├── .dockerignore ├── .gitattributes ├── .github └── workflows │ └── docker.yml ├── .gitignore ├── Dockerfile ├── LICENSE ├── README.md ├── avdc.db ├── avdc.old.db ├── avdc ├── __init__.py ├── actress │ ├── __init__.py │ ├── gfriends.py │ └── xslist.py ├── model │ ├── __init__.py │ ├── actress.py │ ├── cover.py │ └── metadata.py ├── provider │ ├── __init__.py │ ├── arzon.py │ ├── avsox.py │ ├── dlsite.py │ ├── fanza.py │ ├── fc2.py │ ├── jav321.py │ ├── javbus.py │ ├── javdb.py │ ├── javlib.py │ ├── mgstage.py │ └── xcity.py └── utility │ ├── __init__.py │ ├── face_api.py │ ├── httpclient.py │ ├── image.py │ ├── imagesize.py │ ├── misc.py │ └── text2image.py ├── docker-compose.yaml ├── main.py ├── requirements.txt └── server ├── __init__.py ├── api.py ├── database.py ├── db_api.py └── views.py /.dockerignore: -------------------------------------------------------------------------------- 1 | .git 2 | .gitignore 3 | .gitattributes 4 | .dockerignore 5 | Dockerfile* 6 | 7 | # General 8 | *.DS_Store 9 | .AppleDouble 10 | .LSOverride 11 | 12 | # Byte-compiled / optimized / DLL files 13 | __pycache__/ 14 | *.py[cod] 15 | *$py.class 16 | 17 | # Environments 18 | .env 19 | .venv 20 | env/ 21 | venv/ 22 | ENV/ 23 | 24 | # Others 25 | .github/ 26 | *.db 27 | *.md 28 | *.yml 29 | *.yaml 30 | -------------------------------------------------------------------------------- /.gitattributes: -------------------------------------------------------------------------------- 1 | *.py text=auto eol=lf 2 | -------------------------------------------------------------------------------- /.github/workflows/docker.yml: -------------------------------------------------------------------------------- 1 | name: Publish Docker Image 2 | 3 | on: 4 | workflow_dispatch: 5 | 6 | jobs: 7 | build: 8 | name: Build 9 | runs-on: ubuntu-latest 10 | steps: 11 | 12 | - name: Check out 13 | uses: actions/checkout@v2 14 | 15 | - name: Set up QEMU 16 | uses: docker/setup-qemu-action@v1 17 | 18 | - name: Set up Docker Buildx 19 | uses: docker/setup-buildx-action@v1 20 | 21 | - name: Login to DockerHub 22 | uses: docker/login-action@v1 23 | with: 24 | username: ${{ secrets.DOCKER_USERNAME }} 25 | password: ${{ secrets.DOCKER_PASSWORD }} 26 | 27 | - name: Login to GitHub Container Registry 28 | uses: docker/login-action@v1 29 | with: 30 | registry: ghcr.io 31 | username: xjasonlyu 32 | password: ${{ secrets.CR_PAT }} 33 | 34 | - name: Build and Push 35 | uses: docker/build-push-action@v2 36 | with: 37 | context: . 38 | push: true 39 | platforms: linux/amd64,linux/arm64 40 | tags: | 41 | xjasonlyu/avdc-api:latest 42 | ghcr.io/xjasonlyu/avdc-api:latest 43 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | *.egg-info/ 24 | .installed.cfg 25 | *.egg 26 | MANIFEST 27 | 28 | # PyInstaller 29 | # Usually these files are written by a python script from a template 30 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 31 | *.manifest 32 | *.spec 33 | 34 | # Installer logs 35 | pip-log.txt 36 | pip-delete-this-directory.txt 37 | 38 | # Unit test / coverage reports 39 | htmlcov/ 40 | .tox/ 41 | .coverage 42 | .coverage.* 43 | .cache 44 | nosetests.xml 45 | coverage.xml 46 | *.cover 47 | .hypothesis/ 48 | .pytest_cache/ 49 | 50 | # Translations 51 | *.mo 52 | *.pot 53 | 54 | # Django stuff: 55 | *.log 56 | local_settings.py 57 | db.sqlite3 58 | 59 | # Flask stuff: 60 | instance/ 61 | .webassets-cache 62 | 63 | # Scrapy stuff: 64 | .scrapy 65 | 66 | # Sphinx documentation 67 | docs/_build/ 68 | 69 | # PyBuilder 70 | target/ 71 | 72 | # Jupyter Notebook 73 | .ipynb_checkpoints 74 | 75 | # pyenv 76 | .python-version 77 | 78 | # celery beat schedule file 79 | celerybeat-schedule 80 | 81 | # SageMath parsed files 82 | *.sage.py 83 | 84 | # Environments 85 | .env 86 | .venv 87 | env/ 88 | venv/ 89 | ENV/ 90 | env.bak/ 91 | venv.bak/ 92 | 93 | # Spyder project settings 94 | .spyderproject 95 | .spyproject 96 | 97 | # Rope project settings 98 | .ropeproject 99 | 100 | # mkdocs documentation 101 | /site 102 | 103 | # mypy 104 | .mypy_cache/ 105 | 106 | # movie files 107 | *.mp4 108 | 109 | # success/failed folder 110 | JAV_output/**/* 111 | failed/* 112 | 113 | .DS_Store 114 | -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- 1 | FROM python:3.9-slim 2 | LABEL org.opencontainers.image.source="https://github.com/xjasonlyu/avdc-api" 3 | 4 | WORKDIR /app 5 | COPY . /app 6 | 7 | RUN pip install --no-cache-dir -U pip \ 8 | && pip install --no-cache-dir -r requirements.txt \ 9 | && rm -rf requirements.txt 10 | 11 | ENV HTTP_PROXY="" 12 | ENV HTTPS_PROXY="" 13 | 14 | ENV AVDC_DATABASE="" 15 | ENV AVDC_TOKEN="" 16 | 17 | ENV GOOGLE_APPLICATION_CREDENTIALS="/key.json" 18 | 19 | ENV PORT=5000 20 | ENTRYPOINT exec python -m main -p $PORT 21 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | GNU GENERAL PUBLIC LICENSE 2 | Version 3, 29 June 2007 3 | 4 | Copyright (C) 2007 Free Software Foundation, Inc. 5 | Everyone is permitted to copy and distribute verbatim copies 6 | of this license document, but changing it is not allowed. 7 | 8 | Preamble 9 | 10 | The GNU General Public License is a free, copyleft license for 11 | software and other kinds of works. 12 | 13 | The licenses for most software and other practical works are designed 14 | to take away your freedom to share and change the works. By contrast, 15 | the GNU General Public License is intended to guarantee your freedom to 16 | share and change all versions of a program--to make sure it remains free 17 | software for all its users. We, the Free Software Foundation, use the 18 | GNU General Public License for most of our software; it applies also to 19 | any other work released this way by its authors. You can apply it to 20 | your programs, too. 21 | 22 | When we speak of free software, we are referring to freedom, not 23 | price. Our General Public Licenses are designed to make sure that you 24 | have the freedom to distribute copies of free software (and charge for 25 | them if you wish), that you receive source code or can get it if you 26 | want it, that you can change the software or use pieces of it in new 27 | free programs, and that you know you can do these things. 28 | 29 | To protect your rights, we need to prevent others from denying you 30 | these rights or asking you to surrender the rights. Therefore, you have 31 | certain responsibilities if you distribute copies of the software, or if 32 | you modify it: responsibilities to respect the freedom of others. 33 | 34 | For example, if you distribute copies of such a program, whether 35 | gratis or for a fee, you must pass on to the recipients the same 36 | freedoms that you received. You must make sure that they, too, receive 37 | or can get the source code. And you must show them these terms so they 38 | know their rights. 39 | 40 | Developers that use the GNU GPL protect your rights with two steps: 41 | (1) assert copyright on the software, and (2) offer you this License 42 | giving you legal permission to copy, distribute and/or modify it. 43 | 44 | For the developers' and authors' protection, the GPL clearly explains 45 | that there is no warranty for this free software. For both users' and 46 | authors' sake, the GPL requires that modified versions be marked as 47 | changed, so that their problems will not be attributed erroneously to 48 | authors of previous versions. 49 | 50 | Some devices are designed to deny users access to install or run 51 | modified versions of the software inside them, although the manufacturer 52 | can do so. This is fundamentally incompatible with the aim of 53 | protecting users' freedom to change the software. The systematic 54 | pattern of such abuse occurs in the area of products for individuals to 55 | use, which is precisely where it is most unacceptable. Therefore, we 56 | have designed this version of the GPL to prohibit the practice for those 57 | products. If such problems arise substantially in other domains, we 58 | stand ready to extend this provision to those domains in future versions 59 | of the GPL, as needed to protect the freedom of users. 60 | 61 | Finally, every program is threatened constantly by software patents. 62 | States should not allow patents to restrict development and use of 63 | software on general-purpose computers, but in those that do, we wish to 64 | avoid the special danger that patents applied to a free program could 65 | make it effectively proprietary. To prevent this, the GPL assures that 66 | patents cannot be used to render the program non-free. 67 | 68 | The precise terms and conditions for copying, distribution and 69 | modification follow. 70 | 71 | TERMS AND CONDITIONS 72 | 73 | 0. Definitions. 74 | 75 | "This License" refers to version 3 of the GNU General Public License. 76 | 77 | "Copyright" also means copyright-like laws that apply to other kinds of 78 | works, such as semiconductor masks. 79 | 80 | "The Program" refers to any copyrightable work licensed under this 81 | License. Each licensee is addressed as "you". "Licensees" and 82 | "recipients" may be individuals or organizations. 83 | 84 | To "modify" a work means to copy from or adapt all or part of the work 85 | in a fashion requiring copyright permission, other than the making of an 86 | exact copy. The resulting work is called a "modified version" of the 87 | earlier work or a work "based on" the earlier work. 88 | 89 | A "covered work" means either the unmodified Program or a work based 90 | on the Program. 91 | 92 | To "propagate" a work means to do anything with it that, without 93 | permission, would make you directly or secondarily liable for 94 | infringement under applicable copyright law, except executing it on a 95 | computer or modifying a private copy. Propagation includes copying, 96 | distribution (with or without modification), making available to the 97 | public, and in some countries other activities as well. 98 | 99 | To "convey" a work means any kind of propagation that enables other 100 | parties to make or receive copies. Mere interaction with a user through 101 | a computer network, with no transfer of a copy, is not conveying. 102 | 103 | An interactive user interface displays "Appropriate Legal Notices" 104 | to the extent that it includes a convenient and prominently visible 105 | feature that (1) displays an appropriate copyright notice, and (2) 106 | tells the user that there is no warranty for the work (except to the 107 | extent that warranties are provided), that licensees may convey the 108 | work under this License, and how to view a copy of this License. If 109 | the interface presents a list of user commands or options, such as a 110 | menu, a prominent item in the list meets this criterion. 