diff --git a/ebooklib/LICENSE b/ebooklib/LICENSE deleted file mode 100644 index 2def0e8..0000000 --- a/ebooklib/LICENSE +++ /dev/null @@ -1,661 +0,0 @@ - GNU AFFERO GENERAL PUBLIC LICENSE - Version 3, 19 November 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 Affero General Public License is a free, copyleft license for -software and other kinds of works, specifically designed to ensure -cooperation with the community in the case of network server software. - - The licenses for most software and other practical works are designed -to take away your freedom to share and change the works. By contrast, -our General Public Licenses are 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. - - 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. - - Developers that use our General Public Licenses protect your rights -with two steps: (1) assert copyright on the software, and (2) offer -you this License which gives you legal permission to copy, distribute -and/or modify the software. - - A secondary benefit of defending all users' freedom is that -improvements made in alternate versions of the program, if they -receive widespread use, become available for other developers to -incorporate. Many developers of free software are heartened and -encouraged by the resulting cooperation. However, in the case of -software used on network servers, this result may fail to come about. -The GNU General Public License permits making a modified version and -letting the public access it on a server without ever releasing its -source code to the public. - - The GNU Affero General Public License is designed specifically to -ensure that, in such cases, the modified source code becomes available -to the community. It requires the operator of a network server to -provide the source code of the modified version running there to the -users of that server. Therefore, public use of a modified version, on -a publicly accessible server, gives the public access to the source -code of the modified version. - - An older license, called the Affero General Public License and -published by Affero, was designed to accomplish similar goals. This is -a different license, not a version of the Affero GPL, but Affero has -released a new version of the Affero GPL which permits relicensing under -this license. - - 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 Affero 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. Remote Network Interaction; Use with the GNU General Public License. - - Notwithstanding any other provision of this License, if you modify the -Program, your modified version must prominently offer all users -interacting with it remotely through a computer network (if your version -supports such interaction) an opportunity to receive the Corresponding -Source of your version by providing access to the Corresponding Source -from a network server at no charge, through some standard or customary -means of facilitating copying of software. This Corresponding Source -shall include the Corresponding Source for any work covered by version 3 -of the GNU General Public License that is incorporated pursuant to the -following paragraph. - - 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 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 work with which it is combined will remain governed by version -3 of the GNU General Public License. - - 14. Revised Versions of this License. - - The Free Software Foundation may publish revised and/or new versions of -the GNU Affero 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 Affero 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 Affero 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 Affero 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 Affero 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 Affero General Public License for more details. - - You should have received a copy of the GNU Affero General Public License - along with this program. If not, see . - -Also add information on how to contact you by electronic and paper mail. - - If your software can interact with users remotely through a computer -network, you should also make sure that it provides a way for users to -get its source. For example, if your program is a web application, its -interface could display a "Source" link that leads users to an archive -of the code. There are many ways you could offer source, and different -solutions will be better for different programs; see section 13 for the -specific requirements. - - 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 AGPL, see -. \ No newline at end of file diff --git a/ebooklib/__init__.py b/ebooklib/__init__.py deleted file mode 100644 index 020d2f5..0000000 --- a/ebooklib/__init__.py +++ /dev/null @@ -1,42 +0,0 @@ -# This file is part of EbookLib. -# Copyright (c) 2013 Aleksandar Erkalovic -# -# EbookLib is free software: you can redistribute it and/or modify -# it under the terms of the GNU Affero General Public License as published by -# the Free Software Foundation, either version 3 of the License, or -# (at your option) any later version. -# -# EbookLib 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 Affero General Public License for more details. -# -# You should have received a copy of the GNU Affero General Public License -# along with EbookLib. If not, see . - -# Version of ebook library - -VERSION = (0, 16, 0) - -# LIST OF POSSIBLE ITEMS -ITEM_UNKNOWN = 0 -ITEM_IMAGE = 1 -ITEM_STYLE = 2 -ITEM_SCRIPT = 3 -ITEM_NAVIGATION = 4 -ITEM_VECTOR = 5 -ITEM_FONT = 6 -ITEM_VIDEO = 7 -ITEM_AUDIO = 8 -ITEM_DOCUMENT = 9 - -# EXTENSION MAPPER -EXTENSIONS = {ITEM_IMAGE: ['.jpg', '.jpeg', '.gif', '.tiff', '.tif', '.png'], - ITEM_STYLE: ['.css'], - ITEM_VECTOR: ['.svg'], - ITEM_FONT: ['.otf', '.woff', '.ttf'], - ITEM_SCRIPT: ['.js'], - ITEM_NAVIGATION: ['.ncx'], - ITEM_VIDEO: ['.mov', '.mp4', '.avi'], - ITEM_AUDIO: ['.mp3', '.ogg'] - } diff --git a/ebooklib/epub.py b/ebooklib/epub.py deleted file mode 100644 index fd3a0ff..0000000 --- a/ebooklib/epub.py +++ /dev/null @@ -1,1595 +0,0 @@ -# This file is part of EbookLib. -# Copyright (c) 2013 Aleksandar Erkalovic -# -# EbookLib is free software: you can redistribute it and/or modify -# it under the terms of the GNU Affero General Public License as published by -# the Free Software Foundation, either version 3 of the License, or -# (at your option) any later version. -# -# EbookLib 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 Affero General Public License for more details. -# -# You should have received a copy of the GNU Affero General Public License -# along with EbookLib. If not, see . - -import zipfile -import six -import logging -import uuid -import posixpath as zip_path -import os.path -from collections import OrderedDict - -try: - from urllib.parse import unquote -except ImportError: - from urllib import unquote - -from lxml import etree - -import ebooklib - -from ebooklib.utils import parse_string, parse_html_string, guess_type - - -# Version of EPUB library -VERSION = (0, 15, 0) - -NAMESPACES = {'XML': 'http://www.w3.org/XML/1998/namespace', - 'EPUB': 'http://www.idpf.org/2007/ops', - 'DAISY': 'http://www.daisy.org/z3986/2005/ncx/', - 'OPF': 'http://www.idpf.org/2007/opf', - 'CONTAINERNS': 'urn:oasis:names:tc:opendocument:xmlns:container', - 'DC': 'http://purl.org/dc/elements/1.1/', - 'XHTML': 'http://www.w3.org/1999/xhtml'} - -# XML Templates - -CONTAINER_PATH = 'META-INF/container.xml' - -CONTAINER_XML = ''' - - - - - -''' - -NCX_XML = six.b(''' -''') - -NAV_XML = six.b('''''') - -CHAPTER_XML = six.b('''''') - -COVER_XML = six.b(''' - - - - - - - - -''') - - -IMAGE_MEDIA_TYPES = ['image/jpeg', 'image/jpg', 'image/png', 'image/svg+xml'] - - -# TOC elements - -class Section(object): - - def __init__(self, title, href=''): - self.title = title - self.href = href - - -class Link(object): - - def __init__(self, href, title, uid=None): - self.href = href - self.title = title - self.uid = uid - -# Exceptions - - -class EpubException(Exception): - - def __init__(self, code, msg): - self.code = code - self.msg = msg - - def __str__(self): - return repr(self.msg) - -# Items - - -class EpubItem(object): - - """ - Base class for the items in a book. - """ - - def __init__(self, uid=None, file_name='', media_type='', content=six.b(''), manifest=True): - """ - :Args: - - uid: Unique identifier for this