chuck ball tip voluptate ullamco laborum.

        

        --
        
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/emdash-para.md0000644000175100001660000000140214777355103017064 0ustar00runnerdockerBacon ipsum dolor sit amet pork chop id pork belly ham hock, sed meatloaf eu
exercitation flank quis veniam officia. Chuck dolor esse, occaecat est elit
drumstick ground round tri-tip nisi. Eu fugiat drumstick leberkas magna.
Turducken frankfurter nisi aute shank--

--irure ex esse id, ham commodo meatloaf pig pariatur ut cow. Officia salami
in fatback voluptate boudin ullamco beef ribs shank. Duis spare ribs pork
chop, ad leberkas reprehenderit id voluptate salami ham ut in ut cillum
turducken. Nisi ribeye tail capicola dolore andouille. Short ribs id beef
ribs, et nulla ground round do sunt dolore. Dolore nisi ullamco veniam sunt.
Duis brisket drumstick, dolor fatback filet mignon meatloaf laboris tri-tip
speck chuck ball tip voluptate ullamco laborum.

\--
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/emphasis_preserved_whitespace.html0000644000175100001660000000124414777355103023356 0ustar00runnerdocker
         emphasis 
        

        emphasis: some text
        

        repeat: again
        


         bold 
        

        bold: some text
        

        repeat: again
        


         strike 
        

        strike: some text
        

        strike: again
        


        separate emphasis some more text
        



        emphasis.
        

        emphasis?
        

        emphasis!
        

        (emphasis)
        

        [bold}
        

        (strike]
        



        *bold
        

        ~strike
        


        em1em2
        
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/emphasis_preserved_whitespace.md0000644000175100001660000000046514777355103023016 0ustar00runnerdocker_emphasis_

_emphasis:_ some text

_repeat:_ again

**bold**

**bold:** some text

**repeat:** again

~~strike~~

~~strike:~~ some text

~~strike:~~ again

separate _emphasis_ some more text

_emphasis_.

_emphasis_?

_emphasis_!

(_emphasis_)

[**bold**}

(~~strike~~]

* **bold**

~ ~~strike~~

_em1_ _em2_
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/emphasis_whitespace.html0000644000175100001660000000130714777355103021277 0ustar00runnerdocker
         ib
        


        .ib
        


         bi
        


        .bi
        


         is
        


        .is
        


         si
        


        .si
        


         bs
        


        .bs
        


         sb
        


        .sb
        


         sbi
        


        .sbi
        


         bis
        


        .bis
        
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/emphasis_whitespace.md0000644000175100001660000000030314777355103020726 0ustar00runnerdocker_**ib**_

._**ib**_

**_bi_**

.**_bi_**

_~~is~~_

._~~is~~_

_~~si~~_

._~~si~~_

**~~bs~~**

.**~~bs~~**

~~**sb**~~

.~~**sb**~~

~~**_sbi_**~~

.~~**_sbi_**~~

**_~~bis~~_**

.**_~~bis~~_**
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/empty-img-src.html0000644000175100001660000000005114777355103017742 0ustar00runnerdocker
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/empty-img-src.md0000644000175100001660000000000214777355103017372 0ustar00runnerdocker

././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/empty-link.html0000644000175100001660000000030314777355103017336 0ustar00runnerdocker
        Processing empty hyperlinks
        


        This test checks whether empty hyperlinks still appear in the markdown result.
        



        ././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/empty-link.md0000644000175100001660000000023114777355103016772 0ustar00runnerdocker# Processing empty hyperlinks

This test checks whether empty hyperlinks still appear in the markdown result.

[](http://some.link) [](http://some.link)
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/empty-title-tag.html0000644000175100001660000000011314777355103020272 0ustar00runnerdockerThis is an A tag with an empty title property././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/empty-title-tag.md0000644000175100001660000000007314777355103017733 0ustar00runnerdocker[This is an A tag with an empty title property](test.html)
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/flip_emphasis.html0000644000175100001660000000003514777355103020072 0ustar00runnerdockerSomething
else
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/flip_emphasis.md0000644000175100001660000000002514777355103017525 0ustar00runnerdocker*Something* __else__
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/google-like_font-properties.html0000644000175100001660000000173114777355103022671 0ustar00runnerdocker
  
    CAPS-LOCK TEST
  
  
    
        font-weight: bold
        
    
        FONT-WEIGHT: BOLD
        
    
        font-weight: 700
        
    
        FONT-WEIGHT: 700
        
    
        font-weight: 800
        
    
        FONT-WEIGHT: 800
        
    
        font-weight: 900
        
    
        FONT-WEIGHT: 900
        
    
        font-style: italic
        
    
        FONT-STYLE: ITALIC
        
    
        
      font-weight: bold;font-style: italic
        
    
        
      FONT-WEIGHT: BOLD;FONT-STYLE: ITALIC
        
  

././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/google-like_font-properties.md0000644000175100001660000000051414777355103022323 0ustar00runnerdocker**font-weight: bold**   
**FONT-WEIGHT: BOLD**   
**font-weight: 700**   
**FONT-WEIGHT: 700**   
**font-weight: 800**   
**FONT-WEIGHT: 800**   
**font-weight: 900**   
**FONT-WEIGHT: 900**   
_font-style: italic_   
_FONT-STYLE: ITALIC_   
_**font-weight: bold;font-style: italic**_   
_**FONT-WEIGHT: BOLD;FONT-STYLE: ITALIC**_ 
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/header_tags.html0000644000175100001660000000040414777355103017515 0ustar00runnerdocker
    
    
        H1
        
    
        H2
        
    
        H3
        
    
        H4
        
    
        H5
        
    
        H6
        
    H7
    H8
    H9
    H10
    H11
    H12
    NO number
    

././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/header_tags.md0000644000175100001660000000016014777355103017150 0ustar00runnerdocker# H1