111 | 112 | 1. Source Code. 113 | 114 | The "source code" for a work means the preferred form of the work 115 | for making modifications to it. "Object code" means any non-source 116 | form of a work. 117 | 118 | A "Standard Interface" means an interface that either is an official 119 | standard defined by a recognized standards body, or, in the case of 120 | interfaces specified for a particular programming language, one that 121 | is widely used among developers working in that language. 122 | 123 | The "System Libraries" of an executable work include anything, other 124 | than the work as a whole, that (a) is included in the normal form of 125 | packaging a Major Component, but which is not part of that Major 126 | Component, and (b) serves only to enable use of the work with that 127 | Major Component, or to implement a Standard Interface for which an 128 | implementation is available to the public in source code form. A 129 | "Major Component", in this context, means a major essential component 130 | (kernel, window system, and so on) of the specific operating system 131 | (if any) on which the executable work runs, or a compiler used to 132 | produce the work, or an object code interpreter used to run it. 133 | 134 | The "Corresponding Source" for a work in object code form means all 135 | the source code needed to generate, install, and (for an executable 136 | work) run the object code and to modify the work, including scripts to 137 | control those activities. However, it does not include the work's 138 | System Libraries, or general-purpose tools or generally available free 139 | programs which are used unmodified in performing those activities but 140 | which are not part of the work. For example, Corresponding Source 141 | includes interface definition files associated with source files for 142 | the work, and the source code for shared libraries and dynamically 143 | linked subprograms that the work is specifically designed to require, 144 | such as by intimate data communication or control flow between those 145 | subprograms and other parts of the work. 146 | 147 | The Corresponding Source need not include anything that users 148 | can regenerate automatically from other parts of the Corresponding 149 | Source. 150 | 151 | The Corresponding Source for a work in source code form is that 152 | same work. 153 | 154 | 2. Basic Permissions. 155 | 156 | All rights granted under this License are granted for the term of 157 | copyright on the Program, and are irrevocable provided the stated 158 | conditions are met. This License explicitly affirms your unlimited 159 | permission to run the unmodified Program. The output from running a 160 | covered work is covered by this License only if the output, given its 161 | content, constitutes a covered work. This License acknowledges your 162 | rights of fair use or other equivalent, as provided by copyright law. 163 | 164 | You may make, run and propagate covered works that you do not 165 | convey, without conditions so long as your license otherwise remains 166 | in force. You may convey covered works to others for the sole purpose 167 | of having them make modifications exclusively for you, or provide you 168 | with facilities for running those works, provided that you comply with 169 | the terms of this License in conveying all material for which you do 170 | not control copyright. Those thus making or running the covered works 171 | for you must do so exclusively on your behalf, under your direction 172 | and control, on terms that prohibit them from making any copies of 173 | your copyrighted material outside their relationship with you. 174 | 175 | Conveying under any other circumstances is permitted solely under 176 | the conditions stated below. Sublicensing is not allowed; section 10 177 | makes it unnecessary. 178 | 179 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law. 180 | 181 | No covered work shall be deemed part of an effective technological 182 | measure under any applicable law fulfilling obligations under article 183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or 184 | similar laws prohibiting or restricting circumvention of such 185 | measures. 186 | 187 | When you convey a covered work, you waive any legal power to forbid 188 | circumvention of technological measures to the extent such circumvention 189 | is effected by exercising rights under this License with respect to 190 | the covered work, and you disclaim any intention to limit operation or 191 | modification of the work as a means of enforcing, against the work's 192 | users, your or third parties' legal rights to forbid circumvention of 193 | technological measures. 194 | 195 | 4. Conveying Verbatim Copies. 196 | 197 | You may convey verbatim copies of the Program's source code as you 198 | receive it, in any medium, provided that you conspicuously and 199 | appropriately publish on each copy an appropriate copyright notice; 200 | keep intact all notices stating that this License and any 201 | non-permissive terms added in accord with section 7 apply to the code; 202 | keep intact all notices of the absence of any warranty; and give all 203 | recipients a copy of this License along with the Program. 204 | 205 | You may charge any price or no price for each copy that you convey, 206 | and you may offer support or warranty protection for a fee. 207 | 208 | 5. Conveying Modified Source Versions. 209 | 210 | You may convey a work based on the Program, or the modifications to 211 | produce it from the Program, in the form of source code under the 212 | terms of section 4, provided that you also meet all of these conditions: 213 | 214 | a) The work must carry prominent notices stating that you modified 215 | it, and giving a relevant date. 216 | 217 | b) The work must carry prominent notices stating that it is 218 | released under this License and any conditions added under section 219 | 7. This requirement modifies the requirement in section 4 to 220 | "keep intact all notices". 221 | 222 | c) You must license the entire work, as a whole, under this 223 | License to anyone who comes into possession of a copy. This 224 | License will therefore apply, along with any applicable section 7 225 | additional terms, to the whole of the work, and all its parts, 226 | regardless of how they are packaged. This License gives no 227 | permission to license the work in any other way, but it does not 228 | invalidate such permission if you have separately received it. 229 | 230 | d) If the work has interactive user interfaces, each must display 231 | Appropriate Legal Notices; however, if the Program has interactive 232 | interfaces that do not display Appropriate Legal Notices, your 233 | work need not make them do so. 234 | 235 | A compilation of a covered work with other separate and independent 236 | works, which are not by their nature extensions of the covered work, 237 | and which are not combined with it such as to form a larger program, 238 | in or on a volume of a storage or distribution medium, is called an 239 | "aggregate" if the compilation and its resulting copyright are not 240 | used to limit the access or legal rights of the compilation's users 241 | beyond what the individual works permit. Inclusion of a covered work 242 | in an aggregate does not cause this License to apply to the other 243 | parts of the aggregate. 244 | 245 | 6. Conveying Non-Source Forms. 246 | 247 | You may convey a covered work in object code form under the terms 248 | of sections 4 and 5, provided that you also convey the 249 | machine-readable Corresponding Source under the terms of this License, 250 | in one of these ways: 251 | 252 | a) Convey the object code in, or embodied in, a physical product 253 | (including a physical distribution medium), accompanied by the 254 | Corresponding Source fixed on a durable physical medium 255 | customarily used for software interchange. 256 | 257 | b) Convey the object code in, or embodied in, a physical product 258 | (including a physical distribution medium), accompanied by a 259 | written offer, valid for at least three years and valid for as 260 | long as you offer spare parts or customer support for that product 261 | model, to give anyone who possesses the object code either (1) a 262 | copy of the Corresponding Source for all the software in the 263 | product that is covered by this License, on a durable physical 264 | medium customarily used for software interchange, for a price no 265 | more than your reasonable cost of physically performing this 266 | conveying of source, or (2) access to copy the 267 | Corresponding Source from a network server at no charge. 268 | 269 | c) Convey individual copies of the object code with a copy of the 270 | written offer to provide the Corresponding Source. This 271 | alternative is allowed only occasionally and noncommercially, and 272 | only if you received the object code with such an offer, in accord 273 | with subsection 6b. 274 | 275 | d) Convey the object code by offering access from a designated 276 | place (gratis or for a charge), and offer equivalent access to the 277 | Corresponding Source in the same way through the same place at no 278 | further charge. You need not require recipients to copy the 279 | Corresponding Source along with the object code. If the place to 280 | copy the object code is a network server, the Corresponding Source 281 | may be on a different server (operated by you or a third party) 282 | that supports equivalent copying facilities, provided you maintain 283 | clear directions next to the object code saying where to find the 284 | Corresponding Source. Regardless of what server hosts the 285 | Corresponding Source, you remain obligated to ensure that it is 286 | available for as long as needed to satisfy these requirements. 