item (optional) - - file_name: File name for this item (optional) - - media_type: Media type for this item (optional) - - content: Content for this item (optional) - - manifest: Manifest for this item (optional) - """ - self.id = uid - self.file_name = file_name - self.media_type = media_type - self.content = content - self.is_linear = True - self.manifest = manifest - - self.book = None - - def get_id(self): - """ - Returns unique identifier for this item. - - :Returns: - Returns uid number as string. - """ - return self.id - - def get_name(self): - """ - Returns name for this item. By default it is always file name but it does not have to be. - - :Returns: - Returns file name for this item. - """ - return self.file_name - - def get_type(self): - """ - Guess type according to the file extension. Might not be the best way how to do it, but it works for now. - - Items can be of type: - - ITEM_UNKNOWN = 0 - - ITEM_IMAGE = 1 - - ITEM_STYLE = 2 - - ITEM_SCRIPT = 3 - - ITEM_NAVIGATION = 4 - - ITEM_VECTOR = 5 - - ITEM_FONT = 6 - - ITEM_VIDEO = 7 - - ITEM_AUDIO = 8 - - ITEM_DOCUMENT = 9 - - We map type according to the extensions which are defined in ebooklib.EXTENSIONS. - - :Returns: - Returns type of the item as number. - """ - _, ext = zip_path.splitext(self.get_name()) - ext = ext.lower() - - for uid, ext_list in six.iteritems(ebooklib.EXTENSIONS): - if ext in ext_list: - return uid - - return ebooklib.ITEM_UNKNOWN - - def get_content(self, default=six.b('')): - """ - Returns content of the item. Content should be of type 'str' (Python 2) or 'bytes' (Python 3) - - :Args: - - default: Default value for the content if it is not already defined. - - :Returns: - Returns content of the item. - """ - return self.content or default - - def set_content(self, content): - """ - Sets content value for this item. - - :Args: - - content: Content value - """ - self.content = content - - def __str__(self): - return '' % self.id - - -class EpubNcx(EpubItem): - - "Represents Navigation Control File (NCX) in the EPUB." - - def __init__(self, uid='ncx', file_name='toc.ncx'): - super(EpubNcx, self).__init__(uid=uid, file_name=file_name, media_type='application/x-dtbncx+xml') - - def __str__(self): - return '' % self.id - - -class EpubCover(EpubItem): - - """ - Represents Cover image in the EPUB file. - """ - - def __init__(self, uid='cover-img', file_name=''): - super(EpubCover, self).__init__(uid=uid, file_name=file_name) - - def __str__(self): - return '' % (self.id, self.file_name) - - -class EpubHtml(EpubItem): - - """ - Represents HTML document in the EPUB file. - """ - _template_name = 'chapter' - - def __init__(self, uid=None, file_name='', media_type='', content=None, title='', lang=None, direction=None): - super(EpubHtml, self).__init__(uid, file_name, media_type, content) - - self.title = title - self.lang = lang - self.direction = direction - - self.links = [] - self.properties = [] - - def is_chapter(self): - """ - Returns if this document is chapter or not. - - :Returns: - Returns book value. - """ - return True - - def get_type(self): - """ - Always returns ebooklib.ITEM_DOCUMENT as type of this document. - - :Returns: - Always returns ebooklib.ITEM_DOCUMENT - """ - - return ebooklib.ITEM_DOCUMENT - - def set_language(self, lang): - """ - Sets language for this book item. By default it will use language of the book but it - can be overwritten with this call. - """ - self.lang = lang - - def get_language(self): - """ - Get language code for this book item. Language of the book item can be different from - the language settings defined globaly for book. - - :Returns: - As string returns language code. - """ - return self.lang - - def add_link(self, **kwgs): - """ - Add additional link to the document. Links will be embeded only inside of this document. - - >>> add_link(href='styles.css', rel='stylesheet', type='text/css') - """ - self.links.append(kwgs) - - def get_links(self): - """ - Returns list of additional links defined for this document. - - :Returns: - As tuple return list of links. - """ - return (link for link in self.links) - - def get_links_of_type(self, link_type): - """ - Returns list of additional links of specific type. - - :Returns: - As tuple returns list of links. - """ - return (link for link in self.links if link.get('type', '') == link_type) - - def add_item(self, item): - """ - Add other item to this document. It will create additional links according to the item type. - - :Args: - - item: item we want to add defined as instance of EpubItem - """ - if item.get_type() == ebooklib.ITEM_STYLE: - self.add_link(href=item.get_name(), rel='stylesheet', type='text/css') - - if item.get_type() == ebooklib.ITEM_SCRIPT: - self.add_link(src=item.get_name(), type='text/javascript') - - def get_body_content(self): - """ - Returns content of BODY element for this HTML document. Content will be of type 'str' (Python 2) - or 'bytes' (Python 3). - - :Returns: - Returns content of this document. - """ - - try: - html_tree = parse_html_string(self.content) - except: - return '' - - html_root = html_tree.getroottree() - - if len(html_root.find('body')) != 0: - body = html_tree.find('body') - - tree_str = etree.tostring(body, pretty_print=True, encoding='utf-8', xml_declaration=False) - - # this is so stupid - if tree_str.startswith(six.b('')): - n = tree_str.rindex(six.b('')) - - return tree_str[6:n] - - return tree_str - - return '' - - def get_content(self, default=None): - """ - Returns content for this document as HTML string. Content will be of type 'str' (Python 2) - or 'bytes' (Python 3). - - :Args: - - default: Default value for the content if it is not defined. - - :Returns: - Returns content of this document. - """ - - tree = parse_string(self.book.get_template(self._template_name)) - tree_root = tree.getroot() - - tree_root.set('lang', self.lang or self.book.language) - tree_root.attrib['{%s}lang' % NAMESPACES['XML']] = self.lang or self.book.language - - # add to the head also - # - - try: - html_tree = parse_html_string(self.content) - except: - return '' - - html_root = html_tree.getroottree() - - # create and populate head - - _head = etree.SubElement(tree_root, 'head') - - if self.title != '': - _title = etree.SubElement(_head, 'title') - _title.text = self.title - - for lnk in self.links: - if lnk.get('type') == 'text/javascript': - _lnk = etree.SubElement(_head, 'script', lnk) - # force - _lnk.text = '' - else: - _lnk = etree.SubElement(_head, 'link', lnk) - - # this should not be like this - # head = html_root.find('head') - # if head is not None: - # for i in head.getchildren(): - # if i.tag == 'title' and self.title != '': - # continue - # _head.append(i) - - # create and populate body - - _body = etree.SubElement(tree_root, 'body') - if self.direction: - _body.set('dir', self.direction) - - body = html_tree.find('body') - if body is not None: - for i in body.getchildren(): - _body.append(i) - - tree_str = etree.tostring(tree, pretty_print=True, encoding='utf-8', xml_declaration=True) - - return tree_str - - def __str__(self): - return '' % (self.id, self.file_name) - - -class EpubCoverHtml(EpubHtml): - - """ - Represents Cover page in the EPUB file. - """ - - def __init__(self, uid='cover', file_name='cover.xhtml', image_name='', title='Cover'): - super(EpubCoverHtml, self).__init__(uid=uid, file_name=file_name, title=title) - - self.image_name = image_name - self.is_linear = False - - def is_chapter(self): - """ - Returns if this document is chapter or not. - - :Returns: - Returns book value. - """ - - return False - - def get_content(self): - """ - Returns content for cover page as HTML string. Content will be of type 'str' (Python 2) or 'bytes' (Python 3). - - :Returns: - Returns content of this document. - """ - - self.content = self.book.get_template('cover') - - tree = parse_string(super(EpubCoverHtml, self).get_content()) - tree_root = tree.getroot() - - images = tree_root.xpath('//xhtml:img', namespaces={'xhtml': NAMESPACES['XHTML']}) - - images[0].set('src', self.image_name) - images[0].set('alt', self.title) - - tree_str = etree.tostring(tree, pretty_print=True, encoding='utf-8', xml_declaration=True) - - return tree_str - - def __str__(self): - return '' % (self.id, self.file_name) - - -class EpubNav(EpubHtml): - - """ - Represents Navigation Document in the EPUB file. - """ - - def __init__(self, uid='nav', file_name='nav.xhtml', media_type='application/xhtml+xml'): - super(EpubNav, self).