## H2

### H3

#### H4

##### H5

###### H6

####### H7

######## H8

######### H9

H10 H11 H12 NO number
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/horizontal_rule.html0000644000175100001660000000005714777355103020473 0ustar00runnerdocker
    
    
        
    

././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/horizontal_rule.md0000644000175100001660000000000614777355103020121 0ustar00runnerdocker* * *
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/html-escaping.html0000644000175100001660000000027114777355103020004 0ustar00runnerdocker
        Escaped HTML like <div> or & should NOT remain escaped on output
        

        ...even when that escaped HTML is in a <pre> tag
        
...or a <code> tag././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/html-escaping.md0000644000175100001660000000022714777355103017441 0ustar00runnerdockerEscaped HTML like 
         or & should NOT remain escaped on output

    
    
    ...even when that escaped HTML is in a 
         tag

`...or a  tag`
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/html_entities_out_of_text.html0000644000175100001660000000007314777355103022540 0ustar00runnerdockerállás: Country Manager
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/html_entities_out_of_text.md0000644000175100001660000000004614777355103022174 0ustar00runnerdocker[allas: Country Manager](http://thth)
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/images_as_html.html0000644000175100001660000000115714777355103020231 0ustar00runnerdocker

An image with a width attr

An image with a height attr

An image with width and height



././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/images_as_html.md0000644000175100001660000000065614777355103017670 0ustar00runnerdocker An image with a width attr An image with a height attr
An
image with width and height  
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/images_to_alt.html0000644000175100001660000000044014777355103020056 0ustar00runnerdocker
ALT TEXT


        
ALT TEXT

        
http://example.com././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/images_to_alt.md0000644000175100001660000000013214777355103017510 0ustar00runnerdocker[ ALT TEXT ](http://example.com)  
[ALT TEXT](http://example.com)  


././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/images_with_div_wrap.html0000644000175100001660000000012414777355103021441 0ustar00runnerdocker
        
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/images_with_div_wrap.md0000644000175100001660000000006714777355103021103 0ustar00runnerdocker[![](http://example.com/img.png)](http://example.com)

././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/images_with_size.html0000644000175100001660000000152714777355103020610 0ustar00runnerdockerAn image without dimensions

An image with a width attr

An image with a height attr

An image with width and height







././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/images_with_size.md0000644000175100001660000000113214777355103020234 0ustar00runnerdocker![An image without dimensions](image_without_dimensions.jpg) An image with a width attr
An image with a height attr An
image with width and height  ![](image_with_width_and_height.jpg)   
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/img-tag-with-link.html0000644000175100001660000000124414777355103020503 0ustar00runnerdocker
        Processing images with links
        


        This test checks images with associated links.
        

(banana)
[banana]
{banana}
([{}])
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/img-tag-with-link.md0000644000175100001660000000066414777355103020144 0ustar00runnerdocker# Processing images with links

This test checks images with associated links.

[![\(banana\)](http://placehold.it/350x150#\(banana\))](http://some.link)
[![\[banana\]](http://placehold.it/350x150#\[banana\])](http://some.link)
[![{banana}](http://placehold.it/350x150#{banana})](http://some.link)
[![\(\[{}\]\)](http://placehold.it/350x150#\(\[{}\]\))](http://some.link)
[![](http://placehold.it/350x150#\(\[{}\]\))](http://some.link)
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/inplace_baseurl_substitution.html0000644000175100001660000000032114777355103023231 0ustar00runnerdocker



        
read2text header image

        

        
BrettTerpstra.com

        


././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/inplace_baseurl_substitution.md0000644000175100001660000000021014777355103022662 0ustar00runnerdocker![read2text header image](http://brettterpstra.com/uploads/2012/01/read2textheader.jpg)

[BrettTerpstra.com](http://brettterpstra.com/)
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/invalid_start.html0000644000175100001660000000025014777355103020111 0ustar00runnerdocker
   
      
          
         
        1. The ol has an invalid start 
          2. 
         
        2. This should just be ignored 
          3. 
      
        
   
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/invalid_start.md0000644000175100001660000000010414777355103017543 0ustar00runnerdocker  1. The ol has an invalid start 
  2. This should just be ignored 
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/invalid_unicode.html0000644000175100001660000000032114777355103020401 0ustar00runnerdockerB�r

€‚ƒ„…†‡ˆ‰Š‹ŒŽ‘’“”•–—˜™š›œžŸ

����
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/invalid_unicode.md0000644000175100001660000000013314777355103020036 0ustar00runnerdockerB�r €‚ƒ„…†‡ˆ‰Š‹ŒŽ‘’“”•–—˜™š›œžŸ ����
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/kbd_tag.html0000644000175100001660000000004314777355103016641 0ustar00runnerdockerPress [CTRL]+c to copy.
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/kbd_tag.md0000644000175100001660000000003214777355103016273 0ustar00runnerdockerPress `[CTRL]+c` to copy.
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/link_titles.html0000644000175100001660000000017614777355103017576 0ustar00runnerdocker first example

        

         second example
        
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/link_titles.md0000644000175100001660000000012714777355103017226 0ustar00runnerdocker[ first example](http://example.com "MyTitle")  
[ second example](http://example.com)
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/list_tags_example.html0000644000175100001660000000123314777355103020754 0ustar00runnerdocker
        

        Definition List
        

        A list of terms and their definitions/descriptions.
        

        Ordered List
        

        A numbered list.
        

        Unordered List
        

        An unnumbered list.
        

        


        Example 2
        

        

        Vocals
        

        Bruce Dickinson
        

        Guitar
        

        Adrian Smith
        

        Dave Murray
        

        Janick Gers
        

        Bass
        

        Steve Harris
        

        Drums
        

        Nicko McBrain
        

        


          

        • some item
          • 

        • Some other item
          • 

        • some item
          • 

        


          

        1. Some other item
          2. 

        2. some item
          3. 

        3. some item
          4. 