287 | 288 | e) Convey the object code using peer-to-peer transmission, provided 289 | you inform other peers where the object code and Corresponding 290 | Source of the work are being offered to the general public at no 291 | charge under subsection 6d. 292 | 293 | A separable portion of the object code, whose source code is excluded 294 | from the Corresponding Source as a System Library, need not be 295 | included in conveying the object code work. 296 | 297 | A "User Product" is either (1) a "consumer product", which means any 298 | tangible personal property which is normally used for personal, family, 299 | or household purposes, or (2) anything designed or sold for incorporation 300 | into a dwelling. In determining whether a product is a consumer product, 301 | doubtful cases shall be resolved in favor of coverage. For a particular 302 | product received by a particular user, "normally used" refers to a 303 | typical or common use of that class of product, regardless of the status 304 | of the particular user or of the way in which the particular user 305 | actually uses, or expects or is expected to use, the product. A product 306 | is a consumer product regardless of whether the product has substantial 307 | commercial, industrial or non-consumer uses, unless such uses represent 308 | the only significant mode of use of the product. 309 | 310 | "Installation Information" for a User Product means any methods, 311 | procedures, authorization keys, or other information required to install 312 | and execute modified versions of a covered work in that User Product from 313 | a modified version of its Corresponding Source. The information must 314 | suffice to ensure that the continued functioning of the modified object 315 | code is in no case prevented or interfered with solely because 316 | modification has been made. 317 | 318 | If you convey an object code work under this section in, or with, or 319 | specifically for use in, a User Product, and the conveying occurs as 320 | part of a transaction in which the right of possession and use of the 321 | User Product is transferred to the recipient in perpetuity or for a 322 | fixed term (regardless of how the transaction is characterized), the 323 | Corresponding Source conveyed under this section must be accompanied 324 | by the Installation Information. But this requirement does not apply 325 | if neither you nor any third party retains the ability to install 326 | modified object code on the User Product (for example, the work has 327 | been installed in ROM). 328 | 329 | The requirement to provide Installation Information does not include a 330 | requirement to continue to provide support service, warranty, or updates 331 | for a work that has been modified or installed by the recipient, or for 332 | the User Product in which it has been modified or installed. Access to a 333 | network may be denied when the modification itself materially and 334 | adversely affects the operation of the network or violates the rules and 335 | protocols for communication across the network. 336 | 337 | Corresponding Source conveyed, and Installation Information provided, 338 | in accord with this section must be in a format that is publicly 339 | documented (and with an implementation available to the public in 340 | source code form), and must require no special password or key for 341 | unpacking, reading or copying. 342 | 343 | 7. Additional Terms. 344 | 345 | "Additional permissions" are terms that supplement the terms of this 346 | License by making exceptions from one or more of its conditions. 347 | Additional permissions that are applicable to the entire Program shall 348 | be treated as though they were included in this License, to the extent 349 | that they are valid under applicable law. If additional permissions 350 | apply only to part of the Program, that part may be used separately 351 | under those permissions, but the entire Program remains governed by 352 | this License without regard to the additional permissions. 353 | 354 | When you convey a copy of a covered work, you may at your option 355 | remove any additional permissions from that copy, or from any part of 356 | it. (Additional permissions may be written to require their own 357 | removal in certain cases when you modify the work.) You may place 358 | additional permissions on material, added by you to a covered work, 359 | for which you have or can give appropriate copyright permission. 360 | 361 | Notwithstanding any other provision of this License, for material you 362 | add to a covered work, you may (if authorized by the copyright holders of 363 | that material) supplement the terms of this License with terms: 364 | 365 | a) Disclaiming warranty or limiting liability differently from the 366 | terms of sections 15 and 16 of this License; or 367 | 368 | b) Requiring preservation of specified reasonable legal notices or 369 | author attributions in that material or in the Appropriate Legal 370 | Notices displayed by works containing it; or 371 | 372 | c) Prohibiting misrepresentation of the origin of that material, or 373 | requiring that modified versions of such material be marked in 374 | reasonable ways as different from the original version; or 375 | 376 | d) Limiting the use for publicity purposes of names of licensors or 377 | authors of the material; or 378 | 379 | e) Declining to grant rights under trademark law for use of some 380 | trade names, trademarks, or service marks; or 381 | 382 | f) Requiring indemnification of licensors and authors of that 383 | material by anyone who conveys the material (or modified versions of 384 | it) with contractual assumptions of liability to the recipient, for 385 | any liability that these contractual assumptions directly impose on 386 | those licensors and authors. 387 | 388 | All other non-permissive additional terms are considered "further 389 | restrictions" within the meaning of section 10. If the Program as you 390 | received it, or any part of it, contains a notice stating that it is 391 | governed by this License along with a term that is a further 392 | restriction, you may remove that term. If a license document contains 393 | a further restriction but permits relicensing or conveying under this 394 | License, you may add to a covered work material governed by the terms 395 | of that license document, provided that the further restriction does 396 | not survive such relicensing or conveying. 397 | 398 | If you add terms to a covered work in accord with this section, you 399 | must place, in the relevant source files, a statement of the 400 | additional terms that apply to those files, or a notice indicating 401 | where to find the applicable terms. 402 | 403 | Additional terms, permissive or non-permissive, may be stated in the 404 | form of a separately written license, or stated as exceptions; 405 | the above requirements apply either way. 406 | 407 | 8. Termination. 408 | 409 | You may not propagate or modify a covered work except as expressly 410 | provided under this License. Any attempt otherwise to propagate or 411 | modify it is void, and will automatically terminate your rights under 412 | this License (including any patent licenses granted under the third 413 | paragraph of section 11). 414 | 415 | However, if you cease all violation of this License, then your 416 | license from a particular copyright holder is reinstated (a) 417 | provisionally, unless and until the copyright holder explicitly and 418 | finally terminates your license, and (b) permanently, if the copyright 419 | holder fails to notify you of the violation by some reasonable means 420 | prior to 60 days after the cessation. 421 | 422 | Moreover, your license from a particular copyright holder is 423 | reinstated permanently if the copyright holder notifies you of the 424 | violation by some reasonable means, this is the first time you have 425 | received notice of violation of this License (for any work) from that 426 | copyright holder, and you cure the violation prior to 30 days after 427 | your receipt of the notice. 428 | 429 | Termination of your rights under this section does not terminate the 430 | licenses of parties who have received copies or rights from you under 431 | this License. If your rights have been terminated and not permanently 432 | reinstated, you do not qualify to receive new licenses for the same 433 | material under section 10. 434 | 435 | 9. Acceptance Not Required for Having Copies. 436 | 437 | You are not required to accept this License in order to receive or 438 | run a copy of the Program. Ancillary propagation of a covered work 439 | occurring solely as a consequence of using peer-to-peer transmission 440 | to receive a copy likewise does not require acceptance. However, 441 | nothing other than this License grants you permission to propagate or 442 | modify any covered work. These actions infringe copyright if you do 443 | not accept this License. Therefore, by modifying or propagating a 444 | covered work, you indicate your acceptance of this License to do so. 445 | 446 | 10. Automatic Licensing of Downstream Recipients. 447 | 448 | Each time you convey a covered work, the recipient automatically 449 | receives a license from the original licensors, to run, modify and 450 | propagate that work, subject to this License. You are not responsible 451 | for enforcing compliance by third parties with this License. 452 | 453 | An "entity transaction" is a transaction transferring control of an 454 | organization, or substantially all assets of one, or subdividing an 455 | organization, or merging organizations. If propagation of a covered 456 | work results from an entity transaction, each party to that 457 | transaction who receives a copy of the work also receives whatever 458 | licenses to the work the party's predecessor in interest had or could 459 | give under the previous paragraph, plus a right to possession of the 460 | Corresponding Source of the work from the predecessor in interest, if 461 | the predecessor has it or can get it with reasonable efforts. 462 | 463 | You may not impose any further restrictions on the exercise of the 464 | rights granted or affirmed under this License. For example, you may 465 | not impose a license fee, royalty, or other charge for exercise of 466 | rights granted under this License, and you may not initiate litigation 467 | (including a cross-claim or counterclaim in a lawsuit) alleging that 468 | any patent claim is infringed by making, using, selling, offering for 469 | sale, or importing the Program or any portion of it. 470 | 471 | 11. Patents. 472 | 473 | A "contributor" is a copyright holder who authorizes use under this 474 | License of the Program or a work on which the Program is based. The 475 | work thus licensed is called the contributor's "contributor version". 