├── .github ├── FUNDING.yml ├── ISSUE_TEMPLATE │ ├── bug_report.md │ └── feature_request.md ├── pull_request_template.md └── workflows │ ├── docker-deploy-scanner.yml │ ├── docker-deploy-skipper.yml │ ├── docker-test-build-scanner.yml │ ├── docker-test-build-skipper.yml │ └── python-lint-test.yml ├── .gitignore ├── Dockerfile_Jellyfin-Intro-Scanner ├── Dockerfile_Jellyfin-Intro-Skipper ├── LICENSE ├── README.md ├── config ├── data │ ├── fingerprints │ │ └── placeholder │ └── jellyfin_cache │ │ └── placeholder └── path_map.txt ├── decode.py ├── diff_jellyfin_cache.py ├── docs ├── _config.yml ├── docker.md ├── index.md ├── troubleshooting.md └── usage.md ├── ffmpeg_fingerprint.py ├── jellyfin.py ├── jellyfin_api_client.py ├── jellyfin_auto_skip.py ├── jellyfin_queries.py ├── requirements.txt ├── tox.ini └── unused └── ytube_scrape.py /.github/FUNDING.yml: -------------------------------------------------------------------------------- 1 | # These are supported funding model platforms 2 | 3 | github: [mueslimak3r] 4 | patreon: # Replace with a single Patreon username 5 | open_collective: # Replace with a single Open Collective username 6 | ko_fi: # Replace with a single Ko-fi username 7 | tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel 8 | community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry 9 | liberapay: # Replace with a single Liberapay username 10 | issuehunt: # Replace with a single IssueHunt username 11 | otechie: # Replace with a single Otechie username 12 | lfx_crowdfunding: # Replace with a single LFX Crowdfunding project-name e.g., cloud-foundry 13 | custom: # Replace with up to 4 custom sponsorship URLs e.g., ['link1', 'link2'] 14 | -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/bug_report.md: -------------------------------------------------------------------------------- 1 | --- 2 | name: Bug report 3 | about: Create a report to help us improve 4 | title: '' 5 | labels: '' 6 | assignees: '' 7 | 8 | --- 9 | 10 | **Describe the bug** 11 | A clear and concise description of what the bug is. 12 | 13 | **To Reproduce** 14 | Steps to reproduce the behavior: 15 | 1. Go to '...' 16 | 2. Click on '....' 17 | 3. Scroll down to '....' 18 | 4. See error 19 | 20 | **Expected behavior** 21 | A clear and concise description of what you expected to happen. 22 | 23 | **Additional context** 24 | Add any other context about the problem here. 25 | -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/feature_request.md: -------------------------------------------------------------------------------- 1 | --- 2 | name: Feature request 3 | about: Suggest an idea for this project 4 | title: '' 5 | labels: '' 6 | assignees: '' 7 | 8 | --- 9 | 10 | **Is your feature request related to a problem? Please describe.** 11 | A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] 12 | 13 | **Describe the solution you'd like** 14 | A clear and concise description of what you want to happen. 15 | 16 | **Describe alternatives you've considered** 17 | A clear and concise description of any alternative solutions or features you've considered. 18 | 19 | **Additional context** 20 | Add any other context or screenshots about the feature request here. 21 | -------------------------------------------------------------------------------- /.github/pull_request_template.md: -------------------------------------------------------------------------------- 1 | 4 | 5 | **Changes** 6 | 7 | 8 | **Issues** 9 | 11 | -------------------------------------------------------------------------------- /.github/workflows/docker-deploy-scanner.yml: -------------------------------------------------------------------------------- 1 | name: Deploy Jellyfin Intro Scanner 2 | 3 | on: 4 | push: 5 | branches: 6 | - master 7 | paths: 8 | - '**.py' 9 | - 'Dockerfile_Jellyfin-Intro-Scanner' 10 | - '!jellyfin_auto_skip.py' 11 | - '!diff_jellyfin_cache.py' 12 | - '!Dockerfile_Jellyfin-Intro-Skipper' 13 | - '!**.md' 14 | - '!**.gitignore' 15 | - '!docs/**' 16 | - '!.github/**' 17 | 18 | env: 19 | IMAGE_NAME_SCANNER: jellyfin-intro-scanner 20 | REGISTRY: ghcr.io 21 | 22 | jobs: 23 | Scanner_Deploy: 24 | runs-on: ubuntu-latest 25 | permissions: 26 | contents: read 27 | packages: write 28 | 29 | steps: 30 | - name: Convert Names to Lowercase 31 | run: | 32 | echo LOWERCASE_REPOSITORY_OWNER_NAME=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV 33 | - name: Checkout repository 34 | uses: actions/checkout@v3 35 | 36 | - name: Log in to the Container registry 37 | uses: docker/login-action@v1 38 | with: 39 | registry: ${{ env.REGISTRY }} 40 | username: ${{ github.actor }} 41 | password: ${{ secrets.GITHUB_TOKEN }} 42 | 43 | - name: Extract metadata (tags, labels) for Docker 44 | id: meta 45 | uses: docker/metadata-action@v2 46 | with: 47 | images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME_SCANNER }} 48 | 49 | - name: Build and push Docker image 50 | uses: docker/build-push-action@v2 51 | with: 52 | context: . 53 | push: true 54 | tags: ${{ env.REGISTRY }}/${{ env.LOWERCASE_REPOSITORY_OWNER_NAME }}/${{ env.IMAGE_NAME_SCANNER }}:latest 55 | labels: ${{ steps.meta.outputs.labels }} 56 | file: Dockerfile_Jellyfin-Intro-Scanner -------------------------------------------------------------------------------- /.github/workflows/docker-deploy-skipper.yml: -------------------------------------------------------------------------------- 1 | name: Deploy Jellyfin Intro Auto Skipper 2 | 3 | on: 4 | push: 5 | branches: 6 | - master 7 | paths: 8 | - 'jellyfin_auto_skip.py' 9 | - 'Dockerfile_Jellyfin-Intro-Skipper' 10 | 11 | env: 12 | IMAGE_NAME_SKIPPER: jellyfin-intro-skipper 13 | REGISTRY: ghcr.io 14 | 15 | jobs: 16 | Skipper_Deploy: 17 | runs-on: ubuntu-latest 18 | permissions: 19 | contents: read 20 | packages: write 21 | 22 | steps: 23 | - name: Convert Names to Lowercase 24 | run: | 25 | echo LOWERCASE_REPOSITORY_OWNER_NAME=$(echo ${{ github.repository_owner }} | tr '[:upper:]' '[:lower:]') >> $GITHUB_ENV 26 | - name: Checkout repository 27 | uses: actions/checkout@v3 28 | 29 | - name: Log in to the Container registry 30 | uses: docker/login-action@v1 31 | with: 32 | registry: ${{ env.REGISTRY }} 33 | username: ${{ github.actor }} 34 | password: ${{ secrets.GITHUB_TOKEN }} 35 | 36 | - name: Extract metadata (tags, labels) for Docker 37 | id: meta 38 | uses: docker/metadata-action@v2 39 | with: 40 | images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME_SKIPPER }} 41 | 42 | - name: Build and push Docker image 43 | uses: docker/build-push-action@v2 44 | with: 45 | context: . 46 | push: true 47 | tags: ${{ env.REGISTRY }}/${{ env.LOWERCASE_REPOSITORY_OWNER_NAME }}/${{ env.IMAGE_NAME_SKIPPER }}:latest 48 | labels: ${{ steps.meta.outputs.labels }} 49 | file: Dockerfile_Jellyfin-Intro-Skipper -------------------------------------------------------------------------------- /.github/workflows/docker-test-build-scanner.yml: -------------------------------------------------------------------------------- 1 | name: Docker Test Build Jellyfin Intro Scanner 2 | 3 | on: 4 | pull_request: 5 | paths: 6 | - '**.py' 7 | - 'Dockerfile_Jellyfin-Intro-Scanner' 8 | - '!jellyfin_auto_skip.py' 9 | - '!diff_jellyfin_cache.py' 10 | - '!Dockerfile_Jellyfin-Intro-Skipper' 11 | - '!**.md' 12 | - '!**.gitignore' 13 | - '!docs/**' 14 | - '!.github/**' 15 | 16 | env: 17 | IMAGE_NAME_Scanner: jellyfin-intro-scanner-test 18 | 19 | jobs: 20 | Test_Build_Scanner: 21 | runs-on: ubuntu-latest 22 | steps: 23 | - uses: actions/checkout@v2 24 | - name: Build image 25 | run: docker build -f Dockerfile_Jellyfin-Intro-Scanner -t jellyfin-intro-scanner-test . -------------------------------------------------------------------------------- /.github/workflows/docker-test-build-skipper.yml: -------------------------------------------------------------------------------- 1 | name: Docker Image Test Build Jellyfin Intro Auto Skipper 2 | 3 | on: 4 | pull_request: 5 | paths: 6 | - 'jellyfin_auto_skip.py' 7 | - 'Dockerfile_Jellyfin-Intro-Skipper' 8 | 9 | env: 10 | IMAGE_NAME_Skipper: jellyfin-intro-skipper-test 11 | 12 | jobs: 13 | Test_Build_Skipper: 14 | runs-on: ubuntu-latest 15 | steps: 16 | - uses: actions/checkout@v2 17 | - name: Build image 18 | run: docker build -f Dockerfile_Jellyfin-Intro-Skipper -t jellyfin-intro-skipper-test . -------------------------------------------------------------------------------- /.github/workflows/python-lint-test.yml: -------------------------------------------------------------------------------- 1 | name: Python Lint Test 2 | 3 | on: 4 | push: 5 | paths: 6 | - '**.py' 7 | 8 | jobs: 9 | Python_Lint_Test: 10 | runs-on: ubuntu-latest 11 | steps: 12 | - uses: actions/checkout@v2 13 | - name: Set up Python 3.10.2 14 | uses: actions/setup-python@v2 15 | with: 16 | python-version: 3.10.2 17 | - name: Install dependencies 18 | run: | 19 | python -m pip install --upgrade pip 20 | python -m pip install wheel 21 | pip install flake8 22 | pip install pylint 23 | if [ -f requirements.txt ]; then pip install -r requirements.txt; fi 24 | - name: Lint with flake8 25 | run: | 26 | flake8 . --count --ignore=E501,E116,W293,W605,F841 --max-complexity=30 --builtins="_" --show-source --statistics 27 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | .idea 2 | __pycache__/ 3 | *.py[cod] 4 | *.json 5 | *.txt 6 | *.DS_STORE 7 | .vscode 8 | cred.json 9 | venv 10 | config/data -------------------------------------------------------------------------------- /Dockerfile_Jellyfin-Intro-Scanner: -------------------------------------------------------------------------------- 1 | FROM python:3.10 2 | COPY . /app 3 | RUN apt-get update 4 | RUN apt-get install -y ffmpeg libsm6 libxext6 5 | RUN pip install --no-cache-dir --upgrade pip 6 | RUN pip install --no-cache-dir wheel 7 | RUN pip install --no-cache-dir -r /app/requirements.txt 8 | WORKDIR /app 9 | ENTRYPOINT ["python"] 10 | CMD [ "-u", "jellyfin.py", "-j", "-v", "-l" ] 11 | 12 | VOLUME /app/config 13 | -------------------------------------------------------------------------------- /Dockerfile_Jellyfin-Intro-Skipper: -------------------------------------------------------------------------------- 1 | FROM python:3.10 2 | COPY . /app 3 | RUN apt-get update 4 | RUN apt-get install -y ffmpeg libsm6 libxext6 5 | RUN pip install --no-cache-dir --upgrade pip 6 | RUN pip install --no-cache-dir wheel 7 | RUN pip install --no-cache-dir -r /app/requirements.txt 8 | WORKDIR /app 9 | ENTRYPOINT ["python"] 10 | CMD [ "-u", "jellyfin_auto_skip.py", "-a", "-c", "2" ] 11 | 12 | VOLUME /app/config 13 | -------------------------------------------------------------------------------- /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 | # TV Intro Detection 2 | 3 | This project tries to detect intros of tv series by comparing pairs of episodes to find the largest common subset of frames. 4 | 5 | For setup details you can find the documentation here: 6 | 7 | https://mueslimak3r.github.io/tv-intro-detection/ 8 | 9 | ### Notice 10 | `path_map.txt` and env `PATH_MAP` now use `::` to delimit path maps instead of `:`. This allows handling Windows paths 11 | 12 | ### How the script compares videos 13 | Each frame from the first quarter of each episode is extracted and a hash (https://pypi.org/project/ImageHash/) is made on the frame. Each frame hash is added to a long video hash.
14 | In pairs the longest identical string is searched from the two video hashes.
15 | Assumption: this is the intro 16 | 17 | ### How the script finds your videos 18 | When using jellyfin.py, the script queries the jellyfin server and is sent a list of all the tv shows in your library. With that list of shows, it then queries the jellyfin server for the seasons and episodes for each of the shows. Included in the results of those queries is the location on the filesystem for each item (show, season, episode). 19 | 20 | To account for jellyfin potentially using a different filesystem path to access the media than the system running the script would (eg: running in docker, running the script on a separate computer with the media drives mounted as network shares), path mapping is used to translate the path jellyfin sees into a path that the script can use. 21 | 22 | When running decode.py on its own, the -i parameter is used to specify a folder that contains video files. decode.py doesn't do any searching beyond that single folder, so typically the provided folder will be a "season folder" that contains all the video files for that season of a show. 23 | 24 | Individual shows or seasons can be ignored by creating an empty file named `.ignore-intros` inside its folder. 25 | 26 | ### Examples 27 | scan your jellyfin library, store the result in json, verbose logging enabled, logging debug output to file enabled 28 | 29 | `export JELLYFIN_URL="https://myurl" && export JELLYFIN_USERNAME="myusername" && export JELLYFIN_PASSWORD='mypassword'` 30 | 31 | `jellyfin.py -j -v -l` 32 | 33 | or in reverse order 34 | 35 | `jellyfin.py -j -v -l --reverse` 36 | 37 | monitor your jellyfin sessions and automatically skip intros using the stored json data 38 | 39 | `export JELLYFIN_URL="https://myurl" && export JELLYFIN_USERNAME="myusername" && export JELLYFIN_PASSWORD='mypassword'` 40 | 41 | `jellyfin_auto_skip.py` 42 | 43 | manually scan a directory containing at least 2 video files, debug logging enabled, logging debug output to file enabled, delete fingerprint data afterward 44 | `decode.py -i /path/to/tv/season -d -l -c` 45 | 46 | make the script aware of your host:container path mapping by editing `path_map.txt` 47 | 48 | ``` 49 | # use this file if you run jellyfin in a container 50 | # examples: 51 | # 52 | # linux client, Jellyfin on linux 53 | # 54 | # /host/system/tv/path::/jellyfin/container/tv/path 55 | # 56 | # or 57 | # Windows client, Jellyfin on Windows 58 | # 59 | # X:\some\path\TV::Y:\some\path\TV 60 | # 61 | # or 62 | # Windows client, Jellyfin on linux 63 | # 64 | # or 65 | # X:\some\path\TV::/jellyfin/container/tv/path 66 | ``` 67 | -------------------------------------------------------------------------------- /config/data/fingerprints/placeholder: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mueslimak3r/tv-intro-detection/afc397bf12b7e072b0e3a781c9d7a42e8c5dee79/config/data/fingerprints/placeholder -------------------------------------------------------------------------------- /config/data/jellyfin_cache/placeholder: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mueslimak3r/tv-intro-detection/afc397bf12b7e072b0e3a781c9d7a42e8c5dee79/config/data/jellyfin_cache/placeholder -------------------------------------------------------------------------------- /config/path_map.txt: -------------------------------------------------------------------------------- 1 | # use this file if you run jellyfin in a container 2 | # examples: 3 | # 4 | # linux client, Jellyfin on linux 5 | # 6 | # /host/system/tv/path::/jellyfin/container/tv/path 7 | # 8 | # or 9 | # Windows