minimal viable product

.dockerignore

@@ -0,0 +1,18 @@
+# Git
+.git
+.gitignore
+
+# Docker
+.docker
+
+# Python
+tubearchivist/__pycache__/
+tubearchivist/*/__pycache__/
+tubearchivist/*/*/__pycache__/
+tubearchivist/*/*/*/__pycache__/
+.env/
+.venv/
+venv/
+
+# Unneeded graphics
+assets/*

.gitignore

@@ -0,0 +1,11 @@
+# python testing cache
+__pycache__
+
+# django testing db
+db.sqlite3
+
+# frontend fonts
+*ttf.woff
+
+# for local testing only
+testing.sh

.vscode/settings.json

@@ -0,0 +1,5 @@
+{
+    "python.linting.pylintEnabled": true,
+    "python.linting.pycodestyleEnabled": false,
+    "python.linting.enabled": true
+}

Dockerfile

@@ -0,0 +1,41 @@
+# build the tube archivist image from default python slim image
+
+FROM python:3.9.7-slim-bullseye
+
+ENV PYTHONUNBUFFERED 1
+
+# install distro packages needed
+RUN apt-get clean && apt-get -y update && apt-get -y install --no-install-recommends \
+    build-essential \
+    ffmpeg \
+    nginx \
+    curl && rm -rf /var/lib/apt/lists/*
+
+# copy config files
+COPY nginx.conf /etc/nginx/conf.d/
+
+# make folders
+RUN mkdir /cache
+RUN mkdir /youtube
+RUN mkdir /app
+
+# install python dependencies
+COPY ./tubearchivist/requirements.txt /requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt --src /usr/local/src
+
+# copy application into container
+COPY ./tubearchivist /app
+COPY ./run.sh /app
+COPY ./uwsgi.ini /app
+
+# volumes
+VOLUME /cache
+VOLUME /youtube
+
+# start
+WORKDIR /app
+EXPOSE 80
+
+RUN chmod +x ./run.sh
+
+CMD ["./run.sh"]

LICENSE

@@ -0,0 +1,674 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
+
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+the GNU General Public License is intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.  We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors.  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+  To protect your rights, we need to prevent others from denying you
+these rights or asking you to surrender the rights.  Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received.  You must make sure that they, too, receive
+or can get the source code.  And you must show them these terms so they
+know their rights.
+
+  Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
+
+  For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software.  For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
+
+  Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so.  This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software.  The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable.  Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products.  If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
+
+  Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary.  To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                       TERMS AND CONDITIONS
+
+  0. Definitions.
+
+  "This License" refers to version 3 of the GNU General Public License.
+
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
+
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+  1. Source Code.
+
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
+
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+  The Corresponding Source for a work in source code form is that
+same work.
+
+  2. Basic Permissions.
+
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Use with the GNU Affero General Public License.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU Affero General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+Program specifies that a certain numbered version of the GNU General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+    <program>  Copyright (C) <year>  <name of author>
+    This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU GPL, see
+<http://www.gnu.org/licenses/>.
+
+  The GNU General Public License does not permit incorporating your program
+into proprietary programs.  If your program is a subroutine library, you
+may consider it more useful to permit linking proprietary applications with
+the library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.  But first, please read
+<http://www.gnu.org/philosophy/why-not-lgpl.html>.

README.md

@@ -0,0 +1,76 @@
+![banner-tube-archivist-light.png](assets/tube-archivist-banner.jpg?raw=true "Tube Archivist Banner")  
+
+<center><h1>The Tube Archivist<br>Your self hosted Youtube media server</h1></center>
+
+
+## Core functionality
+* Subscribe to your favourite Youtube channels
+* Download Videos using **yt-dlp**
+* Index and make videos searchable
+* Play videos
+* Keep track of viewed and unviewed videos
+
+## Problem Tube Archivist tries to solve
+Once your Youtube video collection grows, it becomes hard to search and find a specific video. That's where Tube Archivist comes in: By indexing your video collection with metadata from Youtube, you can organize, search and enjoy your archived Youtube videos without hassle offline through a convenient web interface.
+
+## Installation
+Take a look at the example `docker-compose.yml` file provided. Tube Archivist depends on three main components split up into seperate docker containers:  
+
+### Tube Archivist
+The main Python application that displays and serves your video collection, built with Django.
+  - Serves the interface on port `8000`
+  - Needs a mandatory volume for the video archive at **/youtube**
+  - And another recommended volume to save the cache for thumbnails and artwork at **/cache**.
+  - The environment variables `ES_URL` and `REDIS_HOST` are needed to tell Tube Archivist where Elasticsearch and Redis respectively are located.
+  - The environment variables `HOST_UID` and `HOST_GID` allowes Tube Archivist to `chown` the video files to the main host system user instead of the container user.
+
+### Elasticsearch
+Stores video meta data and makes everything searchable. Also keeps track of the download queue.
+  - Needs to be accessable over the default port `9200`
+  - Needs a volume at **/usr/share/elasticsearch/data** to store data
+
+Follow the [documentation](https://www.elastic.co/guide/en/elasticsearch/reference/current/docker.html) for additional installation details.
+
+### Redis JSON
+Functions as a cache and temporary link between the application and the filesystem. Used to store and display messages and configuration variables.
+  - Needs to be accessable over the default port `6379`
+  - Takes an optional volume at **/data** to make your configuration changes permanent.
+
+## Getting Started
+1. Go through the **settings** page and look at the available options. Particularly set *Download Format* to you desired video quality before downloading.
+2. Subscribe to some of your favourite Youtube channels on the **channels** page. 
+3. On the **downloads** page, click on *Rescan subscriptions* to add videos from the subscribed channels to your Download queue or click on *Add to download queue* to manually add Video IDs or links.
+4. Click on *Download queue* and let Tube Archivist to it's thing. 
+5. Enjoy your archived collection!
+
+## Potential pitfalls
+**Elastic Search** in Docker requires the kernel setting of the host machine `vm.max_map_count` to be set to least 262144.
+
+To temporary set the value run:  
+```
+sudo sysctl -w vm.max_map_count=262144
+```  
+
+To apply the change permanently depends on your host operating system:  
+- For example on Ubuntu Server add `vm.max_map_count = 262144` to the file */etc/sysctl.conf*.
+- On Arch based systems create a file */etc/sysctl.d/max_map_count.conf* with the content `vm.max_map_count = 262144`. 
+- On any other platform look up in the documentation on how to pass kernel parameters.
+
+
+## Roadmap
+This should be considered as a **minimal viable product**, there is an exstensive list of future functions and improvements planned: 
+- [ ] Scan your filesystem to manually add videos
+- [ ] Access controll
+- [ ] User roles
+- [ ] Delete videos and channel
+- [ ] Create playlists
+- [ ] Show similar videos on video page
+- [ ] Import existing downloaded archive
+- [ ] Multi language support
+- [ ] Backup and restore
+
+
+## Known limitations
+- Video files created by Tube Archivist need to be **mp4** video files for best browser compatibility.
+- Every limitation **yt-dlp** will also be present in Tube Archivist. If yt-dlp can't download or extract a video for any reason, Tube Archivist won't be able to either.
+- For now this is meant to be run in a trusted network environment.