476 | 477 | A contributor's "essential patent claims" are all patent claims 478 | owned or controlled by the contributor, whether already acquired or 479 | hereafter acquired, that would be infringed by some manner, permitted 480 | by this License, of making, using, or selling its contributor version, 481 | but do not include claims that would be infringed only as a 482 | consequence of further modification of the contributor version. For 483 | purposes of this definition, "control" includes the right to grant 484 | patent sublicenses in a manner consistent with the requirements of 485 | this License. 486 | 487 | Each contributor grants you a non-exclusive, worldwide, royalty-free 488 | patent license under the contributor's essential patent claims, to 489 | make, use, sell, offer for sale, import and otherwise run, modify and 490 | propagate the contents of its contributor version. 491 | 492 | In the following three paragraphs, a "patent license" is any express 493 | agreement or commitment, however denominated, not to enforce a patent 494 | (such as an express permission to practice a patent or covenant not to 495 | sue for patent infringement). To "grant" such a patent license to a 496 | party means to make such an agreement or commitment not to enforce a 497 | patent against the party. 498 | 499 | If you convey a covered work, knowingly relying on a patent license, 500 | and the Corresponding Source of the work is not available for anyone 501 | to copy, free of charge and under the terms of this License, through a 502 | publicly available network server or other readily accessible means, 503 | then you must either (1) cause the Corresponding Source to be so 504 | available, or (2) arrange to deprive yourself of the benefit of the 505 | patent license for this particular work, or (3) arrange, in a manner 506 | consistent with the requirements of this License, to extend the patent 507 | license to downstream recipients. "Knowingly relying" means you have 508 | actual knowledge that, but for the patent license, your conveying the 509 | covered work in a country, or your recipient's use of the covered work 510 | in a country, would infringe one or more identifiable patents in that 511 | country that you have reason to believe are valid. 512 | 513 | If, pursuant to or in connection with a single transaction or 514 | arrangement, you convey, or propagate by procuring conveyance of, a 515 | covered work, and grant a patent license to some of the parties 516 | receiving the covered work authorizing them to use, propagate, modify 517 | or convey a specific copy of the covered work, then the patent license 518 | you grant is automatically extended to all recipients of the covered 519 | work and works based on it. 520 | 521 | A patent license is "discriminatory" if it does not include within 522 | the scope of its coverage, prohibits the exercise of, or is 523 | conditioned on the non-exercise of one or more of the rights that are 524 | specifically granted under this License. You may not convey a covered 525 | work if you are a party to an arrangement with a third party that is 526 | in the business of distributing software, under which you make payment 527 | to the third party based on the extent of your activity of conveying 528 | the work, and under which the third party grants, to any of the 529 | parties who would receive the covered work from you, a discriminatory 530 | patent license (a) in connection with copies of the covered work 531 | conveyed by you (or copies made from those copies), or (b) primarily 532 | for and in connection with specific products or compilations that 533 | contain the covered work, unless you entered into that arrangement, 534 | or that patent license was granted, prior to 28 March 2007. 535 | 536 | Nothing in this License shall be construed as excluding or limiting 537 | any implied license or other defenses to infringement that may 538 | otherwise be available to you under applicable patent law. 539 | 540 | 12. No Surrender of Others' Freedom. 541 | 542 | If conditions are imposed on you (whether by court order, agreement or 543 | otherwise) that contradict the conditions of this License, they do not 544 | excuse you from the conditions of this License. If you cannot convey a 545 | covered work so as to satisfy simultaneously your obligations under this 546 | License and any other pertinent obligations, then as a consequence you may 547 | not convey it at all. For example, if you agree to terms that obligate you 548 | to collect a royalty for further conveying from those to whom you convey 549 | the Program, the only way you could satisfy both those terms and this 550 | License would be to refrain entirely from conveying the Program. 551 | 552 | 13. Use with the GNU Affero General Public License. 553 | 554 | Notwithstanding any other provision of this License, you have 555 | permission to link or combine any covered work with a work licensed 556 | under version 3 of the GNU Affero General Public License into a single 557 | combined work, and to convey the resulting work. The terms of this 558 | License will continue to apply to the part which is the covered work, 559 | but the special requirements of the GNU Affero General Public License, 560 | section 13, concerning interaction through a network will apply to the 561 | combination as such. 562 | 563 | 14. Revised Versions of this License. 564 | 565 | The Free Software Foundation may publish revised and/or new versions of 566 | the GNU General Public License from time to time. Such new versions will 567 | be similar in spirit to the present version, but may differ in detail to 568 | address new problems or concerns. 569 | 570 | Each version is given a distinguishing version number. If the 571 | Program specifies that a certain numbered version of the GNU General 572 | Public License "or any later version" applies to it, you have the 573 | option of following the terms and conditions either of that numbered 574 | version or of any later version published by the Free Software 575 | Foundation. If the Program does not specify a version number of the 576 | GNU General Public License, you may choose any version ever published 577 | by the Free Software Foundation. 578 | 579 | If the Program specifies that a proxy can decide which future 580 | versions of the GNU General Public License can be used, that proxy's 581 | public statement of acceptance of a version permanently authorizes you 582 | to choose that version for the Program. 583 | 584 | Later license versions may give you additional or different 585 | permissions. However, no additional obligations are imposed on any 586 | author or copyright holder as a result of your choosing to follow a 587 | later version. 588 | 589 | 15. Disclaimer of Warranty. 590 | 591 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY 592 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT 593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY 594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, 595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 596 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM 597 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF 598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 599 | 600 | 16. Limitation of Liability. 601 | 602 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS 604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY 605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE 606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF 607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD 608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), 609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF 610 | SUCH DAMAGES. 611 | 612 | 17. Interpretation of Sections 15 and 16. 613 | 614 | If the disclaimer of warranty and limitation of liability provided 615 | above cannot be given local legal effect according to their terms, 616 | reviewing courts shall apply local law that most closely approximates 617 | an absolute waiver of all civil liability in connection with the 618 | Program, unless a warranty or assumption of liability accompanies a 619 | copy of the Program in return for a fee. 620 | 621 | END OF TERMS AND CONDITIONS 622 | 623 | How to Apply These Terms to Your New Programs 624 | 625 | If you develop a new program, and you want it to be of the greatest 626 | possible use to the public, the best way to achieve this is to make it 627 | free software which everyone can redistribute and change under these terms. 628 | 629 | To do so, attach the following notices to the program. It is safest 630 | to attach them to the start of each source file to most effectively 631 | state the exclusion of warranty; and each file should have at least 632 | the "copyright" line and a pointer to where the full notice is found. 633 | 634 | 635 | Copyright (C) 636 | 637 | This program is free software: you can redistribute it and/or modify 638 | it under the terms of the GNU General Public License as published by 639 | the Free Software Foundation, either version 3 of the License, or 640 | (at your option) any later version. 641 | 642 | This program is distributed in the hope that it will be useful, 643 | but WITHOUT ANY WARRANTY; without even the implied warranty of 644 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 645 | GNU General Public License for more details. 646 | 647 | You should have received a copy of the GNU General Public License 648 | along with this program. If not, see . 649 | 650 | Also add information on how to contact you by electronic and paper mail. 651 | 652 | If the program does terminal interaction, make it output a short 653 | notice like this when it starts in an interactive mode: 654 | 655 | Copyright (C) 656 | This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. 657 | This is free software, and you are welcome to redistribute it 658 | under certain conditions; type `show c' for details. 659 | 660 | The hypothetical commands `show w' and `show c' should show the appropriate 661 | parts of the General Public License. Of course, your program's commands 662 | might be different; for a GUI interface, you would use an "about box". 663 | 664 | You should also get your employer (if you work as a programmer) or school, 665 | if any, to sign a "copyright disclaimer" for the program, if necessary. 666 | For more information on this, and how to apply and follow the GNU GPL, see 667 | . 