client, Jellyfin on Windows 10 | # 11 | # X:\some\path\TV::Y:\some\path\TV 12 | # 13 | # or 14 | # Windows client, Jellyfin on linux 15 | # 16 | # or 17 | # X:\some\path\TV::/jellyfin/container/tv/path 18 | -------------------------------------------------------------------------------- /decode.py: -------------------------------------------------------------------------------- 1 | import os 2 | import re 3 | import sys 4 | import getopt 5 | import shutil 6 | import json 7 | import cv2 8 | import hashlib 9 | import pandas 10 | import imagehash 11 | 12 | from math import floor 13 | from datetime import datetime, timedelta 14 | from pathlib import Path 15 | 16 | from ffmpeg_fingerprint import get_fingerprint_ffmpeg 17 | 18 | FIRST = 0 19 | SECOND = 1 20 | BOTH = 2 21 | 22 | config_path = Path(os.environ['CONFIG_DIR']) if 'CONFIG_DIR' in os.environ else Path(Path.cwd() / 'config') 23 | data_path = Path(os.environ['DATA_DIR']) if 'DATA_DIR' in os.environ else Path(config_path / 'data') 24 | 25 | preroll_seconds = 0 # adjust the end time to return n seconds prior to the calculated end time 26 | # jellyfin_auto_skip.py also handles pre-roll so adjust it there 27 | # adjusting it here bakes the pre-rolled value into the result 28 | max_fingerprint_mins = 10 29 | min_intro_length_sec = 10 30 | max_intro_length_sec = 180 31 | workers = 4 # number of executors to use 32 | target_image_height = 180 # scale frames to height of 180px 33 | 34 | check_frame = 1 # check_frame should be 1 if hash_fps is lower than video fps 35 | hash_fps = 2 36 | 37 | session_timestamp = datetime.now().strftime("%Y_%m_%d-%I_%M_%S_%p") 38 | 39 | revision_id = 2.0 40 | 41 | 42 | def print_debug(a=[], log=True, log_file=False): 43 | # Here a is the array holding the objects 44 | # passed as the argument of the function 45 | output = ' '.join([str(elem) for elem in a]) 46 | if log: 47 | print(output, file=sys.stderr) 48 | if log_file: 49 | log_path = config_path / 'logs' 50 | log_path.mkdir(parents=True, exist_ok=True) 51 | with (log_path / ('log_%s.txt' % session_timestamp)).open('a') as logger: 52 | logger.write(output + '\n') 53 | 54 | 55 | def dict_by_value(dict, value): 56 | for name, age in dict.items(): 57 | if age == value: 58 | return name 59 | 60 | 61 | def write_fingerprint(path, fingerprint): 62 | path = Path(data_path / 'fingerprints' / replace(path) / 'fingerprint.txt') 63 | with path.open('w+') as text_file: 64 | text_file.write(fingerprint) 65 | 66 | 67 | def replace(s): 68 | return re.sub('[^A-Za-z0-9]+', '', s) 69 | 70 | 71 | def print_timestamp(name, start_frame, end_frame, fps, log_level, log_file): 72 | start_time = 0 if start_frame == 0 else round(start_frame / fps) 73 | end_time = 0 if end_frame == 0 else round(end_frame / fps) 74 | 75 | print_debug(a=['[%s] has start %s end %s' % (name, str(timedelta(seconds=start_time)).split('.')[0], str(timedelta(seconds=end_time)).split('.')[0])], log=log_level > 0, log_file=log_file) 76 | 77 | 78 | def get_timestamp_from_frame(profile): 79 | start_time = 0 if profile['start_frame'] == 0 else profile['start_frame'] / profile['fps'] 80 | end_time = 0 if profile['end_frame'] == 0 else profile['end_frame'] / profile['fps'] 81 | 82 | profile['start_time_ms'] = floor(start_time * 1000) 83 | profile['end_time_ms'] = floor(end_time * 1000) 84 | profile['start_time'] = str(timedelta(seconds=floor(start_time))).split('.')[0] 85 | profile['end_time'] = str(timedelta(seconds=floor(end_time))).split('.')[0] 86 | 87 | 88 | def create_video_fingerprint(profile, hashfps, log_level, log_file): 89 | video_fingerprint = [] 90 | 91 | quarter_frames_or_first_X_mins = min(floor(((profile['total_frames'] / profile['fps']) / 4) * hashfps), floor(max_fingerprint_mins * 60 * hashfps)) 92 | video_fingerprint = get_fingerprint_ffmpeg(profile['Path'], hashfps, quarter_frames_or_first_X_mins, log_level, log_file, session_timestamp) 93 | 94 | return video_fingerprint 95 | 96 | 97 | def get_equal_frames(print1, print2, start1, start2): 98 | equal_frames = [] 99 | 100 | search_range = floor(min(len(print1), len(print2)) / check_frame) 101 | 102 | for j in range(0, search_range): 103 | frame1 = print1[j * check_frame] 104 | frame2 = print2[j * check_frame] 105 | if frame1 - frame2 < 8: 106 | equal_frames.append((int(start1 + (j * check_frame)), int(start2 + (j * check_frame)))) 107 | return equal_frames 108 | 109 | 110 | def get_start_end(print1, print1_fps, print2, print2_fps, log_level): 111 | if not print1 or not print2: 112 | return (0, 0), (0, 0) 113 | 114 | shortest_len = min(len(print1), len(print2)) 115 | 116 | if len(print2) == shortest_len: 117 | longest = print1 118 | shortest = print2 119 | swap = False 120 | else: 121 | longest = print2 122 | shortest = print1 123 | swap = True 124 | print_debug(a=['swapped %s' % swap], log=log_level > 1) 125 | 126 | highest_equal_frames = [] 127 | for k in range(1, len(longest)): 128 | equal_frames = get_equal_frames(longest[-k:], shortest, len(longest) - k, 0) 129 | if equal_frames and len(equal_frames) > 1: 130 | tmp_duration = equal_frames[-1][0] - equal_frames[0][0] 131 | if len(equal_frames) > len(highest_equal_frames) and tmp_duration >= 0 and tmp_duration < len(shortest): 132 | highest_equal_frames = equal_frames 133 | 134 | if k < len(shortest): 135 | equal_frames = get_equal_frames(longest, shortest[k:], 0, k) 136 | if equal_frames and len(equal_frames) > 1: 137 | tmp_duration = equal_frames[-1][0] - equal_frames[0][0] 138 | if len(equal_frames) > len(highest_equal_frames) and tmp_duration >= 0 and tmp_duration < len(shortest): 139 | highest_equal_frames = equal_frames 140 | 141 | if highest_equal_frames: 142 | if swap: 143 | return (floor(highest_equal_frames[0][1] * (print1_fps / hash_fps)), floor(highest_equal_frames[-1][1] * (print1_fps / hash_fps))), (floor(highest_equal_frames[0][0] * (print2_fps / hash_fps)), floor(highest_equal_frames[-1][0] * (print2_fps / hash_fps))) 144 | else: 145 | return (floor(highest_equal_frames[0][0] * (print1_fps / hash_fps)), floor(highest_equal_frames[-1][0] * (print1_fps / hash_fps))), (floor(highest_equal_frames[0][1] * (print2_fps / hash_fps)), floor(highest_equal_frames[-1][1] * (print2_fps / hash_fps))) 146 | else: 147 | return (0, 0), (0, 0) 148 | 149 | 150 | def read_fingerprint(fingerprint_str, log_level, log_file): 151 | fingerprint = [] 152 | if fingerprint_str != '' and len(fingerprint_str) % 16 == 0: 153 | try: 154 | for ndx in range(0, floor(len(fingerprint_str) / 16)): 155 | fingerprint.append(imagehash.hex_to_hash(fingerprint_str[ndx * 16:ndx * 16 + 16])) 156 | print_debug(a=['fingerprint looks valid'], log=log_level > 1, log_file=log_file) 157 | except BaseException as err: 158 | print_debug(a=['error reading season fingerprint'], log=log_level > 0, log_file=log_file) 159 | fingerprint = [] 160 | return fingerprint 161 | 162 | 163 | def read_fingerprint_file(file, log_level, log_file): 164 | if not Path(file).exists(): 165 | return [] 166 | 167 | fingerprint = [] 168 | print_debug(a=['loading existing fingerprint [%s]' % file], log=log_level > 1, log_file=log_file) 169 | with Path(file).open('r') as text_file: 170 | fingerprint_str = text_file.read() 171 | fingerprint = read_fingerprint(fingerprint_str, log_level, log_file) 172 | return fingerprint 173 | 174 | 175 | def get_or_create_fingerprint(profile, log_level, log_file): 176 | start = datetime.now() 177 | video = cv2.VideoCapture(profile['Path']) 178 | fps = video.get(cv2.CAP_PROP_FPS) 179 | 180 | profile['fps'] = fps 181 | profile['total_frames'] = int(video.get(cv2.CAP_PROP_FRAME_COUNT)) 182 | video.release() 183 | 184 | fingerprint = [] 185 | 186 | if Path(data_path / 'fingerprints' / replace(profile['Path']) / 'fingerprint.txt').exists(): 187 | fingerprint = read_fingerprint_file(Path(data_path / 'fingerprints' / replace(profile['Path']) / 'fingerprint.txt'), log_level, log_file) 188 | 189 | if not fingerprint: 190 | print_debug(a=['creating new fingerprint for [%s]' % profile['Path']], log=log_level > 1, log_file=log_file) 191 | fingerprint = create_video_fingerprint(profile, hash_fps, log_level, log_file) 192 | 193 | end = datetime.now() 194 | print_debug(a=["processed fingerprint in %s for [%s]" % (str(end - start), profile['Path'])], log=log_level > 0, log_file=log_file) 195 | return fingerprint 196 | 197 | 198 | def check_files_exist(profiles=[]): 199 | if not profiles: 200 | return False 201 | for p in profiles: 202 | if 'Path' not in p or not Path(p['Path']).exists(): 203 | return False 204 | return True 205 | 206 | 207 | def save_season_fingerprint(fingerprints, profiles, ndx, filtered_lengths, shortest_duration): 208 | size = len(filtered_lengths) 209 | sum = 0 210 | for f in filtered_lengths: 211 | sum += f 212 | average = int(sum / size) 213 | 214 | name = '' 215 | for profile in profiles: 216 | name += replace(profile['Path']) 217 | hash_object = hashlib.md5(name.encode()) 218 | name = hash_object.hexdigest() 219 | 220 | season_fingerprint = {} 221 | season_fingerprint.update(profiles[ndx]) 222 | 223 | tmp_start_frame = floor((profiles[ndx]['start_frame'] / profiles[ndx]['fps']) * hash_fps) if profiles[ndx]['start_frame'] > 0 else 0 224 | tmp_end_frame = floor((profiles[ndx]['end_frame'] / profiles[ndx]['fps']) * hash_fps) if profiles[ndx]['end_frame'] > 0 else 0 225 | 226 | trimmed_fingerprint = fingerprints[ndx][tmp_start_frame:tmp_end_frame + 1] 227 | 228 | fingerprint_str = '' 229 | for f in trimmed_fingerprint: 230 | fingerprint_str += str(f) 231 | 232 | season_fingerprint['fingerprint'] = fingerprint_str 233 | season_fingerprint['reference_duration'] = shortest_duration 234 | season_fingerprint['average_frames'] = average 235 | season_fingerprint['average_sample_size'] = len(filtered_lengths) 236 | season_fingerprint['hash_fps'] = hash_fps 237 | season_fingerprint['revision_id'] = revision_id 238 | 239 | path = Path(data_path / 'fingerprints' / (name + '.json')) 240 | Path(data_path / 'fingerprints').mkdir(parents=True, exist_ok=True) 241 | with path.open('w+') as json_file: 242 | json.dump(season_fingerprint, json_file, indent=4) 243 | 244 | 245 | def intro_duration(profile): 246 | intro_duration = profile['end_frame'] - profile['start_frame'] 247 | if intro_duration < 0: 248 | intro_duration = 0 249 | return intro_duration 250 | 251 | 252 | def reject_outliers(input_list, iq_range=0.2): 253 | if not input_list: 254 | return input_list 255 | 256 | sr = pandas.Series(input_list, copy=True) 257 | pcnt = (1 - iq_range) / 2 258 | qlow, median, qhigh = sr.dropna().quantile([pcnt, 0.50, 1 - pcnt]) 259 | iqr = qhigh - qlow 260 | return sr[(sr - median).abs() <= iqr].values.tolist() 261 | 262 | 263 | def sort_conforming_profile(profile_tuple): 264 | return profile_tuple[1] 265 | 266 | 267 | def correct_errors(fingerprints, profiles, ref_profile, log_level=0, log_file=False): 268 | # skip outlier rejection when there is only the reference profile and one other file 269 | if ref_profile is not None and len(fingerprints) == 2: 270 | diff_from_avg = abs(intro_duration(profiles[1]) - ref_profile['average_frames']) 271 | if diff_from_avg < int(15 * profiles[1]['fps']): 272 | print_debug(a=['single file conforms to reference profile'], log=log_level > 0, log_file=log_file) 273 | return 274 | 275 | # build a list of intro lengths with outliers rejected 276 | lengths = [] 277 | for profile in profiles: 278 | if intro_duration(profile) <= int(profile['fps'] * max_intro_length_sec) and \ 279 | intro_duration(profile) > int(profile['fps'] * 2): 280 | 281 | lengths.append(intro_duration(profile)) 282 | else: 283 | print_debug(a=['excluding profile from pool of durations due to it being to long or short %s start %s end %s' % (profile['Path'], profile['start_frame'], profile['end_frame'])], log=log_level > 1, log_file=log_file) 284 | print_timestamp(profile['Path'], profile['start_frame'], profile['end_frame'], profile['fps'], log_level, log_file) 285 | filtered_lengths = reject_outliers(lengths) 286 | 287 | if len(filtered_lengths) < 1: 288 | for profile in profiles: 289 | profile['start_frame'] = 0 290 | profile['end_frame'] = 0 291 | print_debug(a=['failed to correct - could not establish consistency between episodes'], log=log_level > 0, log_file=log_file) 292 | return 293 | 294 | size = len(filtered_lengths) 295 | sum = 0 296 | for f in filtered_lengths: 297 | sum += f 298 | average = int(sum / size) 299 | 300 | print_debug(a=['average length in frames [%s] from %s of %s files' % (average, len(filtered_lengths), len(profiles))], log=log_level > 0, log_file=log_file) 301 | print_timestamp('average length (time)', 0, average, profiles[0]['fps'], log_level, log_file) 302 | 303 | if average == 0 or int(round(average / profiles[0]['fps'])) < min_intro_length_sec: 304 | for profile in profiles: 305 | profile['start_frame'] = 0 306 | profile['end_frame'] = 0 307 | print_debug(a=['skipping profiles - average duration is too short'], log=log_level > 0, log_file=log_file) 308 | return 309 | 310 | # build a list of conforming and non conforming profiles (int indexes) 311 | # loop through profiles and check if their duration is in the filtered list of intro lengths 312 | conforming_profiles = [] 313 | non_conforming_profiles = [] 314 | for ndx in range(0, len(profiles)): 315 | diff_from_avg = abs(intro_duration(profiles[ndx]) - average) 316 | print_debug(a=['file [%s] diff from average %s' % (profiles[ndx]['Path'], diff_from_avg)], log=log_level > 1, log_file=log_file) 317 | if intro_duration(profiles[ndx]) in filtered_lengths or \ 318 | diff_from_avg < int(15 * profiles[ndx]['fps']): 319 | conforming_profiles.append((ndx, intro_duration(profiles[ndx]))) 320 | else: 321 | print_debug(a=['\nrejected file [%s] with start %s end %s' % (profiles[ndx]['Path'], profiles[ndx]['start_frame'], profiles[ndx]['end_frame'])], log_file=log_file) 322 | print_timestamp(profiles[ndx]['Path'], profiles[ndx]['start_frame'], profiles[ndx]['end_frame'], profiles[ndx]['fps'], log_level, log_file) 323 | non_conforming_profiles.append(ndx) 324 | 325 | print_debug(a=['\nrejected start frame values from %s of %s results\n' % (len(non_conforming_profiles), len(profiles))], log=log_level > 0, log_file=log_file) 326 | 327 | if len(conforming_profiles) < 1: 328 | print_debug(a=['all profiles were rejected'], log=log_level > 0, log_file=log_file) 329 | for profile in profiles: 330 | profile['start_frame'] = 0 331 | profile['end_frame'] = 0 332 | return 333 | 334 | # sort the list of conforming profile indexes and find the mean value 335 | # this profile will be the reference profile used when repairing the rejected profiles 336 | conforming_profiles.sort(key=sort_conforming_profile) 337 | shortest_duration = intro_duration(profiles[conforming_profiles[0][0]]) 338 | print_debug(a=['shortest duration %s from %s' % (shortest_duration, profiles[conforming_profiles[0][0]]['Path'])], log=log_level > 0, log_file=log_file) 339 | ref_profile_ndx = conforming_profiles[int(floor(len(conforming_profiles) / 2))][0] 