deploy.sh

@@ -0,0 +1,73 @@
+#!/bin/bash
+
+# deploy all needed project files to different servers:
+# test for local vm for testing
+# blackhole for local production
+# docker to publish
+
+set -e
+
+function sync_blackhole {
+
+    # docker commands need sudo
+    host="blackhole.local"
+
+    read -sp 'Password: ' remote_pw
+    export PASS=$remote_pw
+    
+    rsync -a --progress --delete-after \
+        --exclude "**/cache" \
+        --exclude "**/__pycache__/" \
+        --exclude "db.sqlite3" \
+        . -e ssh "$host":tubearchivist
+
+    echo "$PASS" | ssh "$host" 'sudo -S docker build -t bbilly1/tubearchivist:latest tubearchivist 2>/dev/null'
+    echo "$PASS" | ssh "$host" 'sudo -S docker-compose up -d 2>/dev/null'
+
+}
+
+function sync_test {
+
+    # docker commands don't need sudo in testing vm
+    host="tubearchivist.local"
+
+    rsync -a --progress --delete-after \
+        --exclude "**/cache" \
+        --exclude "**/__pycache__/" \
+        --exclude "db.sqlite3" \
+        . -e ssh "$host":tubearchivist
+
+    rsync -r --progress --delete docker-compose.yml -e ssh "$host":docker
+
+    ssh "$host" 'docker build -t bbilly1/tubearchivist:latest tubearchivist'
+    ssh "$host" 'docker-compose -f docker/docker-compose.yml up -d'
+
+}
+
+
+function sync_docker {
+
+    if [[ $(systemctl is-active docker) != 'active' ]]; then
+        echo "starting docker"
+        sudo systemctl start docker
+    fi
+
+    sudo docker build -t bbilly1/tubearchivist:latest .
+    sudo docker push bbilly1/tubearchivist:latest
+
+}
+
+
+if [[ $1 == "blackhole" ]]; then
+    sync_blackhole
+elif [[ $1 == "test" ]]; then
+    sync_test
+elif [[ $1 == "docker" ]]; then
+    sync_docker
+else
+    echo "valid options are: blackhole | test | docker"
+fi
+
+
+##
+exit 0

docker-compose.yml

@@ -0,0 +1,45 @@
+version: '3.3'
+
+services:
+  tubearchivist:
+    container_name: tubearchivist
+    restart: always
+    image: bbilly1/tubearchivist:latest
+    ports:
+      - 8000:8000
+    volumes:
+      - ./volumes/tubearchivist/media:/youtube
+      - ./volumes/tubearchivist/cache:/cache
+    environment:
+      - ES_URL=http://archivist-es:9200
+      - REDIS_HOST=archivist-redis
+      - HOST_UID=1000
+      - HOST_GID=1000
+    depends_on:
+      - archivist-es
+      - archivist-redis
+  archivist-redis:
+    image: redislabs/rejson:latest
+    container_name: archivist-redis
+    restart: always
+    ports:
+      - 6379:6379
+    volumes:
+      - ./volumes/tubearchivist/redis:/data
+    depends_on:
+      - archivist-es
+  archivist-es:
+    image: docker.elastic.co/elasticsearch/elasticsearch:7.14.1
+    container_name: archivist-es
+    restart: always
+    environment:
+      - "discovery.type=single-node"
+      - "ES_JAVA_OPTS=-Xms512m -Xmx512m"
+    ulimits:
+      memlock:
+        soft: -1
+        hard: -1
+    volumes:
+      - ./volumes/tubearchivist/es:/usr/share/elasticsearch/data
+    ports:
+      - 9200:9200

nginx.conf

@@ -0,0 +1,18 @@
+server {
+
+    listen 8000;
+
+    location /cache/ {
+        alias /cache/;
+    }
+
+    location /media/ {
+        alias /youtube/;
+    }
+
+    location / {
+        include uwsgi_params;
+        uwsgi_pass localhost:8080;
+    }
+
+}

run.sh

@@ -0,0 +1,20 @@
+#!/bin/bash
+# startup script inside the container for tubearchivist
+
+counter=0
+until curl "$ES_URL" -fs; do
+    echo "waiting for elastic search to start"
+    counter=$((counter+1))
+    if [[ $counter -eq 12 ]]; then
+        # fail after 1 min
+        echo "failed to connect to elastic search, exiting..."
+        exit 1
+    fi
+    sleep 5
+done
+
+python manage.py migrate
+python manage.py collectstatic
+nginx &
+celery -A home.tasks worker --loglevel=INFO --detach
+uwsgi --ini uwsgi.ini

tubearchivist/config/asgi.py

@@ -0,0 +1,16 @@
+"""
+ASGI config for config project.
+
+It exposes the ASGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/3.2/howto/deployment/asgi/
+"""
+
+import os
+
+from django.core.asgi import get_asgi_application
+
+os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'config.settings')
+
+application = get_asgi_application()

tubearchivist/config/settings.py

@@ -0,0 +1,144 @@
+"""
+Django settings for config project.
+
+Generated by 'django-admin startproject' using Django 3.2.5.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/3.2/topics/settings/
+
+For the full list of settings and their values, see
+https://docs.djangoproject.com/en/3.2/ref/settings/
+"""
+
+from pathlib import Path
+from os import environ
+
+# Build paths inside the project like this: BASE_DIR / 'subdir'.
+BASE_DIR = Path(__file__).resolve().parent.parent
+
+
+# Quick-start development settings - unsuitable for production
+# See https://docs.djangoproject.com/en/3.2/howto/deployment/checklist/
+
+# SECURITY WARNING: keep the secret key used in production secret!
+SECRET_KEY = 'Fvid^aUL6LohRZz*kZFvq85B&JW&kB9o*#jdzWsdWE8*XkCLR8'
+
+# SECURITY WARNING: don't run with debug turned on in production!
+DEBUG = bool(environ.get('DJANGO_DEBUG'))
+
+ALLOWED_HOSTS = ['*']
+
+
+# Application definition
+
+INSTALLED_APPS = [
+    'home.apps.HomeConfig',
+    'django.contrib.admin',
+    'django.contrib.auth',
+    'django.contrib.contenttypes',
+    'django.contrib.sessions',
+    'django.contrib.messages',
+    'whitenoise.runserver_nostatic',
+    'django.contrib.staticfiles',
+    'django.contrib.humanize'
+]
+
+MIDDLEWARE = [
+    'django.middleware.security.SecurityMiddleware',
+    'django.contrib.sessions.middleware.SessionMiddleware',
+    'whitenoise.middleware.WhiteNoiseMiddleware',
+    'django.middleware.common.CommonMiddleware',
+    'django.middleware.csrf.CsrfViewMiddleware',
+    'django.contrib.auth.middleware.AuthenticationMiddleware',
+    'django.contrib.messages.middleware.MessageMiddleware',
+    'django.middleware.clickjacking.XFrameOptionsMiddleware',
+]
+
+ROOT_URLCONF = 'config.urls'
+
+TEMPLATES = [
+    {
+        'BACKEND': 'django.template.backends.django.DjangoTemplates',
+        'DIRS': [],
+        'APP_DIRS': True,
+        'OPTIONS': {
+            'context_processors': [
+                'django.template.context_processors.debug',
+                'django.template.context_processors.request',
+                'django.contrib.auth.context_processors.auth',
+                'django.contrib.messages.context_processors.messages',
+            ],
+        },
+    },
+]
+
+WSGI_APPLICATION = 'config.wsgi.application'
+
+
+# Database
+# https://docs.djangoproject.com/en/3.2/ref/settings/#databases
+
+DATABASES = {
+    'default': {
+        'ENGINE': 'django.db.backends.sqlite3',
+        'NAME': BASE_DIR / 'db.sqlite3',
+    }
+}
+
+
+# Password validation
+# https://docs.djangoproject.com/en/3.2/ref/settings/#auth-password-validators
+
+AUTH_PASSWORD_VALIDATORS = [
+    {
+        'NAME': 'django.contrib.auth.password_validation.UserAttributeSimilarityValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.MinimumLengthValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.CommonPasswordValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.NumericPasswordValidator',
+    },
+]
+
+
+# Internationalization
+# https://docs.djangoproject.com/en/3.2/topics/i18n/
+
+LANGUAGE_CODE = 'en-us'
+
+TIME_ZONE = 'UTC'
+
+USE_I18N = True
+
+USE_L10N = True
+
+USE_TZ = True
+
+
+# Static files (CSS, JavaScript, Images)
+# https://docs.djangoproject.com/en/3.2/howto/static-files/
+
+STATIC_URL = '/static/'
+
+# STATICFILES_DIRS = [
+#     str(BASE_DIR.joinpath('static')),
+#     '/cache/'
+# ]
+
+# STATIC_URL = '/static/'
+STATICFILES_DIRS = (str(BASE_DIR.joinpath('static')),)
+# MEDIA_ROOT = str(BASE_DIR.joinpath('media'))
+# MEDIA_URL = '/media/'
+
+STATIC_ROOT = str(BASE_DIR.joinpath('staticfiles'))
+
+STATICFILES_STORAGE = 'whitenoise.storage.CompressedManifestStaticFilesStorage'
+
+# Default primary key field type
+# https://docs.djangoproject.com/en/3.2/ref/settings/#default-auto-field
+
+DEFAULT_AUTO_FIELD = 'django.db.models.BigAutoField'