        


          

        • something else here
          • 

        • some item
          • 

        
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/list_tags_example.md0000644000175100001660000000066614777355103020421 0ustar00runnerdockerDefinition List

    A list of terms and their definitions/descriptions.
Ordered List

    A numbered list.
Unordered List

    An unnumbered list.

#### Example 2

Vocals

    Bruce Dickinson
Guitar

    Adrian Smith
    Dave Murray
    Janick Gers
Bass

    Steve Harris
Drums

    Nicko McBrain

  * some item
  * Some other item
  * some item

  1. Some other item
  2. some item
  3. some item

  * something else here
  * some item
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/long_lines.html0000644000175100001660000000165314777355103017407 0ustar00runnerdockerasd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd  asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/long_lines.md0000644000175100001660000000164414777355103017043 0ustar00runnerdockerasd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd
asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd
asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd
asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd
asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd
asd asd asd asd asd
![](http://www.foooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooooo.com)
asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd
asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd
asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd
asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd
asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd asd
asd asd asd asd asd
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/lrm_after_b.html0000644000175100001660000000002014777355103017515 0ustar00runnerdockerb‎
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/lrm_after_b.md0000644000175100001660000000000614777355103017155 0ustar00runnerdocker**b**
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/lrm_after_i.html0000644000175100001660000000001714777355103017532 0ustar00runnerdockerFoo‎././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/lrm_after_i.md0000644000175100001660000000000614777355103017164 0ustar00runnerdocker_Foo_
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/lrm_inside_i.html0000644000175100001660000000002214777355103017700 0ustar00runnerdockerFoo‎bar././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/lrm_inside_i.md0000644000175100001660000000001214777355103017333 0ustar00runnerdocker_Foo bar_
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/mark_code.html0000644000175100001660000000023214777355103017172 0ustar00runnerdocker
  

        Normal text with 'pre' code block.
        

        import os

def function():
    a = 1

        

        Normal text continues.
        


././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/mark_code.md0000644000175100001660000000020614777355103016627 0ustar00runnerdockerNormal text with 'pre' code block.

[code]

    import os
    
    def function():
        a = 1
    
[/code]

Normal text continues.
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/mixed_nested_lists.html0000644000175100001660000000101614777355103021135 0ustar00runnerdocker
          
  
        1. ordered
          2. 
  
        2. ...
          3. 
  
            
    
          • unordered
            • 
    
          • ...
            • 
  
          
  
        3. end
          4. 

        


          
  
        • unordered
          • 
  
        • ...
          • 
  
            
    
          1. ordered
            2. 
    
          2. ...
            3. 
  
          
  
        • end
          • 

        



          
  
        • unordered
          • 
  
        • ...
          • 
  
            
    
          1. ordered
            2. 
    
          2. code:
      
            a
b
c
            
    
            3. 
    
          3. ...
            4. 
    
              
      
            1. ordered
              2. 
      
            2. code:
        
              d
e
f
              
      
              3. 
      
            3. ...
              4. 
    
            
    
          4. end
            5. 
  
          
  
        • end
          • 

        
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/mixed_nested_lists.md0000644000175100001660000000055414777355103020577 0ustar00runnerdocker  1. ordered
  2. ...
     * unordered
     * ...
  3. end

  * unordered
  * ...
    1. ordered
    2. ...
  * end

  * unordered
  * ...
    1. ordered
    2. code: 
           
           a
           b
           c

    3. ...
       1. ordered
       2. code: 
              
              d
              e
              f

       3. ...
    4. end
  * end

././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/nbsp.html0000644000175100001660000000141214777355103016211 0ustar00runnerdocker
  
    NBSP handling test #1
  
  
    
        NBSP handling test #1
        

    
        In this test all NBSPs will be replaced with ordinary spaces (unicode_snob = False).
        

    
        Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
    tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
    quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
    consequat.
        

    
        Duis aute irure dolor in reprehenderit in voluptate velit esse
    cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
    proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
        
  


././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/nbsp.md0000644000175100001660000000105714777355103015652 0ustar00runnerdocker# NBSP handling test #1

In this test all NBSPs will be replaced with ordinary spaces (unicode_snob =
False).

Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat.

Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore
eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt
in culpa qui officia deserunt mollit anim id est laborum.
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/nbsp_unicode.html0000644000175100001660000000142414777355103017722 0ustar00runnerdocker
  
    NBSP handling test #2
  
  
    
        NBSP handling test #2
        

    
        In this test all NBSPs will be replaced with unicode non-breaking spaces (unicode_snob = True).
        

    
        Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
    tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
    quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
    consequat.
        

    
        Duis aute irure dolor in reprehenderit in voluptate velit esse
    cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
    proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
        
  

././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/nbsp_unicode.md0000644000175100001660000000110614777355103017353 0ustar00runnerdocker# NBSP handling test #2

In this test all NBSPs will be replaced with unicode non-breaking spaces
(unicode_snob = True).

Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat.

Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore
eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt
in culpa qui officia deserunt mollit anim id est laborum.
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/no_inline_links_example.html0000644000175100001660000000057414777355103022144 0ustar00runnerdockerGoogler
 No href
 No href but title available
 Example



link text

Empty link title
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/no_inline_links_example.md0000644000175100001660000000036714777355103021600 0ustar00runnerdocker[Googler][1] No href No href but title available [ Example][2] [ [ [ link text
][3]][3]][3] [Empty link title][4]

   [1]: http://google.com

   [2]: http://example.com (Example title)

   [3]: http://example.com (abc)

   [4]: http://example.com
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/no_inline_links_images_to_alt.html0000644000175100001660000000044114777355103023311 0ustar00runnerdocker
ALT TEXT


        
ALT TEXT

        
http://example.com
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/no_inline_links_images_to_alt.md0000644000175100001660000000021414777355103022743 0ustar00runnerdocker[ ![ALT TEXT][1] ][2]  
[![ALT TEXT][1]][2]  
[![http://example.com][1]][2]