340 | 341 | if ref_profile is None: 342 | print_debug(a=['saving season fingerprint'], log=log_level > 0, log_file=log_file) 343 | save_season_fingerprint(fingerprints, profiles, ref_profile_ndx, filtered_lengths, shortest_duration) 344 | 345 | if len(non_conforming_profiles) < 1: 346 | print_debug(a=['no profiles were rejected!'], log=log_level > 0, log_file=log_file) 347 | return 348 | 349 | # reprocess the rejected profiles by comparing them to the reference profile 350 | for nprofile in non_conforming_profiles: 351 | print_debug(a=['reprocessing %s by comparing to %s' % (profiles[nprofile]['Path'], profiles[ref_profile_ndx]['Path'])], log=log_level > 0, log_file=log_file) 352 | tmp_profile = {} 353 | tmp_profile.update(profiles[ref_profile_ndx]) 354 | tmp_index = len(fingerprints) 355 | 356 | if ref_profile is None or profiles[ref_profile_ndx]['Path'] != ref_profile['Path']: 357 | tmp_start_frame = floor((profiles[ref_profile_ndx]['start_frame'] / profiles[ref_profile_ndx]['fps']) * hash_fps) if profiles[ref_profile_ndx]['start_frame'] > 0 else 0 358 | tmp_end_frame = floor((profiles[ref_profile_ndx]['end_frame'] / profiles[ref_profile_ndx]['fps']) * hash_fps) if profiles[ref_profile_ndx]['end_frame'] > 0 else 0 359 | fingerprints.append(fingerprints[ref_profile_ndx][tmp_start_frame:tmp_end_frame + 1]) 360 | else: 361 | fingerprints.append(fingerprints[ref_profile_ndx]) 362 | profiles.append(tmp_profile) 363 | 364 | print_timestamp(profiles[tmp_index]['Path'], profiles[tmp_index]['start_frame'], profiles[tmp_index]['end_frame'], profiles[tmp_index]['fps'], log_level, log_file) 365 | 366 | process_pairs(fingerprints, profiles, tmp_index, nprofile, SECOND, log_level, log_file) 367 | profiles.pop() 368 | fingerprints.pop() 369 | 370 | # repeat building a list of lengths and filtering them 371 | lengths = [] 372 | for profile in profiles: 373 | lengths.append(intro_duration(profile)) 374 | new_filtered_lengths = reject_outliers(lengths) 375 | 376 | # repeat checking each profile's duration against the new filtered list of lengths 377 | repaired = 0 378 | for nprofile in range(0, len(profiles)): 379 | diff_from_avg = abs(intro_duration(profiles[nprofile]) - average) 380 | guessed_start = floor(profiles[nprofile]['end_frame'] - (shortest_duration / 2)) 381 | if guessed_start < 0: 382 | guessed_start = 0 383 | guessed_start_diff = abs(profiles[nprofile]['end_frame'] - guessed_start - average) 384 | if intro_duration(profiles[nprofile]) >= int(min_intro_length_sec * profiles[nprofile]['fps']): 385 | if nprofile in non_conforming_profiles: 386 | repaired += 1 387 | print_debug(a=['\nreprocess successful for file [%s] new start %s end %s' % (profiles[nprofile]['Path'], profiles[nprofile]['start_frame'], profiles[nprofile]['end_frame'])], log=log_level > 0, log_file=log_file) 388 | print_timestamp(profiles[nprofile]['Path'], profiles[nprofile]['start_frame'], profiles[nprofile]['end_frame'], profiles[nprofile]['fps'], log_level, log_file) 389 | ''' 390 | elif intro_duration(profiles[nprofile]) > int(2 * profiles[nprofile]['fps']) and guessed_start_diff < int(15 * profiles[nprofile]['fps']): 391 | if nprofile in non_conforming_profiles: 392 | repaired += 1 393 | profiles[nprofile]['start_frame'] = guessed_start 394 | print_debug(a=['\nreprocess successful by guessing start for file [%s] - new start %s end %s' % (profiles[nprofile]['Path'], profiles[nprofile]['start_frame'], profiles[nprofile]['end_frame'])], log=log_level > 0, log_file=log_file) 395 | print_timestamp(profiles[nprofile]['Path'], profiles[nprofile]['start_frame'], profiles[nprofile]['end_frame'], profiles[nprofile]['fps'], log_level, log_file) 396 | ''' 397 | elif nprofile in non_conforming_profiles: 398 | print_debug(a=['\nfailed to locate intro by reprocessing %s' % profiles[nprofile]['Path']], log_file=log_file) 399 | print_debug(a=['file [%s] new start %s end %s' % (profiles[nprofile]['Path'], profiles[nprofile]['start_frame'], profiles[nprofile]['end_frame'])], log=log_level > 0, log_file=log_file) 400 | print_timestamp(profiles[nprofile]['Path'], profiles[nprofile]['start_frame'], profiles[nprofile]['end_frame'], profiles[nprofile]['fps'], log_level, log_file) 401 | profiles[nprofile]['start_frame'] = 0 402 | profiles[nprofile]['end_frame'] = 0 403 | print_debug(a=['\nrepaired %s/%s non conforming profiles\n' % (repaired, len(non_conforming_profiles))], log=log_level > 0, log_file=log_file) 404 | 405 | 406 | def process_pairs(fingerprints, profiles, ndx_1, ndx_2, mode, log_level, log_file): 407 | 408 | start_end = get_start_end(fingerprints[ndx_1], profiles[ndx_1]['fps'], fingerprints[ndx_2], profiles[ndx_2]['fps'], log_level) 409 | 410 | if mode == BOTH or mode == FIRST: 411 | profiles[ndx_1]['start_frame'] = start_end[0][0] 412 | if profiles[ndx_1]['start_frame'] < 0: 413 | print_debug(a=["start frame is negative (%s), setting to 0 for [%s]" % (profiles[ndx_1]['start_frame'], profiles[ndx_1]['Path'])], log=log_level > 1) 414 | profiles[ndx_1]['start_frame'] = 0 415 | 416 | profiles[ndx_1]['end_frame'] = start_end[0][1] 417 | if profiles[ndx_1]['end_frame'] < 0: 418 | print_debug(a=["end frame is negative (%s), setting to 0 for [%s]" % (profiles[ndx_1]['end_frame'], profiles[ndx_1]['Path'])], log=log_level > 1) 419 | profiles[ndx_1]['end_frame'] = 0 420 | 421 | print_timestamp(profiles[ndx_1]['Path'], profiles[ndx_1]['start_frame'], profiles[ndx_1]['end_frame'], profiles[ndx_1]['fps'], log_level, log_file) 422 | 423 | if mode == BOTH or mode == SECOND: 424 | profiles[ndx_2]['start_frame'] = start_end[1][0] 425 | if profiles[ndx_2]['start_frame'] < 0: 426 | print_debug(a=["start frame is negative (%s), setting to 0 for [%s]" % (profiles[ndx_2]['start_frame'], profiles[ndx_2]['Path'])], log=log_level > 1) 427 | profiles[ndx_2]['start_frame'] = 0 428 | 429 | profiles[ndx_2]['end_frame'] = start_end[1][1] 430 | if profiles[ndx_2]['end_frame'] < 0: 431 | print_debug(a=["end frame is negative (%s), setting to 0 for [%s]" % (profiles[ndx_2]['end_frame'], profiles[ndx_2]['Path'])], log=log_level > 1) 432 | profiles[ndx_2]['end_frame'] = 0 433 | 434 | print_timestamp(profiles[ndx_2]['Path'], profiles[ndx_2]['start_frame'], profiles[ndx_2]['end_frame'], profiles[ndx_2]['fps'], log_level, log_file) 435 | 436 | 437 | def process_directory(profiles=[], ref_profile=None, hashfps=2, log_level=0, log_file=False, cleanup=True, log_timestamp=None): 438 | global session_timestamp 439 | global hash_fps 440 | 441 | hash_fps = hashfps 442 | 443 | if log_timestamp is not None: 444 | session_timestamp = log_timestamp 445 | 446 | start = datetime.now() 447 | print_debug(a=['started at', start], log=log_level > 0, log_file=log_file) 448 | print_debug(a=["Check Frame: %s\n" % str(check_frame)], log=log_level > 0, log_file=log_file) 449 | print_debug(a=["Hash fps: %s\n" % str(hash_fps)], log=log_level > 0, log_file=log_file) 450 | 451 | if cleanup: 452 | print_debug(a=['fingerprint files will be cleaned up'], log=log_level > 0, log_file=log_file) 453 | 454 | if not check_files_exist(profiles): 455 | print_debug(a=['input files invalid or cannot be accessed'], log=log_level > 0, log_file=log_file) 456 | return {} 457 | 458 | if (ref_profile is not None and len(profiles) < 1) or (ref_profile is None and len(profiles) < 2): 459 | print_debug(a=['fewer than 2 valid fingerprints were found - skipping'], log=log_level > 0, log_file=log_file) 460 | return {} 461 | 462 | print_debug(a=['processing %s files' % len(profiles)], log=log_level > 0, log_file=log_file) 463 | 464 | if cleanup and Path(data_path / 'fingerprints').is_dir(): 465 | try: 466 | shutil.rmtree(Path(data_path / 'fingerprints')) 467 | except OSError as e: 468 | print_debug(a=["Error: %s : %s" % ('fingerprints', e.strerror)], log_file=log_file) 469 | 470 | fingerprints = [] # list of hash values 471 | 472 | hashing_start = datetime.now() 473 | for p in profiles: 474 | fingerprint = get_or_create_fingerprint(p, log_level, log_file) 475 | if fingerprint: 476 | fingerprints.append(fingerprint) 477 | hashing_end = datetime.now() 478 | print_debug(a=["got or created fingerprints in %s" % str(hashing_end - hashing_start)], log=log_level > 0, log_file=log_file) 479 | 480 | if ref_profile is not None and 'hash_fps' in ref_profile and ref_profile['hash_fps'] == hash_fps: 481 | fingerprint = read_fingerprint(ref_profile['fingerprint'], log_level, log_file) 482 | if fingerprint and abs(len(fingerprint) - floor(intro_duration(ref_profile) / (ref_profile['fps'] / hash_fps))) < 3: 483 | print_debug(a=["loaded reference profile"], log=log_level > 0, log_file=log_file) 484 | print_timestamp(ref_profile['Path'], ref_profile['start_frame'], ref_profile['end_frame'], ref_profile['fps'], log_level, log_file) 485 | fingerprints.insert(0, fingerprint) 486 | ref_profile.pop('fingerprint', None) 487 | profiles.insert(0, ref_profile) 488 | else: 489 | ref_profile = None 490 | else: 491 | ref_profile = None 492 | 493 | if (ref_profile is not None and len(fingerprints) < 1) or (ref_profile is None and len(fingerprints) < 2): 494 | print_debug(a=['fewer than 2 valid fingerprints were found - skipping'], log=log_level > 0, log_file=log_file) 495 | return {} 496 | 497 | # loop through each pair and store the start/end frames in their profiles 498 | # then do the same for the remaining profile if count is odd 499 | # 500 | # use mode: FIRST, SECOND, BOTH to decide whether to save the values to the first, second, or both profiles 501 | # changing modes is useful for processing a new profile against one that's already processed 502 | # for instance, if a profile is rejected it could be reprocessed against a different profile without risking... 503 | # ...overwriting the the start/end frame values for the reference profile 504 | counter = 0 505 | process_pairs_start = datetime.now() 506 | 507 | if ref_profile is not None: 508 | for i in range(1, len(fingerprints)): 509 | process_pairs(fingerprints, profiles, 0, i, SECOND, log_level, log_file) 510 | else: 511 | while len(fingerprints) - 1 > counter: 512 | process_pairs(fingerprints, profiles, counter, counter + 1, BOTH, log_level, log_file) 513 | counter += 2 514 | if len(fingerprints) % 2 != 0: 515 | process_pairs(fingerprints, profiles, -2, -1, SECOND, log_level, log_file) 516 | 517 | process_pairs_end = datetime.now() 518 | print_debug(a=["processed fingerprint pairs in: " + str(process_pairs_end - process_pairs_start)], log=log_level > 0, log_file=log_file) 519 | 520 | correct_errors_start = datetime.now() 521 | correct_errors(fingerprints, profiles, ref_profile, log_level, log_file) 522 | correct_errors_end = datetime.now() 523 | print_debug(a=["finished error correction in: " + str(correct_errors_end - correct_errors_start)], log=log_level > 0, log_file=log_file) 524 | 525 | if ref_profile is not None: 526 | fingerprints.pop(0) 527 | profiles.pop(0) 528 | 529 | # finally, automatically reject episodes with intros shorted than a specified length (default 15 seconds) 530 | # apply pre-roll if wanted 531 | # use the fps and start/end frame values to calculate the timestamps for the intros and add them to the profiles 532 | for profile in profiles: 533 | if intro_duration(profile) < int(min_intro_length_sec * profile['fps']): 534 | print_debug(a=['%s - intro is less than %s seconds - skipping' % (profile['Path'], min_intro_length_sec)], log=log_level > 1, log_file=log_file) 535 | profile['start_frame'] = 0 536 | profile['end_frame'] = 0 537 | elif preroll_seconds > 0 and profile['end_frame'] > profile['start_frame'] + floor(profile['fps'] * preroll_seconds): 538 | profile['end_frame'] -= floor(profile['fps'] * preroll_seconds) 539 | get_timestamp_from_frame(profile) 540 | print_debug(a=[profile['Path'] + " start time: " + profile['start_time'] + " end time: " + profile['end_time']], log=log_level > 1, log_file=log_file) 541 | 542 | end = datetime.now() 543 | print_debug(a=["ended at", end], log=log_level > 0, log_file=True) 544 | print_debug(a=["run time: " + str(end - start)], log=log_level > 0, log_file=True) 545 | 546 | if cleanup and Path(data_path / 'fingerprints').is_dir(): 547 | try: 548 | shutil.rmtree(Path(data_path / 'fingerprints')) 549 | except OSError as e: 550 | print_debug(a=["Error: %s : %s" % ('fingerprints', e.strerror)], log_file=log_file) 551 | return profiles 552 | 553 | 554 | def main(argv): 555 | 556 | path = '' 557 | ref_path = '' 558 | log_level = 0 559 | cleanup = False 560 | log = False 561 | try: 562 | opts, args = getopt.getopt(argv, "hi:dvclr:") 563 | except getopt.GetoptError: 564 | print_debug(['decode.py -i -v (verbose - some logging) -d (debug - most logging) -c (cleanup) -s (slow mode) -l (log to file)\n']) 565 | sys.exit(2) 566 | 567 | for opt, arg in opts: 568 | if opt == '-h': 569 | print_debug(['decode.py -i -v (verbose - some logging) -d (debug - most logging) -c (cleanup) -s (slow mode) -l (log to file)\n']) 570 | sys.exit() 571 | elif opt == '-i': 572 | path = arg 573 | elif opt == '-l': 574 | log = True 575 | elif opt == '-d': 576 | log_level = 2 577 | elif opt == '-v': 578 | log_level = 1 579 | elif opt == '-c': 580 | cleanup = True 581 | elif opt == '-r': 582 | ref_path = arg 583 | 584 | if path == '' or not Path(path).is_dir(): 585 | print_debug(['decode.py -i -v (verbose - some logging) -d (debug - most logging) -c (cleanup) -s (slow mode) -l (log to file)\n']) 586 | sys.exit(2) 587 | 588 | common_video_extensions = ['.webm', '.mkv', '.avi', '.mts', '.m2ts', '.ts', '.mov', '.wmv', '.mp4', '.m4v', '.mpg', '.mpeg', '.m2v'] 589 | 590 | ref_profile = None 591 | if ref_path != '' and Path(ref_path).exists(): 592 | with Path(ref_path).open('r') as profile_json: 593 | ref_profile = json.load(profile_json) 594 | 595 | profiles = [] 596 | for child in Path(path).iterdir(): 597 | if child.name[0] == '.': 598 | continue 599 | matched_ext = False 600 | for ext in common_video_extensions: 601 | if child.name.endswith(ext): 602 | matched_ext = True 603 | if matched_ext: 604 | profile = {} 605 | profile['Path'] = str(child.resolve()) 606 | profiles.append(profile) 607 | 608 | result = process_directory(profiles=profiles, ref_profile=ref_profile, log_level=log_level, log_file=log, cleanup=cleanup) 609 | print(result) 610 | 611 | 612 | if __name__ == "__main__": 613 | main(sys.argv[1:]) 614 | -------------------------------------------------------------------------------- /diff_jellyfin_cache.py: -------------------------------------------------------------------------------- 1 | import sys 2 | import getopt 3 | import json 4 | 5 | from pathlib import Path 6 | from math import floor 7 | from datetime import timedelta 8 | 9 | 10 | def get_timestamp(start_ms, end_ms): 11 | start_time = floor(start_ms / 1000) if start_ms != 0 else 0 12 | end_time = floor(end_ms / 1000) if end_ms != 0 else 0 13 | 14 | start = str(timedelta(seconds=start_time)).split('.')[0] 15 | end = str(timedelta(seconds=end_time)).split('.')