tubearchivist/config/urls.py

@@ -0,0 +1,22 @@
+"""config URL Configuration
+
+The `urlpatterns` list routes URLs to views. For more information please see:
+    https://docs.djangoproject.com/en/3.2/topics/http/urls/
+Examples:
+Function views
+    1. Add an import:  from my_app import views
+    2. Add a URL to urlpatterns:  path('', views.home, name='home')
+Class-based views
+    1. Add an import:  from other_app.views import Home
+    2. Add a URL to urlpatterns:  path('', Home.as_view(), name='home')
+Including another URLconf
+    1. Import the include() function: from django.urls import include, path
+    2. Add a URL to urlpatterns:  path('blog/', include('blog.urls'))
+"""
+from django.contrib import admin
+from django.urls import path, include
+
+urlpatterns = [
+    path('', include('home.urls')),
+    path('admin/', admin.site.urls),
+]

tubearchivist/config/wsgi.py

@@ -0,0 +1,16 @@
+"""
+WSGI config for config project.
+
+It exposes the WSGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/3.2/howto/deployment/wsgi/
+"""
+
+import os
+
+from django.core.wsgi import get_wsgi_application
+
+os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'config.settings')
+
+application = get_wsgi_application()

tubearchivist/home/__init__.py

@@ -0,0 +1,40 @@
+""" handle startup """
+
+import os
+
+from home.src.config import AppConfig
+from home.src.helper import set_message
+from home.src.index_management import index_check
+
+from .tasks import app as celery_app
+
+
+def sync_redis_state():
+    """ make sure redis gets the config.json values """
+    print('sync redis')
+    config = AppConfig().config
+    sort_order = config['archive']['sort']
+    set_message('sort_order', sort_order, expire=False)
+    hide_watched = bool(int(config['archive']['hide_watched']))
+    set_message('hide_watched', hide_watched, expire=False)
+    show_subed_only = bool(int(config['archive']['show_subed_only']))
+    set_message('show_subed_only', show_subed_only, expire=False)
+
+
+def make_folders():
+    """ make needed folders here to avoid letting docker messing it up """
+    folders = ['download', 'channels', 'videos']
+    config = AppConfig().config
+    cache_dir = config['application']['cache_dir']
+    for folder in folders:
+        folder_path = os.path.join(cache_dir, folder)
+        try:
+            os.makedirs(folder_path)
+        except FileExistsError:
+            continue
+
+
+__all__ = ('celery_app',)
+make_folders()
+sync_redis_state()
+index_check()

tubearchivist/home/admin.py

@@ -0,0 +1,3 @@
+from django.contrib import admin
+
+# Register your models here.

tubearchivist/home/apps.py

@@ -0,0 +1,6 @@
+from django.apps import AppConfig
+
+
+class HomeConfig(AppConfig):
+    default_auto_field = 'django.db.models.BigAutoField'
+    name = 'home'

tubearchivist/home/config.json

@@ -0,0 +1,25 @@
+{
+    "archive": {
+        "sort": "published",
+        "hide_watched": false,
+        "show_subed_only": false,
+        "page_size": 12
+    },
+    "subscriptions": {
+        "auto_search": false,
+        "auto_download": false,
+        "channel_size": 50
+    },
+    "downloads": {
+        "limit_count": 5,
+        "limit_speed": false,
+        "sleep_interval": 3,
+        "format": "bestvideo[height<=720]+bestaudio/best[height<=720]"
+    },
+    "application": {
+        "cache_dir": "/cache",
+        "videos": "/youtube",
+        "file_template": "%(id)s_%(title)s.mp4",
+        "colors": "dark"
+    }
+}

tubearchivist/home/models.py

@@ -0,0 +1,3 @@
+from django.db import models
+
+# Create your models here.

tubearchivist/home/src/config.py

@@ -0,0 +1,60 @@
+"""
+Functionality:
+- read and write config
+- load config variables into redis
+- needs to be a separate module to avoid circular import
+"""
+
+import json
+import os
+
+from home.src.helper import get_message, set_message
+
+
+class AppConfig:
+    """ handle user settings and application variables """
+
+    def __init__(self):
+        self.config = self.get_config()
+
+    def get_config(self):
+        """ get config from default file or redis if changed """
+        config = self.get_config_redis()
+        if not config:
+            with open('home/config.json', 'r', encoding="utf-8") as f:
+                config_str = f.read()
+                config = json.loads(config_str)
+
+        config['application']['REDIS_HOST'] = os.environ.get('REDIS_HOST')
+        config['application']['es_url'] = os.environ.get('ES_URL')
+        config['application']['HOST_UID'] = int(os.environ.get('HOST_UID'))
+        config['application']['HOST_GID'] = int(os.environ.get('HOST_GID'))
+        return config
+
+    @staticmethod
+    def get_config_redis():
+        """ read config json set from redis to overwrite defaults """
+        config = get_message('config')
+        if not list(config.values())[0]:
+            return False
+
+        return config
+
+    def update_config(self, form_post):
+        """ update config values from settings form """
+        config = self.config
+        for key, value in form_post.items():
+            to_write = value[0]
+            if len(to_write):
+                if to_write == '0':
+                    to_write = False
+                elif to_write.isdigit():
+                    to_write = int(to_write)
+
+                config_dict, config_value = key.split('.')
+                config[config_dict][config_value] = to_write
+
+        with open('home/config.json', 'w', encoding="utf-8") as f:
+            f.write(json.dumps(config))
+
+        set_message('config', config, expire=False)