   [1]: http://example.com/img.png

   [2]: http://example.com
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/no_inline_links_nested.html0000644000175100001660000000007714777355103021771 0ustar00runnerdockerthisthat
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/no_inline_links_nested.md0000644000175100001660000000010014777355103021410 0ustar00runnerdocker[[this][1]that][2]

   [1]: /test2/

   [2]: http://google.com

././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/no_mailto_links.html0000644000175100001660000000010514777355103020426 0ustar00runnerdockerSend an email to me@example.com.
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/no_mailto_links.md0000644000175100001660000000004114777355103020061 0ustar00runnerdockerSend an email to me@example.com.
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/no_p_in_table.html0000644000175100001660000000146014777355103020042 0ustar00runnerdocker 
       
     
        This is a test document
         With some text, code, bolds and italics.  
        This is second header
         
        Displaynone text
         
    
        
        
         Header 1 Header 2 Header 3 
        
        
         
        Content 1
        		 
        2
        		 200 Image! 
        
        
         
        Content 1 longer
        		 
        Content 2
        		 
        blah
        		 
        
        
         
        Content 
        		 
        Content 2
        		 
        blah
        		 
        
        
         
        t 
        		 
        Content 2
        		 
        blah blah blah
        		 
        
    
        

   
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/no_p_in_table.md0000644000175100001660000000051414777355103017475 0ustar00runnerdocker# This is a test document

With some text, `code`, **bolds** and _italics_.

## This is second header

Displaynone text

Header 1 | Header 2 | Header 3  
---|---|---  
Content 1 | 2 | ![200](http://lorempixel.com/200/200) Image!  
Content 1 longer | Content 2 | blah  
Content  | Content 2 | blah  
t  | Content 2 | blah blah blah

././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/no_wrap_links.html0000644000175100001660000000022714777355103020117 0ustar00runnerdockerAnd here is a long link I had at hand.
        
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/no_wrap_links.md0000644000175100001660000000021014777355103017543 0ustar00runnerdockerAnd [here](http://bugs.debian.org/cgi-bin/pkgreport.cgi?tag=multiarch;users=debian-dpkg@lists.debian.org) is a long link I had at hand.
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/no_wrap_links_no_inline_links.html0000644000175100001660000000022314777355103023345 0ustar00runnerdockerAnd here is a long link I had at hand.
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/no_wrap_links_no_inline_links.md0000644000175100001660000000021114777355103022776 0ustar00runnerdockerAnd [here](http://bugs.debian.org/cgi-bin/pkgreport.cgi?tag=multiarch;users=debian-dpkg@lists.debian.org) is a long link I had at hand. 
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/normal.html0000644000175100001660000000433514777355103016546 0ustar00runnerdocker
  
    Normal
    
  
  
    
        
      test doc
    
        
    
        
      first issue
    
        
    
        
      
      
    
        
    
          
      
        • 
        bit
      
          • 
      
        • 
        bold italic
      
          • 
      
            
        
          • 
          orange
        
            • 
        
          • 
          apple
        
            • 
      
          
      
        • 
        final
      
          • 
    
        
    
        
      
      
    
        
    
        
      text to separate lists
    
        
    
        
      
      
    
        
    
          
      
        1. 
        now with numbers
      
          2. 
      
        2. 
        the prisoner
      
          3. 
      
            
        
          1. 
          not an italic number
        
            2. 
        
          2. 
          a bold human being
        
            3. 
      
          
      
        3. 
        end
      
          4. 
    
        
    
        
      
      
    
        
    
        
      
        bold
        
        italic
        
              
    
        
    
        
      
        def func(x):
  if x < 1:
    return 'a'
  return 'b'
      
        
    
        
    
        
      Some fixed width text here
        
      italic fixed width text
    
        



    
        
        2012. Now that was a good year. So was 2011. That's all.
    
        

    
        
        3.14159 is an approximation of pi.
    
        

    
        
        + not + a list item
    
        

    
        
        +foo
    
        

    
        
        - foo - bar
    
        

    
        
        -foo
    
        

    
        
        not a header
        
        --
    
        

    
        
        not a hr
        
        
        
        ---
        
        
        - - -
    
        

    
        
        c:\tmp, \\server\path, \_/, foo\bar, #\#, \\#
    
        
  

././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/normal.md0000644000175100001660000000120614777355103016174 0ustar00runnerdocker#  test doc

first issue

  * bit
  * _**bold italic**_
    * orange
    * apple
  * final

text to separate lists

  1. now with numbers
  2. the prisoner
     1. not an _italic number_
     2. a **bold human** being
  3. end

**bold**  
_italic_  

    
    
    def func(x):
      if x < 1:
        return 'a'
      return 'b'
          

Some `fixed width text` here  
_`italic fixed width text`_

2012\. Now that was a good year. So was 2011. That's all.

3.14159 is an approximation of pi.

\+ not + a list item

+foo

\- foo - bar

-foo 

not a header  
\--

not a hr  
  
\---  
\- - -

c:\tmp, \\\server\path, \\_/, foo\bar, #\\#, \\\\#
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/normal_escape_snob.html0000644000175100001660000000443014777355103021103 0ustar00runnerdocker
  
    Normal
    
  
  
    
        
      test doc
    
        
    
        
      first issue
    
        
    
        
      
      
    
        
    
          
      
        • 
        bit
      
          • 
      
        • 
        bold italic
      
          • 
      
            
        
          • 
          orange
        
            • 
        
          • 
          apple
        
            • 
      
          
      
        • 
        final
      
          • 
    
        
    
        
      
      
    
        
    
        
      text to separate lists
    
        
    
        
      
      
    
        
    
          
      
        1. 
        now with numbers
      
          2. 
      
        2. 
        the prisoner
      
          3. 
      
            
        
          1. 
          not an italic number
        
            2. 
        
          2. 
          a bold human being
        
            3. 
      
          
      
        3. 
        end
      
          4. 
    