__init__(uid=uid, file_name=file_name, media_type=media_type) - - def is_chapter(self): - """ - Returns if this document is chapter or not. - - :Returns: - Returns book value. - """ - - return False - - def __str__(self): - return '' % (self.id, self.file_name) - - -class EpubImage(EpubItem): - - """ - Represents Image in the EPUB file. - """ - - def __init__(self): - super(EpubImage, self).__init__() - - def get_type(self): - return ebooklib.ITEM_IMAGE - - def __str__(self): - return '' % (self.id, self.file_name) - - -# EpubBook - -class EpubBook(object): - - def __init__(self): - self.EPUB_VERSION = None - - self.reset() - - # we should have options here - - def reset(self): - "Initialises all needed variables to default values" - - self.metadata = {} - self.items = [] - self.spine = [] - self.guide = [] - self.toc = [] - self.bindings = [] - - self.IDENTIFIER_ID = 'id' - self.FOLDER_NAME = 'EPUB' - - self._id_html = 0 - self._id_image = 0 - self._id_static = 0 - - self.title = '' - self.language = 'en' - self.direction = None - - self.templates = { - 'ncx': NCX_XML, - 'nav': NAV_XML, - 'chapter': CHAPTER_XML, - 'cover': COVER_XML - } - - self.add_metadata('OPF', 'generator', '', { - 'name': 'generator', 'content': 'Ebook-lib %s' % '.'.join([str(s) for s in VERSION]) - }) - - # default to using a randomly-unique identifier if one is not specified manually - self.set_identifier(str(uuid.uuid4())) - - # custom prefixes and namespaces to be set to the content.opf doc - self.prefixes = [] - self.namespaces = {} - - def set_identifier(self, uid): - """ - Sets unique id for this epub - - :Args: - - uid: Value of unique identifier for this book - """ - - self.uid = uid - - self.set_unique_metadata('DC', 'identifier', self.uid, {'id': self.IDENTIFIER_ID}) - - def set_title(self, title): - """ - Set title. You can set multiple titles. - - :Args: - - title: Title value - """ - - self.title = title - - self.add_metadata('DC', 'title', self.title) - - def set_language(self, lang): - """ - Set language for this epub. You can set multiple languages. Specific items in the book can have - different language settings. - - :Args: - - lang: Language code - """ - - self.language = lang - - self.add_metadata('DC', 'language', lang) - - def set_direction(self, direction): - """ - :Args: - - direction: Options are "ltr", "rtl" and "default" - """ - - self.direction = direction - - def set_cover(self, file_name, content, create_page=True): - """ - Set cover and create cover document if needed. - - :Args: - - file_name: file name of the cover page - - content: Content for the cover image - - create_page: Should cover page be defined. Defined as bool value (optional). Default value is True. - """ - - # as it is now, it can only be called once - c0 = EpubCover(file_name=file_name) - c0.content = content - self.add_item(c0) - - if create_page: - c1 = EpubCoverHtml(image_name=file_name) - self.add_item(c1) - - self.add_metadata(None, 'meta', '', OrderedDict([('name', 'cover'), ('content', 'cover-img')])) - - def add_author(self, author, file_as=None, role=None, uid='creator'): - "Add author for this document" - - self.add_metadata('DC', 'creator', author, {'id': uid}) - - if file_as: - self.add_metadata(None, 'meta', file_as, {'refines': '#' + uid, - 'property': 'file-as', - 'scheme': 'marc:relators'}) - if role: - self.add_metadata(None, 'meta', role, {'refines': '#' + uid, - 'property': 'role', - 'scheme': 'marc:relators'}) - - def add_metadata(self, namespace, name, value, others=None): - "Add metadata" - - if namespace in NAMESPACES: - namespace = NAMESPACES[namespace] - - if namespace not in self.metadata: - self.metadata[namespace] = {} - - if name not in self.metadata[namespace]: - self.metadata[namespace][name] = [] - - self.metadata[namespace][name].append((value, others)) - - def get_metadata(self, namespace, name): - "Retrieve metadata" - - if namespace in NAMESPACES: - namespace = NAMESPACES[namespace] - - return self.metadata[namespace][name] - - def set_unique_metadata(self, namespace, name, value, others=None): - "Add metadata if metadata with this identifier does not already exist, otherwise update existing metadata." - - if namespace in NAMESPACES: - namespace = NAMESPACES[namespace] - - if namespace in self.metadata and name in self.metadata[namespace]: - self.metadata[namespace][name] = [(value, others)] - else: - self.add_metadata(namespace, name, value, others) - - def add_item(self, item): - """ - Add additional item to the book. If not defined, media type and chapter id will be defined - for the item. - - :Args: - - item: Item instance - """ - if item.media_type == '': - (has_guessed, media_type) = guess_type(item.get_name().lower()) - - if has_guessed: - if media_type is not None: - item.media_type = media_type - else: - item.media_type = has_guessed - else: - item.media_type = 'application/octet-stream' - - if not item.get_id(): - # make chapter_, image_ and static_ configurable - if isinstance(item, EpubHtml): - item.id = 'chapter_%d' % self._id_html - self._id_html += 1 - elif isinstance(item, EpubImage): - item.id = 'image_%d' % self._id_image - self._id_image += 1 - else: - item.id = 'static_%d' % self._id_image - self._id_image += 1 - - item.book = self - self.items.append(item) - - return item - - def get_item_with_id(self, uid): - """ - Returns item for defined UID. - - >>> book.get_item_with_id('image_001') - - :Args: - - uid: UID for the item - - :Returns: - Returns item object. Returns None if nothing was found. - """ - for item in self.get_items(): - if item.id == uid: - return item - - return None - - def get_item_with_href(self, href): - """ - Returns item for defined HREF. - - >>> book.get_item_with_href('EPUB/document.xhtml') - - :Args: - - href: HREF for the item we are searching for - - :Returns: - Returns item object. Returns None if nothing was found. - """ - for item in self.get_items(): - if item.get_name() == href: - return item - - return None - - def get_items(self): - """ - Returns all items attached to this book. - - :Returns: - Returns all items as tuple. - """ - return (item for item in self.items) - - def get_items_of_type(self, item_type): - """ - Returns all items of specified type. - - >>> book.get_items_of_type(epub.ITEM_IMAGE) - - :Args: - - item_type: Type for items we are searching for - - :Returns: - Returns found items as tuple. - """ - return (item for item in self.items if item.get_type() == item_type) - - def get_items_of_media_type(self, media_type): - """ - Returns all items of specified media type. - - :Args: - - media_type: Media type for items we are searching for - - :Returns: - Returns found items as tuple. - """ - return (item for item in self.items if item.media_type == media_type) - - def set_template(self, name, value): - """ - Defines templates which are used to generate certain types of pages. When defining new value for the template - we have to use content of type 'str' (Python 2) or 'bytes' (Python 3). - - At the moment we use these templates: - - ncx - - nav - - chapter - - cover - - :Args: - - name: Name for the template - - value: Content for the template - """ - - self.templates[name] = value - - def get_template(self, name): - """ - Returns value for the template. - - :Args: - - name: template name - - :Returns: - Value of the template. - """ - return self.templates.get(name) - - def add_prefix(self, name, uri): - """ - Appends custom prefix to be added to the content.opf document - - >>> epub_book.add_prefix('bkterms', 'http://booktype.org/') - - :Args: - - name: namespave name - - uri: URI for the namespace - """ - - self.prefixes.append('%s: %s' % (name, uri)) - - -class EpubWriter(object): - DEFAULT_OPTIONS = { - 'epub2_guide': True, - 'epub3_landmark': True, - 'landmark_title': 'Guide', - 'spine_direction': True, - 'package_direction': False - } - - def __init__(self, name, book, options=None): - self.file_name = name - self.book = book - - self.options = dict(self.DEFAULT_OPTIONS) - if options: - self.options.update(options) - - def process(self): - # should cache this html parsing so we don't do it for every plugin - for plg in self.options.get('plugins', []): - if hasattr(plg, 'before_write'): - plg.before_write(self.book) - - for item in self.book.get_items(): - if