tubearchivist/home/src/download.py

@@ -0,0 +1,477 @@
+"""
+Functionality:
+- handele the download queue
+- manage subscriptions to channels
+- downloading videos
+"""
+
+import json
+import shutil
+import os
+
+from datetime import datetime
+from time import sleep
+
+import requests
+import yt_dlp as youtube_dl
+
+from home.src.index import YoutubeChannel, index_new_video
+from home.src.config import AppConfig
+from home.src.helper import clean_string, DurationConverter, set_message
+
+
+class PendingList:
+    """ manage the pending videos list """
+
+    CONFIG = AppConfig().config
+    ES_URL = CONFIG['application']['es_url']
+    VIDEOS = CONFIG['application']['videos']
+
+    @staticmethod
+    def parse_url_list(youtube_ids):
+        """ extract youtube ids from list """
+        missing_videos = []
+        for entry in youtube_ids:
+            url = entry['url']
+            url_type = entry['type']
+            if url_type == 'video':
+                missing_videos.append(url)
+            elif url_type == 'channel':
+                youtube_ids = ChannelSubscription().get_last_youtube_videos(
+                    url, limit=False
+                )
+                missing_videos = missing_videos + youtube_ids
+
+        return missing_videos
+
+    def add_to_pending(self, missing_videos):
+        """ build the bulk json data from pending """
+        # check if channel is indexed
+        channel_handler = ChannelSubscription()
+        all_indexed = channel_handler.get_channels(subscribed_only=False)
+        all_channel_ids = [i['channel_id'] for i in all_indexed]
+        # check if already there
+        all_downloaded = self.get_all_downloaded()
+        # loop
+        bulk_list = []
+        for video in missing_videos:
+            if isinstance(video, str):
+                youtube_id = video
+            elif isinstance(video, tuple):
+                youtube_id = video[0]
+            if youtube_id in all_downloaded:
+                # skip already downlaoded
+                continue
+            video = self.get_youtube_details(youtube_id)
+            # skip on download error
+            if not video:
+                continue
+
+            if video['channel_id'] in all_channel_ids:
+                video['channel_indexed'] = True
+            else:
+                video['channel_indexed'] = False
+            video['status'] = "pending"
+            action = {"create": {"_id": youtube_id, "_index": "ta_download"}}
+            bulk_list.append(json.dumps(action))
+            bulk_list.append(json.dumps(video))
+        # add last newline
+        bulk_list.append('\n')
+        query_str = '\n'.join(bulk_list)
+        headers = {'Content-type': 'application/x-ndjson'}
+        url = self.ES_URL + '/_bulk'
+        request = requests.post(url, data=query_str, headers=headers)
+        # notify
+        mess_dict = {
+            "status": "pending",
+            "level": "info",
+            "title": "Adding to download queue.",
+            "message": 'Processing IDs...'
+        }
+        set_message('progress:download', mess_dict)
+        if not request.ok:
+            print(request)
+
+    @staticmethod
+    def get_youtube_details(youtube_id):
+        """ get details from youtubedl for single pending video """
+        obs = {
+            'default_search': 'ytsearch',
+            'quiet': True,
+            'skip_download': True,
+        }
+        try:
+            vid = youtube_dl.YoutubeDL(obs).extract_info(youtube_id)
+        except youtube_dl.utils.DownloadError:
+            print('failed to extract info for: ' + youtube_id)
+            return False
+        # parse response
+        seconds = vid['duration']
+        duration_str = DurationConverter.get_str(seconds)
+        upload_date = vid['upload_date']
+        upload_dt = datetime.strptime(upload_date, "%Y%m%d")
+        published = upload_dt.strftime("%Y-%m-%d")
+        # build dict
+        youtube_details = {
+            "youtube_id": youtube_id,
+            "channel_name": vid['channel'],
+            "vid_thumb_url": vid['thumbnail'],
+            "title": vid['title'],
+            "channel_id": vid['channel_id'],
+            "duration": duration_str,
+            "published": published,
+            "timestamp": int(datetime.now().strftime("%s"))
+        }
+        return youtube_details
+
+    def get_all_pending(self):
+        """ get a list of all pending videos in ta_download """
+        headers = {'Content-type': 'application/json'}
+        # get PIT ID
+        url = self.ES_URL + '/ta_download/_pit?keep_alive=1m'
+        response = requests.post(url)
+        json_data = json.loads(response.text)
+        pit_id = json_data['id']
+        # query
+        data = {
+            "size": 50, "query": {"match_all": {}},
+            "pit": {"id": pit_id, "keep_alive": "1m"},
+            "sort": [{"timestamp": {"order": "desc"}}]
+        }
+        query_str = json.dumps(data)
+        url = self.ES_URL + '/_search'
+        all_pending = []
+        all_ignore = []
+        while True:
+            response = requests.get(url, data=query_str, headers=headers)
+            json_data = json.loads(response.text)
+            all_hits = json_data['hits']['hits']
+            if all_hits:
+                for hit in all_hits:
+                    youtube_id = hit['_source']['youtube_id']
+                    status = hit['_source']['status']
+                    if status == 'pending':
+                        all_pending.append(hit['_source'])
+                    elif status == 'ignore':
+                        all_ignore.append(youtube_id)
+                    search_after = hit['sort']
+                # update search_after with last hit data
+                data['search_after'] = search_after
+                query_str = json.dumps(data)
+            else:
+                break
+        # clean up PIT
+        query_str = json.dumps({"id": pit_id})
+        requests.delete(self.ES_URL + '/_pit', data=query_str, headers=headers)
+        return all_pending, all_ignore
+
+    def get_all_indexed(self):
+        """ get a list of all videos indexed """
+        headers = {'Content-type': 'application/json'}
+        # get PIT ID
+        url = self.ES_URL + '/ta_video/_pit?keep_alive=1m'
+        response = requests.post(url)
+        json_data = json.loads(response.text)
+        pit_id = json_data['id']
+        # query
+        data = {
+            "size": 500, "query": {"match_all": {}},
+            "pit": {"id": pit_id, "keep_alive": "1m"},
+            "sort": [{"published": {"order": "desc"}}]
+        }
+        query_str = json.dumps(data)
+        url = self.ES_URL + '/_search'
+        all_indexed = []
+        while True:
+            response = requests.get(url, data=query_str, headers=headers)
+            json_data = json.loads(response.text)
+            all_hits = json_data['hits']['hits']
+            if all_hits:
+                for hit in all_hits:
+                    all_indexed.append(hit)
+                    search_after = hit['sort']
+                # update search_after with last hit data
+                data['search_after'] = search_after
+                query_str = json.dumps(data)
+            else:
+                break
+        # clean up PIT
+        query_str = json.dumps({"id": pit_id})
+        requests.delete(self.ES_URL + '/_pit', data=query_str, headers=headers)
+        return all_indexed
+
+    def get_all_downloaded(self):
+        """ get a list of all videos in archive """
+        all_channel_folders = os.listdir(self.VIDEOS)
+        all_downloaded = []
+        for channel_folder in all_channel_folders:
+            channel_path = os.path.join(self.VIDEOS, channel_folder)
+            all_videos = os.listdir(channel_path)
+            youtube_vids = [i[9:20] for i in all_videos]
+            for youtube_id in youtube_vids:
+                all_downloaded.append(youtube_id)
+        return all_downloaded
+
+    def delete_from_pending(self, youtube_id):
+        """ delete the youtube_id from ta_download """
+        url = f'{self.ES_URL}/ta_download/_doc/{youtube_id}'
+        response = requests.delete(url)
+        if not response.ok:
+            print(response.text)
+
+    def ignore_from_pending(self, ignore_list):
+        """ build the bulk query string """
+
+        stamp = int(datetime.now().strftime("%s"))
+        bulk_list = []
+
+        for youtube_id in ignore_list:
+            action = {"update": {"_id": youtube_id, "_index": "ta_download"}}
+            source = {"doc": {"status": 'ignore', "timestamp": stamp}}
+            bulk_list.append(json.dumps(action))
+            bulk_list.append(json.dumps(source))
+
+        # add last newline
+        bulk_list.append('\n')
+        query_str = '\n'.join(bulk_list)
+
+        headers = {'Content-type': 'application/x-ndjson'}
+        url = self.ES_URL + '/_bulk'
+        request = requests.post(url, data=query_str, headers=headers)
+        mess_dict = {
+            "status": "ignore",
+            "level": "info",
+            "title": "Added to ignore list",
+            "message": ''
+        }
+        set_message('progress:download', mess_dict)
+        if not request.ok:
+            print(request)
+
+
+class ChannelSubscription:
+    """ manage the list of channels subscribed """
+
+    def __init__(self):