        
    
        
      
      
    
        
    
        
      
        bold
        
        italic
        
        text with _underscore but not _italicized
        
              
    
        
    
        
      
        def func(x):
  if x < 1:
    return 'a'
  return 'b'
      
        
    
        
    
        
      Some fixed width text here
        
      italic fixed width text
    
        



    
        
        2012. Now that was a good year. So was 2011. That's all.
    
        

    
        
        3.14159 is an approximation of pi.
    
        

    
        
        + not + a list item
    
        

    
        
        +foo
    
        

    
        
        - foo - bar
    
        

    
        
        -foo
    
        

    
        
        not a header
        
        --
    
        

    
        
        not a hr
        
        
        
        ---
        
        
        - - -
    
        
    
    
        
        c:\tmp, \\server\path, \_/, foo\bar, #\#, \\#
    
        
  

././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/normal_escape_snob.md0000644000175100001660000000127014777355103020536 0ustar00runnerdocker#  test doc

first issue

  * bit
  * _**bold italic**_
    * orange
    * apple
  * final

text to separate lists

  1. now with numbers
  2. the prisoner
     1. not an _italic number_
     2. a **bold human** being
  3. end

**bold**  
_italic_  
text with \_underscore but not \_italicized  

    
    
    def func(x):
      if x < 1:
        return 'a'
      return 'b'
          

Some `fixed width text` here  
_`italic fixed width text`_

2012\. Now that was a good year. So was 2011. That's all.

3.14159 is an approximation of pi.

\+ not + a list item

+foo

\- foo - bar

-foo 

not a header  
\--

not a hr  
  
\---  
\- - -

c:\tmp, \\\server\path, \\\_/, foo\bar, \#\\\#, \\\\\#
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/pad_table.html0000644000175100001660000000375514777355103017176 0ustar00runnerdocker 
       
     
        This is a test document
         With some text, code, bolds and italics.  
        This is second header
         
        Displaynone text
         
    
        
        
         Header 1 Header 2 Header 3 
        
        
         Content 1 2 200 Image! 
        
        
         Content 1 longer Content 2 blah 
        
        
         Content  Content 2 blah 
        
        
         t  Content 2 blah blah blah 
        
    
        


    
         
         H1 H2 H3 
        
        
         C1 Content 2 x 
        
        
         C123 Content 2 xyz 
        
    
        

some content between the tables
        

    
         
         Header 1 Header 2 Header 3 
        
        
         Content 1 Content 2 200 Image! 
        
        
         Content 1 Content 2 longer 200 Image! 
        
    
        

something else entirely
        

    
        
      
        
        OneTwoThree
        
              
      
        
        ABC
        
        
        AB+C
        
        
        A+BC
        
        
        A+B+C
        
              
    
        

    
        
      
        
        One+TwoThree
        
              
      
        
        ABC
        
        
        AB+C
        
        
        A+BC
        
        
        A+B+C
        
              
    
        

 
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/pad_table.md0000644000175100001660000000245314777355103016624 0ustar00runnerdocker# This is a test document

With some text, `code`, **bolds** and _italics_.

## This is second header

Displaynone text

| Header 1         | Header 2  | Header 3                                     |
|------------------|-----------|----------------------------------------------|
| Content 1        | 2         | ![200](http://lorempixel.com/200/200) Image! |
| Content 1 longer | Content 2 | blah                                         |
| Content          | Content 2 | blah                                         |
| t                | Content 2 | blah blah blah                               |

| H1   | H2        | H3  |
|------|-----------|-----|
| C1   | Content 2 | x   |
| C123 | Content 2 | xyz |

some content between the tables  
| Header 1  | Header 2         | Header 3                                     |
|-----------|------------------|----------------------------------------------|
| Content 1 | Content 2        | ![200](http://lorempixel.com/200/200) Image! |
| Content 1 | Content 2 longer | ![200](http://lorempixel.com/200/200) Image! |

something else entirely  
| One   | Two | Three |
|-------|-----|-------|
| A     | B   | C     |
| A     | B+C |
| A+B   | C   |
| A+B+C |

| One+Two | Three |
|---------|-------|
| A       | B     | C |
| A       | B+C   |
| A+B     | C     |
| A+B+C   |
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/pad_table_empty.html0000644000175100001660000000002014777355103020372 0ustar00runnerdocker
        
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/pad_table_empty.md0000644000175100001660000000000514777355103020031 0ustar00runnerdocker|  |
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/pad_table_no_closed_tr.html0000644000175100001660000000030114777355103021710 0ustar00runnerdocker
        
	
        
		xxx 
		xxx
		xxxx
	
        
		xxxx 
		xxxx
		xxxx

        
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/pad_table_no_closed_tr.md0000644000175100001660000000007214777355103021351 0ustar00runnerdocker| **xxx** | **xxx** | xxxx | **xxxx** | **xxxx** | xxxx |
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/pre.html0000644000175100001660000000037014777355103016037 0ustar00runnerdocker
  
    initial crowded pre handling test #1
  
  

        a
b
c
        

    
        Ensure that HTML that starts with a crowded <pre>
    is converted to reasonable Markdown.
        
  

././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/pre.md0000644000175100001660000000015514777355103015474 0ustar00runnerdocker
    a
    b
    c

Ensure that HTML that starts with a crowded `
        ` is converted to reasonable
Markdown.
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/preformatted_in_list.html0000644000175100001660000000017014777355103021464 0ustar00runnerdocker


          

        • Run this command:

          ls -l *.html
          • 

        • ?
          • 

        • Profit!
          • 

        


././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/preformatted_in_list.md0000644000175100001660000000011014777355103021112 0ustar00runnerdocker  * Run this command: 
        
        ls -l *.html

  * ?
  * Profit!
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/protect_links.html0000644000175100001660000000013614777355103020131 0ustar00runnerdockerfoo././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/protect_links.md0000644000175100001660000000012714777355103017565 0ustar00runnerdocker[foo]()
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/q_tag.html0000644000175100001660000000007714777355103016350 0ustar00runnerdockerIf this is a test, he said, then it should pass.
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/q_tag.md0000644000175100001660000000006514777355103016001 0ustar00runnerdocker"If this is a test," he said, "then it should pass".
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/rlm_inside_strong.html0000644000175100001660000000003414777355103020767 0ustar00runnerdockerFoo‏bar././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/rlm_inside_strong.md0000644000175100001660000000001414777355103020421 0ustar00runnerdocker**Foo bar**
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/single_line_break.html0000644000175100001660000000030614777355103020704 0ustar00runnerdocker



        Hello world.
        