668 | 669 | The GNU General Public License does not permit incorporating your program 670 | into proprietary programs. If your program is a subroutine library, you 671 | may consider it more useful to permit linking proprietary applications with 672 | the library. If this is what you want to do, use the GNU Lesser General 673 | Public License instead of this License. But first, please read 674 | . 675 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # AVDC-API Backend Server 2 | 3 | API Version 4 | 5 | ![](https://img.shields.io/badge/build-passing-brightgreen.svg?style=flat) 6 | ![](https://img.shields.io/github/license/xjasonlyu/avdc-api.svg?style=flat) 7 | ![GitHub last commit](https://img.shields.io/github/last-commit/xjasonlyu/avdc-api) 8 | ![](https://img.shields.io/badge/Python-3.9-yellow.svg?style=flat&logo=python) 9 | ![](https://img.shields.io/badge/Flask-1.1.x-blue.svg?style=flat) 10 | 11 | ## Features 12 | 13 | - Flask-based server is compatible with [Jellyfin.Plugin.AVDC](https://github.com/xjasonlyu/jellyfin-plugin-avdc) 14 | - Cover image can be cropped based on [Google Vision](https://cloud.google.com/vision/docs/detecting-faces) 15 | - Metadata can be stored in Database (e.g. Sqlite, Mysql) 16 | 17 | ## License 18 | 19 | This software is released under the [GPL-3.0](LICENSE) open-source license. 20 | -------------------------------------------------------------------------------- /avdc.db: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xjasonlyu/avdc-api/295063fe2c184204534754730f9a9df0c5eef560/avdc.db -------------------------------------------------------------------------------- /avdc.old.db: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xjasonlyu/avdc-api/295063fe2c184204534754730f9a9df0c5eef560/avdc.old.db -------------------------------------------------------------------------------- /avdc/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xjasonlyu/avdc-api/295063fe2c184204534754730f9a9df0c5eef560/avdc/__init__.py -------------------------------------------------------------------------------- /avdc/actress/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/xjasonlyu/avdc-api/295063fe2c184204534754730f9a9df0c5eef560/avdc/actress/__init__.py -------------------------------------------------------------------------------- /avdc/actress/gfriends.py: -------------------------------------------------------------------------------- 1 | import json 2 | from os.path import splitext 3 | from urllib.parse import quote 4 | 5 | from cachetools import cached, TTLCache 6 | 7 | from avdc.utility.httpclient import get_html 8 | from avdc.utility.image import getRemoteImageSizeByURL 9 | from avdc.utility.misc import concurrentMap 10 | 11 | REPO = 'xinxin8816/gfriends' 12 | 13 | REPO_RAW_URL = f'https://raw.githubusercontent.com/{REPO}/master' 14 | 15 | 16 | @cached(cache=TTLCache(maxsize=1, ttl=3600)) 17 | def _getIndex() -> dict: 18 | url = f'{REPO_RAW_URL}/Filetree.json' 19 | return json.loads(get_html(url, raise_for_status=True)) 20 | 21 | 22 | def search(name: str) -> list[str]: 23 | content: dict[str, dict[str, str]] = _getIndex().get('Content') 24 | 25 | result_set = set() 26 | for company in content.keys(): 27 | for img in content[company]: 28 | if name.lower() == splitext(img)[0].lower(): 29 | result_set.add('/'.join([REPO_RAW_URL, 'Content', 30 | quote(company), quote(content[company][img])])) 31 | 32 | results = list(result_set) 33 | if results: # auto sort by height and width 34 | sizes = concurrentMap(getRemoteImageSizeByURL, results, max_workers=len(results)) 35 | results = [i for _, i in sorted(zip(sizes, results), 36 | key=lambda x: (x[0][0], x[0][1]), reverse=True)] 37 | return results 38 | 39 | 40 | if __name__ == '__main__': 41 | # print(search('霧島レオナ')) 42 | # print(search('高瀬りな')) 43 | # print(search('橋本ありな')) 44 | # print(search('桜空もも')) 45 | # print(search('鈴木心春')) 46 | # print(search('三原ほのか')) 47 | print(search('詩音乃らん')) 48 | -------------------------------------------------------------------------------- /avdc/actress/xslist.py: -------------------------------------------------------------------------------- 1 | from typing import Optional 2 | 3 | from lxml import etree 4 | 5 | from avdc.model.actress import Actress 6 | from avdc.utility.httpclient import get_html 7 | 8 | XSLIST_URL = 'https://xslist.org/' 9 | 10 | 11 | def search(name: str) -> list[tuple[str, str]]: 12 | text = get_html(f'{XSLIST_URL}/search', params={ 13 | 'query': name, 14 | 'lg': 'zh' 15 | }) 16 | 17 | tree = etree.fromstring(text, etree.HTMLParser()) 18 | 19 | results = [] 20 | for item in tree.xpath('//ul/li'): 21 | title = item.xpath('.//h3/a/text()')[0] 22 | href = item.xpath('.//h3/a/@href')[0] 23 | results.append((title, href)) 24 | 25 | return results 26 | 27 | 28 | def parseURL(name: str) -> Optional[str]: 29 | for title, href in search(name): 30 | if name == title.split('-')[-1].strip() or \ 31 | name.isascii() and name.lower() == title.split('-')[0].strip().lower(): 32 | return href 33 | 34 | 35 | def extractName(text: str) -> str: 36 | tree = etree.fromstring(text, etree.HTMLParser()) 37 | return tree.xpath('//*[@id="sss1"]/header/h1/span/text()')[0] 38 | 39 | 40 | def extractInfo(text: str): 41 | # //*[@id="layout"]/div/p[1] 42 | tree = etree.fromstring(text, etree.HTMLParser()) 43 | infos: list[str] = tree.xpath('//*[@id="layout"]/div/p[1]/text()') 44 | extra: list[str] = tree.xpath('//*[@id="layout"]/div/p[1]/span/text()') 45 | return [parseInfo(i) for i in infos[:6] + extra] 46 | 47 | 48 | def parseInfo(info: str) -> str: 49 | return info.split(':', maxsplit=1)[-1].replace('n/a', '').strip() 50 | 51 | 52 | def main(name: str): 53 | url = parseURL(name) 54 | if not url: 55 | return 56 | 57 | text = get_html(url, raise_for_status=True) 58 | return Actress(extractName(text), *extractInfo(text), 59 | source=url, provider='xslist') 60 | 61 | 62 | if __name__ == '__main__': 63 | # print(main('桃園怜奈')) 64 | # print(main('桜空もも')) 65 | print(main('大原あむ')) 66 | -------------------------------------------------------------------------------- /avdc/model/__init__.py: -------------------------------------------------------------------------------- 1 | import json 2 | from typing import Optional, Iterator, Any 3 | 4 | 5 | class BaseModel: 6 | 7 | def __init__(self, 8 | source: Optional[str] = None, 9 | provider: Optional[str] = None, 10 | **kwargs): 11 | self.sources: list[str] = kwargs.pop('sources', []) 12 | self.providers: list[str] = kwargs.pop('providers', []) 13 | 14 | if source: 15 | assert isinstance(source, str) 16 | self.sources.append(source) 17 | 18 | if provider: 19 | assert isinstance(provider, str) 20 | self.providers.append(provider) 21 | 22 | def __str__(self) -> str: 23 | return self.toJSON() 24 | 25 | def __iter__(self) -> Iterator: 26 | return ((k, v) for k, v in vars(self).items() 27 | if not k.startswith('_')) 28 | 29 | def __eq__(self, other) -> bool: 30 | if not isinstance(other, self.__class__): 31 | return False 32 | 33 | for k in dict(self).keys(): 34 | if getattr(self, k) != getattr(other, k): 35 | return False 36 | return True 37 | 38 | def __add__(self, other): 39 | if not isinstance(other, self.__class__): 40 | raise TypeError(f'invalid type to add: {type(other)}') 41 | 42 | m = {} 43 | for k, v in dict(other).items(): 44 | if k in ('sources', 'providers'): 45 | m[k] = self.get(k) + v 46 | elif k in ('release', ): 47 | m[k] = self.get(k) if self.get(k) not in ('', '0000-00-00') else v 48 | else: 49 | m[k] = self.get(k) or v 50 | 51 | return self.__class__(**m) 52 | 53 | def get(self, key: str, default: Any = None) -> Any: 54 | return getattr(self, key, default) 55 | 56 | def toJSON(self) -> str: 57 | return json.dumps( 58 | dict(self), 59 | ensure_ascii=False, 60 | sort_keys=True, 61 | indent=4, 62 | separators=(",", ": "), 63 | ) 64 | 65 | def toDict(self) -> dict: 66 | return dict(self) 67 | -------------------------------------------------------------------------------- /avdc/model/actress.py: -------------------------------------------------------------------------------- 1 | from datetime import date, datetime 2 | from typing import Optional, Union 3 | 4 | from avdc.model import BaseModel 5 | 6 | 7 | class Actress(BaseModel): 8 | 9 | def __init__(self, 10 | name: str, 11 | birthday: Optional[Union[str, date]] = None, 12 | measurements: Optional[str] = None, 13 | cup_size: Optional[str] = None, 14 | av_activity: Optional[Union[str, date]] = None, 15 | sign: Optional[str] = None, 16 | blood_type: Optional[str] = None, 17 | height: Optional[str] = None, 18 | nationality: Optional[str] = None, 19 | images: Optional[list[str]] = None, 20 | **kwargs): 21 | self.name = name 22 | self.birthday = self.parseDate(birthday) 23 | self.measurements = measurements 24 | self.av_activity = self.parseDate(av_activity) 25 | _ = sign # ignore 26 | self.blood_type = blood_type 27 | self.height = height 28 | self.nationality = nationality 29 | self.images = images 30 | self.cup_size = cup_size.upper().removesuffix('CUP').strip() \ 31 | if isinstance(cup_size, str) else None 32 | 33 | super().__init__(**kwargs) 34 | 35 | @staticmethod 36 | def parseDate(d: Union[str, date]) -> Optional[str]: 37 | if isinstance(d, date): 38 | return str(d) 39 | 40 | for fmt in ('%Y年%m月%d日', '%Y年%m月', '%Y年', 41 | '%Y-%m-%d', '%Y/%m/%d', 42 | '%B %d, %Y', '%B %Y', '%Y'): 43 | try: 44 | return datetime.strptime(d, fmt).strftime('%Y-%m-%d') 45 | except TypeError: 46 | break 47 | except ValueError: 48 | continue 49 | -------------------------------------------------------------------------------- /avdc/model/cover.py: -------------------------------------------------------------------------------- 1 | from dotmap import DotMap 2 | 3 | 4 | # simply use DotMap 5 | class Cover(DotMap): 6 | pass 7 | -------------------------------------------------------------------------------- /avdc/model/metadata.py: -------------------------------------------------------------------------------- 1 | from typing import Any 2 | 3 | from avdc.model import BaseModel 4 | 5 | 6 | class Metadata(BaseModel): 7 | 8 | def __init__(self, **kwargs): 9 | # raw metadata 10 | self._raw: dict[str, Any] = kwargs 11 | 12 | # required fields 13 | self.vid: str = self._get('vid', '').strip().upper() 14 | self.title: str = self._get('title', '') 15 | 16 | # info fields 17 | self.overview: str = self._get('overview', '') 18 | self.release: str = str(self._get('release', '')) 19 | self.runtime: int = self._get_runtime() 20 | self.label: str = self._get('label', '') 21 | self.studio: str = self._get('studio', '') 22 | self.series: str = self._get('series', '') 23 | self.genres: list[str] = self._get('genres', []) 24 | 25 | # cast fields 26 | self.actresses: list[str] = self._get('actresses', []) 27 | self.director: str = self._get('director', '') 28 | 29 | # image fields 30 | self.cover: str = self._get('cover', '') 31 | self.images: list[str] = self._get('images', []) 32 | 33 | super().