+        config = AppConfig().config
+        self.es_url = config['application']['es_url']
+        self.channel_size = config['subscriptions']['channel_size']
+
+    def get_channels(self, subscribed_only=True):
+        """ get a list of all channels subscribed to """
+        headers = {'Content-type': 'application/json'}
+        # get PIT ID
+        url = self.es_url + '/ta_channel/_pit?keep_alive=1m'
+        response = requests.post(url)
+        json_data = json.loads(response.text)
+        pit_id = json_data['id']
+        # query
+        if subscribed_only:
+            data = {
+                "query": {"term": {"channel_subscribed": {"value": True}}},
+                "size": 50, "pit": {"id": pit_id, "keep_alive": "1m"},
+                "sort": [{"channel_name.keyword": {"order": "asc"}}]
+            }
+        else:
+            data = {
+                "query": {"match_all": {}},
+                "size": 50, "pit": {"id": pit_id, "keep_alive": "1m"},
+                "sort": [{"channel_name.keyword": {"order": "asc"}}]
+            }
+        query_str = json.dumps(data)
+        url = self.es_url + '/_search'
+        all_channels = []
+        while True:
+            response = requests.get(url, data=query_str, headers=headers)
+            json_data = json.loads(response.text)
+            all_hits = json_data['hits']['hits']
+            if all_hits:
+                for hit in all_hits:
+                    source = hit['_source']
+                    search_after = hit['sort']
+                    all_channels.append(source)
+                # update search_after with last hit data
+                data['search_after'] = search_after
+                query_str = json.dumps(data)
+            else:
+                break
+        # clean up PIT
+        query_str = json.dumps({"id": pit_id})
+        requests.delete(self.es_url + '/_pit', data=query_str, headers=headers)
+        return all_channels
+
+    def get_last_youtube_videos(self, channel_id, limit=True):
+        """ get a list of last videos from channel """
+        url = f'https://www.youtube.com/channel/{channel_id}/videos'
+        obs = {
+            'default_search': 'ytsearch', 'quiet': True,
+            'skip_download': True, 'extract_flat': True
+        }
+        if limit:
+            obs['playlistend'] = self.channel_size
+        chan = youtube_dl.YoutubeDL(obs).extract_info(url, download=False)
+        last_videos = [(i['id'], i['title']) for i in chan['entries']]
+        return last_videos
+
+    def find_missing(self):
+        """ add missing videos from subscribed channels to pending """
+        all_channels = self.get_channels()
+        pending_handler = PendingList()
+        all_pending, all_ignore = pending_handler.get_all_pending()
+        all_pending_ids = [i['youtube_id'] for i in all_pending]
+        all_downloaded = pending_handler.get_all_downloaded()
+        to_ignore = all_pending_ids + all_ignore + all_downloaded
+        missing_videos = []
+        counter = 1
+        for channel in all_channels:
+            channel_id = channel['channel_id']
+            last_videos = self.get_last_youtube_videos(channel_id)
+            set_message('progress:download', {
+                "status": "rescan",
+                "level": "info",
+                "title": "Rescanning: Looking for new videos.",
+                "message": f'Progress: {counter}/{len(all_channels)}'
+                }
+            )
+            for video in last_videos:
+                youtube_id = video[0]
+                if youtube_id not in to_ignore:
+                    missing_videos.append(youtube_id)
+            counter = counter + 1
+
+        return missing_videos
+
+    def change_subscribe(self, channel_id, channel_subscribed):
+        """ subscribe or unsubscribe from channel and update """
+        if not isinstance(channel_subscribed, bool):
+            print('invalid status, should be bool')
+            return
+        headers = {'Content-type': 'application/json'}
+        channel_handler = YoutubeChannel(channel_id)
+        channel_dict = channel_handler.channel_dict
+        channel_dict['channel_subscribed'] = channel_subscribed
+        if channel_subscribed:
+            # handle subscribe
+            url = self.es_url + '/ta_channel/_doc/' + channel_id
+            payload = json.dumps(channel_dict)
+            print(channel_dict)
+        else:
+            url = self.es_url + '/ta_channel/_update/' + channel_id
+            payload = json.dumps({'doc': channel_dict})
+        # update channel
+        request = requests.post(url, data=payload, headers=headers)
+        if not request.ok:
+            print(request.text)
+        # sync to videos
+        channel_handler.sync_to_videos()
+
+
+class VideoDownloader:
+    """ handle the video download functionality """
+
+    def __init__(self, youtube_id_list):
+        self.youtube_id_list = youtube_id_list
+        self.config = AppConfig().config
+
+    def download_list(self):
+        """ download the list of youtube_ids """
+        for youtube_id in self.youtube_id_list:
+            try:
+                self.dl_single_vid(youtube_id)
+            except youtube_dl.utils.DownloadError:
+                print('failed to download ' + youtube_id)
+                continue
+            vid_dict = index_new_video(youtube_id)
+            self.move_to_archive(vid_dict)
+            self.delete_from_pending(youtube_id)
+            if self.config['downloads']['sleep_interval']:
+                sleep(self.config['downloads']['sleep_interval'])
+
+    @staticmethod
+    def progress_hook(response):
+        """ process the progress_hooks from youtube_dl """
+        # title
+        filename = response['filename'][12:].replace('_', ' ')
+        title = "Downloading: " + os.path.split(filename)[-1]
+        # message
+        try:
+            percent = response['_percent_str']
+            size = response['_total_bytes_str']
+            speed = response['_speed_str']
+            eta = response['_eta_str']
+            message = f'{percent} of {size} at {speed} - time left: {eta}'
+        except KeyError:
+            message = ''
+        mess_dict = {
+            "status": "downloading",
+            "level": "info",
+            "title": title,
+            "message": message
+        }
+        set_message('progress:download', mess_dict)
+
+    def dl_single_vid(self, youtube_id):
+        """ download single video """
+        obs = {
+            'default_search': 'ytsearch',
+            'merge_output_format': 'mp4', 'restrictfilenames': True,
+            'outtmpl': (self.config['application']['cache_dir'] +
+                        '/download/' +
+                        self.config['application']['file_template']),
+            'progress_hooks': [self.progress_hook],
+            'quiet': True, 'continuedl': True, 'retries': 3
+        }
+        if self.config['downloads']['format']:
+            obs['format'] = self.config['downloads']['format']
+        if self.config['downloads']['limit_speed']:
+            obs['ratelimit'] = self.config['downloads']['limit_speed'] * 1024
+        external = False
+        if external:
+            obs['external_downloader'] = 'aria2c'
+        # check if already in cache to continue from there
+        cache_dir = self.config['application']['cache_dir']
+        all_cached = os.listdir(cache_dir + '/download/')
+        for file_name in all_cached:
+            if youtube_id in file_name:
+                obs['outtmpl'] = cache_dir + '/download/' + file_name
+        with youtube_dl.YoutubeDL(obs) as ydl:
+            try:
+                ydl.download([youtube_id])
+            except youtube_dl.utils.DownloadError:
+                print('retry failed download: ' + youtube_id)
+                sleep(10)
+                ydl.download([youtube_id])
+
+    def move_to_archive(self, vid_dict):
+        """ move downloaded video from cache to archive """
+        videos = self.config['application']['videos']
+        channel_name = vid_dict['channel']['channel_name']
+        channel_name_clean = clean_string(channel_name)
+        media_url = vid_dict['media_url']
+        youtube_id = vid_dict['youtube_id']
+        # make archive folder
+        videos = self.config['application']['videos']
+        new_folder = os.path.join(videos, channel_name_clean)
+        os.makedirs(new_folder, exist_ok=True)
+        # find real filename
+        cache_dir = self.config['application']['cache_dir']
+        for file_str in os.listdir(cache_dir + '/download'):
+            if youtube_id in file_str:
+                old_file = file_str
+        old_file_path = os.path.join(cache_dir, 'download', old_file)
+        new_file_path = os.path.join(videos, media_url)
+        # move and fix permission
+        shutil.move(old_file_path, new_file_path)
+        os.chown(
+            new_file_path,
+            self.config['application']['HOST_UID'],
+            self.config['application']['HOST_GID']
+        )
+
+    def delete_from_pending(self, youtube_id):
+        """ delete downloaded video from pending index if its there """
+        es_url = self.config['application']['es_url']
+        url = f'{es_url}/ta_download/_doc/{youtube_id}'
+        response = requests.delete(url)
+        if not response.ok and not response.status_code == 404:
+            print(response.text)