        And hello html2text.
        
        
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/single_line_break.md0000644000175100001660000000004214777355103020335 0ustar00runnerdockerHello world.
And hello html2text.
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/stressed_with_html_entities.html0000644000175100001660000000005514777355103023070 0ustar00runnerdocker
        hello world ><
        
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/stressed_with_html_entities.md0000644000175100001660000000002314777355103022517 0ustar00runnerdocker**hello** world ><
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/sub_tag.html0000644000175100001660000000023014777355103016670 0ustar00runnerdocker
        
  According to the computations by Nakamura, Johnson, and Mason1 this
  will result in the complete annihilation of both particles.

        
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/sub_tag.md0000644000175100001660000000021314777355103016325 0ustar00runnerdockerAccording to the computations by Nakamura, Johnson, and Mason1 this
will result in the complete annihilation of both particles.
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/sup_tag.html0000644000175100001660000000016714777355103016717 0ustar00runnerdocker
        
  One of the most common equations in all of physics is E=mc2.

        
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/sup_tag.md0000644000175100001660000000011014777355103016337 0ustar00runnerdockerOne of the most common equations in all of physics is E=mc2.
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/table_ignore.html0000644000175100001660000000250414777355103017704 0ustar00runnerdocker 
       
     
        This is a test document
         With some text, code, bolds and italics.  
        This is second header
         
        Displaynone text
         
    
        
        
         Header 1 Header 2 Header 3 
        
        
         Content 1 2 200 Image! 
        
        
         Content 1 longer Content 2 blah 
        
        
         Content  Content 2 blah 
        
        
         t  Content 2 blah blah blah 
        
    
        


    
         
         H1 H2 H3 
        
        
         C1 Content 2 x 
        
        
         C123 Content 2 xyz 
        
    
        

some content between the tables
        

    
         
         Header 1 Header 2 Header 3 
        
        
         Content 1 Content 2 200 Image! 
        
        
         Content 1 Content 2 longer 200 Image! 
        
    
        

something else entirely
 
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/table_ignore.md0000644000175100001660000000110014777355103017327 0ustar00runnerdocker# This is a test document

With some text, `code`, **bolds** and _italics_.

## This is second header

Displaynone text

Header 1 Header 2 Header 3  
Content 1 2 ![200](http://lorempixel.com/200/200) Image!  
Content 1 longer Content 2 blah  
Content  Content 2 blah  
t  Content 2 blah blah blah  
H1 H2 H3  
C1 Content 2 x  
C123 Content 2 xyz  
some content between the tables  
Header 1 Header 2 Header 3  
Content 1 Content 2 ![200](http://lorempixel.com/200/200) Image!  
Content 1 Content 2 longer ![200](http://lorempixel.com/200/200) Image!  
something else entirely
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/test_html2text.py0000644000175100001660000001743314777355103017737 0ustar00runnerdockerimport glob
import os
import re
import subprocess
import sys

import pytest

import html2text

skip = object()


def cleanup_eol(clean_str):
    if os.name == "nt" or sys.platform == "cygwin":
        # Fix the unwanted CR to CRCRLF replacement
        # during text pipelining on Windows/cygwin
        # on cygwin, os.name == 'posix', not nt
        clean_str = re.sub(r"\r+", "\r", clean_str)
        clean_str = clean_str.replace("\r\n", "\n")
    return clean_str


def generate_testdata():
    test_dir_name = os.path.dirname(os.path.realpath(__file__))
    for fn in glob.glob("%s/*.html" % test_dir_name):
        module_args = {}
        cmdline_args = []
        func_args = {}
        base_fn = os.path.basename(fn).lower()

        if base_fn.startswith("default_image_alt"):
            module_args["default_image_alt"] = "Image"
            cmdline_args.append("--default-image-alt=Image")
            func_args = skip

        if base_fn.startswith("google"):
            module_args["google_doc"] = True
            cmdline_args.append("--googledoc")
            func_args = skip

        if base_fn.find("unicode") >= 0:
            module_args["unicode_snob"] = True
            cmdline_args.append("--unicode-snob")
            func_args = skip

        if base_fn.find("flip_emphasis") >= 0:
            module_args["emphasis_mark"] = "*"
            module_args["strong_mark"] = "__"
            cmdline_args.append("-e")
            func_args = skip

        if base_fn.find("escape_snob") >= 0:
            module_args["escape_snob"] = True
            cmdline_args.append("--escape-all")
            func_args = skip

        if base_fn.find("table_bypass") >= 0:
            module_args["bypass_tables"] = True
            cmdline_args.append("--bypass-tables")
            func_args = skip

        if base_fn.startswith("table_ignore"):
            module_args["ignore_tables"] = True
            cmdline_args.append("--ignore-tables")
            func_args = skip

        if base_fn.startswith("bodywidth"):
            module_args["body_width"] = 0
            cmdline_args.append("--body-width=0")
            func_args["bodywidth"] = 0

        if base_fn.startswith("protect_links"):
            module_args["protect_links"] = True
            cmdline_args.append("--protect-links")
            func_args = skip

        if base_fn.startswith("images_as_html"):
            module_args["images_as_html"] = True
            cmdline_args.append("--images-as-html")
            func_args = skip

        if base_fn.startswith("images_to_alt"):
            module_args["images_to_alt"] = True
            cmdline_args.append("--images-to-alt")
            func_args = skip