isinstance(item, EpubHtml): - for plg in self.options.get('plugins', []): - if hasattr(plg, 'html_before_write'): - plg.html_before_write(self.book, item) - - def _write_container(self): - container_xml = CONTAINER_XML % {'folder_name': self.book.FOLDER_NAME} - self.out.writestr(CONTAINER_PATH, container_xml) - - def _write_opf_metadata(self, root): - # This is really not needed - # problem is uppercase/lowercase - # for ns_name, values in six.iteritems(self.book.metadata): - # if ns_name: - # for n_id, ns_url in six.iteritems(NAMESPACES): - # if ns_name == ns_url: - # nsmap[n_id.lower()] = NAMESPACES[n_id] - - nsmap = {'dc': NAMESPACES['DC'], 'opf': NAMESPACES['OPF']} - nsmap.update(self.book.namespaces) - - metadata = etree.SubElement(root, 'metadata', nsmap=nsmap) - - el = etree.SubElement(metadata, 'meta', {'property': 'dcterms:modified'}) - if 'mtime' in self.options: - mtime = self.options['mtime'] - else: - import datetime - mtime = datetime.datetime.now() - el.text = mtime.strftime('%Y-%m-%dT%H:%M:%SZ') - - for ns_name, values in six.iteritems(self.book.metadata): - if ns_name == NAMESPACES['OPF']: - for values in values.values(): - for v in values: - if 'property' in v[1] and v[1]['property'] == 'dcterms:modified': - continue - try: - el = etree.SubElement(metadata, 'meta', v[1]) - if v[0]: - el.text = v[0] - except ValueError: - logging.error('Could not create metadata.') - else: - for name, values in six.iteritems(values): - for v in values: - try: - if ns_name: - el = etree.SubElement(metadata, '{%s}%s' % (ns_name, name), v[1]) - else: - el = etree.SubElement(metadata, '%s' % name, v[1]) - - el.text = v[0] - except ValueError: - logging.error('Could not create metadata "{}".'.format(name)) - - def _write_opf_manifest(self, root): - manifest = etree.SubElement(root, 'manifest') - _ncx_id = None - - # mathml, scripted, svg, remote-resources, and switch - # nav - # cover-image - - for item in self.book.get_items(): - if not item.manifest: - continue - - if isinstance(item, EpubNav): - etree.SubElement(manifest, 'item', {'href': item.get_name(), - 'id': item.id, - 'media-type': item.media_type, - 'properties': 'nav'}) - elif isinstance(item, EpubNcx): - _ncx_id = item.id - etree.SubElement(manifest, 'item', {'href': item.file_name, - 'id': item.id, - 'media-type': item.media_type}) - - elif isinstance(item, EpubCover): - etree.SubElement(manifest, 'item', {'href': item.file_name, - 'id': item.id, - 'media-type': item.media_type, - 'properties': 'cover-image'}) - else: - opts = {'href': item.file_name, - 'id': item.id, - 'media-type': item.media_type} - - if hasattr(item, 'properties') and len(item.properties) > 0: - opts['properties'] = ' '.join(item.properties) - - etree.SubElement(manifest, 'item', opts) - - return _ncx_id - - def _write_opf_spine(self, root, ncx_id): - spine_attributes = {'toc': ncx_id or 'ncx'} - if self.book.direction and self.options['spine_direction']: - spine_attributes['page-progression-direction'] = self.book.direction - - spine = etree.SubElement(root, 'spine', spine_attributes) - - for _item in self.book.spine: - # this is for now - # later we should be able to fetch things from tuple - - is_linear = True - - if isinstance(_item, tuple): - item = _item[0] - - if len(_item) > 1: - if _item[1] == 'no': - is_linear = False - else: - item = _item - - if isinstance(item, EpubHtml): - opts = {'idref': item.get_id()} - - if not item.is_linear or not is_linear: - opts['linear'] = 'no' - elif isinstance(item, EpubItem): - opts = {'idref': item.get_id()} - - if not item.is_linear or not is_linear: - opts['linear'] = 'no' - else: - opts = {'idref': item} - - try: - itm = self.book.get_item_with_id(item) - - if not itm.is_linear or not is_linear: - opts['linear'] = 'no' - except: - pass - - etree.SubElement(spine, 'itemref', opts) - - def _write_opf_guide(self, root): - # - http://www.idpf.org/epub/20/spec/OPF_2.0.1_draft.htm#Section2.6 - - if len(self.book.guide) > 0 and self.options.get('epub2_guide'): - guide = etree.SubElement(root, 'guide', {}) - - for item in self.book.guide: - if 'item' in item: - chap = item.get('item') - if chap: - _href = chap.file_name - _title = chap.title - else: - _href = item.get('href', '') - _title = item.get('title', '') - - if _title is None: - _title = '' - ref = etree.SubElement(guide, 'reference', {'type': item.get('type', ''), - 'title': _title, - 'href': _href}) - - def _write_opf_bindings(self, root): - if len(self.book.bindings) > 0: - bindings = etree.SubElement(root, 'bindings', {}) - for item in self.book.bindings: - etree.SubElement(bindings, 'mediaType', item) - - def _write_opf_file(self, root): - tree_str = etree.tostring(root, pretty_print=True, encoding='utf-8', xml_declaration=True) - - self.out.writestr('%s/content.opf' % self.book.FOLDER_NAME, tree_str) - - def _write_opf(self): - package_attributes = {'xmlns': NAMESPACES['OPF'], - 'unique-identifier': self.book.IDENTIFIER_ID, - 'version': '3.0'} - if self.book.direction and self.options['package_direction']: - package_attributes['dir'] = self.book.direction - - root = etree.Element('package', package_attributes) - - prefixes = ['rendition: http://www.idpf.org/vocab/rendition/#'] + self.book.prefixes - root.attrib['prefix'] = ' '.join(prefixes) - - # METADATA - self._write_opf_metadata(root) - - # MANIFEST - _ncx_id = self._write_opf_manifest(root) - - # SPINE - self._write_opf_spine(root, _ncx_id) - - # GUIDE - self._write_opf_guide(root) - - # BINDINGS - self._write_opf_bindings(root) - - # WRITE FILE - self._write_opf_file(root) - - def _get_nav(self, item): - # just a basic navigation for now - nav_xml = parse_string(self.book.get_template('nav')) - root = nav_xml.getroot() - - root.set('lang', self.book.language) - root.attrib['{%s}lang' % NAMESPACES['XML']] = self.book.language - - nav_dir_name = os.path.dirname(item.file_name) - - head = etree.SubElement(root, 'head') - title = etree.SubElement(head, 'title') - title.text = self.book.title - - # for now this just handles css files and ignores others - for _link in item.links: - _lnk = etree.SubElement(head, 'link', { - 'href': _link.get('href', ''), 'rel': 'stylesheet', 'type': 'text/css' - }) - - body = etree.SubElement(root, 'body') - nav = etree.SubElement(body, 'nav', {'{%s}type' % NAMESPACES['EPUB']: 'toc', 'id': 'id'}) - - content_title = etree.SubElement(nav, 'h2') - content_title.text = self.book.title - - def _create_section(itm, items): - ol = etree.SubElement(itm, 'ol') - for item in items: - if isinstance(item, tuple) or isinstance(item, list): - li = etree.SubElement(ol, 'li') - if isinstance(item[0], EpubHtml): - a = etree.SubElement(li, 'a', {'href': os.path.relpath(item[0].file_name, nav_dir_name)}) - elif isinstance(item[0], Section) and item[0].href != '': - a = etree.SubElement(li, 'a', {'href': os.path.relpath(item[0].href, nav_dir_name)}) - elif isinstance(item[0], Link): - a = etree.SubElement(li, 'a', {'href': os.path.relpath(item[0].href, nav_dir_name)}) - else: - a = etree.SubElement(li, 'span') - a.text = item[0].title - - _create_section(li, item[1]) - - elif isinstance(item, Link): - li = etree.SubElement(ol, 'li') - a = etree.SubElement(li, 'a', {'href': os.path.relpath(item.href, nav_dir_name)}) - a.text = item.title - elif isinstance(item, EpubHtml): - li = etree.SubElement(ol, 'li') - a = etree.SubElement(li, 'a', {'href': os.path.relpath(item.file_name, nav_dir_name)}) - a.text = item.title - - _create_section(nav, self.book.toc) - - # LANDMARKS / GUIDE - # - http://www.idpf.org/epub/30/spec/epub30-contentdocs.html#sec-xhtml-nav-def-types-landmarks - - if len(self.book.guide) > 0 and self.options.get('epub3_landmark'): - - # Epub2 guide types do not map completely to epub3 landmark types. - guide_to_landscape_map = { - 'notes': 'rearnotes', - 'text': 'bodymatter' - } - - guide_nav = etree.SubElement(body, 'nav', {'{%s}type' % NAMESPACES['EPUB']: 'landmarks'}) - - guide_content_title = etree.SubElement(guide_nav, 'h2') - guide_content_title.text = self.options.get('landmark_title', 'Guide') - - guild_ol = etree.SubElement(guide_nav, 'ol') - - for elem in self.book.guide: - li_item = etree.SubElement(guild_ol, 'li') - - if 'item' in elem: - chap = elem.get('item', None) - if chap: - _href = chap.file_name - _title = chap.title - else: - _href = elem.get('href', '') - _title = elem.get('title', '') - - guide_type = elem.get('type', '') - a_item = etree.SubElement(li_item, 'a', { - '{%s}type' % NAMESPACES['EPUB']: guide_to_landscape_map.get(guide_type, guide_type), - 'href': os.path.relpath(_href, nav_dir_name) - }) - a_item.text = _title - - tree_str = etree.tostring(nav_xml, pretty_print=True, encoding='utf-8', xml_declaration=True) - - return tree_str - - def _get_ncx(self): - - # we should be able to setup language for NCX as also - ncx = parse_string(self.book.get_template('ncx')) - root = ncx.getroot() - - head = etree.SubElement(root, 'head') - - # get this id - uid = etree.SubElement(head, 'meta', {'content': self.book.uid, 'name': 'dtb:uid'}) - uid = etree.SubElement(head, 'meta', {'content': '0', 'name': 'dtb:depth'}) - uid = etree.SubElement(head, 'meta', {'content': '0', 'name': 'dtb:totalPageCount'}) - uid = etree.SubElement(head, 'meta', {'content': '0', 'name': 'dtb:maxPageNumber'}) - - doc_title = etree.SubElement(root, 'docTitle') - title = etree.SubElement(doc_title, 'text') - title.text = self.book.title - -# doc_author = etree.SubElement(root, 'docAuthor') -# author = etree.SubElement(doc_author, 'text') -# author.text = 'Name of the person' - - # For now just make a very simple navMap - nav_map = etree.SubElement(root, 'navMap') - - def _create_section(itm, items, uid): - for item in items: - if isinstance(item, tuple) or isinstance(item, list): - section, subsection = item[0], item[1] - - np = etree.SubElement(itm, 'navPoint', { - 'id': section.get_id() if isinstance(section, EpubHtml) else 'sep_%d' % uid - }) - nl = etree.SubElement(np, 'navLabel') - nt = etree.SubElement(nl, 'text') - nt.text = section.title - - # CAN NOT HAVE EMPTY SRC HERE - href = '' - if isinstance(section, EpubHtml): - href = section.file_name - elif isinstance(section, Section) and section.href != '': - href = section.href - elif isinstance(section, Link): - href = section.href - - nc = etree.SubElement(np, 'content', {'src': href}) - - uid = _create_section(np, subsection, uid + 1) - elif isinstance(item, Link): - _parent = itm - _content = _parent.find('content') - - if _content is not None: - if _content.get('src') == '': - _content.set('src', item.href) - - np = etree.SubElement(itm, 'navPoint', {'id': item.uid}) - nl = etree.SubElement(np, 'navLabel') - nt = etree.SubElement(nl, 'text') - nt.text = item.title - - nc = etree.SubElement(np, 'content', {'src': item.href}) - elif isinstance(item, EpubHtml): - _parent = itm - _content = _parent.find('content') - - if _content is not None: - if _content.get('src') == '': - _content.set('src', item.file_name) - - np = etree.SubElement(itm, 'navPoint', {'id': item.get_id()}) - nl = etree.SubElement(np, 'navLabel') - nt = etree.SubElement(nl, 'text') - nt.text = item.title - - nc = etree.SubElement(np, 'content', {'src': item.file_name}) - - return uid - - _create_section(nav_map, self.book.toc, 0) - - tree_str = etree.tostring(root, pretty_print=True, encoding='utf-8', xml_declaration=True) - - return tree_str - - def _write_items(self): - for item in self.book.get_items(): - if isinstance(item, EpubNcx): - self.out.writestr('%s/%s' % (self.book.FOLDER_NAME, item.file_name), self._get_ncx()) - elif isinstance(item, EpubNav): - self.out.writestr('%s/%s' % (self.book.FOLDER_NAME, item.file_name), self._get_nav(item)) - elif item.manifest: - self.out.writestr('%s/%s' % (self.book.FOLDER_NAME, item.file_name), item.get_content()) - else: - self.out.writestr('%s' % item.file_name, item.get_content()) - - def write(self): - # check for the option allowZip64 - self.out = zipfile.ZipFile(self.file_name, 'w', zipfile.ZIP_DEFLATED) - self.out.writestr('mimetype', 'application/epub+zip', compress_type=zipfile.ZIP_STORED) - - self._write_container() - self._write_opf() - self._write_items() - - self.out.close() - - -class EpubReader(object): - DEFAULT_OPTIONS = {} - - def __init__(self, epub_file_name, options=None): - self.file_name = epub_file_name - self.book = EpubBook() - self.zf = None - - self.opf_file = '' - self.opf_dir = '' - - self.options = dict(self.DEFAULT_OPTIONS) - if options: - self.options.update(options) - - def process(self): - # should cache this html parsing so we don't do it for every plugin - for plg in self.options.get('plugins', []): - if hasattr(plg, 'after_read'): - plg.after_read(self.book) - - for item in self.book.get_items(): - if isinstance(item, EpubHtml): - for plg in self.options.get('plugins', []): - if hasattr(plg, 'html_after_read'): - plg.html_after_read(self.book, item) - - def load(self): - self._load() - - return self.book - - def read_file(self, name): - # Raises KeyError - name = os.path.normpath(name) - return self.zf.read(name) - - def _load_container(self): - meta_inf = self.read_file('META-INF/container.xml') - tree = parse_string(meta_inf) - - for root_file in tree.findall('//xmlns:rootfile[@media-type]', namespaces={'xmlns': NAMESPACES['CONTAINERNS']}): - if root_file.get('media-type') == 'application/oebps-package+xml': - self.opf_file = root_file.get('full-path') - self.opf_dir = zip_path.dirname(self.opf_file) - - def _load_metadata(self): - container_root = self.container.getroot() - - # get epub version - self.book.version = container_root.get('version', None) - - # get unique-identifier - if container_root.get('unique-identifier', None): - self.book.IDENTIFIER_ID = container_root.get('unique-identifier') - - # get xml:lang - # get metadata - metadata = self.container.find('{%s}%s' % (NAMESPACES['OPF'], 'metadata')) - - nsmap = metadata.nsmap - nstags = dict((k, '{%s}' % v) for k, v in six.iteritems(nsmap)) - default_ns = nstags.get(None, '') - - nsdict = dict((v, {}) for v in nsmap.values()) - - def add_item(ns, tag, value, extra): - if ns not in nsdict: - nsdict[ns] = {} - - values = nsdict[ns].setdefault(tag, []) - values.append((value, extra)) - - for t in metadata: - if not etree.iselement(t) or t.tag is etree.Comment: - continue - if t.tag == default_ns + 'meta': - name = t.get('name') - others = dict((k, v) for k, v in t.items()) - - if name and ':' in name: - prefix, name = name.split(':', 1) - else: - prefix = None - - add_item(t.nsmap.get(prefix, prefix), name, t.text, others) - else: - tag = t.tag[t.tag.rfind('}') + 1:] - - if (t.prefix and t.prefix.lower() == 'dc') and tag == 'identifier': - _id = t.get('id', None) - - if _id: - self.book.IDENTIFIER_ID = _id - - others = dict((k, v) for k, v in t.items()) - add_item(t.nsmap[t.prefix], tag, t.text, others) - - self.book.metadata = nsdict - - titles = self.book.get_metadata('DC', 'title') - if len(titles) > 0: - self.book.title = titles[0][0] - - for value, others in self.book.get_metadata('DC', 'identifier'): - if others.get('id') == self.book.IDENTIFIER_ID: - self.book.uid = value - - def _load_manifest(self): - for r in self.container.find('{%s}%s' % (NAMESPACES['OPF'], 'manifest')): - if r is not None and r.tag != '{%s}item' % NAMESPACES['OPF']: - continue - - media_type = r.get('media-type') - _properties = r.get('properties', '') - - if _properties: - properties = _properties.split(' ') - else: - properties = [] - - # people use wrong content types - if media_type == 'image/jpg': - media_type = 'image/jpeg' - - if media_type == 'application/x-dtbncx+xml': - ei = EpubNcx(uid=r.get('id'), file_name=unquote(r.get('href'))) - - ei.content = self.read_file(zip_path.join(self.opf_dir, ei.file_name)) - elif media_type == 'application/xhtml+xml': - if 'nav' in properties: - ei = EpubNav(uid=r.get('id'), file_name=unquote(r.get('href'))) - - ei.content = self.read_file(zip_path.join(self.opf_dir, r.get('href'))) - elif 'cover' in properties: - ei = EpubCoverHtml() - - ei.content = self.read_file(zip_path.join(self.opf_dir, unquote(r.get('href')))) - else: - ei = EpubHtml() - - ei.id = r.get('id') - ei.file_name = unquote(r.get('href')) - ei.media_type = media_type - ei.content = self.read_file(zip_path.join(self.opf_dir, ei.get_name())) - ei.properties = properties - elif media_type in IMAGE_MEDIA_TYPES: - if 'cover-image' in properties: - ei = EpubCover(uid=r.get('id'), file_name=unquote(r.get('href'))) - - ei.media_type = media_type - ei.content = self.read_file(zip_path.join(self.opf_dir, ei.get_name())) - else: - ei = EpubImage() - - ei.id = r.get('id') - ei.file_name = unquote(r.get('href')) - ei.media_type = media_type - ei.content = self.read_file(zip_path.join(self.opf_dir, ei.get_name())) - else: - # different types - ei = EpubItem() - - ei.id = r.get('id') - ei.file_name = unquote(r.get('href')) - ei.media_type = media_type - - ei.content = self.read_file(zip_path.join(self.opf_dir, ei.get_name())) - - self.book.add_item(ei) - - def _parse_ncx(self, data): - tree = parse_string(data) - tree_root = tree.getroot() - - nav_map = tree_root.find('{%s}navMap' % NAMESPACES['DAISY']) - - def _get_children(elems, n, nid): - label, content = '', '' - children = [] - - for a in elems.getchildren(): - if a.tag == '{%s}navLabel' % NAMESPACES['DAISY']: - label = a.getchildren()[0].text - if a.tag == '{%s}content' % NAMESPACES['DAISY']: - content = a.get('src', '') - if a.tag == '{%s}navPoint' % NAMESPACES['DAISY']: - children.append(_get_children(a, n + 1, a.get('id', ''))) - - if len(children) > 0: - if n == 0: - return children - - return (Section(label, href=content), - children) - else: - return Link(content, label, nid) - - self.book.toc = _get_children(nav_map, 0, '') - - def _parse_nav(self, data, base_path): - html_node = parse_html_string(data) - nav_node = html_node.xpath("//nav[@*='toc']")[0] - - def parse_list(list_node): - items = [] - - for item_node in list_node.findall('li'): - - sublist_node = item_node.find('ol') - link_node = item_node.find('a') - - if sublist_node is not None: - title = item_node[0].text - children = parse_list(sublist_node) - - if link_node is not None: - href = zip_path.normpath(zip_path.join(base_path, link_node.get('href'))) - items.append((Section(title, href=href), children)) - else: - items.append((Section(title), children)) - elif link_node is not None: - title = link_node.text - href = zip_path.normpath(zip_path.join(base_path, link_node.get('href'))) - - items.append(Link(href, title)) - - return items - - self.book.toc = parse_list(nav_node.find('ol')) - - def _load_spine(self): - spine = self.container.find('{%s}%s' % (NAMESPACES['OPF'], 'spine')) - - self.book.spine = [(t.get('idref'), t.get('linear', 'yes')) for t in spine] - - toc = spine.get('toc', '') - self.book.set_direction(spine.get('page-progression-direction', None)) - - # should read ncx or nav file - if toc: - try: - ncxFile = self.read_file(zip_path.join(self.opf_dir, self.book.get_item_with_id(toc).get_name())) - except KeyError: - raise EpubException(-1, 'Can not find ncx file.') - - self._parse_ncx(ncxFile) - - def _load_guide(self): - guide = self.container.find('{%s}%s' % (NAMESPACES['OPF'], 'guide')) - if guide is not None: - self.book.guide = [{'href': t.get('href'), 'title': t.get('title'), 'type': t.get('type')} for t in guide] - - def _load_opf_file(self): - try: - s = self.read_file(self.opf_file) - except KeyError: - raise EpubException(-1, 'Can not find container file') - - self.container = parse_string(s) - - self._load_metadata() - self._load_manifest() - self._load_spine() - self._load_guide() - - # read nav file if found - # - if not self.book.toc: - nav_item = next((item for item in self.book.items if isinstance(item, EpubNav)), None) - if nav_item: - self._parse_nav(nav_item.content, zip_path.dirname(nav_item.file_name)) - - def _load(self): - try: - self.zf = zipfile.ZipFile(self.file_name, 'r', compression=zipfile.ZIP_DEFLATED, allowZip64=True) - except zipfile.BadZipfile as bz: - raise EpubException(0, 'Bad Zip file') - except zipfile.LargeZipFile as bz: - raise EpubException(1, 'Large Zip file') - - # 1st check metadata - self._load_container() - self._load_opf_file() - - self.zf.close() - - -# WRITE - -def write_epub(name, book, options=None): - """ - Creates epub file with the content defined in EpubBook. - - >>> ebooklib.write_epub('book.epub', book) - - :Args: - - name: file name for the output file - - book: instance of EpubBook - - options: extra opions as dictionary (optional) - """ - epub = EpubWriter(name, book, options) - - epub.process() - - try: - epub.write() - except IOError: - pass - -# READ - - -def read_epub(name, options=None): - """ - Creates new instance of EpubBook with the content defined in the input file. - - >>> book = ebooklib.read_epub('book.epub') - - :Args: - - name: full path to the input file - - options: extra options as dictionary (optional) - - :Returns: - Instance of EpubBook. - """ - reader = EpubReader(name, options) - - book = reader.load() - reader.process() - - return book diff --git a/ebooklib/plugins/__init__.py b/ebooklib/plugins/__init__.py deleted file mode 100644 index e69de29..0000000 diff --git a/ebooklib/plugins/base.py b/ebooklib/plugins/base.py deleted file mode 100644 index 6351f81..0000000 --- a/ebooklib/plugins/base.py +++ /dev/null @@ -1,49 +0,0 @@ -# This file is part of EbookLib. -# Copyright (c) 2013 Aleksandar Erkalovic -# -# EbookLib is free software: you can redistribute it and/or modify -# it under the terms of the GNU Affero General Public License as published by -# the Free Software Foundation, either version 3 of the License, or -# (at your option) any later version. -# -# EbookLib 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 Affero General Public License for more details. -# -# You should have received a copy of the GNU Affero General Public License -# along with EbookLib. If not, see . - - -class BasePlugin(object): - def before_write(self, book): - "Processing before save" - return True - - def after_write(self, book): - "Processing after save" - return True - - def before_read(self, book): - "Processing before save" - return True - - def after_read(self, book): - "Processing after save" - return True - - def item_after_read(self, book, item): - "Process general item after read." - return True - - def item_before_write(self, book, item): - "Process general item before write." - return True - - def html_after_read(self, book, chapter): - "Processing HTML before read." - return True - - def html_before_write(self, book, chapter): - "Processing HTML before save." - return True diff --git a/ebooklib/plugins/booktype.py b/ebooklib/plugins/booktype.py deleted file mode 100644 index 5518258..0000000 --- a/ebooklib/plugins/booktype.py +++ /dev/null @@ -1,119 +0,0 @@ -# This file is part of EbookLib. -# Copyright (c) 2013 Aleksandar Erkalovic -# -# EbookLib is free software: you can redistribute it and/or modify -# it under the terms of the GNU Affero General Public License as published by -# the Free Software Foundation, either version 3 of the License, or -# (at your option) any later version. -# -# EbookLib 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 Affero General Public License for more details. -# -# You should have received a copy of the GNU Affero General Public License -# along with EbookLib. If not, see . - -from ebooklib.plugins.base import BasePlugin -from ebooklib.utils import parse_html_string - -class BooktypeLinks(BasePlugin): - NAME = 'Booktype Links' - - def __init__(self, booktype_book): - self.booktype_book = booktype_book - - def html_before_write(self, book, chapter): - from lxml import etree - - try: - from urlparse import urlparse, urljoin - except ImportError: - from urllib.parse import urlparse, urljoin - - try: - tree = parse_html_string(chapter.content) - except: - return - - root = tree.getroottree() - - if len(root.find('body')) != 0: - body = tree.find('body') - - # should also be aware to handle - # ../chapter/ - # ../chapter/#reference - # ../chapter#reference - - for _link in body.xpath('//a'): - # This is just temporary for the footnotes - if _link.get('href', '').find('InsertNoteID') != -1: - _ln = _link.get('href', '') - i = _ln.find('#') - _link.set('href', _ln[i:]); - - continue - - _u = urlparse(_link.get('href', '')) - - # Let us care only for internal links at the moment - if _u.scheme == '': - if _u.path != '': - _link.set('href', '%s.xhtml' % _u.path) - - if _u.fragment != '': - _link.set('href', urljoin(_link.get('href'), '#%s' % _u.fragment)) - - if _link.get('name') != None: - _link.set('id', _link.get('name')) - etree.strip_attributes(_link, 'name') - - chapter.content = etree.tostring(tree, pretty_print=True, encoding='utf-8') - - - - -class BooktypeFootnotes(BasePlugin): - NAME = 'Booktype Footnotes' - - def __init__(self, booktype_book): - self.booktype_book = booktype_book - - def html_before_write(self, book, chapter): - from lxml import etree - - from ebooklib import epub - - try: - tree = parse_html_string(chapter.content) - except: - return - - root = tree.getroottree() - - if len(root.find('body')) != 0: - body = tree.find('body') - - # 1 - #