[0] 16 | 17 | return (start, end) 18 | 19 | 20 | def get_dir_contents(path: Path, fullpath: bool): 21 | file_paths = [] 22 | for child in path.iterdir(): 23 | if child.name[0] == '.': 24 | continue 25 | file_paths.append(str(child.resolve()) if fullpath else str(child.name)) 26 | file_paths.sort() 27 | return file_paths 28 | 29 | 30 | def print_dir_contents(path: Path, padding: int): 31 | if not path.is_dir(): 32 | return 33 | 34 | contents = get_dir_contents(path, False) 35 | for c in contents: 36 | print('%s' % c.rjust(len(c) + padding)) 37 | 38 | 39 | def intro_duration(profile): 40 | intro_duration = profile['end_frame'] - profile['start_frame'] 41 | if intro_duration < 0: 42 | intro_duration = 0 43 | return intro_duration 44 | 45 | 46 | def get_item(path: Path): 47 | if not path.exists(): 48 | return 49 | 50 | profile = None 51 | with path.open('r') as json_file: 52 | profile = json.load(json_file) 53 | 54 | if profile is None: 55 | return 56 | if 'start_time_ms' not in profile or 'end_time_ms' not in profile: 57 | return 58 | 59 | profile['intro_duration'] = intro_duration(profile) 60 | 61 | return profile 62 | 63 | 64 | def get_season(path: Path): 65 | if not path.is_dir(): 66 | return 67 | 68 | season = { 69 | 'SeasonFingerprint': None, 70 | 'Episodes': {}, 71 | 'SeriesName': None, 72 | 'SeasonName': None, 73 | 'SeriesId': None, 74 | 'SeasonId': None, 75 | } 76 | 77 | contents = get_dir_contents(path, True) 78 | for c in contents: 79 | if c.endswith('.json'): 80 | item = get_item(Path(c)) 81 | if not item: 82 | continue 83 | 84 | if 'SeriesName' in item and item['SeriesName'] != '': 85 | season['SeriesName'] = item['SeriesName'] 86 | if 'SeasonName' in item and item['SeasonName'] != '': 87 | season['SeasonName'] = item['SeasonName'] 88 | if 'SeasonId' in item and item['SeasonId'] != '': 89 | season['SeasonId'] = item['SeasonId'] 90 | if 'SeriesId' in item and item['SeriesId'] != '': 91 | season['SeriesId'] = item['SeriesId'] 92 | 93 | if c.endswith('season.json'): 94 | season['SeasonFingerprint'] = get_item(Path(c)) 95 | else: 96 | season['Episodes'][item['EpisodeId']] = item 97 | return season 98 | 99 | 100 | def get_series(path: Path): 101 | # print('%s:' % str(path).rjust(len(str(path)) + padding)) 102 | if not path.is_dir(): 103 | return 104 | 105 | series = { 106 | 'Seasons': {}, 107 | 'SeriesName': None, 108 | 'SeriesId': None, 109 | } 110 | 111 | contents = get_dir_contents(path, True) 112 | for c in contents: 113 | season = get_season(Path(c)) 114 | if season is None: 115 | continue 116 | 117 | if 'SeriesName' in season and season['SeriesName'] != '': 118 | series['SeriesName'] = season['SeriesName'] 119 | if 'SeriesId' in season and season['SeriesId'] != '': 120 | series['SeriesId'] = season['SeriesId'] 121 | 122 | series['Seasons'][season['SeasonId']] = season 123 | 124 | return series 125 | 126 | 127 | def print_series(path: Path, padding: int): 128 | if not path.is_dir(): 129 | return 130 | 131 | series = get_series(path) 132 | if not series or not series['Seasons']: 133 | return 134 | 135 | seriesName = series['SeriesName'] 136 | print('%s:' % str(seriesName).rjust(len(str(seriesName)) + padding)) 137 | 138 | for season_key in series['Seasons']: 139 | season = series['Seasons'][season_key] 140 | if not season['Episodes']: 141 | continue 142 | 143 | seasonName = season['SeasonName'] 144 | print('%s:' % str(seasonName).rjust(len(str(seasonName)) + padding + 2)) 145 | episodes = season['Episodes'] 146 | 147 | for episode_key in episodes: 148 | episode = episodes[episode_key] 149 | start, end = get_timestamp(episode['start_time_ms'], episode['end_time_ms']) 150 | print_str = '%s - start: %s end %s' % (episode['Name'], start, end) 151 | print(print_str.rjust(len(str(print_str)) + padding + 4)) 152 | 153 | if 'SeasonFingerprint' in season and season['SeasonFingerprint'] is not None: 154 | seasonFingerprint = season['SeasonFingerprint'] 155 | start, end = get_timestamp(seasonFingerprint['start_time_ms'], seasonFingerprint['end_time_ms']) 156 | print_str = 'season fingerprint [%s - start: %s end %s]' % (seasonFingerprint['Name'], start, end) 157 | print(print_str.rjust(len(str(print_str)) + padding + 4)) 158 | 159 | 160 | def filter_dirs(old_path: Path, new_path: Path): 161 | old_path_contents = get_dir_contents(old_path, False) 162 | new_path_contents = get_dir_contents(new_path, False) 163 | 164 | contents_in_both = list(set(old_path_contents).intersection(set(new_path_contents))) 165 | contents_in_both.sort() 166 | 167 | contents_not_in_both = list(set(old_path_contents).symmetric_difference(set(new_path_contents))) 168 | contents_not_in_both.sort() 169 | 170 | if contents_not_in_both: 171 | print('series not in both:') 172 | for e in contents_not_in_both: 173 | if e in old_path_contents: 174 | path = Path(old_path / e) 175 | else: 176 | path = Path(new_path / e) 177 | print('%s:' % str(path).rjust(len(str(path)) + 2)) 178 | print_dir_contents(path, 4) 179 | print('\n') 180 | 181 | if path.is_dir(): 182 | print_series(path, 4) 183 | return contents_in_both 184 | 185 | 186 | def filter_ids(old_dict: dict, new_dict: dict): 187 | old_list = list(old_dict.keys()) 188 | new_list = list(new_dict.keys()) 189 | 190 | in_both = list(set(old_list).intersection(set(new_list))) 191 | not_in_both = list(set(old_list).symmetric_difference(set(new_list))) 192 | return in_both, not_in_both 193 | 194 | 195 | def check_if_in_list_of_dict(dict_list, value): 196 | if dict_list is None: 197 | return -1 198 | 199 | for ndx in range(0, len(dict_list)): 200 | if value in dict_list[ndx].values(): 201 | return ndx 202 | return -1 203 | 204 | 205 | def diff_data(old_path: Path, new_path: Path): 206 | SeriesIds = filter_dirs(old_path, new_path) 207 | total_episodes = 0 208 | total_diffs = 0 209 | percent_diff = 0 210 | 211 | diff_threshold = 2 212 | 213 | print('\n\n------------------------------------------------\n\n') 214 | 215 | print('series in both:') 216 | 217 | for Id in SeriesIds: 218 | has_logged_series = False 219 | 220 | old_series = get_series(Path(old_path / Id)) 221 | new_series = get_series(Path(new_path / Id)) 222 | 223 | seasons, seasons_not_in_both = filter_ids(old_series['Seasons'], new_series['Seasons']) 224 | 225 | for season_id in seasons: 226 | has_logged_season = False 227 | 228 | episodes, episodes_not_in_both = filter_ids(old_series['Seasons'][season_id]['Episodes'], new_series['Seasons'][season_id]['Episodes']) 229 | for episode_id in episodes: 230 | total_episodes += 1 231 | old_ep = old_series['Seasons'][season_id]['Episodes'][episode_id] 232 | new_ep = new_series['Seasons'][season_id]['Episodes'][episode_id] 233 | 234 | old_duration = old_ep['intro_duration'] / old_ep['fps'] if old_ep['intro_duration'] > 0 else 0 235 | new_duration = new_ep['intro_duration'] / new_ep['fps'] if new_ep['intro_duration'] > 0 else 0 236 | 237 | diff = abs(old_duration - new_duration) 238 | if diff > diff_threshold: 239 | total_diffs += 1 240 | if not has_logged_series: 241 | seriesName = old_series['SeriesName'] 242 | print('%s:' % str(seriesName).rjust(len(str(seriesName)) + 2)) 243 | has_logged_series = True 244 | 245 | if not has_logged_season: 246 | seasonName = old_ep['SeasonName'] 247 | print('%s:' % str(seasonName).rjust(len(str(seasonName)) + 4)) 248 | has_logged_season = True 249 | 250 | log_str = 'intro duration for episode [%s] of season [%s] series [%s] differs' % (old_ep['Name'], old_ep['SeasonName'], old_ep['SeriesName']) 251 | print('%s' % str(log_str).rjust(len(str(log_str)) + 6)) 252 | start1, end1 = get_timestamp(old_ep['start_time_ms'], old_ep['end_time_ms']) 253 | log_str = 'old start: %s end %s' % (start1, end1) 254 | print('%s' % str(log_str).rjust(len(str(log_str)) + 6)) 255 | start2, end2 = get_timestamp(new_ep['start_time_ms'], new_ep['end_time_ms']) 256 | log_str = 'new start: %s end %s\n' % (start2, end2) 257 | print('%s' % str(log_str).rjust(len(str(log_str)) + 6)) 258 | log_str = 'diff %s seconds' % diff 259 | print('%s' % str(log_str).rjust(len(str(log_str)) + 6)) 260 | 261 | percent_diff = (total_diffs / total_episodes) * 100 262 | print('%s/%s episodes ( %s percent ) changed more than %s sec' % (total_diffs, total_episodes, percent_diff, diff_threshold)) 263 | 264 | 265 | def main(argv): 266 | old_cache_path_str = '' 267 | new_cache_path_str = '' 268 | 269 | try: 270 | opts, args = getopt.getopt(argv, "ho:n:") 271 | except getopt.GetoptError: 272 | print('diff_jellyfin_cache.py -o -n ') 273 | sys.exit(2) 274 | 275 | for opt, arg in opts: 276 | if opt == '-h': 277 | print('diff_jellyfin_cache.py -o -n ') 278 | sys.exit() 279 | elif opt == '-o': 280 | old_cache_path_str = arg 281 | elif opt == '-n': 282 | new_cache_path_str = arg 283 | 284 | if old_cache_path_str == '' or new_cache_path_str == '': 285 | print('enter both cache paths') 286 | return 287 | 288 | if not Path(old_cache_path_str).exists() or not Path(old_cache_path_str).is_dir() \ 289 | or not Path(new_cache_path_str).exists() or not Path(new_cache_path_str).is_dir(): 290 | print('cache paths aren\'t valid') 291 | return 292 | 293 | old_path = Path(old_cache_path_str) 294 | new_path = Path(new_cache_path_str) 295 | 296 | diff_data(old_path, new_path) 297 | 298 | 299 | if __name__ == "__main__": 300 | main(sys.argv[1:]) 301 | -------------------------------------------------------------------------------- /docs/_config.yml: -------------------------------------------------------------------------------- 1 | title: TV Intro Detection 2 | description: This project tries to detect intros of tv series by comparing pairs of episodes to find the largest common subset of frames. 3 | 4 | remote_theme: just-the-docs/just-the-docs 5 | 6 | # Color scheme supports "light" (default) and "dark" 7 | color_scheme: dark 8 | 9 | kramdown: 10 | syntax_highlighter_opts: 11 | block: 12 | line_numbers: false 13 | 14 | -------------------------------------------------------------------------------- /docs/docker.md: -------------------------------------------------------------------------------- 1 | # Running with Docker 2 | 3 | ### Docker Compose - Scanner & Skipper 4 | 5 | ``` 6 | --- 7 | version: "3.8" 8 | 9 | services: 10 | Jellyfin-Intro-Scanner: 11 | image: ghcr.io/mueslimak3r/jellyfin-intro-scanner:latest 12 | 13 | container_name: Jellyfin-Intro-Scanner 14 | environment: 15 | - JELLYFIN_URL=http://Jellyfin:port 16 | - JELLYFIN_USERNAME=username 17 | - JELLYFIN_PASSWORD=password 18 | volumes: 19 | - /path/to/media/on/host:/path/to/media/on/Jellyfin/container 20 | - /path/to/config:/app/config 21 | restart: unless-stopped 22 | 23 | Jellyfin-Intro-Skipper: 24 | image: ghcr.io/mueslimak3r/jellyfin-intro-skipper:latest 25 | 26 | container_name: Jellyfin-Intro-Skipper 27 | environment: 28 | - JELLYFIN_URL=http://Jellyfin:port 29 | - JELLYFIN_USERNAME=username 30 | - JELLYFIN_PASSWORD=password 31 | volumes: 32 | - /path/to/config:/app/config 33 | restart: unless-stopped 34 | ``` 35 | 36 | ### Docker Run - Scanner 37 | ``` 38 | docker run -d \ 39 | --name=Jellyfin-Intro-Scanner \ 40 | -e JELLYFIN_URL=http://Jellyfin:port \ 41 | -e JELLYFIN_USERNAME=username \ 42 | -e JELLYFIN_PASSWORD='password' \ 43 | -v /path/to/media/on/host:/path/to/media/on/Jellyfin/container \ 44 | -v /path/to/config:/app/config \ 45 | --restart unless-stopped \ 46 | ghcr.io/mueslimak3r/jellyfin-intro-scanner:latest 47 | ``` 48 | 49 | ### Docker Run - Skipper 50 | ``` 51 | docker run -d \ 52 | --name=Jellyfin-Intro-Skipper \ 53 | -e JELLYFIN_URL=http://Jellyfin:port \ 54 | -e JELLYFIN_USERNAME=username \ 55 | -e JELLYFIN_PASSWORD='password' \ 56 | -v /path/to/config:/app/config \ 57 | --restart unless-stopped \ 58 | ghcr.io/mueslimak3r/jellyfin-intro-skipper:latest 59 | ``` 60 | 61 | ### Parameters - used by both scanner and skipper 62 | 63 | | Parameter | Function | Description | 64 | |:-|:-:|-:| 65 | | Required | ```-e JELLYFIN_URL=http://Jellyfin:port``` | Jellyfin URL | 66 | |--- 67 | | Required | ```-e JELLYFIN_USERNAME=username``` | Jellyfin User Username | 68 | |--- 69 | | Required | ```-e JELLYFIN_PASSWORD='password'``` | Jellyfin User Password | 70 | |--- 71 | | Required | ```-v /path/to/config:/app/config``` | Location of config/data on disk. Must use the same locations for Jellyfin-Intro-Scanner & Jellyfin-Intro-Skipper containers to work correctly together. | 72 | |--- 73 | | Required | ```-v /path/to/media/on/host:/path/to/media/on/Jellyfin/container``` | Location of media library on disk. If you use the same volume path for your Jellyfin container, you don't have to edit ```path_map.txt``` in your config folder. (If you need to change it you must first create a ```path_map.txt``` in your config folder. ***Not in the data subfolder***). | 74 | |--- 75 | | Optional | ```-e REVERSE_SORT=TRUE``` | Process shows in reverse order | 76 | |--- 77 | | Optional | ```-e PATH_MAP="/srv/mount1/tv::/data/tv1,/srv/mount2/tv::/data/tv2"``` | Specify host:container path mapping. Mappings specified here are added to those specified in ```path_map.txt``` | 78 | |--- 79 | | Optional | ```-e CONFIG_DIR=/config``` | Use a different directory to store config files. The directory specified should be reflected in the ```/app/config``` path mapping. | 80 | |--- 81 | | Optional | ```-e DATA_DIR=/config/data``` | Use a different directory to store cached data. Modifying this will likely require a new path mapping such as ```-v /path/to/data:/data``` | 82 | |--- 83 | | Optional | ```-e LOG_LEVEL=INFO/VERBOSE/DEBUG``` | Change the log level (default is verbose for docker) | 84 | | Optional | ```-e AUTO_SKIP_COOLDOWN=4``` | Specify the cooldown time (seconds) for the auto skipper (default 2) | 85 | {:.table-striped} 86 | 87 | ### Docker with network shares 88 | 89 | Network shares need to be mounted with a driver. This example uses a Windows host, two SMB shares, and a local drive. 90 | 91 | ``` 92 | --- 93 | version: "3.8" 94 | 95 | volumes: 96 | mymount: 97 | name: mymount 98 | driver_opts: 99 | type: cifs 100 | o: "user=Guest,iocharset=utf8,vers=3.1.1,rw" 101 | device: //192.168.0.101/MyMount 102 | myothermount: 103 | name: myothermount 104 | driver_opts: 105 | type: cifs 106 | o: "user=Guest,iocharset=utf8,vers=3.1.1,rw" 107 | device: //192.168.0.102/MyOtherMount 108 | 109 | services: 110 | Jellyfin-Intro-Scanner: 111 | image: ghcr.io/mueslimak3r/jellyfin-intro-scanner:latest 112 | 113 | container_name: Jellyfin-Intro-Scanner 114 | environment: 115 | - JELLYFIN_URL=http://192.168.0.1212:8096 116 | - JELLYFIN_USERNAME=myuser 117 | - JELLYFIN_PASSWORD=mypassword 118 | - PATH_MAP=/mnt/mymount/TV::/jellyfin-mymount/TV,/mnt/myothermount/TV::/jellyfin-myothermount/TV,/mnt/x/TV/::/jellyfin-x/TV 119 | # - LOG_LEVEL=DEBUG 120 | volumes: 121 | - mymount:/mnt/mymount 122 | - myothermount:/mnt/myothermount 123 | - /x/TV:/mnt/x/TV 124 | - /c/Tools/Jellyfin-Intro-Skip/config:/app/config 125 | restart: unless-stopped 126 | 127 | Jellyfin-Intro-Skipper: 128 | image: ghcr.io/mueslimak3r/jellyfin-intro-skipper:latest 129 | 130 | container_name: Jellyfin-Intro-Skipper 131 | environment: 132 | - JELLYFIN_URL=http://192.168.0.1212:8096 133 | - JELLYFIN_USERNAME=myuser 134 | - JELLYFIN_PASSWORD=mypassword 135 | volumes: 136 | - /c/Tools/Jellyfin-Intro-Skip/config:/app/config 137 | restart: unless-stopped 138 | ``` 139 | -------------------------------------------------------------------------------- /docs/index.md: -------------------------------------------------------------------------------- 1 | # Project Overview 2 | 3 | This project tries to detect intros of tv series by comparing pairs of episodes to find the largest common subset of frames. 4 | 5 | ### How the script compares videos 6 | Each frame from the first quarter of each episode is extracted and a hash (https://pypi.org/project/ImageHash/) is made on the frame. Each frame hash is added to a long video hash.