        if base_fn.startswith("images_with_size"):
            module_args["images_with_size"] = True
            cmdline_args.append("--images-with-size")
            func_args = skip

        if base_fn.startswith("single_line_break"):
            module_args["body_width"] = 0
            cmdline_args.append("--body-width=0")
            module_args["single_line_break"] = True
            cmdline_args.append("--single-line-break")
            func_args = skip

        if base_fn.startswith("no_inline_links"):
            module_args["inline_links"] = False
            cmdline_args.append("--reference-links")
            func_args = skip

        if base_fn.startswith("no_mailto_links"):
            module_args["ignore_mailto_links"] = True
            cmdline_args.append("--ignore-mailto-links")
            func_args = skip

        if base_fn.startswith("no_wrap_links"):
            module_args["wrap_links"] = False
            cmdline_args.append("--no-wrap-links")
            func_args = skip

        if base_fn.startswith("mark_code"):
            module_args["mark_code"] = True
            cmdline_args.append("--mark-code")
            func_args = skip

        if base_fn.startswith("backquote_code_style"):
            module_args["backquote_code_style"] = True
            cmdline_args.append("--backquote-code-style")
            func_args = skip

        if base_fn.startswith("pad_table"):
            module_args["pad_tables"] = True
            cmdline_args.append("--pad-tables")
            func_args = skip

        if base_fn.startswith("wrap_list_items"):
            module_args["wrap_list_items"] = True
            cmdline_args.append("--wrap-list-items")
            func_args = skip

        if base_fn.startswith("wrap_tables"):
            module_args["wrap_tables"] = True
            cmdline_args.append("--wrap-tables")
            func_args = skip

        if base_fn == "inplace_baseurl_substitution.html":
            module_args["baseurl"] = "http://brettterpstra.com"
            module_args["body_width"] = 0
            func_args["baseurl"] = "http://brettterpstra.com"
            func_args["bodywidth"] = 0
            # CLI doesn't support baseurl.
            cmdline_args = skip

        if base_fn in ["sup_tag.html", "sub_tag.html"]:
            module_args["include_sup_sub"] = True
            cmdline_args.append("--include-sup-sub")
            func_args = skip

        yield fn, module_args, cmdline_args, func_args


def generate_module_testdata():
    for fn, module_args, cmdline_args, func_args in generate_testdata():
        yield fn, module_args


def generate_command_testdata():
    for fn, module_args, cmdline_args, func_args in generate_testdata():
        if cmdline_args is not skip:
            yield fn, cmdline_args


def generate_function_testdata():
    for fn, module_args, cmdline_args, func_args in generate_testdata():
        if func_args is not skip:
            yield fn, func_args


@pytest.mark.parametrize("fn,module_args", generate_module_testdata())
def test_module(fn, module_args):
    h = html2text.HTML2Text()
    h.fn = fn

    if module_args.pop("google_doc", False):
        h.google_doc = True
        h.ul_item_mark = "-"
        h.body_width = 0
        h.hide_strikethrough = True

    for k, v in module_args.items():
        setattr(h, k, v)

    expected = get_baseline(fn)
    with open(fn) as inf:
        actual = cleanup_eol(inf.read())
        actual = h.handle(actual)
    assert actual.rstrip() == expected.rstrip()


@pytest.mark.parametrize("fn,cmdline_args", generate_command_testdata())
def test_command(fn, cmdline_args):
    args = list(cmdline_args)
    cmd = [sys.executable, "-m", "html2text"]

    if "--googledoc" in args:
        args.remove("--googledoc")
        cmd += ["-g", "-d", "-b", "0", "-s"]

    if args:
        cmd.extend(args)

    cmd += [fn]

    expected = get_baseline(fn)
    out = subprocess.check_output(cmd)

    actual = out.decode()

    actual = cleanup_eol(actual)
    assert actual.rstrip() == expected.rstrip()


@pytest.mark.parametrize("fn,func_args", generate_function_testdata())
def test_function(fn, func_args):
    with open(fn) as inf:
        actual = html2text.html2text(inf.read(), **func_args)
    expected = get_baseline(fn)
    assert actual.rstrip() == expected.rstrip()


def get_baseline_name(fn):
    return os.path.splitext(fn)[0] + ".md"


def get_baseline(fn):
    name = get_baseline_name(fn)
    with open(name, encoding="utf-8") as f:
        out = f.read()
    return cleanup_eol(out)


def test_tag_callback():
    def _skip_certain_tags(h2t, tag, attrs, start):
        if tag == "b":
            return True

    h = html2text.HTML2Text()
    h.tag_callback = _skip_certain_tags
    ret = h.handle(
        'this is a txt and this is a with text and '
        "some italics too."
    )
    assert ret == "this is a txt and this is a with text and some _italics_ too.\n\n"


def test_strong_emptied() -> None:
    """When strong is being set to empty, it should not mark it."""
    h = html2text.HTML2Text()
    h.emphasis_mark = "_"
    h.strong_mark = ""
    string = "A B C."
    assert h.handle(string) == "A B _C_.\n\n"
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/test_memleak.py0000644000175100001660000000131714777355103017411 0ustar00runnerdockerimport html2text

# See https://github.com/Alir3z4/html2text/issues/13 for more information.

INSTR = "miow "


def test_same_string():
    h2t = html2text.HTML2Text()
    result = h2t.handle(INSTR)
    # Now, we shouldn't get leak of the previous run to the new one.
    assert h2t.handle(INSTR) == result


def test_empty_string():
    h2t = html2text.HTML2Text()
    h2t.handle(INSTR)
    # And even less when the input is empty.
    assert h2t.handle("") == "\n\n"


def test_abbr_data():
    h2t = html2text.HTML2Text()
    result = h2t.handle('
        foo TLA bar
        ')
    assert result == "foo TLA bar\n\n  *[TLA]: Three Letter Acronym\n\n"
    assert h2t.abbr_data is None
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/test_newlines_on_multiple_calls.py0000644000175100001660000000044514777355103023410 0ustar00runnerdockerimport html2text