  1. prvi footnote ^
    2. - - # 1

    - # - for footnote in body.xpath('//span[@class="InsertNoteMarker"]'): - footnote_id = footnote.get('id')[:-8] - a = footnote.getchildren()[0].getchildren()[0] - - footnote_text = body.xpath('//li[@id="%s"]' % footnote_id)[0] - - a.attrib['{%s}type' % epub.NAMESPACES['EPUB']] = 'noteref' - ftn = etree.SubElement(body, 'aside', {'id': footnote_id}) - ftn.attrib['{%s}type' % epub.NAMESPACES['EPUB']] = 'footnote' - ftn_p = etree.SubElement(ftn, 'p') - ftn_p.text = footnote_text.text - - old_footnote = body.xpath('//ol[@id="InsertNote_NoteList"]') - if len(old_footnote) > 0: - body.remove(old_footnote[0]) - - chapter.content = etree.tostring(tree, pretty_print=True, encoding='utf-8') diff --git a/ebooklib/plugins/sourcecode.py b/ebooklib/plugins/sourcecode.py deleted file mode 100644 index 4f973a2..0000000 --- a/ebooklib/plugins/sourcecode.py +++ /dev/null @@ -1,68 +0,0 @@ -# This file is part of EbookLib. -# Copyright (c) 2013 Aleksandar Erkalovic -# -# EbookLib is free software: you can redistribute it and/or modify -# it under the terms of the GNU Affero General Public License as published by -# the Free Software Foundation, either version 3 of the License, or -# (at your option) any later version. -# -# EbookLib 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 Affero General Public License for more details. -# -# You should have received a copy of the GNU Affero General Public License -# along with EbookLib. If not, see . - -from ebooklib.plugins.base import BasePlugin -from ebooklib.utils import parse_html_string - -class SourceHighlighter(BasePlugin): - def __init__(self): - pass - - def html_before_write(self, book, chapter): - from lxml import etree, html - - from pygments import highlight - from pygments.formatters import HtmlFormatter - - from ebooklib import epub - - try: - tree = parse_html_string(chapter.content) - except: - return - - root = tree.getroottree() - - had_source = False - - if len(root.find('body')) != 0: - body = tree.find('body') - # check for embeded source - for source in body.xpath('//pre[contains(@class,"source-")]'): - css_class = source.get('class') - - source_text = (source.text or '') + ''.join([html.tostring(child) for child in source.iterchildren()]) - - if 'source-python' in css_class: - from pygments.lexers import PythonLexer - -# _text = highlight(source_text, PythonLexer(), HtmlFormatter(linenos="inline")) - _text = highlight(source_text, PythonLexer(), HtmlFormatter()) - - if 'source-css' in css_class: - from pygments.lexers import CssLexer - - _text = highlight(source_text, CssLexer(), HtmlFormatter()) - - _parent = source.getparent() - _parent.replace(source, etree.XML(_text)) - - had_source = True - - if had_source: - chapter.add_link(href="style/code.css", rel="stylesheet", type="text/css") - chapter.content = etree.tostring(tree, pretty_print=True, encoding='utf-8') - diff --git a/ebooklib/plugins/standard.py b/ebooklib/plugins/standard.py deleted file mode 100644 index 61576f9..0000000 --- a/ebooklib/plugins/standard.py +++ /dev/null @@ -1,230 +0,0 @@ -# This file is part of EbookLib. -# Copyright (c) 2013 Aleksandar Erkalovic -# -# EbookLib is free software: you can redistribute it and/or modify -# it under the terms of the GNU Affero General Public License as published by -# the Free Software Foundation, either version 3 of the License, or -# (at your option) any later version. -# -# EbookLib 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 Affero General Public License for more details. -# -# You should have received a copy of the GNU Affero General Public License -# along with EbookLib. If not, see . - -import six - -from ebooklib.plugins.base import BasePlugin -from ebooklib.utils import parse_html_string - -# TODO: -# - should also look for the _required_ elements -# http://www.w3.org/html/wg/drafts/html/master/tabular-data.html#the-table-element - -ATTRIBUTES_GLOBAL = ['accesskey', 'class', 'contenteditable', 'contextmenu', 'dir', 'draggable', - 'dropzone', 'hidden', 'id', 'inert', 'itemid', 'itemprop', 'itemref', - 'itemscope', 'itemtype', 'lang', 'spellcheck', 'style', 'tabindex', - 'title', 'translate', 'epub:type'] - -# Remove for now from here -DEPRECATED_TAGS = ['acronym', 'applet', 'basefont', 'big', 'center', 'dir', 'font', 'frame', - 'frameset', 'isindex', 'noframes', 's', 'strike', 'tt'] - - -def leave_only(item, tag_list): - for _attr in six.iterkeys(item.attrib): - if _attr not in tag_list: - del item.attrib[_attr] - - -class SyntaxPlugin(BasePlugin): - NAME = 'Check HTML syntax' - - def html_before_write(self, book, chapter): - from lxml import etree - - try: - tree = parse_html_string(chapter.content) - except: - return - - root = tree.getroottree() - - # delete deprecated tags - # i should really have a list of allowed tags - for tag in DEPRECATED_TAGS: - etree.strip_tags(root, tag) - - head = tree.find('head') - - if head is not None and len(head) != 0: - - for _item in head: - if _item.tag == 'base': - leave_only(_item, ATTRIBUTES_GLOBAL + ['href', 'target']) - elif _item.tag == 'link': - leave_only(_item, ATTRIBUTES_GLOBAL + ['href', 'crossorigin', 'rel', 'media', 'hreflang', 'type', 'sizes']) - elif _item.tag == 'title': - if _item.text == '': - head.remove(_item) - elif _item.tag == 'meta': - leave_only(_item, ATTRIBUTES_GLOBAL + ['name', 'http-equiv', 'content', 'charset']) - # just remove for now, but really should not be like this - head.remove(_item) - elif _item.tag == 'script': - leave_only(_item, ATTRIBUTES_GLOBAL + ['src', 'type', 'charset', 'async', 'defer', 'crossorigin']) - elif _item.tag == 'source': - leave_only(_item, ATTRIBUTES_GLOBAL + ['src', 'type', 'media']) - elif _item.tag == 'style': - leave_only(_item, ATTRIBUTES_GLOBAL + ['media', 'type', 'scoped']) - else: - leave_only(_item, ATTRIBUTES_GLOBAL) - - - if len(root.find('body')) != 0: - body = tree.find('body') - - for _item in body.iter(): - # it is not - # - - if _item.tag == 'a': - leave_only(_item, ATTRIBUTES_GLOBAL + ['href', 'target', 'download', 'rel', 'hreflang', 'type']) - elif _item.tag == 'area': - leave_only(_item, ATTRIBUTES_GLOBAL + ['alt', 'coords', 'shape', 'href', 'target', 'download', 'rel', 'hreflang', 'type']) - elif _item.tag == 'audio': - leave_only(_item, ATTRIBUTES_GLOBAL + ['src', 'crossorigin', 'preload', 'autoplay', 'mediagroup', 'loop', 'muted', 'controls']) - elif _item.tag == 'blockquote': - leave_only(_item, ATTRIBUTES_GLOBAL + ['cite']) - elif _item.tag == 'button': - leave_only(_item, ATTRIBUTES_GLOBAL + ['autofocus', 'disabled', 'form', 'formaction', 'formenctype', 'formmethod', 'formnovalidate', - 'formtarget', 'name', 'type', 'value', 'menu']) - elif _item.tag == 'canvas': - leave_only(_item, ATTRIBUTES_GLOBAL + ['width', 'height']) - elif _item.tag == 'canvas': - leave_only(_item, ATTRIBUTES_GLOBAL + ['width', 'height']) - elif _item.tag == 'del': - leave_only(_item, ATTRIBUTES_GLOBAL + ['cite', 'datetime']) - elif _item.tag == 'details': - leave_only(_item, ATTRIBUTES_GLOBAL + ['open']) - elif _item.tag == 'embed': - leave_only(_item, ATTRIBUTES_GLOBAL + ['src', 'type', 'width', 'height']) - elif _item.tag == 'fieldset': - leave_only(_item, ATTRIBUTES_GLOBAL + ['disable', 'form', 'name']) - elif _item.tag == 'details': - leave_only(_item, ATTRIBUTES_GLOBAL + ['accept-charset', 'action', 'autocomplete', 'enctype', 'method', 'name', 'novalidate', 'target']) - elif _item.tag == 'iframe': - leave_only(_item, ATTRIBUTES_GLOBAL + ['src', 'srcdoc', 'name', 'sandbox', 'seamless', 'allowfullscreen', 'width', 'height']) - elif _item.tag == 'img': - _src = _item.get('src', '').lower() - if _src.startswith('http://') or _src.startswith('https://'): - if 'remote-resources' not in chapter.properties: - chapter.properties.append('remote-resources') - # THIS DOES NOT WORK, ONLY VIDEO AND AUDIO FILES CAN BE REMOTE RESOURCES - # THAT MEANS I SHOULD ALSO CATCH -# -# EbookLib is free software: you can redistribute it and/or modify -# it under the terms of the GNU Affero General Public License as published by -# the Free Software Foundation, either version 3 of the License, or -# (at your option) any later version. -# -# EbookLib 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 Affero General Public License