7 | In pairs the longest identical string is searched from the two video hashes.
8 | Assumption: this is the intro 9 | 10 | ### How the script finds your videos 11 | When using jellyfin.py, the script queries the jellyfin server and is sent a list of all the tv shows in your library. With that list of shows, it then queries the jellyfin server for the seasons and episodes for each of the shows. Included in the results of those queries is the location on the filesystem for each item (show, season, episode). 12 | 13 | To account for jellyfin potentially using a different filesystem path to access the media than the system running the script would (eg: running in docker, running the script on a separate computer with the media drives mounted as network shares), path mapping is used to translate the path jellyfin sees into a path that the script can use. 14 | 15 | When running decode.py on its own, the -i parameter is used to specify a folder that contains video files. decode.py doesn't do any searching beyond that single folder, so typically the provided folder will be a "season folder" that contains all the video files for that season of a show. 16 | 17 | Individual shows or seasons can be ignored by creating an empty file named `.ignore-intros` inside its folder. 18 | 19 | ### Examples 20 | scan your jellyfin library, store the result in json, verbose logging enabled, logging debug output to file enabled 21 | 22 | ``` 23 | export JELLYFIN_URL="https://myurl" && export JELLYFIN_USERNAME="myusername" && export JELLYFIN_PASSWORD='mypassword' 24 | 25 | jellyfin.py -j -v -l 26 | ``` 27 | 28 | or in reverse order 29 | 30 | ``` 31 | jellyfin.py -j -v -l --reverse 32 | ``` 33 | 34 | monitor your jellyfin sessions and automatically skip intros using the stored json data 35 | 36 | ``` 37 | export JELLYFIN_URL="https://myurl" && export JELLYFIN_USERNAME="myusername" && export JELLYFIN_PASSWORD='mypassword' 38 | 39 | jellyfin_auto_skip.py 40 | ``` 41 | 42 | manually scan a directory containing at least 2 video files, debug logging enabled, logging debug output to file enabled, delete fingerprint data afterward 43 | 44 | ``` 45 | decode.py -i /path/to/tv/season -d -l -c 46 | ``` 47 | 48 | make the script aware of your host:container path mapping by editing `path_map.txt` 49 | 50 | ``` 51 | # use this file if you run jellyfin in a container 52 | # examples: 53 | # 54 | # linux client, Jellyfin on linux 55 | # 56 | # /host/system/tv/path::/jellyfin/container/tv/path 57 | # 58 | # or 59 | # Windows client, Jellyfin on Windows 60 | # 61 | # X:\some\path\TV::Y:\some\path\TV 62 | # 63 | # or 64 | # Windows client, Jellyfin on linux 65 | # 66 | # or 67 | # X:\some\path\TV::/jellyfin/container/tv/path 68 | ``` 69 | -------------------------------------------------------------------------------- /docs/troubleshooting.md: -------------------------------------------------------------------------------- 1 | # Troubleshooting 2 | If the `decode.py` script is killed while processing media you may encounter issues the next time you run it. This is because corrupt fingerprint files are likely left over from the killed session. 3 | Simply remove the directory fingerprints before running the script again. 4 | 5 | This can be avoided by using the "clean" flag `-c`, which clears the `/config/data/fingerprints` folder on startup and after completing. 6 | This issue is mostly only relevant when running `decode.py` on its own. Using `jellyfin.py` avoids the need to manage the `fingerprints` folder manually 7 | -------------------------------------------------------------------------------- /docs/usage.md: -------------------------------------------------------------------------------- 1 | # Running The Scripts 2 | 3 | 1. Install python3 (tested with 3.8.9+) 4 | 2. Install ffmpeg 5 | 3. Install python dependencies from `requirements.txt` 6 | 4. To use with Jellyfin, run `jellyfin.py`. This will query Jellyfin for a list of series and their paths. 7 | 5. To process a directory manually, run `decode.py` and pass the parameter `-i` with the path to a directory containing at least **two** episodes of the same season 8 | 9 | By default there is little/no output to stdout or stderr until the script has finished processing some media. Run `jellyfin.py` or `decode.py` with the `-d` parameter for verbose output 10 | 11 | When using `jellyfin.py`, the results can be saved to `json` using the `-j` parameter. These will be saved in a sub-directory in `pwd`. Saving the results as json also allows them to be checked in subsequent runs to skip already processed files. 12 | 13 | Individual shows or seasons can be ignored by creating an empty file named `.ignore-intros` inside its folder. 14 | 15 | ### Examples 16 | scan your jellyfin library, store the result in json, verbose logging enabled, logging debug output to file enabled 17 | 18 | ``` 19 | export JELLYFIN_URL="https://myurl" && export JELLYFIN_USERNAME="myusername" && export JELLYFIN_PASSWORD='mypassword' 20 | 21 | jellyfin.py -j -v -l 22 | ``` 23 | 24 | or in reverse order 25 | 26 | ``` 27 | jellyfin.py -j -v -l --reverse 28 | ``` 29 | 30 | monitor your jellyfin sessions and automatically skip intros using the stored json data 31 | 32 | ``` 33 | export JELLYFIN_URL="https://myurl" && export JELLYFIN_USERNAME="myusername" && export JELLYFIN_PASSWORD='mypassword' 34 | 35 | jellyfin_auto_skip.py 36 | ``` 37 | 38 | manually scan a directory containing at least 2 video files, debug logging enabled, logging debug output to file enabled, delete fingerprint data afterward 39 | 40 | ``` 41 | decode.py -i /path/to/tv/season -d -l -c 42 | ``` 43 | 44 | make the script aware of your host:container path mapping by editing `path_map.txt` 45 | 46 | ``` 47 | # use this file if you run jellyfin in a container 48 | # example: 49 | # /host/system/tv/path::/jellyfin/container/tv/path 50 | 51 | /srv/my-mnt-title/media/tv::/data/tv 52 | ``` 53 | -------------------------------------------------------------------------------- /ffmpeg_fingerprint.py: -------------------------------------------------------------------------------- 1 | import os 2 | import re 3 | import cv2 4 | import imagehash 5 | import sys 6 | import getopt 7 | from subprocess import Popen, PIPE, SubprocessError 8 | 9 | from pathlib import Path 10 | from PIL import Image 11 | from datetime import datetime 12 | 13 | config_path = Path(os.environ['CONFIG_DIR']) if 'CONFIG_DIR' in os.environ else Path(Path.cwd() / 'config') 14 | data_path = Path(os.environ['DATA_DIR']) if 'DATA_DIR' in os.environ else Path(config_path / 'data') 15 | 16 | session_timestamp = datetime.now().strftime("%Y_%m_%d-%I_%M_%S_%p") 17 | 18 | img_extension = '.jpeg' 19 | img_size = (384, 216) 20 | 21 | 22 | def print_debug(a=[], log=True, log_file=False): 23 | # Here a is the array holding the objects 24 | # passed as the argument of the function 25 | output = ' '.join([str(elem) for elem in a]) 26 | if log: 27 | print(output, file=sys.stderr) 28 | if log_file: 29 | log_path = config_path / 'logs' 30 | log_path.mkdir(parents=True, exist_ok=True) 31 | with (log_path / ('log_%s.txt' % session_timestamp)).open('a') as logger: 32 | logger.write(output + '\n') 33 | 34 | 35 | def write_fingerprint(path, fingerprint): 36 | Path(data_path / 'fingerprints' / replace(str(path))).mkdir(parents=True, exist_ok=True) 37 | path = Path(data_path / 'fingerprints' / replace(str(path)) / 'fingerprint.txt') 38 | with path.open('w+') as text_file: 39 | text_file.write(fingerprint) 40 | 41 | 42 | def replace(s): 43 | return re.sub('[^A-Za-z0-9]+', '', s) 44 | 45 | 46 | def get_frames(path, hash_fps, frame_nb, log_level, log_file): 47 | if path is None or path == '' or frame_nb == 0: 48 | return False 49 | print_debug(a=['running ffmpeg'], log=log_level > 0, log_file=log_file) 50 | start = datetime.now() 51 | 52 | command = ["ffmpeg", "-i", path, "-vf", 'fps=%s' % str(hash_fps), "-frames:v", str(frame_nb), "-f", "image2pipe", "-pix_fmt", "rgb24", "-vcodec", "rawvideo", "-s", "384x216", "-"] 53 | 54 | with Path(os.devnull).open('w') as devnull_fp: 55 | proc = Popen(command, stdout=PIPE, stderr=devnull_fp, bufsize=10**8) 56 | 57 | filein = proc.stdout 58 | bytes_list = [] 59 | for _ in range(frame_nb): 60 | try: 61 | output = filein.read(img_size[0] * img_size[1] * 3) 62 | except SubprocessError as err: 63 | filein.close() 64 | proc.kill() 65 | return [], False 66 | bytes_list.append(output) 67 | filein.close() 68 | proc.wait() 69 | end = datetime.now() 70 | print_debug(a=["ran ffmpeg in %s" % str(end - start)], log=log_level > 0, log_file=log_file) 71 | return bytes_list, proc.returncode == 0 72 | 73 | 74 | def get_fingerprint_ffmpeg(path, hash_fps, frame_nb, log_level=1, log_file=False, log_timestamp=None): 75 | global session_timestamp 76 | 77 | if path is None or path == '' or frame_nb == 0: 78 | return [] 79 | 80 | if log_timestamp is not None: 81 | session_timestamp = log_timestamp 82 | 83 | bytes_list, ret = get_frames(path, hash_fps, frame_nb, log_level, log_file) 84 | 85 | if not bytes_list or not ret: 86 | print_debug(a=['ffmpeg error'], log=log_level > 0, log_file=log_file) 87 | return [] 88 | 89 | fingerprint_str = "" 90 | fingerprint_list = [] 91 | 92 | start = datetime.now() 93 | ndx = 0 94 | for frame_bytes in bytes_list: 95 | img = Image.frombytes('RGB', img_size, frame_bytes) 96 | frame_fingerprint = imagehash.dhash(img) 97 | fingerprint_str += str(frame_fingerprint) 98 | fingerprint_list.append(frame_fingerprint) 99 | ndx += 1 100 | 101 | if fingerprint_str != '': 102 | write_fingerprint(path, fingerprint_str) 103 | end = datetime.now() 104 | print_debug(a=["made hash in %s" % str(end - start)], log=log_level > 0, log_file=log_file) 105 | return fingerprint_list 106 | 107 | 108 | def main(argv): 109 | 110 | dir = '' 111 | log_level = 0 112 | try: 113 | opts, args = getopt.getopt(argv, "hi:dvc") 114 | except getopt.GetoptError: 115 | print_debug(['decode.py -i -v (verbose - some logging) -d (debug - most logging) -c (cleanup) -s (slow mode)\n']) 116 | sys.exit(2) 117 | 118 | for opt, arg in opts: 119 | if opt == '-h': 120 | print_debug(['decode.py -i -v (verbose - some logging) -d (debug - most logging) -c (cleanup) -s (slow mode)\n']) 121 | sys.exit() 122 | elif opt == '-i': 123 | dir = arg 124 | elif opt == '-d': 125 | log_level = 2 126 | elif opt == '-v': 127 | log_level = 1 128 | 129 | if dir == '' or not Path(dir).is_dir(): 130 | print_debug(['decode.py -i -v (verbose - some logging) -d (debug - most logging) -c (cleanup) -s (slow mode)\n']) 131 | sys.exit(2) 132 | 133 | common_video_extensions = ['.webm', '.mkv', '.avi', '.mts', '.m2ts', '.ts', '.mov', '.wmv', '.mp4', '.m4v', '.mpg', '.mpeg', '.m2v'] 134 | 135 | if Path(dir).is_dir(): 136 | start = datetime.now() 137 | for child in Path(dir).iterdir(): 138 | if child.name[0] == '.': 139 | continue 140 | matched_ext = False 141 | for ext in common_video_extensions: 142 | if child.name.endswith(ext): 143 | matched_ext = True 144 | if matched_ext: 145 | max_fingerprint_mins = 10 146 | path = str(child.resolve()) 147 | video = cv2.VideoCapture(path) 148 | frames = int(video.get(cv2.CAP_PROP_FRAME_COUNT)) 149 | fps = video.get(cv2.CAP_PROP_FPS) 150 | quarter_frames_or_first_X_mins = min(int(frames / 4), int(fps * 60 * max_fingerprint_mins)) 151 | video.release() 152 | result = get_fingerprint_ffmpeg(path, quarter_frames_or_first_X_mins, log_level, True, None) 153 | end = datetime.now() 154 | print_debug(["total runtime %s" % str(end - start)]) 155 | else: 156 | print_debug(['input directory invalid or cannot be accessed']) 157 | return {} 158 | 159 | 160 | if __name__ == "__main__": 161 | main(sys.argv[1:]) 162 | -------------------------------------------------------------------------------- /jellyfin.py: -------------------------------------------------------------------------------- 1 | import os 2 | import re 3 | import sys 4 | import getopt 5 | 6 | import jellyfin_queries 7 | import json 8 | import shutil 9 | import hashlib 10 | 11 | 12 | from time import sleep 13 | from math import floor 14 | from pathlib import Path 15 | from datetime import datetime 16 | from jellyfin_api_client import jellyfin_login, jellyfin_logout 17 | from decode import process_directory, read_fingerprint, create_video_fingerprint 18 | 19 | server_url = os.environ['JELLYFIN_URL'] if 'JELLYFIN_URL' in os.environ else '' 20 | server_username = os.environ['JELLYFIN_USERNAME'] if 'JELLYFIN_USERNAME' in os.environ else '' 21 | server_password = os.environ['JELLYFIN_PASSWORD'] if 'JELLYFIN_PASSWORD' in os.environ else '' 22 | env_path_map_str = os.environ['PATH_MAP'] if 'PATH_MAP' in os.environ else '' 23 | env_reverse_sort_str = os.environ['REVERSE_SORT'] if 'REVERSE_SORT' in os.environ else '' 24 | env_log_level_str = os.environ['LOG_LEVEL'] if 'LOG_LEVEL' in os.environ else '' 25 | 26 | 27 | config_path = Path(os.environ['CONFIG_DIR']) if 'CONFIG_DIR' in os.environ else Path(Path.cwd() / 'config') 28 | data_path = Path(os.environ['DATA_DIR']) if 'DATA_DIR' in os.environ else Path(config_path / 'data') 29 | 30 | minimum_episode_duration = 15 # minutes 31 | maximum_episodes_per_season = 30 # meant to skip daily shows like jeopardy 32 | sleep_after_finish_sec = 300 # sleep for 5 minutes after the script finishes. If it runs automatically this prevents it rapidly looping 33 | 34 | session_timestamp = datetime.now().strftime("%Y_%m_%d-%I_%M_%S_%p") 35 | 36 | hash_fps = 2 37 | 38 | revision_id = 2.0 39 | 40 | 41 | def print_debug(a=[], log=True, log_file=False): 42 | # Here a is the array holding the objects 43 | # passed as the argument of the function 44 | output = ' '.join([str(elem) for elem in a]) 45 | if log: 46 | print(output, file=sys.stderr) 47 | if log_file: 48 | log_path = config_path / 'logs' 49 | log_path.mkdir(parents=True, exist_ok=True) 50 | with (log_path / ('log_%s.txt' % session_timestamp)).open('a') as logger: 51 | logger.write(output + '\n') 52 | 53 | 54 | def replace(s): 55 | return re.sub('[^A-Za-z0-9]+', '', s) 56 | 57 | 58 | def get_path_map(log_level=0): 59 | path_map = [] 60 | 61 | if env_path_map_str != '': 62 | env_maps = env_path_map_str.strip().split(',') 63 | for m