tubearchivist/home/src/helper.py

@@ -0,0 +1,145 @@
+"""
+Loose collection of helper functions
+- don't import AppConfig class here to avoid circular imports
+"""
+
+import json
+import os
+import re
+import string
+import subprocess
+import unicodedata
+
+import requests
+import redis
+
+REDIS_HOST = os.environ.get('REDIS_HOST')
+
+
+def get_total_hits(index, es_url, match_field):
+    """ get total hits from index """
+    headers = {'Content-type': 'application/json'}
+    data = {"query": {"match": {match_field: True}}}
+    payload = json.dumps(data)
+    url = f'{es_url}/{index}/_search?filter_path=hits.total'
+    request = requests.post(url, data=payload, headers=headers)
+    if not request.ok:
+        print(request.text)
+    total_json = json.loads(request.text)
+    total_hits = total_json['hits']['total']['value']
+    return total_hits
+
+
+def clean_string(file_name):
+    """ clean string to only asci characters """
+    whitelist = "-_.() " + string.ascii_letters + string.digits
+    normalized = unicodedata.normalize('NFKD', file_name)
+    ascii_only = normalized.encode('ASCII', 'ignore').decode().strip()
+    white_listed = ''.join(c for c in ascii_only if c in whitelist)
+    cleaned = re.sub(r'[ ]{2,}', ' ', white_listed)
+    return cleaned
+
+
+def process_url_list(url_str):
+    """ parse url_list to find valid youtube video or channel ids """
+    url_list = re.split('\n+', url_str[0])
+    youtube_ids = []
+    for url in url_list:
+        url_clean = url.strip().split('/')[-1].replace('watch?v=', '')
+        url_no_param = url_clean.split('&')[0]
+        str_len = len(url_no_param)
+        if str_len == 11:
+            link_type = 'video'
+        elif str_len == 24:
+            link_type = 'channel'
+
+        youtube_ids.append({"url": url_no_param, "type": link_type})
+
+    return youtube_ids
+
+
+def set_message(key, message, expire=True):
+    """ write new message to redis """
+    redis_connection = redis.Redis(host=REDIS_HOST)
+    redis_connection.execute_command(
+        'JSON.SET', key, '.', json.dumps(message)
+    )
+    if expire:
+        redis_connection.execute_command('EXPIRE', key, 20)
+
+
+def get_message(key):
+    """ get any message from JSON key """
+    redis_connection = redis.Redis(host=REDIS_HOST)
+    reply = redis_connection.execute_command('JSON.GET', key)
+    if reply:
+        json_str = json.loads(reply)
+    else:
+        json_str = {"status": False}
+    return json_str
+
+
+def get_dl_message(cache_dir):
+    """ get latest message if available """
+    redis_connection = redis.Redis(host=REDIS_HOST)
+    reply = redis_connection.execute_command('JSON.GET', 'progress:download')
+    if reply:
+        json_str = json.loads(reply)
+    elif json_str := monitor_cache_dir(cache_dir):
+        json_str = monitor_cache_dir(cache_dir)
+    else:
+        json_str = {"status": False}
+    return json_str
+
+
+def monitor_cache_dir(cache_dir):
+    """
+    look at download cache dir directly as alterative progress info
+    """
+    dl_cache = os.path.join(cache_dir, 'download')
+    cache_file = os.listdir(dl_cache)
+    if cache_file:
+        filename = cache_file[0][12:].replace('_', ' ').split('.')[0]
+        mess_dict = {
+            "status": "downloading",
+            "level": "info",
+            "title": "Downloading: " + filename,
+            "message": ""
+        }
+    else:
+        return False
+
+    return mess_dict
+
+
+class DurationConverter:
+    """
+    using ffmpeg to get and parse duration from filepath
+    """
+
+    @staticmethod
+    def get_sec(file_path):
+        """ read duration from file """
+        duration = subprocess.run([
+            "ffprobe", "-v", "error", "-show_entries", "format=duration",
+            "-of", "default=noprint_wrappers=1:nokey=1", file_path
+        ], capture_output=True, check=True)
+        duration_sec = int(float(duration.stdout.decode().strip()))
+        return duration_sec
+
+    @staticmethod
+    def get_str(duration_sec):
+        """ takes duration in sec and returns clean string """
+        hours = duration_sec // 3600
+        minutes = (duration_sec - (hours * 3600)) // 60
+        secs = duration_sec - (hours * 3600) - (minutes * 60)
+
+        duration_str = str()
+        if hours:
+            duration_str = str(hours).zfill(2) + ':'
+        if minutes:
+            duration_str = duration_str + str(minutes).zfill(2) + ':'
+        else:
+            duration_str = duration_str + '00:'
+        duration_str = duration_str + str(secs).zfill(2)
+        return duration_str