for more details. -# -# You should have received a copy of the GNU Affero General Public License -# along with EbookLib. If not, see . - -import six -import subprocess - -from ebooklib.plugins.base import BasePlugin -from ebooklib.utils import parse_html_string - -# Recommend usage of -# - https://github.com/w3c/tidy-html5 - -def tidy_cleanup(content, **extra): - cmd = [] - - for k, v in six.iteritems(extra): - - if v: - cmd.append('--%s' % k) - cmd.append(v) - else: - cmd.append('-%s' % k) - - # must parse all other extra arguments - try: - p = subprocess.Popen(['tidy']+cmd, shell=False, - stdin=subprocess.PIPE, stdout=subprocess.PIPE, - stderr=subprocess.PIPE, close_fds=True) - except OSError: - return (3, None) - - p.stdin.write(content) - - (cont, p_err) = p.communicate() - - # 0 - all ok - # 1 - there were warnings - # 2 - there were errors - # 3 - exception - - return (p.returncode, cont) - - -class TidyPlugin(BasePlugin): - NAME = 'Tidy HTML' - OPTIONS = {'char-encoding': 'utf8', - 'tidy-mark': 'no' - } - - def __init__(self, extra = {}): - self.options = dict(self.OPTIONS) - self.options.update(extra) - - def html_before_write(self, book, chapter): - if not chapter.content: - return None - - (_, chapter.content) = tidy_cleanup(chapter.content, **self.options) - - return chapter.content - - def html_after_read(self, book, chapter): - if not chapter.content: - return None - - (_, chapter.content) = tidy_cleanup(chapter.content, **self.options) - - return chapter.content - diff --git a/ebooklib/utils.py b/ebooklib/utils.py deleted file mode 100644 index 162f4c9..0000000 --- a/ebooklib/utils.py +++ /dev/null @@ -1,60 +0,0 @@ -# This file is part of EbookLib. -# Copyright (c) 2013 Aleksandar Erkalovic -# -# EbookLib is free software: you can redistribute it and/or modify -# it under the terms of the GNU Affero General Public License as published by -# the Free Software Foundation, either version 3 of the License, or -# (at your option) any later version. -# -# EbookLib 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 Affero General Public License for more details. -# -# You should have received a copy of the GNU Affero General Public License -# along with EbookLib. If not, see . - -import io -import mimetypes - -from lxml import etree - - -mimetype_initialised = False - - -def debug(obj): - import pprint - - pp = pprint.PrettyPrinter(indent=4) - pp.pprint(obj) - - -def parse_string(s): - try: - tree = etree.parse(io.BytesIO(s.encode('utf-8'))) - except: - tree = etree.parse(io.BytesIO(s)) - - return tree - - -def parse_html_string(s): - from lxml import html - - utf8_parser = html.HTMLParser(encoding='utf-8') - - html_tree = html.document_fromstring(s, parser=utf8_parser) - - return html_tree - - -def guess_type(extenstion): - global mimetype_initialised - - if not mimetype_initialised: - mimetypes.init() - mimetypes.add_type('application/xhtml+xml', '.xhtml') - mimetype_initialised = True - - return mimetypes.guess_type(extenstion) diff --git a/parsers/ebook.py b/parsers/ebook.py deleted file mode 100644 index 9ca2cc1..0000000 --- a/parsers/ebook.py +++ /dev/null @@ -1,208 +0,0 @@ -#!/usr/bin/env python3 - -# This file is a part of Lector, a Qt based ebook reader -# Copyright (C) 2017 BasioMeusPuga - -# 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 . - -import os -import re -import sys -import shutil -import zipfile -import collections -from urllib.parse import unquote - -import ebooklib.epub -import KindleUnpack.kindleunpack as KindleUnpack - - -class ParseEBook: - def __init__(self, filename, temp_dir, file_md5): - # TODO - # Maybe also include book description - self.filename = filename - self.filename_copy = filename - self.book = None - self.temp_dir = temp_dir - self.temp_dir_copy = temp_dir - self.file_md5 = file_md5 - - # This is a crazy lazy thing - # But it works for now - - self.use_KindleUnpack = False - kindle_extensions = ['.mobi', '.azw', '.azw3', '.azw4', '.prc'] - if os.path.splitext(self.filename)[1].lower() in kindle_extensions: - self.use_KindleUnpack = True - self.temp_dir = os.path.join( - self.temp_dir, os.path.basename(self.filename)) - - def read_book(self): - if self.use_KindleUnpack: - with HidePrinting(): - KindleUnpack.unpackBook(self.filename, self.temp_dir) - - new_filename_with_ext = os.path.splitext( - os.path.basename(self.filename))[0] + '.epub' - - self.filename = os.path.join( - self.temp_dir, 'mobi8', new_filename_with_ext) - if not os.path.exists(self.filename): - zip_dir = os.path.join(self.temp_dir, 'mobi7') - zip_file = os.path.join( - self.temp_dir_copy, new_filename_with_ext) - self.filename = shutil.make_archive(zip_file, 'zip', zip_dir) - - self.temp_dir = self.temp_dir_copy - - try: - self.book = ebooklib.epub.read_epub(self.filename) - except (KeyError, AttributeError): - print('Cannot parse ' + self.filename) - return - except FileNotFoundError: - print('Intermediate FNF: ' + self.filename_copy) - return - - def get_title(self): - return self.book.title.strip() - - def get_author(self): - try: - return self.book.metadata['http://purl.org/dc/elements/1.1/']['creator'][0][0] - except KeyError: - return - - def get_year(self): - try: - return self.book.metadata['http://purl.org/dc/elements/1.1/']['date'][0][0][:4] - except KeyError: - return - - def get_cover_image(self): - # Get cover image - # This seems hack-ish, but that's never stopped me before - image_path = None - try: - cover = self.book.metadata['http://www.idpf.org/2007/opf']['cover'][0][1]['content'] - cover_item = self.book.get_item_with_id(cover) - if cover_item: - return cover_item.get_content() - except KeyError: - pass - - # In case no cover_item is returned, we look for a cover in the guide - for i in self.book.guide: - try: - if (i['title'].lower in ['cover', 'cover-image', 'coverimage'] or - i['type'] == 'coverimagestandard'): - image_path = i['href'] - break - except KeyError: - pass - - # If that fails, we find the first image referenced in the book - if not image_path: - for i in self.book.items: - if i.media_type == 'application/xhtml+xml': - _regex = re.search(r"src=\"(.*)\"\/", i.content.decode('utf-8')) - if _regex: - image_path = _regex[1] - break - - if image_path: - for i in self.book.get_items_of_type(ebooklib.ITEM_IMAGE): - if os.path.basename(i.file_name) == os.path.basename(image_path): - return i.get_content() - - # And if that too fails, we get the first image referenced in the file - for i in self.book.items: - if i.media_type == 'image/jpeg' or i.media_type == 'image/png': - return i.get_content() - - def get_isbn(self): - try: - identifier = self.book.metadata['http://purl.org/dc/elements/1.1/']['identifier'] - for i in identifier: - identifier_provider = i[1]['{http://www.idpf.org/2007/opf}scheme'] - if identifier_provider.lower() == 'isbn': - isbn = i[0] - return isbn - except KeyError: - return - - def get_tags(self): - try: - subject = self.book.metadata['http://purl.org/dc/elements/1.1/']['subject'] - tags = [i[0] for i in subject] - return tags - except KeyError: - return - - def get_contents(self): - extract_path = os.path.join(self.temp_dir, self.file_md5) - zipfile.ZipFile(self.filename).extractall(extract_path) - - contents = collections.OrderedDict() - - def flatten_section(toc_element): - output_list = [] - for i in toc_element: - if isinstance(i, (tuple, list)): - output_list.extend(flatten_section(i)) - else: - output_list.append(i) - return output_list - - for i in self.book.toc: - if isinstance(i, (tuple, list)): - flattened = flatten_section(i) - - for j in flattened: - title = j.title - href = unquote(j.href) - try: - content = self.book.get_item_with_href(href).get_content() - contents[title] = content.decode() - except AttributeError: - pass - - else: - title = i.title - href = unquote(i.href) - try: - content = self.book.get_item_with_href(href).get_content() - if content: - contents[title] = content.decode() - else: - raise AttributeError - except AttributeError: - contents[title] = 'Parse Error' - - # Special settings that have to be returned with the file - # Referenced in sorter.py - file_settings = { - 'images_only': False} - - return contents, file_settings - - -class HidePrinting: - def __enter__(self): - self._original_stdout = sys.stdout - sys.stdout = None - - def __exit__(self, exc_type, exc_val, exc_tb): - sys.stdout = self._original_stdout