__init__(**kwargs) 34 | 35 | if not self.vid: 36 | raise ValueError('metadata missing vid') 37 | if not self.title: 38 | raise ValueError('metadata missing title') 39 | if not self.cover: 40 | raise ValueError('metadata missing cover') 41 | 42 | def _get(self, key: str, default: Any = None) -> Any: 43 | return self._raw.get(key) or default 44 | 45 | def _get_runtime(self) -> int: 46 | try: 47 | return int(self._get('runtime', 0)) 48 | except ValueError: 49 | return 0 50 | 51 | 52 | def test(): 53 | m1 = Metadata(**{'vid': '0', 'title': 't', 'cover': 'n', 'source': 'ss', 'provider': 'ab'}) 54 | m2 = Metadata(**{'vid': '0', 'title': 't', 'cover': 'n', 'source': 'ss', 'provider': 'ab'}) 55 | m3 = Metadata(**{'vid': '1', 'title': 't', 'cover': 'm', 'source': 'ss', 'provider': 'ab'}) 56 | m4 = Metadata(**{'vid': '0', 'title': 'tt', 'cover': 'k', 'source': 'test', 'provider': 'abc'}) 57 | # m5 = Metadata(**{'vid': '0', 'title': 'nn', 'cover': 'v', 'source': 'test2', 'provider': 'abcd'}) 58 | 59 | assert m1 == m1 == m2 60 | assert m1 != m3 and m2 != m3 61 | assert m1 + m4 == m2 + m4 62 | 63 | 64 | if __name__ == '__main__': 65 | test() 66 | -------------------------------------------------------------------------------- /avdc/provider/__init__.py: -------------------------------------------------------------------------------- 1 | class ProviderError(Exception): 2 | pass 3 | 4 | 5 | class NotFound(ProviderError): 6 | pass 7 | -------------------------------------------------------------------------------- /avdc/provider/arzon.py: -------------------------------------------------------------------------------- 1 | import re 2 | from typing import Optional 3 | from urllib.parse import urljoin 4 | 5 | from lxml import etree 6 | 7 | from avdc.model.metadata import Metadata 8 | from avdc.provider import NotFound 9 | from avdc.utility.httpclient import Session 10 | 11 | 12 | def getTitle(content: bytes) -> str: 13 | tree = etree.fromstring(content, etree.HTMLParser()) 14 | title = tree.xpath('//*[@id="detail_new"]/div[2]/table/tr/td[2]/h1/text()')[0] 15 | return re.sub(r'^【.*?】', '', title) 16 | 17 | 18 | def getOverview(content: bytes) -> str: 19 | tree = etree.fromstring(content, etree.HTMLParser()) 20 | elements = tree.xpath('//*[@id="detail_new"]/table/tr/td[1]/table/tr[2]/td/div/text()') 21 | return [i.strip() for i in elements if i.strip()][0] 22 | 23 | 24 | def getCover(content: bytes) -> str: 25 | tree = etree.fromstring(content, etree.HTMLParser()) 26 | url = tree.xpath('//*[@id="detail_new"]/table/tr/td[1]/table/tr[1]/td[1]/a/img/@src')[0] 27 | return urljoin('https:', url) 28 | 29 | 30 | def getDirector(content: bytes) -> str: 31 | tree = etree.fromstring(content, etree.HTMLParser()) 32 | try: 33 | director = tree.xpath('//*[@id="detail_new"]/table/tr/td[1]/table/tr[3]/td/div/table/tr[5]/td[2]/a/text()')[0] 34 | except IndexError: 35 | return '' 36 | else: 37 | return director.strip() 38 | 39 | 40 | def getActresses(content: bytes) -> list[str]: 41 | tree = etree.fromstring(content, etree.HTMLParser()) 42 | actresses = tree.xpath('//*[@id="detail_new"]/table/tr/td[1]/table/tr[3]/td/div/table/tr[1]/td[2]/a/text()') 43 | return [actress.strip() for actress in actresses if actress.strip()] 44 | 45 | 46 | # def getGenres(content: bytes) -> list[str]: 47 | # pass 48 | 49 | 50 | def getImages(content: bytes) -> list[str]: 51 | tree = etree.fromstring(content, etree.HTMLParser()) 52 | images = tree.xpath('//*[@id="detail_new"]/div[3]/img/@src') 53 | return [urljoin('https:', img.strip()) for img in images if img.strip()] 54 | 55 | 56 | def getStudio(content: bytes) -> str: 57 | tree = etree.fromstring(content, etree.HTMLParser()) 58 | try: 59 | result = tree.xpath('//*[@id="detail_new"]/table/tr/td[1]/table/tr[3]/td/div/table/tr[2]/td[2]/a/text()')[0] 60 | except IndexError: 61 | return '' 62 | else: 63 | return result.strip() 64 | 65 | 66 | def getSeries(content: bytes) -> str: 67 | tree = etree.fromstring(content, etree.HTMLParser()) 68 | try: 69 | result = tree.xpath('//*[@id="detail_new"]/table/tr/td[1]/table/tr[3]/td/div/table/tr[4]/td[2]/a/text()')[0] 70 | except IndexError: 71 | return getSeries2(content) # fallback 72 | else: 73 | return result.strip() 74 | 75 | 76 | def getSeries2(content: bytes) -> str: 77 | tree = etree.fromstring(content, etree.HTMLParser()) 78 | try: 79 | result = tree.xpath('//*[@id="detail_new"]/table/tr/td[1]/table/tr[3]/td/div/table/tr[3]/td[2]/a/text()')[0] 80 | except IndexError: 81 | return '' 82 | else: 83 | return result.strip() 84 | 85 | 86 | def getRelease(content: bytes) -> str: 87 | tree = etree.fromstring(content, etree.HTMLParser()) 88 | try: 89 | result = tree.xpath('//*[@id="detail_new"]/table/tr/td[1]/table/tr[3]/td/div/table/tr[6]/td[2]/text()')[0] 90 | except IndexError: 91 | return '' 92 | else: 93 | release = re.findall(r'(\d{4}/\d{2}/\d{2})', result.strip())[0] 94 | return release.replace('/', '-') 95 | 96 | 97 | def getRuntime(content: bytes) -> str: 98 | tree = etree.fromstring(content, etree.HTMLParser()) 99 | try: 100 | result: str = tree.xpath('//*[@id="detail_new"]/table/tr/td[1]/table/tr[3]/td/div/table/tr[7]/td[2]/text()')[0] 101 | except IndexError: 102 | return '' 103 | else: 104 | return result.strip().removesuffix('分') 105 | 106 | 107 | def getVID(content: bytes) -> str: 108 | tree = etree.fromstring(content, etree.HTMLParser()) 109 | try: 110 | result: str = tree.xpath('//*[@id="detail_new"]/table/tr/td[1]/table/tr[3]/td/div/table/tr[8]/td[2]/text()')[0] 111 | except IndexError: 112 | return '' 113 | else: 114 | return re.findall(r'(\w+[\-_]\w+)', result.strip())[0] 115 | 116 | 117 | def check_age(s: Session): 118 | r = s.get('https://www.arzon.jp/index.php', params={ 119 | 'action': 'adult_customer_agecheck', 120 | 'agecheck': 1, 121 | 'redirect': 'https://www.arzon.jp/' 122 | }) 123 | r.raise_for_status() 124 | 125 | 126 | def search(s: Session, keyword: str) -> Optional[int]: 127 | url = f'https://www.arzon.jp/itemlist.html' 128 | content = s.get(url, params={ 129 | 'q': keyword, 130 | 't': 'all', 131 | 'm': 'all', 132 | 'mkt': 'all', 133 | 'disp': 30, 134 | 'sort': 'saledate' 135 | }).content 136 | 137 | tree = etree.fromstring(content, etree.HTMLParser()) 138 | href = tree.xpath('//*[@id="item"]/div[1]/dl/dt/a/@href') 139 | 140 | try: 141 | item_id = int(re.findall(r'item_(\d+)\.html', href[0])[0]) 142 | except (IndexError, TypeError, ValueError): 143 | return 144 | else: 145 | return item_id 146 | 147 | 148 | def main(keyword: str) -> Metadata: 149 | with Session() as session: 150 | # pass age check 151 | check_age(session) 152 | 153 | # search for item id 154 | item_id = search(session, keyword) 155 | if item_id is None: 156 | raise NotFound(f'arzon: {keyword} not found') 157 | 158 | item_url = f'https://www.arzon.jp/item_{item_id}.html' 159 | content = session.get(item_url).content 160 | 161 | # headers={'Referer': 'https://www.arzon.jp/'} 162 | 163 | return Metadata(**{ 164 | 'title': getTitle(content), 165 | 'studio': getStudio(content), 166 | 'overview': getOverview(content), 167 | 'runtime': getRuntime(content), 168 | 'director': getDirector(content), 169 | 'actresses': getActresses(content), 170 | 'release': getRelease(content), 171 | 'vid': getVID(content), 172 | 'cover': getCover(content), 173 | 'genres': [], 174 | 'images': getImages(content), 175 | 'label': getSeries(content), 176 | 'source': item_url, 177 | 'provider': 'arzon', 178 | 'series': getSeries(content), 179 | }) 180 | 181 | 182 | if __name__ == '__main__': 183 | print(main('ssni-999')) 184 | -------------------------------------------------------------------------------- /avdc/provider/avsox.py: -------------------------------------------------------------------------------- 1 | from bs4 import BeautifulSoup 2 | from cachetools import cached, TTLCache 3 | from lxml import etree 4 | 5 | from avdc.model.metadata import Metadata 6 | from avdc.provider import NotFound 7 | from avdc.utility.httpclient import get_html 8 | from avdc.utility.misc import extractTitle 9 | 10 | 11 | def getTitle(content: str) -> str: 12 | tree = etree.fromstring(content, etree.HTMLParser()) 13 | title = tree.xpath('/html/body/div[2]/h3/text()')[0] 14 | return extractTitle(title) 15 | 16 | 17 | def getActresses(content: str) -> list[str]: # //*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text() 18 | soup = BeautifulSoup(content, 'lxml') 19 | a = soup.find_all(attrs={'class': 'avatar-box'}) 20 | d = [] 21 | for i in a: 22 | d.append(i.span.get_text()) 23 | return d 24 | 25 | 26 | def getStudio(content: str) -> str: 27 | tree = etree.fromstring(content, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 28 | result = tree.xpath('//p[contains(text(),"メーカー:")]/following-sibling::p[1]/a/text()') 29 | return result[0] if result else '' 30 | 31 | 32 | def getRuntime(content: str) -> str: 33 | tree = etree.fromstring(content, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 34 | result = tree.xpath('//span[contains(text(),"収録時間:")]/../text()') 35 | return result[0].removesuffix('分') if result else '' 36 | 37 | 38 | def getLabel(content: str) -> str: 39 | tree = etree.fromstring(content, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 40 | result = tree.xpath('//p[contains(text(),"メーカー:")]/following-sibling::p[1]/a/text()') 41 | return result[0] if result else '' 42 | 43 | 44 | def getVID(content: str) -> str: 45 | tree = etree.fromstring(content, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 46 | return tree.xpath('//span[contains(text(),"品番:")]/../span[2]/text()')[0] 47 | 48 | 49 | def getRelease(content: str) -> str: 50 | tree = etree.fromstring(content, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 51 | result = tree.xpath('//span[contains(text(),"発売日:")]/../text()') 52 | return result[0] if result else '' 53 | 54 | 55 | def getCover(content: str) -> str: 56 | tree = etree.fromstring(content, etree.HTMLParser()) 57 | return tree.xpath('/html/body/div[2]/div[1]/div[1]/a/img/@src')[0] 58 | 59 | 60 | # def getSmallCover(content: str) -> str: 61 | # tree = etree.fromstring(content, etree.HTMLParser()) 62 | # result = str(tree.xpath('//*[@id="waterfall"]/div/a/div[1]/img/@src')).strip(" ['']") 