tubearchivist/home/src/index.py

@@ -0,0 +1,380 @@
+"""
+Functionality:
+- index new videos into elastisearch
+- extract video info with yt_dlp
+- scrape youtube channel page if needed
+"""
+
+import json
+import re
+
+from datetime import datetime
+from time import sleep
+import os
+
+import requests
+import yt_dlp as youtube_dl
+
+from bs4 import BeautifulSoup
+
+from home.src.config import AppConfig
+from home.src.helper import clean_string, DurationConverter
+
+
+class YoutubeChannel:
+    """ represents a single youtube channel """
+
+    CONFIG = AppConfig().config
+    ES_URL = CONFIG['application']['es_url']
+    CACHE_DIR = CONFIG['application']['cache_dir']
+
+    def __init__(self, channel_id):
+        self.channel_id = channel_id
+        self.json_data = None
+        self.source = None
+        self.channel_dict = self.build_channel_dict()
+
+    def build_channel_dict(self, scrape=False):
+        """ combine the dicts build from extracted json payload """
+        if scrape:
+            channel_dict = False
+        else:
+            channel_dict = self.get_es_channel()
+        if not channel_dict:
+            print('scrape data from youtube')
+            self.scrape_channel()
+            channel_dict = self.parse_channel_main()
+            channel_dict.update(self.parse_channel_meta())
+            self.source = 'scraped'
+        return channel_dict
+
+    def get_es_channel(self):
+        """ get from elastic search first if possible """
+        channel_id = self.channel_id
+        url = f'{self.ES_URL}/ta_channel/_doc/{channel_id}'
+        response = requests.get(url)
+        if response.ok:
+            channel_source = response.json()['_source']
+            self.source = 'elastic'
+            return channel_source
+        return False
+
+    def scrape_channel(self):
+        """ scrape channel page for additional infos """
+        channel_id = self.channel_id
+        url = f'https://www.youtube.com/channel/{channel_id}/about?hl=en'
+        response = requests.get(url)
+        if response.ok:
+            channel_page = response.text
+        else:
+            print(f'failed to extract channel info for: {channel_id}')
+            raise ConnectionError
+        soup = BeautifulSoup(channel_page, 'html.parser')
+        # load script into json
+        all_scripts = soup.find('body').find_all('script')
+        for script in all_scripts:
+            if 'var ytInitialData = ' in str(script):
+                script_content = str(script)
+                break
+        # extract payload
+        script_content = script_content.split('var ytInitialData = ')[1]
+        json_raw = script_content.rstrip(';</script>')
+        json_data = json.loads(json_raw)
+        # add to self
+        self.json_data = json_data
+
+    def parse_channel_main(self):
+        """ extract maintab values from scraped channel json data """
+        main_tab = self.json_data['header']['c4TabbedHeaderRenderer']
+        channel_name = main_tab['title']
+        last_refresh = int(datetime.now().strftime("%s"))
+        # channel_subs
+        try:
+            sub_text_simple = main_tab['subscriberCountText']['simpleText']
+            sub_text = sub_text_simple.split(' ')[0]
+            if sub_text[-1] == 'K':
+                channel_subs = int(float(sub_text.replace('K', ''))*1000)
+            elif sub_text[-1] == 'M':
+                channel_subs = int(float(sub_text.replace('M', ''))*1000000)
+            elif int(sub_text) >= 0:
+                channel_subs = int(sub_text)
+            else:
+                message = f'{sub_text} not dealt with'
+                print(message)
+        except KeyError:
+            channel_subs = 0
+        # banner
+        try:
+            all_banners = main_tab['banner']['thumbnails']
+            banner = sorted(all_banners, key=lambda k: k['width'])[-1]['url']
+        except KeyError:
+            banner = False
+        # build and return dict
+        main_channel_dict = {
+            'channel_active': True,
+            'channel_last_refresh': last_refresh,
+            'channel_subs': channel_subs,
+            'channel_banner_url': banner,
+            'channel_name': channel_name,
+            'channel_id': self.channel_id
+        }
+        return main_channel_dict
+
+    def parse_channel_meta(self):
+        """ extract meta tab values from channel payload """
+        # meta tab
+        json_data = self.json_data
+        meta_tab = json_data['metadata']['channelMetadataRenderer']
+        description = meta_tab['description']
+        all_thumbs = meta_tab['avatar']['thumbnails']
+        thumb_url = sorted(all_thumbs, key=lambda k: k['width'])[-1]['url']
+        # stats tab
+        renderer = 'twoColumnBrowseResultsRenderer'
+        all_tabs = json_data['contents'][renderer]['tabs']
+        for tab in all_tabs:
+            if 'tabRenderer' in tab.keys():
+                if tab['tabRenderer']['title'] == 'About':
+                    about_tab = (tab['tabRenderer']['content']
+                                 ['sectionListRenderer']['contents'][0]
+                                 ['itemSectionRenderer']['contents'][0]
+                                 ['channelAboutFullMetadataRenderer'])
+                    break
+        try:
+            channel_views_text = about_tab['viewCountText']['simpleText']
+            channel_views = int(re.sub(r"\D", "", channel_views_text))
+        except KeyError:
+            channel_views = 0
+
+        meta_channel_dict = {
+            'channel_description': description,
+            'channel_thumb_url': thumb_url,
+            'channel_views': channel_views
+        }
+
+        return meta_channel_dict
+
+    def upload_to_es(self):
+        """ upload channel data to elastic search """
+        url = f'{self.ES_URL}/ta_channel/_doc/{self.channel_id}'
+        response = requests.put(url, json=self.channel_dict)
+        print(f'added {self.channel_id} to es')
+        if not response.ok:
+            print(response.text)
+
+    def clear_cache(self):
+        """ delete banner and thumb from cache if available """
+        channel_cache = os.path.join(self.CACHE_DIR, 'channels')
+        thumb = os.path.join(channel_cache, self.channel_id + '_thumb.jpg')
+        banner = os.path.join(channel_cache, self.channel_id + '_banner.jpg')
+        if os.path.exists(thumb):
+            os.remove(thumb)
+        if os.path.exists(banner):
+            os.remove(banner)
+
+    def sync_to_videos(self):
+        """ sync new channel_dict to all videos of channel """
+        headers = {'Content-type': 'application/json'}
+        channel_id = self.channel_id
+        # add ingest pipeline
+        processors = []
+        for field, value in self.channel_dict.items():
+            line = {"set": {"field": "channel." + field, "value": value}}
+            processors.append(line)
+        data = {
+            "description": channel_id,
+            "processors": processors
+        }
+        payload = json.dumps(data)
+        url = self.ES_URL + '/_ingest/pipeline/' + channel_id
+        request = requests.put(url, data=payload, headers=headers)
+        if not request.ok:
+            print(request.text)
+        # apply pipeline
+        data = {
+            "query": {"match": {"channel.channel_id": channel_id}}
+        }
+        payload = json.dumps(data)
+        url = self.ES_URL + '/ta_video/_update_by_query?pipeline=' + channel_id
+        request = requests.post(url, data=payload, headers=headers)
+        if not request.ok:
+            print(request.text)
+
+    def get_total_hits(self):
+        """ get total channels indexed """
+        headers = {'Content-type': 'application/json'}
+        data = {"query": {"match_all": {}}}
+        payload = json.dumps(data)
+        url = f'{self.ES_URL}/ta_channel/_search?filter_path=hits.total'
+        request = requests.post(url, data=payload, headers=headers)
+        if not request.ok:
+            print(request.text)
+        total_hits = json.loads(request.text)['hits']['total']['value']
+        return total_hits
+
+
+class YoutubeVideo:
+    """ represents a signle youtube video """
+
+    CONFIG = AppConfig().config
+    ES_URL = CONFIG['application']['es_url']
+    CACHE_DIR = CONFIG['application']['cache_dir']
+
+    def __init__(self, youtube_id):
+        self.youtube_id = youtube_id
+        self.channel_id = None
+        self.vid_dict = self.get_wrapper()
+
+    def get_wrapper(self):
+        """ wrapper to loop around youtube_dl to retry on failure """
+        print(f'get video data for {self.youtube_id}')
+        for i in range(3):
+            try:
+                vid_dict = self.get_youtubedl_vid_data()
+            except KeyError as e:
+                print(e)
+                sleep((i + 1) ** 2)
+                continue
+            else:
+                break
+
+        return vid_dict
+
+    def get_youtubedl_vid_data(self):
+        """ parse youtubedl extract info """
+        youtube_id = self.youtube_id
+        obs = {
+            'quiet': True,
+            'default_search': 'ytsearch',
+            'skip_download': True
+        }
+        try:
+            vid = youtube_dl.YoutubeDL(obs).extract_info(youtube_id)
+        except (
+                youtube_dl.utils.ExtractorError,
+                youtube_dl.utils.DownloadError
+                ):
+            print('failed to get info for ' + youtube_id)
+            return False
+        # extract
+        self.channel_id = vid['channel_id']
+        upload_date = vid['upload_date']
+        upload_date_time = datetime.strptime(upload_date, "%Y%m%d")
+        published = upload_date_time.strftime("%Y-%m-%d")
+        last_refresh = int(datetime.now().strftime("%s"))
+        # likes
+        try:
+            like_count = vid['like_count']
+        except KeyError:
+            like_count = 0
+        try:
+            dislike_count = vid['dislike_count']
+        except KeyError:
+            dislike_count = 0
+        # build dicts
+        stats = {
+            "view_count": vid['view_count'],
+            "like_count": like_count,
+            "dislike_count": dislike_count,
+            "average_rating": vid['average_rating']
+        }
+        vid_basic = {
+            "title": vid['title'],
+            "description": vid['description'],
+            "category": vid['categories'],
+            "vid_thumb_url": vid['thumbnail'],
+            "tags": vid['tags'],
+            "published": published,
+            "stats": stats,
+            "vid_last_refresh": last_refresh,
+            "date_downloaded": last_refresh,
+            "youtube_id": youtube_id,
+            "active": True,
+            "channel": False
+        }
+
+        return vid_basic
+
+    def add_new_player(self):
+        """ add player information for new videos """
+        cache_path = self.CACHE_DIR + '/download/'
+        all_cached = os.listdir(cache_path)
+        for file_cached in all_cached:
+            if self.youtube_id in file_cached:
+                vid_path = os.path.join(cache_path, file_cached)
+                duration_handler = DurationConverter()
+                duration = duration_handler.get_sec(vid_path)
+                duration_str = duration_handler.get_str(duration)
+                player = {
+                    "watched": False,
+                    "duration": duration,
+                    "duration_str": duration_str
+                }
+                break
+
+        self.vid_dict['player'] = player
+
+    def build_file_path(self, channel_name):
+        """ build media_url from where file will be located """
+        clean_channel_name = clean_string(channel_name)
+        timestamp = self.vid_dict['published'].replace('-', '')
+        youtube_id = self.vid_dict['youtube_id']
+        title = self.vid_dict['title']
+        clean_title = clean_string(title)
+        filename = f'{timestamp}_{youtube_id}_{clean_title}.mp4'
+        media_url = os.path.join(clean_channel_name, filename)
+        self.vid_dict['media_url'] = media_url
+
+    def get_es_data(self):
+        """ get current data from elastic search """
+        url = self.ES_URL + '/ta_video/_doc/' + self.youtube_id
+        response = requests.get(url)
+        if not response.ok:
+            print(response.text)
+        es_vid_dict = json.loads(response.text)
+        return es_vid_dict
+
+    def upload_to_es(self):
+        """ upload channel data to elastic search """
+        url = f'{self.ES_URL}/ta_video/_doc/{self.youtube_id}'
+        response = requests.put(url, json=self.vid_dict)
+        if not response.ok:
+            print(response.text)
+
+    def delete_cache(self):
+        """ delete thumbnail from cache if exist """
+        video_cache = os.path.join(self.CACHE_DIR, 'videos')
+        thumb = os.path.join(video_cache, self.youtube_id + '.jpg')
+        if os.path.exists(thumb):
+            os.remove(thumb)
+
+    def deactivate(self):
+        """ deactivate document on extractor error """
+        youtube_id = self.youtube_id
+        headers = {'Content-type': 'application/json'}
+        url = f'{self.ES_URL}/ta_video/_update/{youtube_id}'
+        data = {"script": "ctx._source.active = false"}
+        json_str = json.dumps(data)
+        response = requests.post(url, data=json_str, headers=headers)
+        print(f'deactivated {youtube_id}')
+        if not response.ok:
+            print(response.text)
+
+
+def index_new_video(youtube_id):
+    """ combine video and channel classes for new video index """
+    vid_handler = YoutubeVideo(youtube_id)
+    channel_handler = YoutubeChannel(vid_handler.channel_id)
+    # add filepath to vid_dict
+    channel_name = channel_handler.channel_dict['channel_name']
+    vid_handler.build_file_path(channel_name)
+    # add channel and player to video
+    vid_handler.add_new_player()
+    vid_handler.vid_dict['channel'] = channel_handler.channel_dict
+    # add new channel to es
+    if channel_handler.source == 'scraped':
+        channel_handler.channel_dict['channel_subscribed'] = False
+        channel_handler.upload_to_es()
+    # upload video to es
+    vid_handler.upload_to_es()
+    # return vid_dict for further processing
+    return vid_handler.vid_dict