in env_maps: 64 | map = m.strip().split('::') 65 | if len(map) != 2: 66 | continue 67 | path_map.append((Path(map[0].replace('\\', '/')), Path(map[1].replace('\\', '/')))) 68 | 69 | if (config_path / 'path_map.txt').exists(): 70 | with (config_path / 'path_map.txt').open('r') as file: 71 | for line in file: 72 | if line.startswith('#'): 73 | continue 74 | map = line.strip().split('::') 75 | if len(map) != 2: 76 | continue 77 | path_map.append((Path(map[0].replace('\\', '/')), Path(map[1].replace('\\', '/')))) 78 | 79 | if log_level > 1: 80 | print_debug(a=['path maps: %s' % path_map], log=True) 81 | for path in path_map: 82 | if Path(path[0]).exists() and Path(path[0]).is_dir(): 83 | print_debug(a=['top level contents of mapped path [%s]' % str(path[0])], log=True) 84 | for child in Path(path[0]).iterdir(): 85 | print_debug(a=[str(child.resolve())], log=True) 86 | else: 87 | print_debug(a=['mapped path [%s] isn\'t accessible' % str(path[0])], log=True) 88 | 89 | if Path(path[1]).exists() and Path(path[1]).is_dir(): 90 | print_debug(a=['top level contents of mapped path [%s]' % str(path[1])], log=True) 91 | for child in Path(path[1]).iterdir(): 92 | print_debug(a=[str(child.resolve())], log=True) 93 | else: 94 | print_debug(a=['mapped path [%s] isn\'t accessible' % str(path[1])], log=True) 95 | 96 | return path_map 97 | 98 | 99 | def check_season_valid(season=None, episodes=[], repair=False, debug=False): 100 | if season is None or not episodes: 101 | return [] 102 | 103 | path = data_path / 'jellyfin_cache' / str(season['SeriesId']) / str(season['SeasonId']) 104 | 105 | filtered_episodes = [] 106 | failed_to_find_files = False 107 | 108 | if path.exists(): 109 | for episode in episodes: 110 | if not Path(episode['Path']).exists(): 111 | failed_to_find_files = True 112 | continue 113 | 114 | should_add = True 115 | if Path(path / (str(episode['EpisodeId']) + '.json')).exists(): 116 | should_add = False 117 | if repair: 118 | with Path(path / (str(episode['EpisodeId']) + '.json')).open('r') as json_file: 119 | profile = json.load(json_file) 120 | if 'start_frame' in profile and 'end_frame' in profile: 121 | start_frame = int(profile['start_frame']) 122 | end_frame = int(profile['end_frame']) 123 | if start_frame == 0 and end_frame == 0: 124 | should_add = True 125 | print_debug(a=['will repair ep [%s] of season [%s] of show [%s]' % (episode['Name'], season['Name'], season['SeriesName'])], log=debug, log_file=debug) 126 | if should_add: 127 | filtered_episodes.append(episode) 128 | else: 129 | for episode in episodes: 130 | if not Path(episode['Path']).exists(): 131 | failed_to_find_files = True 132 | continue 133 | filtered_episodes.append(episode) 134 | 135 | if failed_to_find_files: 136 | print_debug(a=['skipping season [%s] of show [%s] - failed to access some of the media files' % (season['Name'], season['SeriesName'])], log=debug, log_file=debug) 137 | print_debug(a=['path for the first episode [%s]' % episodes[0]['Path']], log=debug, log_file=debug) 138 | 139 | if not filtered_episodes: 140 | return [] 141 | if len(filtered_episodes) > maximum_episodes_per_season: 142 | print_debug(a=['skipping season [%s] of show [%s] - it contains %s episodes (more than max %s)' % (season['Name'], season['SeriesName'], len(filtered_episodes), maximum_episodes_per_season)], log=debug, log_file=debug) 143 | return [] 144 | 145 | duration_mins = int(filtered_episodes[0]['Duration']) 146 | if duration_mins > 0: 147 | duration_mins = duration_mins / 60 / 1000 148 | if filtered_episodes[0]['Duration'] < minimum_episode_duration * 60 * 1000: 149 | print_debug(a=['skipping season [%s] of show [%s] - episodes are too short (%s minutes) (less than minimum %s minutes)' % (season['Name'], season['SeriesName'], duration_mins, minimum_episode_duration)], log=debug, log_file=debug) 150 | return [] 151 | 152 | season_hash_exists = 1 if season['SeasonFingerprint'] is not None else 0 153 | if len(filtered_episodes) + season_hash_exists < 2: 154 | print_debug(a=['skipping season [%s] of show [%s] - it doesn\'t contain at least 2 episodes' % (season['Name'], season['SeriesName'])], log=debug, log_file=debug) 155 | return [] 156 | 157 | if len(filtered_episodes) > 0 and len(episodes) - len(filtered_episodes) > 0: 158 | print_debug(a=['season [%s] of show [%s] - will skip %s of %s episodes' % (season['Name'], season['SeriesName'], len(episodes) - len(filtered_episodes), len(episodes))], log=True, log_file=debug) 159 | return filtered_episodes 160 | 161 | 162 | def get_file_paths(season=None): 163 | if season is None or 'Episodes' not in season: 164 | return [] 165 | 166 | file_paths = [] 167 | for episode in season['Episodes']: 168 | file_paths.append(episode['Path']) 169 | return file_paths 170 | 171 | 172 | def check_if_in_list_of_dict(dict_list, value): 173 | if dict_list is None: 174 | return -1 175 | 176 | for ndx in range(0, len(dict_list)): 177 | if value in dict_list[ndx].values(): 178 | return ndx 179 | return -1 180 | 181 | 182 | def remake_season_fingerprint(episodes=[], season_fingerprint=None, debug=False): 183 | if not episodes: 184 | return None 185 | 186 | ndx = -1 187 | if 'EpisodeId' in season_fingerprint: 188 | ep_id = season_fingerprint['EpisodeId'] 189 | ndx = check_if_in_list_of_dict(episodes, ep_id) 190 | 191 | if ndx == -1 and 'Name' in season_fingerprint: 192 | ndx = check_if_in_list_of_dict(episodes, season_fingerprint['Name']) 193 | 194 | if ndx == -1: 195 | trimmed_path = season_fingerprint['Path' if 'Path' in season_fingerprint else 'path'].split('/')[-1] 196 | for i in range(0, len(episodes)): 197 | if trimmed_path in str(episodes[i]['Path']): 198 | ndx = i 199 | break 200 | 201 | if ndx == -1: 202 | print_debug(a=['failed to match season fingerprint to episode in jellyfin'], log=debug, log_file=debug) 203 | return None 204 | 205 | profile = season_fingerprint 206 | profile.update(episodes[ndx]) 207 | if 'path' in profile: 208 | profile.pop('path', None) 209 | profile['fingerprint'] = None 210 | profile['revision_id'] = revision_id 211 | 212 | fingerprint = create_video_fingerprint(profile, hash_fps, 2 if debug else 0, debug) 213 | 214 | if not fingerprint: 215 | print_debug(a=['failed to create new fingerprint'], log=debug, log_file=debug) 216 | return None 217 | 218 | tmp_start_frame = floor((profile['start_frame'] / profile['fps']) * hash_fps) if profile['start_frame'] > 0 else 0 219 | tmp_end_frame = floor((profile['end_frame'] / profile['fps']) * hash_fps) if profile['end_frame'] > 0 else 0 220 | 221 | try: 222 | trimmed_fingerprint = fingerprint[tmp_start_frame:tmp_end_frame + 1] 223 | fingerprint_str = '' 224 | for f in trimmed_fingerprint: 225 | fingerprint_str += str(f) 226 | profile['fingerprint'] = fingerprint_str 227 | profile['hash_fps'] = hash_fps 228 | return profile 229 | except BaseException as err: 230 | print_debug(a=['failed to trim new fingerprint'], log=debug, log_file=debug) 231 | return None 232 | 233 | 234 | def intro_duration(profile): 235 | intro_duration = profile['end_frame'] - profile['start_frame'] 236 | if intro_duration < 0: 237 | intro_duration = 0 238 | return intro_duration 239 | 240 | 241 | def get_season_fingerprint(season=None, episodes=[], debug=False): 242 | if season is None: 243 | return None 244 | 245 | season_fp_dict = None 246 | path = Path(data_path / 'jellyfin_cache' / str(season['SeriesId']) / str(season['SeasonId']) / ('season' + '.json')) 247 | if path.exists(): 248 | with path.open('r') as json_file: 249 | season_fp_dict = json.load(json_file) 250 | 251 | if season_fp_dict is None: 252 | return None 253 | 254 | fingerprint_list = [] 255 | if 'revision_id' in season_fp_dict and season_fp_dict['revision_id'] == revision_id \ 256 | and 'fingerprint' in season_fp_dict and \ 257 | 'hash_fps' in season_fp_dict and season_fp_dict['hash_fps'] == hash_fps: 258 | fingerprint_list = read_fingerprint(season_fp_dict['fingerprint'], 2 if debug else 0, debug) 259 | 260 | profile_modified = False 261 | 262 | if fingerprint_list and abs(len(fingerprint_list) - floor(intro_duration(season_fp_dict) / (season_fp_dict['fps'] / hash_fps))) > 2: 263 | print_debug(a=['season fingerprint is wrong length %s instead of %s for season %s of show %s' % (len(fingerprint_list), 264 | floor(intro_duration(season_fp_dict) / (season_fp_dict['fps'] / hash_fps)), 265 | season['Name'], season['SeriesName'])], log=debug, log_file=debug) 266 | 267 | if not fingerprint_list or abs(len(fingerprint_list) - floor(intro_duration(season_fp_dict) / (season_fp_dict['fps'] / hash_fps))) > 2: 268 | print_debug(a=['trying to remake season fingerprint for season %s of show %s' % (season['Name'], season['SeriesName'])], log=debug, log_file=debug) 269 | season_fp_dict = remake_season_fingerprint(episodes, season_fp_dict, debug) 270 | profile_modified = True 271 | else: 272 | print_debug(a=['found valid season fingerprint for season %s of show %s' % (season['Name'], season['SeriesName'])], log=debug, log_file=debug) 273 | 274 | if profile_modified and season_fp_dict is not None: 275 | with path.open('w+') as json_file: 276 | json.dump(season_fp_dict, json_file, indent=4) 277 | return season_fp_dict 278 | 279 | 280 | def get_jellyfin_shows(reverse_sort=False, repair=False, log_level=0, log_file=False): 281 | if server_url == '' or server_username == '' or server_password == '': 282 | print_debug(a=['missing server info']) 283 | return 284 | 285 | path_map = get_path_map(log_level) 286 | 287 | client = jellyfin_login(server_url, server_username, server_password, "TV Intro Detection Scanner") 288 | shows_query = jellyfin_queries.get_shows(client, path_map, reverse_sort) 289 | if not shows_query: 290 | print_debug(a=['Error - got 0 shows from jellyfin']) 291 | return [] 292 | print_debug(a=['jellyfin has %s shows' % len(shows_query)]) 293 | if repair: 294 | print_debug(a=['repair mode is enabled']) 295 | 296 | shows = [] 297 | season_count = 0 298 | episode_count = 0 299 | for show in shows_query: 300 | should_skip_series = False 301 | if 'Path' in show and show['Path'] and Path(show['Path']).is_dir(): 302 | for child in Path(show['Path']).iterdir(): 303 | if child.name == '.ignore-intros': 304 | print_debug(a=['ignoring series [%s]' % show['Name']], log=log_level > 0) 305 | should_skip_series = True 306 | break 307 | if should_skip_series: 308 | continue 309 | 310 | seasons = [] 311 | seasons_query = jellyfin_queries.get_seasons(client, path_map, show) 312 | 313 | if not seasons_query: 314 | continue 315 | 316 | for season in seasons_query: 317 | should_skip_season = False 318 | if 'Path' in season and season['Path'] and Path(season['Path']).is_dir(): 319 | for child in Path(season['Path']).iterdir(): 320 | if child.name == '.ignore-intros': 321 | print_debug(a=['ignoring season [%s] of show [%s]' % (season['Name'], show['Name'])], log=log_level > 0) 322 | should_skip_season = True 323 | break 324 | if should_skip_season: 325 | continue 326 | 327 | episodes = jellyfin_queries.get_episodes(client, path_map, season) 328 | if not episodes: 329 | continue 330 | 331 | season['SeasonFingerprint'] = get_season_fingerprint(season=season, episodes=episodes, debug=log_level > 1) 332 | 333 | season['Episodes'] = check_season_valid(season, episodes, repair, debug=log_level > 1) 334 | if season['Episodes']: 335 | episode_count += len(season['Episodes']) 336 | seasons.append(season) 337 | if seasons: 338 | season_count += len(seasons) 339 | show['Seasons'] = seasons 340 | shows.append(show) 341 | 342 | jellyfin_logout() 343 | 344 | print_debug(a=['found %s qualifying shows' % len(shows)], log_file=log_file and episode_count > 0) 345 | print_debug(a=['found %s qualifying seasons' % season_count], log_file=log_file and episode_count > 0) 346 | print_debug(a=['found %s qualifying episodes\n' % episode_count], log_file=log_file and episode_count > 0) 347 | 348 | return shows 349 | 350 | 351 | def copy_season_fingerprint(result: list = [], dir_path: Path = None, debug: bool = False, log_file: bool = False): 352 | if not result or dir_path is None: 353 | return 354 | 355 | name = '' 356 | for profile in result: 357 | name += replace(profile['Path']) 358 | hash_object = hashlib.md5(name.encode()) 359 | name = hash_object.hexdigest() 360 | 361 | src_path = Path(data_path / 'fingerprints' / (name + '.json')) 362 | dst_path = Path(dir_path / ('season' + '.json')) 363 | dir_path.mkdir(parents=True, exist_ok=True) 364 | if src_path.exists(): 365 | if debug: 366 | print_debug(a=['saving season fingerprint to jellyfin_cache'], log_file=log_file) 367 | shutil.copyfile(src_path, dst_path) 368 | 369 | 370 | def save_season(season=None, result=None, save_json=False, debug=False, log_file=False): 371 | if not result or season is None: 372 | return 373 | path = data_path / 'jellyfin_cache' / str(season['SeriesId']) / str(season['SeasonId']) 374 | if save_json: 375 | copy_season_fingerprint(result, path, debug, log_file) 376 | 377 | for ndx in range(0, len(season['Episodes'])): 378 | if ndx >= len(result): 379 | if debug: 380 | print_debug(a=['episode index past bounds of result'], log_file=log_file) 381 | break 382 | if season['Episodes'][ndx]['Path'] == result[ndx]['Path']: 383 | season['Episodes'][ndx].update(result[ndx]) 384 | print(season['Episodes'][ndx]) 385 | season['Episodes'][ndx]['created'] = str(datetime.now()) 386 | if save_json: 387 | Path(path).mkdir(parents=True, exist_ok=True) 388 | with Path(path / (str(season['Episodes'][ndx]['EpisodeId']) + '.json')).open('w+') as json_file: 389 | json.dump(season['Episodes'][ndx], json_file, indent=4) 390 | elif debug: 391 | print_debug(a=['index mismatch'], log_file=log_file) 392 | 393 | 394 | def process_jellyfin_shows(log_level=0, log_file=False, save_json=False, reverse_sort=False, repair=False): 395 | start = datetime.now() 396 | print_debug(a=["\n\nstarted new session at %s\n" % start]) 397 | if reverse_sort: 398 | print_debug(['will process shows in reverse order']) 399 | 400 | shows = get_jellyfin_shows(reverse_sort, repair, log_level, log_file) 401 | 402 | if (data_path / 'fingerprints').is_dir(): 403 | try: 404 | shutil.rmtree(data_path / 'fingerprints') 405 | except OSError as e: 406 | print_debug(a=["Error: %s : %s" % ('deleting fingerprints directory', e.strerror)], log_file=log_file) 407 | 408 | show_ndx = 0 409 | total_processed = 0 410 | for show in shows: 411 | show_ndx += 1 412 | show_start_time = datetime.now() 413 | 414 | print_debug(a=['%s/%s - %s' % (show_ndx, len(shows), show['Name'])], log_file=log_file) 415 | 416 | season_ndx = 1 417 | for season in show['Seasons']: 418 | season_ndx += 1 419 | 420 | season_start_time = datetime.now() 421 | file_paths = get_file_paths(season) 422 | result = [] 423 | 424 | if file_paths: 425 | print_debug(a=['%s/%s - %s - %s episodes' % (season_ndx, len(show['Seasons']), season['Name'], len(season['Episodes']))], log_file=log_file) 426 | result = process_directory(profiles=season['Episodes'], ref_profile=season['SeasonFingerprint'], hashfps=hash_fps, 