63 | # return result 64 | 65 | 66 | def getGenres(content: str) -> list[str]: 67 | soup = BeautifulSoup(content, 'lxml') 68 | a = soup.find_all(attrs={'class': 'genre'}) 69 | d = [] 70 | for i in a: 71 | d.append(i.get_text()) 72 | return d 73 | 74 | 75 | def getSeries(content: str) -> str: 76 | tree = etree.fromstring(content, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 77 | result = tree.xpath('//span[contains(text(),"シリーズ:")]/../span[2]/text()') 78 | return result[0] if result else '' 79 | 80 | 81 | @cached(cache=TTLCache(maxsize=1, ttl=3600)) 82 | def _getAvsoxSite() -> str: 83 | text = get_html('https://tellme.pw/avsox') 84 | return etree.HTML(text).xpath('//div[@class="container"]/div/a/@href')[0] 85 | 86 | 87 | def main(keyword: str) -> Metadata: 88 | avsox_site = _getAvsoxSite() 89 | 90 | def search_url(v): 91 | x = get_html(avsox_site + '/ja/search/' + v) 92 | tree = etree.fromstring(x, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 93 | for r in tree.xpath('//*[@id="waterfall"]/div/a/@href'): 94 | return str(r), x 95 | return None, x 96 | 97 | url, search_page = search_url(keyword) 98 | 99 | if not url or url.count('https://') > 1: 100 | raise NotFound(f'avsox: {keyword} not found') 101 | 102 | text = get_html(url, raise_for_status=True) 103 | soup = BeautifulSoup(text, 'lxml') 104 | info = str(soup.find(attrs={'class': 'row movie'})) 105 | 106 | return Metadata(**{ 107 | 'actresses': getActresses(text), 108 | 'title': getTitle(text), 109 | 'studio': getStudio(info), 110 | 'overview': '', # 111 | 'runtime': getRuntime(info), 112 | 'director': '', # 113 | 'release': getRelease(info), 114 | 'vid': getVID(info), 115 | 'cover': getCover(text), 116 | # 'small_cover': getSmallCover(search_page), 117 | 'genres': getGenres(text), 118 | 'label': getLabel(info), 119 | 'source': url, 120 | 'provider': 'avsox', 121 | 'series': getSeries(info), 122 | }) 123 | 124 | 125 | if __name__ == "__main__": 126 | # print(main('012717_472')) 127 | print(main('092719-001')) 128 | -------------------------------------------------------------------------------- /avdc/provider/dlsite.py: -------------------------------------------------------------------------------- 1 | from lxml import etree 2 | 3 | from avdc.model.metadata import Metadata 4 | from avdc.utility.httpclient import get_html 5 | from avdc.utility.misc import extractTitle 6 | 7 | 8 | # print(get_html('https://www.dlsite.com/pro/work/=/product_id/VJ013152.html')) 9 | # title //*[@id="work_name"]/a/text() 10 | # studio //th[contains(text(),"ブランド名")]/../td/span[1]/a/text() 11 | # release //th[contains(text(),"販売日")]/../td/a/text() 12 | # story //th[contains(text(),"シナリオ")]/../td/a/text() 13 | # senyo //th[contains(text(),"声優")]/../td/a/text() 14 | # tag //th[contains(text(),"ジャンル")]/../td/div/a/text() 15 | # jianjie //*[@id="main_inner"]/div[3]/text() 16 | # photo //*[@id="work_left"]/div/div/div[2]/div/div[1]/div[1]/ul/li/img/@src 17 | 18 | # https://www.dlsite.com/pro/work/=/product_id/VJ013152.html 19 | 20 | 21 | def getTitle(a: str) -> str: 22 | tree = etree.fromstring(a, etree.HTMLParser()) 23 | title = tree.xpath('//*[@id="work_name"]/a/text()')[0] 24 | return extractTitle(title) 25 | 26 | 27 | def getActresses(a: str) -> list[str]: # //*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text() 28 | tree = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 29 | return tree.xpath('//th[contains(text(),"声优")]/../td/a/text()') 30 | 31 | 32 | def getStudio(a: str) -> str: 33 | tree = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 34 | try: 35 | try: 36 | result = tree.xpath('//th[contains(text(),"系列名")]/../td/span[1]/a/text()')[0] 37 | except (IndexError, Exception): 38 | result = tree.xpath('//th[contains(text(),"社团名")]/../td/span[1]/a/text()')[0] 39 | except (IndexError, Exception): 40 | result = '' 41 | return result 42 | 43 | 44 | def getRuntime(a: str) -> str: 45 | tree = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 46 | result1 = str(tree.xpath('//strong[contains(text(),"時長")]/../span/text()')).strip(" ['']") 47 | result2 = str(tree.xpath('//strong[contains(text(),"時長")]/../span/a/text()')).strip(" ['']") 48 | return str(result1 + result2).strip('+').rstrip('mi') 49 | 50 | 51 | def getLabel(a: str) -> str: 52 | tree = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 53 | try: 54 | try: 55 | result = tree.xpath('//th[contains(text(),"系列名")]/../td/span[1]/a/text()')[0] 56 | except (IndexError, Exception): 57 | result = tree.xpath('//th[contains(text(),"社团名")]/../td/span[1]/a/text()')[0] 58 | except (IndexError, Exception): 59 | result = '' 60 | return result 61 | 62 | 63 | def getRelease(a: str) -> str: 64 | tree = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 65 | result = tree.xpath('//th[contains(text(),"贩卖日")]/../td/a/text()')[0] 66 | return result.replace('年', '-').replace('月', '-').replace('日', '') 67 | 68 | 69 | def getGenres(a: str) -> list[str]: 70 | tree = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 71 | return tree.xpath('//th[contains(text(),"分类")]/../td/div/a/text()') 72 | 73 | 74 | def getSmallCover(a: str, index: int = 0) -> str: 75 | # same issue mentioned below, 76 | # javdb sometime returns multiple results 77 | # DO NOT just get the first one, get the one with correct index number 78 | tree = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 79 | try: 80 | result = tree.xpath("//div[@class='item-image fix-scale-cover']/img/@src")[index] 81 | if 'https' not in result: 82 | result = 'https:' + result 83 | return result 84 | except (IndexError, Exception): # 2020.7.17 Repair Cover Url crawl 85 | result = tree.xpath("//div[@class='item-image fix-scale-cover']/img/@data-src")[index] 86 | if 'https' not in result: 87 | result = 'https:' + result 88 | return result 89 | 90 | 91 | def getCover(text: str) -> str: 92 | tree = etree.fromstring(text, etree.HTMLParser()) 93 | result = tree.xpath('//*[@id="work_left"]/div/div/div[2]/div/div[1]/div[1]/ul/li/img/@src')[0] 94 | return result 95 | 96 | 97 | def getDirector(a: str) -> str: 98 | tree = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 99 | try: 100 | result = tree.xpath('//th[contains(text(),"剧情")]/../td/a/text()')[0] 101 | except (IndexError, Exception): 102 | result = '' 103 | return result 104 | 105 | 106 | def getOverview(text: str) -> str: 107 | tree = etree.fromstring(text, etree.HTMLParser()) 108 | total = [] 109 | result = tree.xpath('//*[@id="main_inner"]/div[3]/text()') 110 | for i in result: 111 | total.append(i.strip('\r\n')) 112 | return str(total).strip(" ['']").replace("', '', '", r'\n').replace("', '", r'\n').strip(", '', '") 113 | 114 | 115 | def getSeries(a: str) -> str: 116 | tree = etree.fromstring(a, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 117 | try: 118 | try: 119 | result = tree.xpath('//th[contains(text(),"系列名")]/../td/span[1]/a/text()')[0] 120 | except (IndexError, Exception): 121 | result = tree.xpath('//th[contains(text(),"社团名")]/../td/span[1]/a/text()')[0] 122 | except (IndexError, Exception): 123 | result = '' 124 | return result 125 | 126 | 127 | def main(keyword: str) -> Metadata: 128 | keyword = keyword.upper() 129 | 130 | url = f'https://www.dlsite.com/pro/work/=/product_id/{keyword}.html' 131 | text = get_html(url, 132 | cookies={'locale': 'zh-cn'}, 133 | raise_for_status=True) 134 | 135 | return Metadata(**{ 136 | 'actresses': getActresses(text), 137 | 'title': getTitle(text), 138 | 'studio': getStudio(text), 139 | 'overview': getOverview(text), 140 | 'runtime': '', 141 | 'director': getDirector(text), 142 | 'release': getRelease(text), 143 | 'vid': keyword, 144 | 'cover': 'https:' + getCover(text), 145 | # 'small_cover': '', 146 | 'genres': getGenres(text), 147 | 'label': getLabel(text), 148 | # 'star_photos': '', 149 | 'source': url, 150 | 'provider': 'dlsite', 151 | 'series': getSeries(text), 152 | }) 153 | 154 | 155 | if __name__ == "__main__": 156 | # print(main('VJ013178')) 157 | print(main('VJ014291')) 158 | -------------------------------------------------------------------------------- /avdc/provider/fanza.py: -------------------------------------------------------------------------------- 1 | import re 2 | from urllib.parse import urlencode 3 | 4 | from lxml import etree 5 | 6 | from avdc.model.metadata import Metadata 7 | from avdc.provider import NotFound 8 | from avdc.utility.httpclient import get_html 9 | from avdc.utility.misc import extractTitle 10 | 11 | 12 | def getTitle(text: str) -> str: 13 | html = etree.fromstring(text, etree.HTMLParser()) 14 | title = html.xpath('//*[starts-with(@id, "title")]/text()')[0] 15 | return extractTitle(title) 16 | 17 | 18 | def getActresses(text: str) -> str: 19 | # //*[@id="center_column"]/div[2]/div[1]/div/table/tbody/tr[1]/td/text() 20 | html = etree.fromstring(text, etree.HTMLParser()) 21 | result = ( 22 | str( 23 | html.xpath( 24 | "//td[contains(text(),'出演者')]/following-sibling::td/span/a/text()" 25 | ) 26 | ).strip(" ['']").replace("', '", ",") 27 | ) 28 | return result 29 | 30 | 31 | def getStudio(text: str) -> str: 32 | html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 33 | try: 34 | result = html.xpath( 35 | "//td[contains(text(),'メーカー')]/following-sibling::td/a/text()" 36 | )[0] 37 | except IndexError: 38 | result = html.xpath( 39 | "//td[contains(text(),'メーカー')]/following-sibling::td/text()" 40 | )[0] 41 | return result 42 | 43 | 44 | def getRuntime(text: str) -> str: 45 | html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 46 | result = html.xpath("//td[contains(text(),'収録時間')]/following-sibling::td/text()")[0] 47 | return re.search(r"\d+", str(result)).group() 48 | 49 | 50 | def getLabel(text: str) -> str: 51 | html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 52 | try: 53 | result = html.xpath( 54 | "//td[contains(text(),'レーベル：')]/following-sibling::td/a/text()" 55 | )[0] 56 | except: 57 | result = html.xpath( 58 | "//td[contains(text(),'レーベル：')]/following-sibling::td/text()" 59 | )[0] 60 | return result 61 | 62 | 63 | def getVID(text: str) -> str: 64 | html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 65 | try: 66 | result = html.xpath( 67 | "//td[contains(text(),'品番：')]/following-sibling::td/a/text()" 68 | )[0] 69 | except: 70 | result = html.xpath( 71 | "//td[contains(text(),'品番：')]/following-sibling::td/text()" 72 | )[0] 73 | return result 74 | 75 | 76 | def getRelease(text: str) -> str: 77 | html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 78 | try: 79 | result = html.xpath( 80 | "//td[contains(text(),'発売日：')]/following-sibling::td/a/text()" 81 | )[0].lstrip("\n") 82 | except: 83 | try: 84 | result = html.xpath( 85 | "//td[contains(text(),'発売日：')]/following-sibling::td/text()" 86 | )[0].lstrip("\n") 87 | except: 88 | result = "----" 89 | if result == "----": 90 | try: 91 | result = html.xpath( 92 | "//td[contains(text(),'配信開始日：')]/following-sibling::td/a/text()" 93 | )[0].lstrip("\n") 94 | except: 95 | try: 96 | result = html.xpath( 97 | "//td[contains(text(),'配信開始日：')]/following-sibling::td/text()" 98 | )[0].lstrip("\n") 99 | except: 100 | pass 101 | return result.replace("/", "-") 102 | 103 | 104 | def getGenres(text: str) -> list[str]: 105 | html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 106 | try: 107 | result = html.xpath("//td[contains(text(),'ジャンル：')]/following-sibling::td/a/text()") 108 | except: 109 | result = html.xpath("//td[contains(text(),'ジャンル：')]/following-sibling::td/text()") 110 | return result 111 | 112 | 113 | def getCover(text: str, number: str) -> str: 114 | html = etree.fromstring(text, etree.HTMLParser()) 115 | cover_number = number 116 | try: 117 | result = html.xpath('//*[@id="' + cover_number + '"]/@href')[0] 118 | except: 119 | # sometimes fanza modify _ to \u0005f for image id 120 | if "_" in cover_number: 121 | cover_number = cover_number.replace("_", r"\u005f") 122 | try: 123 | result = html.xpath('//*[@id="' + cover_number + '"]/@href')[0] 124 | except: 125 | # (TODO) handle more edge case 126 | # print(html) 127 | # raise exception here, same behavior as before 128 | # people's major requirement is fetching the picture 129 | raise ValueError("can not find image") 130 | return result 131 | 132 | 133 | def getDirector(text: str) -> str: 134 | html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 135 | try: 136 | result = html.xpath( 137 | "//td[contains(text(),'監督：')]/following-sibling::td/a/text()" 138 | )[0] 139 | except: 140 | result = html.xpath( 141 | "//td[contains(text(),'監督：')]/following-sibling::td/text()" 142 | )[0] 143 | return result 144 | 145 | 146 | def getOverview(text: str) -> str: 147 | html = etree.fromstring(text, etree.HTMLParser()) 148 | try: 149 | result = str(html.xpath("//div[@class='mg-b20 lh4']/text()")[0]).replace( 150 | "\n", "" 151 | ) 152 | if result == "": 153 | result = str(html.xpath("//div[@class='mg-b20 lh4']//p/text()")[0]).replace( 154 | "\n", "" 155 | ) 156 | except: 157 | # (TODO) handle more edge case 158 | # print(html) 159 | return "" 160 | return result 161 | 162 | 163 | def getSeries(text: str) -> str: 164 | try: 165 | html = etree.fromstring(text, etree.HTMLParser()) # //table/tr[1]/td[1]/text() 166 | try: 167 | result = html.xpath( 168 | "//td[contains(text(),'シリーズ：')]/following-sibling::td/a/text()" 169 | )[0] 170 | except: 171 | result = html.xpath( 172 | "//td[contains(text(),'シリーズ：')]/following-sibling::td/text()" 173 | )[0] 174 | return result 175 | except: 176 | return "" 177 | 178 | 179 | def getImages(content: str) -> list[str]: # 获取剧照 180 | hr = re.compile(r'
') 181 | html = hr.search(content) 182 | if html: 183 | html = html.group() 184 | hf = re.compile(r' Metadata: 197 | # fanza allow letter + number + underscore, normalize the input here 198 | # @note: I only find the usage of underscore as h_test123456789 199 | fanza_search_number = keyword 200 | # AV_Data_Capture.py.getVIDber() over format the input, restore the h_ prefix 201 | if fanza_search_number.startswith("h-"): 202 | fanza_search_number = fanza_search_number.replace("h-", "h_") 203 | 204 | fanza_search_number = re.sub(r"[^0-9a-zA-Z_]", "", fanza_search_number).lower() 205 | 206 | fanza_urls = [ 207 | "https://www.dmm.co.jp/digital/videoa/-/detail/=/cid=", 208 | "https://www.dmm.co.jp/mono/dvd/-/detail/=/cid=", 209 | "https://www.dmm.co.jp/digital/anime/-/detail/=/cid=", 210 | "https://www.dmm.co.jp/mono/anime/-/detail/=/cid=", 211 | "https://www.dmm.co.jp/digital/videoc/-/detail/=/cid=", 212 | "https://www.dmm.co.jp/digital/nikkatsu/-/detail/=/cid=", 213 | "https://www.dmm.co.jp/rental/-/detail/=/cid=", 214 | ] 215 | chosen_url = "" 216 | 217 | text = '' 218 | for url in fanza_urls: 219 | chosen_url = url + fanza_search_number 220 | text = get_html( 221 | "https://www.dmm.co.jp/age_check/=/declared=yes/?{}".format( 222 | urlencode({"rurl": chosen_url}) 223 | ), 224 | # raise_for_status=True, 225 | ) 226 | if "404 Not Found" not in text: 227 | break 228 | 229 | if not text or "404 Not Found" in text: 230 | raise NotFound(f'fanza: {keyword} not found') 231 | 232 | # for some old page, the input number does not match the page 233 | # for example, the url will be cid=test012 234 | # but the hinban on the page is test00012 235 | # so get the hinban first, and then pass it to following functions 236 | fanza_hinban = getVID(text) 237 | 238 | return Metadata(**{ 239 | 'title': getTitle(text).strip(), 240 | 'studio': getStudio(text), 241 | 'overview': getOverview(text), 242 | 'runtime': getRuntime(text), 243 | 'director': getDirector(text) if 'anime' not in chosen_url else '', 244 | 'actresses': getActresses(text) if 'anime' not in chosen_url else '', 245 | 'release': getRelease(text), 246 | 'vid': fanza_hinban, 247 | 'cover': getCover(text, fanza_hinban), 248 | 'genres': getGenres(text), 249 | 'images': getImages(text), 250 | 'label': getLabel(text), 251 | 'source': chosen_url, 252 | 'provider': 'fanza', 253 | 'series': getSeries(text), 254 | }) 255 | 256 | 257 | if __name__ == '__main__': 258 | # print(main('DV-1562')) 259 | # print(main('96fad1217')) 260 | # print(main('pred00251')) 261 | print(main('118ABP115')) 262 | -------------------------------------------------------------------------------- /avdc/provider/fc2.py: -------------------------------------------------------------------------------- 1 | import json 2 | from urllib.parse import urljoin 3 | 4 | from lxml import etree 5 | 6 | from avdc.model.metadata import Metadata 7 | from avdc.provider import NotFound 8 | from avdc.utility.httpclient import get_html, Session 9 | 10 | 11 | def getTitle(text: str) -> str: 12 | html = etree.fromstring(text, etree.HTMLParser()) 13 | result = html.xpath('/html/head/title/text()') 14 | return result[0] if result else '' 15 | 16 | 17 | def getOverview(text: str, session: Session) -> str: 18 | html = etree.fromstring(text, etree.HTMLParser()) 19 | result = html.xpath('//*[@id="top"]/div[1]/section[4]/iframe/@src') 20 | if not result: 21 | return '' 22 | 23 | url = urljoin('https://adult.contents.fc2.com/', result[0]) 24 | return '\n'.join(i.strip() for i in 25 | etree.fromstring(session.get(url).text, 26 | etree.HTMLParser()).xpath('/html/body/div/text()') 27 | if i.strip()) 28 | 29 | 30 | def getStudio(text: str) -> str: # 获取厂商 31 | html = etree.fromstring(text, etree.HTMLParser()) 32 | result = html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[2]/ul/li[3]/a/text()') 33 | return result[0] if result else '' 34 | 35 | 36 | def getRelease(text: str) -> str: 37 | html = etree.fromstring(text, etree.HTMLParser()) 38 | result: list[str] = html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[2]/div[2]/p/text()') 39 | text = result[0].replace('/', '-').replace(':', ' ') if result else '0000-00-00' 40 | return text.split()[-1] 41 | 42 | 43 | def getCover(text: str) -> str: 44 | html = etree.fromstring(text, etree.HTMLParser()) 45 | result = html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[1]/span/img/@src') 46 | return urljoin('https:', result[0]) if result else '' 47 | 48 | 49 | def getGenres(number: str) -> list[str]: 50 | url = f'https://adult.contents.fc2.com/api/v4/article/{number}/tag?' 51 | data = json.loads(get_html(url)) 52 | if data['code'] != 200: 53 | raise ValueError(f"Bad code: {data['code']}") 54 | return [i['tag'] for i in data.get('tags', [])] 55 | 56 | 57 | def getImages(text: str) -> list[str]: # 获取剧照 58 | html = etree.fromstring(text, etree.HTMLParser()) 59 | results = html.xpath('//*[@id="top"]/div[1]/section[2]/ul/li') 60 | return [result.xpath('.//a/@href')[0] for result in results 61 | if result.xpath('.//a/@href')] 62 | 63 | 64 | def checkProduct(text: str) -> bool: 65 | html = etree.fromstring(text, etree.HTMLParser()) 66 | title = html.xpath('/html/head/title/text()')[0] 67 | return 'Unable to find Product.' not in title 68 | 69 | 70 | def main(keyword: str) -> Metadata: 71 | keyword = keyword.upper() \ 72 | .replace('_', '-') \ 73 | .replace('FC2PPV-', '') \ 74 | .replace('FC2-PPV-', '') \ 75 | .replace('FC2-', '') 76 | 77 | if not keyword.isdecimal(): 78 | raise ValueError(f'invalid product number: {keyword}') 79 | 80 | with Session() as session: 81 | url = f'https://adult.contents.fc2.com/article/{keyword}/' 82 | text = session.get(url).text 83 | # overview 84 | overview = getOverview(text, session) 85 | 86 | if not checkProduct(text): 87 | raise NotFound(f'{keyword} not found') 88 | 89 | return Metadata(**{ 90 | 'title': getTitle(text), 91 | 'studio': getStudio(text), 92 | 'overview': overview, 93 | 'runtime': 0, 94 | 'director': getStudio(text), 95 | 'actresses': [], # fc2 no actresses 96 | 'release': getRelease(text), 97 | 'vid': f'FC2-{keyword}', 98 | 'label': '', 99 | 'cover': getCover(text), 100 | 'images': getImages(text), 101 | 'genres': getGenres(keyword), 102 | 'source': url, 103 | 'provider': 'fc2', 104 | 'series': '', 105 | }) 106 | 107 | 108 | if __name__ == '__main__': 109 | # print(main('FC2-1603395')) 110 | print(main('FC2PPV-1455209')) 111 | -------------------------------------------------------------------------------- /avdc/provider/jav321.py: -------------------------------------------------------------------------------- 1 | import re 2 | 3 | from bs4 import BeautifulSoup 4 | from lxml import html 5 | 6 | from avdc.model.metadata import Metadata 7 | from avdc.utility.httpclient import post 8 | 9 | 10 | def get_bold_text(h: str) -> str: 11 | soup = BeautifulSoup(h, "html.parser") 12 | if soup.b: 13 | return soup.b.text 14 | else: 15 | return "UNKNOWN_TAG" 16 | 17 | 18 | def get_anchor_info(h: str) -> str: 19 | result = [] 20 | 21 | data = BeautifulSoup(h, "html.parser").find_all("a", href=True) 22 | for d in data: 23 | result.append(d.text) 24 | 25 | return ",".join(result) 26 | 27 | 28 | def get_text_info(h: str) -> str: 29 | return h.split(": ")[1] 30 | 31 | 32 | def getTitle(lx: html.HtmlElement) -> str: 33 | return lx.xpath("/html/body/div[2]/div[1]/div[1]/div[1]/h3/text()")[0].strip() 34 | 35 | 36 | def getImages(content: str) -> list[str]: # 获取剧照 37 | hr = re.compile( 38 | r'
[\s\S]*?