# See https://github.com/Alir3z4/html2text/issues/163 for more information.


def test_newline_on_multiple_calls():
    h = html2text.HTML2Text()
    html = "
        test
        "
    md1 = h.handle(html)
    md2 = h.handle(html)
    md3 = h.handle(html)
    assert md1 == md2 == md3
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/text_after_list.html0000644000175100001660000000003414777355103020446 0ustar00runnerdocker
        • item
        
text
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/text_after_list.md0000644000175100001660000000001714777355103020103 0ustar00runnerdocker  * item

text
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/url-escaping.html0000644000175100001660000000253114777355103017643 0ustar00runnerdocker
        Markdown-sensible characters processing
        


        This test checks special characters processing inside URLs: parenthesis and brackets should be escaped to keep markdown image and anchor syntax safe and sound.
        




        And here are images with tricky attribute values:
        

(banana)
        
[banana]
        
{banana}
        
([{}])

././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/url-escaping.md0000644000175100001660000000202714777355103017277 0ustar00runnerdocker# Markdown-sensible characters processing

This test checks special characters processing inside URLs: parenthesis and
brackets should be escaped to keep markdown image and anchor syntax safe and
sound.

  * [Some MSDN link using parenthesis](http://msdn.microsoft.com/en-us/library/system.drawing.drawing2d\(v=vs.110\))
  * [Google search result URL with unescaped brackets](https://www.google.ru/search?q=\[brackets are cool\])
  * [Yet another test for [brackets], {curly braces} and (parenthesis) processing inside the anchor](https://www.google.ru/search?q='\[\({}\)\]')
  * Use automatic links like  when the URL is the label
  * Exempt [non-absolute_URIs](non-absolute_URIs) from automatic link detection

And here are images with tricky attribute values:

![\(banana\)](http://placehold.it/350x150#\(banana\))  
![\[banana\]](http://placehold.it/350x150#\[banana\])  
![{banana}](http://placehold.it/350x150#{banana})  
![\(\[{}\]\)](http://placehold.it/350x150#\(\[{}\]\))
![](http://placehold.it/350x150#\(\[{}\]\))
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/wrap_list_items_example.html0000644000175100001660000000116614777355103022175 0ustar00runnerdocker
          

        • One two three four five six seven eight nine ten eleven twelve thirteen fourteen fifteen sixteen seventeen eighteen nineteen twenty.
          • 

        • One two three four five six seven eight nine ten eleven twelve thirteen fourteen fifteen sixteen seventeen eighteen nineteen twenty.
          • 

        

Text between lists.


          

        • One two three four five six seven eight nine ten eleven twelve thirteen fourteen fifteen sixteen seventeen eighteen nineteen twenty.
          • 

        • One two three four five six seven eight nine ten eleven twelve thirteen fourteen fifteen sixteen seventeen eighteen nineteen twenty.
          • 

        

Text after list.
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/wrap_list_items_example.md0000644000175100001660000000113414777355103021624 0ustar00runnerdocker  * One two three four five six seven eight nine ten eleven twelve thirteen
    fourteen fifteen sixteen seventeen eighteen nineteen twenty.
  * One two three four five six seven eight nine ten eleven twelve thirteen
    fourteen fifteen sixteen seventeen eighteen nineteen twenty.

Text between lists.

  * One two three four five six seven eight nine ten eleven twelve thirteen
    fourteen fifteen sixteen seventeen eighteen nineteen twenty.
  * One two three four five six seven eight nine ten eleven twelve thirteen
    fourteen fifteen sixteen seventeen eighteen nineteen twenty.

Text after list.
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/wrap_tables.html0000644000175100001660000000146114777355103017556 0ustar00runnerdocker 
       
     
        This is a test document
         With some text, code, bolds and italics.  
        This is second header
         
        Displaynone text
         
    
        
        
         Header 1 Header 2 Header 3 
        
        
         Content 1 2 200 Image! 
        
        
         Content 1 longer Content 2 Here is some really long text that will wrap to the next line. Because it's so long. 
        
        
         Content  Content 2 blah 
        
        
         t  Content 2 blah blah blah 
        
    
        

 
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/test/wrap_tables.md0000644000175100001660000000063314777355103017212 0ustar00runnerdocker# This is a test document

With some text, `code`, **bolds** and _italics_.

## This is second header

Displaynone text

Header 1 | Header 2 | Header 3  
---|---|---  
Content 1 | 2 | ![200](http://lorempixel.com/200/200) Image!  
Content 1 longer | Content 2 | Here is some really long text that will wrap to
the next line. Because it's so long.  
Content  | Content 2 | blah  
t  | Content 2 | blah blah blah
././@PaxHeader0000000000000000000000000000002600000000000010213 xustar0022 mtime=1744689731.0
html2text-2025.4.15/tox.ini0000644000175100001660000000145014777355103014717 0ustar00runnerdocker[tox]
envlist =
    black
    flake8
    isort
    mypy
    py{39,310,311,312,313,py3}
minversion = 4.11.4

[testenv]
commands =
    pytest --cov=./ --cov-report=xml {posargs}
deps =
    pytest
    pytest-cov
setenv =
    PYTHONUTF8 = 1

[testenv:black]
basepython = python3
commands = black --check --diff .
deps = black
skip_install = true

[testenv:flake8]
basepython = python3
commands = flake8
deps =
    flake8
    Flake8-pyproject
skip_install = true

[testenv:isort]
basepython = python3
commands = isort --check-only --diff .
deps = isort
skip_install = true

[testenv:mypy]
commands = mypy --strict html2text
deps = mypy

[testenv:pre-commit]
basepython = python3
commands =
    isort --atomic .
    flake8
    black .
deps =
    isort
    flake8
    Flake8-pyproject
    black
skip_install = true