427 | cleanup=False, log_level=log_level, log_file=log_file, log_timestamp=session_timestamp) 428 | if result: 429 | save_season(season, result, save_json, log_level > 0, log_file) 430 | total_processed += len(result) 431 | else: 432 | print_debug(a=['no results - the decoder may not have access to the specified media files'], log_file=log_file) 433 | if (data_path / 'fingerprints').is_dir(): 434 | try: 435 | shutil.rmtree(data_path / 'fingerprints') 436 | except OSError as e: 437 | print_debug(a=["Error: %s : %s" % ('deleting fingerprints directory', e.strerror)], log_file=log_file) 438 | season_end_time = datetime.now() 439 | if result: 440 | print_debug(a=['processed season [%s] in %s' % (season['Name'], str(season_end_time - season_start_time))], log_file=log_file) 441 | if file_paths: 442 | sleep(2) 443 | show_end_time = datetime.now() 444 | print_debug(a=['processed show [%s] in %s\n' % (show['Name'], str(show_end_time - show_start_time))], log_file=log_file) 445 | 446 | end = datetime.now() 447 | print_debug(a=["total runtime: " + str(end - start)], log_file=log_file and total_processed > 0) 448 | if sleep_after_finish_sec > 0: 449 | print_debug(a=['sleeping for %s seconds' % sleep_after_finish_sec]) 450 | sleep(300) 451 | 452 | 453 | def main(argv): 454 | log_level = 0 455 | save_json = False 456 | log = False 457 | reverse_sort = False 458 | repair = False 459 | 460 | try: 461 | opts, args = getopt.getopt(argv, "hdvjlr", ["reverse", "repair"]) 462 | except getopt.GetoptError: 463 | print_debug(['jellyfin.py -d (debug) -j (save json) -l (log to file)']) 464 | print_debug(['saving to json is currently the only way to skip previously processed files in subsequent runs\n']) 465 | sys.exit(2) 466 | 467 | for opt, arg in opts: 468 | if opt == '-h': 469 | print_debug(['jellyfin.py -d (debug) -j (save json) -l (log to file)']) 470 | print_debug(['saving to json is currently the only way to skip previously processed files in subsequent runs\n']) 471 | sys.exit() 472 | elif opt == '-d': 473 | log_level = 2 474 | elif opt == '-v': 475 | log_level = 1 476 | elif opt == '-j': 477 | save_json = True 478 | elif opt == '-l': 479 | log = True 480 | elif opt in ("-r", "--reverse"): 481 | reverse_sort = True 482 | elif opt in ("--repair"): 483 | repair = True 484 | 485 | if server_url == '' or server_username == '' or server_password == '': 486 | print_debug(['you need to export env variables: JELLYFIN_URL, JELLYFIN_USERNAME, JELLYFIN_PASSWORD\n']) 487 | return 488 | 489 | if env_reverse_sort_str == 'TRUE': 490 | reverse_sort = True 491 | elif env_reverse_sort_str == 'FALSE': 492 | reverse_sort = False 493 | 494 | if env_log_level_str == 'DEBUG': 495 | log_level = 2 496 | elif env_log_level_str == 'VERBOSE': 497 | log_level = 1 498 | elif env_log_level_str == 'INFO': 499 | log_level = 0 500 | process_jellyfin_shows(log_level, log, save_json, reverse_sort, repair) 501 | 502 | 503 | if __name__ == "__main__": 504 | main(sys.argv[1:]) 505 | -------------------------------------------------------------------------------- /jellyfin_api_client.py: -------------------------------------------------------------------------------- 1 | ''' 2 | Big thanks to the jellyfin/jellyfin-mpv-shim devs for most of the code in this file! 3 | Adapted from: 4 | https://github.com/jellyfin/jellyfin-mpv-shim/blob/ed8a61d6984c79ac81ef9db1f84af940ca036e0f/jellyfin_mpv_shim/clients.py 5 | Main project: 6 | https://github.com/jellyfin/jellyfin-mpv-shim 7 | ''' 8 | 9 | import sys 10 | import json 11 | import uuid as UUID 12 | import time 13 | import logging 14 | import re 15 | import os 16 | 17 | from pathlib import Path 18 | from jellyfin_apiclient_python import JellyfinClient 19 | from jellyfin_apiclient_python.connection_manager import CONNECTION_STATE 20 | from getpass import getpass 21 | from typing import Optional 22 | 23 | # server_url = os.environ['JELLYFIN_URL'] 24 | # server_username = os.environ['JELLYFIN_USERNAME'] 25 | # server_password = os.environ['JELLYFIN_PASSWORD'] 26 | 27 | jellyfin_client_manager = None 28 | jellyfin_current_client = None 29 | 30 | global_app_name = "tv-intro-detection" 31 | global_user_app_name = "TV Intro Detection" 32 | 33 | CLIENT_VERSION = "0.0.1" 34 | USER_AGENT = "%s/%s" % (global_user_app_name, CLIENT_VERSION) 35 | CAPABILITIES = { 36 | "PlayableMediaTypes": "", 37 | "SupportsMediaControl": False, 38 | "SupportedCommands": (), 39 | } 40 | 41 | connect_retry_mins = 0 42 | 43 | ignore_ssl_cert = False 44 | config_path = Path(os.environ['CONFIG_DIR']) if 'CONFIG_DIR' in os.environ else Path(Path.cwd() / 'config') 45 | 46 | credentials_location = Path(config_path / (global_app_name + '-cred.json')) 47 | 48 | log = logging.getLogger("clients") 49 | path_regex = re.compile("^(https?://)?([^/:]+)(:[0-9]+)?(/.*)?$") 50 | 51 | 52 | def expo(max_value: Optional[int] = None): 53 | n = 0 54 | while True: 55 | a = 2 ** n 56 | if max_value is None or a < max_value: 57 | yield a 58 | n += 1 59 | else: 60 | yield max_value 61 | 62 | 63 | class ClientManager(object): 64 | def __init__(self): 65 | self.callback = lambda client, event_name, data: None 66 | self.credentials = [] 67 | self.clients = {} 68 | self.usernames = {} 69 | self.is_stopping = False 70 | 71 | def cli_connect(self): 72 | is_logged_in = self.try_connect() 73 | add_another = False 74 | 75 | if "add" in sys.argv: 76 | add_another = True 77 | 78 | while not is_logged_in or add_another: 79 | server = input(_("Server URL: ")) 80 | username = input(_("Username: ")) 81 | password = getpass(_("Password: ")) 82 | 83 | is_logged_in = self.login(server, username, password) 84 | 85 | if is_logged_in: 86 | log.info(_("Successfully added server.")) 87 | add_another = input(_("Add another server?") + " [y/N] ") 88 | add_another = add_another in ("y", "Y", "yes", "Yes") 89 | else: 90 | log.warning(_("Adding server failed.")) 91 | 92 | @staticmethod 93 | def client_factory(): 94 | uuid = str(UUID.uuid4()) 95 | if Path(config_path / (global_app_name + '-uuid.txt')).exists(): 96 | with Path(config_path / (global_app_name + '-uuid.txt')).open('r') as uuid_file: 97 | uuid = uuid_file.read() 98 | else: 99 | with Path(config_path / (global_app_name + '-uuid.txt')).open('w+') as uuid_file: 100 | uuid_file.write(uuid) 101 | client = JellyfinClient(allow_multiple_clients=True) 102 | client.config.data["app.default"] = True 103 | client.config.app( 104 | global_user_app_name, CLIENT_VERSION, global_user_app_name, uuid 105 | ) 106 | client.config.data["http.user_agent"] = USER_AGENT 107 | client.config.data["auth.ssl"] = not ignore_ssl_cert 108 | return client 109 | 110 | def _connect_all(self): 111 | is_logged_in = False 112 | for server in self.credentials: 113 | if self.connect_client(server): 114 | is_logged_in = True 115 | return is_logged_in 116 | 117 | def try_connect(self): 118 | if credentials_location.exists(): 119 | with credentials_location.open('r') as cf: 120 | self.credentials = json.load(cf) 121 | 122 | if "Servers" in self.credentials: 123 | credentials_old = self.credentials 124 | self.credentials = [] 125 | for server in credentials_old["Servers"]: 126 | server["uuid"] = str(UUID.uuid4()) 127 | server["username"] = "" 128 | self.credentials.append(server) 129 | 130 | is_logged_in = self._connect_all() 131 | if connect_retry_mins and not is_logged_in: 132 | log.warning( 133 | "Connection failed. Will retry for {0} minutes.".format( 134 | connect_retry_mins 135 | ) 136 | ) 137 | for attempt in range(connect_retry_mins * 2): 138 | time.sleep(30) 139 | is_logged_in = self._connect_all() 140 | if is_logged_in: 141 | break 142 | 143 | return is_logged_in 144 | 145 | def save_credentials(self): 146 | if credentials_location.exists(): 147 | with credentials_location.open('w') as cf: 148 | json.dump(self.credentials, cf) 149 | 150 | def login( 151 | self, server: str, username: str, password: str, force_unique: bool = False 152 | ): 153 | if server.endswith("/"): 154 | server = server[:-1] 155 | 156 | protocol, host, port, path = path_regex.match(server).groups() 157 | 158 | if not protocol: 159 | log.warning("Adding http:// because it was not provided.") 160 | protocol = "http://" 161 | 162 | if protocol == "http://" and not port: 163 | log.warning("Adding port 8096 for insecure local http connection.") 164 | log.warning( 165 | "If you want to connect to standard http port 80, use :80 in the url." 166 | ) 167 | port = ":8096" 168 | 169 | server = "".join(filter(bool, (protocol, host, port, path))) 170 | 171 | client = self.client_factory() 172 | client.auth.connect_to_address(server) 173 | result = client.auth.login(server, username, password) 174 | if "AccessToken" in result: 175 | credentials = client.auth.credentials.get_credentials() 176 | server = credentials["Servers"][0] 177 | if force_unique: 178 | server["uuid"] = server["Id"] 179 | else: 180 | server["uuid"] = str(UUID.uuid4()) 181 | server["username"] = username 182 | if force_unique and server["Id"] in self.clients: 183 | return client 184 | self.connect_client(server) 185 | self.credentials.append(server) 186 | self.save_credentials() 187 | return client 188 | return None 189 | 190 | def setup_client(self, client: "JellyfinClient", server): 191 | def event(event_name, data): 192 | if event_name == "WebSocketDisconnect": 193 | timeout_gen = expo(100) 194 | if server["uuid"] in self.clients: 195 | while not self.is_stopping: 196 | timeout = next(timeout_gen) 197 | log.info( 198 | "No connection to server. Next try in {0} second(s)".format( 199 | timeout 200 | ) 201 | ) 202 | self._disconnect_client(server=server) 203 | time.sleep(timeout) 204 | if self.connect_client(server): 205 | break 206 | else: 207 | self.callback(client, event_name, data) 208 | 209 | client.callback = event 210 | client.callback_ws = event 211 | client.start(websocket=True) 212 | 213 | client.jellyfin.post_capabilities(CAPABILITIES) 214 | 215 | def remove_client(self, uuid: str): 216 | self.credentials = [ 217 | server for server in self.credentials if server["uuid"] != uuid 218 | ] 219 | self.save_credentials() 220 | self._disconnect_client(uuid=uuid) 221 | 222 | def connect_client(self, server): 223 | if self.is_stopping: 224 | return False 225 | 226 | is_logged_in = False 227 | client = self.client_factory() 228 | state = client.authenticate({"Servers": [server]}, discover=False) 229 | server["connected"] = state["State"] == CONNECTION_STATE["SignedIn"] 230 | if server["connected"]: 231 | is_logged_in = True 232 | self.clients[server["uuid"]] = client 233 | self.setup_client(client, server) 234 | if server.get("username"): 235 | self.usernames[server["uuid"]] = server["username"] 236 | 237 | return is_logged_in 238 | 239 | def _disconnect_client(self, uuid: Optional[str] = None, server=None): 240 | if uuid is None and server is not None: 241 | uuid = server["uuid"] 242 | 243 | if uuid not in self.clients: 244 | return 245 | 246 | if server is not None: 247 | server["connected"] = False 248 | 249 | client = self.clients[uuid] 250 | del self.clients[uuid] 251 | client.stop() 252 | 253 | def remove_all_clients(self): 254 | self.stop_all_clients() 255 | self.credentials = [] 256 | self.save_credentials() 257 | 258 | def stop_all_clients(self): 259 | for key, client in list(self.clients.items()): 260 | del self.clients[key] 261 | client.stop() 262 | 263 | def stop(self): 264 | self.is_stopping = True 265 | for client in self.clients.values(): 266 | client.stop() 267 | 268 | def get_username_from_client(self, client): 269 | # This is kind of convoluted. It may fail if a server 270 | # was added before we started saving usernames. 271 | for uuid, client2 in self.clients.items(): 272 | if client2 is client: 273 | if uuid in self.usernames: 274 | return self.usernames[uuid] 275 | for server in self.credentials: 276 | if server["uuid"] == uuid: 277 | return server.get("username", "Unknown") 278 | break 279 | 280 | return "Unknown" 281 | 282 | 283 | def initialize_jellyfin_api_client(): 284 | global jellyfin_client_manager 285 | jellyfin_client_manager = ClientManager() 286 | 287 | 288 | def jellyfin_login(server_url, server_username, server_password, app_name=None): 289 | global jellyfin_client_manager 290 | global jellyfin_current_client 291 | global global_app_name 292 | global global_user_app_name 293 | 294 | if app_name is not None: 295 | global_user_app_name = app_name 296 | global_app_name = re.sub('[^0-9a-zA-Z]', '-', app_name) 297 | 298 | if jellyfin_client_manager is not None: 299 | jellyfin_logout() 300 | initialize_jellyfin_api_client() 301 | jellyfin_current_client = jellyfin_client_manager.login(server_url, server_username, server_password) 302 | return jellyfin_current_client 303 | 304 | 305 | def jellyfin_logout(): 306 | global jellyfin_client_manager 307 | if jellyfin_client_manager is not None: 308 | jellyfin_client_manager.stop() 309 | jellyfin_client_manager = None 310 | 311 | 312 | def jellyfin_client(): 313 | global jellyfin_current_client 314 | 315 | if jellyfin_current_client is None: 316 | jellyfin_login() 317 | return jellyfin_current_client 318 | -------------------------------------------------------------------------------- /jellyfin_auto_skip.py: -------------------------------------------------------------------------------- 1 | import os 2 | import json 3 | import arrow 4 | import signal 5 | import sys 6 | import getopt 7 | 8 | from pathlib import Path 9 | from time import sleep 10 | from datetime import datetime, timezone 11 | from jellyfin_api_client import jellyfin_login, jellyfin_logout 12 | 13 | server_url = os.environ['JELLYFIN_URL'] if 'JELLYFIN_URL' in os.environ else '' 14 | server_username = os.environ['JELLYFIN_USERNAME'] if 'JELLYFIN_USERNAME' in os.environ else '' 15 | server_password = os.environ['JELLYFIN_PASSWORD'] if 'JELLYFIN_PASSWORD' in os.environ else '' 16 | 17 | mon_all_users = os.environ['MONITOR_ALL_USERS'] if 'MONITOR_ALL_USERS' in os.environ else '' 18 | env_cooldown_str = os.environ['AUTO_SKIP_COOLDOWN'] if 'AUTO_SKIP_COOLDOWN' in os.environ else '' 19 | 20 | config_path = Path(os.environ['CONFIG_DIR']) if 'CONFIG_DIR' in os.environ else Path(Path.cwd() / 'config') 21 | data_path = Path(os.environ['DATA_DIR']) if 'DATA_DIR' in os.environ else Path(config_path / 'data') 22 | 23 | TICKS_PER_MS = 10000 24 | preroll_seconds = 3 25 | minimum_intro_length = 10 # seconds 26 | cooldown_time = 5 27 | 28 | client = None 29 | should_exit = False 30 | 31 | SESSIONS_CULL_COOLDOWN = 300 32 | SESSION_CULL_STALE_AGE = 60 33 | active_sessions = {} 34 | last_sessions_cull = datetime.now(timezone.utc) 35 | 36 | 37 | def monitor_sessions(monitor_all_users=False): 38 | global should_exit 39 | global active_sessions 40 | 41 | if client is None: 42 | return False 43 | 44 | start = datetime.now(timezone.utc) 45 | try: 46 | sessions = client.jellyfin.sessions() 47 | except BaseException as err: 48 | should_exit = True 49 | print("error communicating with the server %s" % err) 50 | print('will exit') 51 | return False 52 | 53 | for session in sessions: 54 | if not monitor_all_users and session['UserId'] != client.auth.jellyfin_user_id(): 55 | continue 56 | if 'PlayState' not in session or session['PlayState']['CanSeek'] is False: 57 | continue 58 | if 'Capabilities' not in session or session['Capabilities']['SupportsMediaControl'] is False: 59 | continue 60 | if 'LastPlaybackCheckIn' not in session: 61 | continue 62 | if 'NowPlayingItem' not in session: 63 | continue 64 | 65 | sessionId = session['Id'] 66 | 67 | # print('user id %s' % session['UserId']) 68 | print('\nclient: [%s] session: [%s]' % (session['DeviceName'], sessionId)) 69 | 70 | lastPlaybackTime = arrow.get(session['LastPlaybackCheckIn']).to('utc').datetime 71 | timeDiff = start - lastPlaybackTime 72 | 73 | item = session['NowPlayingItem'] 74 | print('seconds since last client playback check in: %s' % timeDiff.seconds) 75 | if not session['PlayState']['IsPaused'] and timeDiff.seconds < 8 and 'Id' in item: 76 | if 'SeriesName' in item and 'SeasonName' in item and 'Name' in item: 77 | print('currently playing %s - %s - Episode [%s]' % (item['SeriesName'], item['SeasonName'], item['Name'])) 78 | print('item id %s' % item['Id']) 79 | else: 80 | print('not playing or hasn\'t checked in') 81 | continue 82 | 83 | if 'SeriesId' not in item or 'SeasonId' not in item: 84 | print('playing item isn\'t a series') 85 | continue 86 | 87 | position_ticks = int(session['PlayState']['PositionTicks']) 88 | print('current position %s minutes' % (((position_ticks / TICKS_PER_MS) / 1000) / 60)) 89 | 90 | file_path = Path(data_path / 'jellyfin_cache' / str(item['SeriesId']) / str(item['SeasonId']) / (str(item['Id']) + '.json')) 91 | start_time_ticks = 0 92 | end_time_ticks = 0 93 | if file_path.exists(): 94 | with file_path.open('r') as json_file: 95 | dict = json.load(json_file) 96 | if 'start_time_ms' in dict and 'end_time_ms' in dict: 97 | start_time_ticks = int(dict['start_time_ms']) * TICKS_PER_MS 98 | end_time_ticks = int(dict['end_time_ms']) * TICKS_PER_MS 99 | else: 100 | print('couldn\'t find json file for item. This likely means the episode hasn\'t been processed - checked for file [%s]' % str(file_path)) 101 | continue 102 | 103 | if start_time_ticks == 0 and end_time_ticks == 0: 104 | print('no useable intro data - start_time and end_time are both 0') 105 | continue 106 | 107 | print('pos %ss intro start %ss end %ss' % (position_ticks / TICKS_PER_MS / 1000, start_time_ticks / TICKS_PER_MS / 1000, end_time_ticks / TICKS_PER_MS / 1000)) 108 | 109 | # ignore any weird timestamps/check in times that sometimes show up when starting playback and seeking 110 | # todo: fix this absolute mess 111 | failedCheck = True 112 | if sessionId in active_sessions: 113 | cachedLastPlaybackTime, cachedPositionTicks = active_sessions[sessionId] 114 | cachedLastPlaybackTimeDiff = lastPlaybackTime - cachedLastPlaybackTime 115 | print('diff between client check in timestamps %s' % cachedLastPlaybackTimeDiff) 116 | 117 | posTicksDiff = position_ticks - cachedPositionTicks 118 | posTimeDiff = start - cachedLastPlaybackTime 119 | if cachedLastPlaybackTimeDiff.seconds < 0 or cachedLastPlaybackTimeDiff.seconds > cooldown_time + 8: 120 | print('bad session continuity in check in time, ignoring') 121 | elif posTicksDiff < 0 or posTicksDiff > (posTimeDiff.seconds + 2) * 1000 * TICKS_PER_MS: 122 | print('bad session continuity in position time, ignoring') 123 | print('posTicksDiff %s should be less than %s' % (posTicksDiff, (posTimeDiff.seconds + 2) * 1000 * TICKS_PER_MS)) 124 | else: 125 | failedCheck = False 126 | active_sessions[sessionId] = (lastPlaybackTime, position_ticks) 127 | 128 | if failedCheck or position_ticks < start_time_ticks or position_ticks > end_time_ticks: 129 | continue 130 | 131 | if position_ticks < TICKS_PER_MS * 500: 132 | print('position is less than 0.5 seconds, ignoring to prevent skipping while buffering') 133 | continue 134 | 135 | if end_time_ticks - start_time_ticks < minimum_intro_length * 1000 * TICKS_PER_MS: 136 | print('ignoring episode - intro is less than %ss' % minimum_intro_length) 137 | continue 138 | 139 | preroll_ticks = preroll_seconds * 1000 * TICKS_PER_MS 140 | if end_time_ticks - preroll_ticks >= 0: 141 | end_time_ticks -= preroll_ticks 142 | 143 | print('trying to send seek to client') 144 | client.jellyfin.sessions(handler="/%s/Message" % sessionId, action="POST", json={ 145 | "Text": "Skipping Intro", 146 | "TimeoutMs": 5000 147 | }) 148 | 149 | sleep(1) 150 | params = { 151 | "SeekPositionTicks": end_time_ticks 152 | } 153 | client.jellyfin.sessions(handler="/%s/Playing/seek" % sessionId, action="POST", params=params) 154 | sleep(10) 155 | return True 156 | 157 | 158 | def init_client(): 159 | global client 160 | global should_exit 161 | 162 | print('initializing client') 163 | if client is not None and not should_exit: 164 | try: 165 | jellyfin_logout() 166 | except BaseException as err: 167 | print("error communicating with the server %s" % err) 168 | print('will exit') 169 | should_exit = True 170 | client = None 171 | return 172 | if not should_exit: 173 | sleep(1) 174 | try: 175 | client = jellyfin_login(server_url, server_username, server_password, "TV Intro Auto Skipper") 176 | except BaseException as err: 177 | print("error communicating with the server %s" % err) 178 | print('will exit') 179 | should_exit = True 180 | 181 | 182 | def monitor_loop(monitor_all_users=False): 183 | global should_exit 184 | global active_sessions 185 | global last_sessions_cull 186 | 187 | if server_url == '' or server_username == '' or server_password == '': 188 | print('missing server info') 189 | return 190 | 191 | init_client() 192 | if should_exit: 193 | return 194 | 195 | print('will monitor [%s]' % ('all users' if monitor_all_users else 'current user')) 196 | print('cooldown between check-ins is set to %s seconds' % cooldown_time) 197 | print('listening for jellyfin sessions...') 198 | while not should_exit: 199 | if not monitor_sessions(monitor_all_users) and not should_exit: 200 | init_client() 201 | currTime = datetime.now(timezone.utc) 202 | sessionCullTimeDiff = currTime - last_sessions_cull 203 | if sessionCullTimeDiff.seconds > SESSIONS_CULL_COOLDOWN: 204 | print('\nchecking for stale sessions') 205 | sessionsToRemove = [] 206 | for sessionId in active_sessions: 207 | cachedLastPlaybackTime, cachedPositionTicks = active_sessions[sessionId] 208 | playbackCheckinDiff = currTime - cachedLastPlaybackTime 209 | if playbackCheckinDiff.seconds > SESSION_CULL_STALE_AGE: 210 | sessionsToRemove.append(sessionId) 211 | for sessionToRemove in sessionsToRemove: 212 | if sessionToRemove in active_sessions: 213 | active_sessions.pop(sessionToRemove) 214 | print('removed stale session %s' % sessionId) 215 | last_sessions_cull = datetime.now(timezone.utc) 216 | sleep(cooldown_time) 217 | 218 | if client is not None: 219 | try: 220 | jellyfin_logout() 221 | except BaseException as err: 222 | print("error communicating with the server %s" % err) 223 | print('will exit') 224 | return 225 | 226 | 227 | def main(argv): 228 | global cooldown_time 229 | 230 | all_users = mon_all_users 231 | 232 | try: 233 | opts, args = getopt.getopt(argv, 'hac:', ['cooldown']) 234 | except getopt.GetoptError: 235 | print('jellyfin_auto_skip.py -a (all users)\n') 236 | sys.exit(2) 237 | 238 | for opt, arg in opts: 239 | if opt == '-h': 240 | print('jellyfin_auto_skip.py -a (all users)\n') 241 | sys.exit() 242 | elif opt == '-a': 243 | all_users = True 244 | elif opt in ('-c', '--cooldown'): 245 | if arg != '' and arg.isnumeric(): 246 | cooldown_nb = int(arg) 247 | if cooldown_nb > 0 and cooldown_nb < 300: 248 | cooldown_time = cooldown_nb 249 | 250 | if server_url == '' or server_username == '' or server_password == '': 251 | print('you need to export env variables: JELLYFIN_URL, JELLYFIN_USERNAME, JELLYFIN_PASSWORD\n') 252 | return 253 | 254 | if mon_all_users == 'TRUE': 255 | all_users = True 256 | elif mon_all_users == 'FALSE': 257 | all_users = False 258 | 259 | if env_cooldown_str != '' and env_cooldown_str.isnumeric(): 260 | cooldown_nb = int(env_cooldown_str) 261 | if cooldown_nb > 0 and cooldown_nb < 300: 262 | cooldown_time = cooldown_nb 263 | 264 | monitor_loop(all_users) 265 | 266 | 267 | def receiveSignal(signalNumber, frame): 268 | global should_exit 269 | 270 | if signalNumber == signal.SIGINT: 271 | print('will exit') 272 | should_exit = True 273 | return 274 | 275 | 276 | if __name__ == "__main__": 277 | signal.signal(signal.SIGINT, receiveSignal) 278 | main(sys.argv[1:]) 279 | -------------------------------------------------------------------------------- /jellyfin_queries.py: -------------------------------------------------------------------------------- 1 | from time import sleep 2 | from pathlib import Path 3 | 4 | 5 | def map_path(path, path_map): 6 | new_path = path 7 | 8 | repr_path = path.replace('\\', '/') 9 | for mapping in path_map: 10 | path_map_parts_list = list(Path(mapping[1]).parts) 11 | jellyfin_path_parts_list = list(Path(repr_path).parts) 12 | 13 | path_map_parts = set(path_map_parts_list) 14 | jellyfin_path_parts = set(jellyfin_path_parts_list) 15 | 16 | if path_map_parts.issubset(jellyfin_path_parts): 17 | new_path = str(Path(mapping[0]).joinpath(Path(*jellyfin_path_parts_list[len(path_map_parts_list):]))) 18 | break 19 | return new_path 20 | 21 | 22 | def get_shows(client=None, path_map=[], reverse_sort=False): 23 | if client is None: 24 | return [] 25 | 26 | shows = [] 27 | 28 | try: 29 | result = client.jellyfin.user_items(params={ 30 | 'Recursive': True, 31 | 'includeItemTypes': ( 32 | "Series" 33 | ), 34 | 'SortBy': 'DateCreated,SortName', 35 | 'SortOrder': 'Ascending' if reverse_sort else 'Descending', 36 | 'enableImages': False, 37 | 'enableUserData': False, 38 | 'Fields': ( 39 | "Path" 40 | ), 41 | # added this limit for safety in case someone runs this without understanding what it does 42 | # remove the limit to process all shows 43 | # 'Limit': 1 44 | }) 45 | 46 | if 'Items' in result and result['Items']: 47 | for item in result['Items']: 48 | show = {} 49 | show['Name'] = item['Name'] 50 | show['SeriesId'] = item['Id'] 51 | show['Path'] = map_path(item['Path'], path_map) if 'Path' in item else None 52 | shows.append(show) 53 | except BaseException as err: 54 | return [] 55 | sleep(0.2) 56 | return shows 57 | 58 | 59 | def get_seasons(client=None, path_map=[], series=None): 60 | if client is None or series is None: 61 | return [] 62 | 63 | seasons = [] 64 | 65 | try: 66 | result = client.jellyfin.get_seasons(series['SeriesId']) 67 | 68 | if 'Items' in result and result['Items']: 69 | for item in result['Items']: 70 | season = {} 71 | season['Name'] = item['Name'] 72 | season['SeriesName'] = series['Name'] 73 | season['SeriesId'] = series['SeriesId'] 74 | season['SeasonId'] = item['Id'] 75 | season['Path'] = map_path(item['Path'], path_map) if 'Path' in item else None 76 | seasons.append(season) 77 | except BaseException as err: 78 | return [] 79 | sleep(0.2) 80 | return seasons 81 | 82 | 83 | def get_episodes(client=None, path_map=[], season=None): 84 | if client is None or season is None: 85 | return [] 86 | 87 | episodes = [] 88 | 89 | try: 90 | result = client.jellyfin.shows("/%s/Episodes" % season['SeriesId'], { 91 | 'UserId': "{UserId}", 92 | 'SeasonId': season['SeasonId'], 93 | 'Fields': ( 94 | "Path" 95 | ) 96 | }) 97 | 98 | if 'Items' in result and result['Items']: 99 | for item in result['Items']: 100 | episode = {} 101 | episode['Name'] = item['Name'] 102 | episode['SeriesName'] = season['SeriesName'] 103 | episode['SeasonName'] = season['Name'] 104 | episode['Duration'] = int(item['RunTimeTicks']) / 10000 105 | episode['SeriesId'] = season['SeriesId'] 106 | episode['SeasonId'] = season['SeasonId'] 107 | episode['EpisodeId'] = item['Id'] 108 | episode['ProviderIds'] = {} 109 | if 'ProviderIds' in item: 110 | episode['ProviderIds'] = item['ProviderIds'].deepcopy() 111 | if 'Path' in item: 112 | episode['Path'] = map_path(item['Path'], path_map) 113 | episodes.append(episode) 114 | except BaseException as err: 115 | return [] 116 | return episodes 117 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | arrow==1.2.2 2 | certifi==2023.7.22 3 | charset-normalizer==2.0.12 4 | idna==3.3 5 | ImageHash==4.2.1 6 | jellyfin-apiclient-python==1.8.1 7 | numpy==1.22.0 8 | opencv-python==4.5.5.64 9 | pandas==1.4.1 10 | Pillow==10.0.1 11 | python-dateutil==2.8.2 12 | pytz==2022.1 13 | PyWavelets==1.3.0 14 | requests==2.31.0 15 | scipy==1.10.0 16 | six==1.16.0 17 | urllib3==1.26.18 18 | websocket-client==1.3.1 19 | -------------------------------------------------------------------------------- /tox.ini: -------------------------------------------------------------------------------- 1 | [flake8] 2 | ignore = E501,E116,W293,W605,F841 3 | max-complexity = 30 4 | builtins = _ -------------------------------------------------------------------------------- /unused/ytube_scrape.py: -------------------------------------------------------------------------------- 1 | import os 2 | import sys 3 | import getopt 4 | from pathlib import Path 5 | from datetime import datetime 6 | 7 | config_path = os.environ['CONFIG_DIR'] if 'CONFIG_DIR' in os.environ else './config' 8 | data_path = os.environ['DATA_DIR'] if 'DATA_DIR' in os.environ else os.path.join(config_path, 'data') 9 | 10 | session_timestamp = datetime.now().strftime("%Y_%m_%d-%I_%M_%S_%p") 11 | 12 | 13 | def print_debug(a=[], log=True, log_file=False): 14 | # Here a is the array holding the objects 15 | # passed as the argument of the function 16 | output = ' '.join([str(elem) for elem in a]) 17 | if log: 18 | print(output, file=sys.stderr) 19 | if log_file: 20 | log_path = os.path.join(config_path, 'logs') 21 | Path(log_path).mkdir(parents=True, exist_ok=True) 22 | with open(os.path.join(log_path, 'log_%s.txt' % session_timestamp), "a") as logger: 23 | logger.write(output + '\n') 24 | 25 | 26 | def get_video(name='', log_level=0, log_file=False, cleanup=True, log_timestamp=None): 27 | print(name) 28 | 29 | 30 | def main(argv): 31 | 32 | name = '' 33 | log_level = 0 34 | cleanup = False 35 | log = False 36 | try: 37 | opts, args = getopt.getopt(argv, "hi:dvcl") 38 | except getopt.GetoptError: 39 | print_debug(['ytube_scrape.py -i -v (verbose - some logging) -d (debug - most logging) -l (log to file)\n']) 40 | sys.exit(2) 41 | 42 | for opt, arg in opts: 43 | if opt == '-h': 44 | print_debug(['decode.py -i -v (verbose - some logging) -d (debug - most logging) -l (log to file)\n']) 45 | sys.exit() 46 | elif opt == '-i': 47 | name = arg 48 | elif opt == '-l': 49 | log = True 50 | elif opt == '-d': 51 | log_level = 2 52 | elif opt == '-v': 53 | log_level = 1 54 | 55 | result = get_video(name=name, log_level=log_level, log_file=log, cleanup=cleanup) 56 | print(result) 57 | 58 | 59 | if __name__ == "__main__": 60 | main(sys.argv[1:]) 61 | --------------------------------------------------------------------------------