tubearchivist/home/src/index_management.py

@@ -0,0 +1,517 @@
+"""
+Functionality:
+- initial elastic search setup
+- index configuration is represented in INDEX_CONFIG
+- index mapping and settings validation
+- backup and restore
+"""
+
+import json
+import os
+
+from datetime import datetime
+
+import requests
+
+from home.src.config import AppConfig
+
+
+# expected mapping and settings
+INDEX_CONFIG = [
+    {
+        'index_name': 'channel',
+        'expected_map': {
+            "channel_id": {
+                "type": "keyword",
+            },
+            "channel_name": {
+                "type": "text",
+                "fields": {
+                    "keyword": {
+                        "type": "keyword",
+                        "ignore_above": 256,
+                        "normalizer": "to_lower"
+                    },
+                    "search_as_you_type": {
+                        "type": "search_as_you_type",
+                        "doc_values": False,
+                        "max_shingle_size": 3
+                    }
+                }
+            },
+            "channel_banner_url": {
+                "type": "keyword",
+                "index": False
+            },
+            "channel_thumb_url": {
+                "type": "keyword",
+                "index": False
+            },
+            "channel_description": {
+                "type": "text"
+            },
+            "channel_last_refresh": {
+                "type": "date",
+                "format": "epoch_second"
+            }
+        },
+        'expected_set': {
+            "analysis": {
+                "normalizer": {
+                    "to_lower": {
+                        "type": "custom",
+                        "filter": ["lowercase"]
+                    }
+                }
+            },
+            "number_of_replicas": 0
+        }
+    },
+    {
+        'index_name': 'video',
+        'expected_map': {
+            "vid_thumb_url": {
+                "type": "text",
+                "index": False
+            },
+            "date_downloaded": {
+                "type": "date"
+            },
+            "channel": {
+                "properties": {
+                    "channel_id": {
+                        "type": "keyword",
+                    },
+                    "channel_name": {
+                        "type": "text",
+                        "fields": {
+                            "keyword": {
+                                "type": "keyword",
+                                "ignore_above": 256,
+                                "normalizer": "to_lower"
+                            },
+                            "search_as_you_type": {
+                                "type": "search_as_you_type",
+                                "doc_values": False,
+                                "max_shingle_size": 3
+                            }
+                        }
+                    },
+                    "channel_banner_url": {
+                        "type": "keyword",
+                        "index": False
+                    },
+                    "channel_thumb_url": {
+                        "type": "keyword",
+                        "index": False
+                    },
+                    "channel_description": {
+                        "type": "text"
+                    },
+                    "channel_last_refresh": {
+                        "type": "date",
+                        "format": "epoch_second"
+                    }
+                }
+            },
+            "description": {
+                "type": "text"
+            },
+            "media_url": {
+                "type": "keyword",
+                "index": False
+            },
+            "title": {
+                "type": "text",
+                "fields": {
+                    "keyword": {
+                        "type": "keyword",
+                        "ignore_above": 256,
+                        "normalizer": "to_lower"
+                    },
+                    "search_as_you_type": {
+                        "type": "search_as_you_type",
+                        "doc_values": False,
+                        "max_shingle_size": 3
+                    }
+                }
+            },
+            "vid_last_refresh": {
+                "type": "date"
+            },
+            "youtube_id": {
+                "type": "keyword"
+            },
+            "published": {
+                "type": "date"
+            },
+        },
+        'expected_set': {
+            "analysis": {
+                "normalizer": {
+                    "to_lower": {
+                        "type": "custom",
+                        "filter": ["lowercase"]
+                    }
+                }
+            },
+            "number_of_replicas": 0
+        }
+    },
+    {
+        'index_name': 'download',
+        'expected_map': {
+            "timestamp": {
+                "type": "date"
+            },
+            "channel_id": {
+                "type": "keyword"
+            },
+            "channel_name": {
+                "type": "text",
+                "fields": {
+                    "keyword": {
+                        "type": "keyword",
+                        "ignore_above": 256,
+                        "normalizer": "to_lower"
+                    }
+                }
+            },
+            "status": {
+                "type": "keyword"
+            },
+            "title": {
+                "type": "text",
+                "fields": {
+                    "keyword": {
+                        "type": "keyword",
+                        "ignore_above": 256,
+                        "normalizer": "to_lower"
+                    }
+                }
+            },
+            "vid_thumb_url": {
+                "type": "keyword"
+            },
+            "youtube_id": {
+                "type": "keyword"
+            }
+        },
+        'expected_set': {
+            "analysis": {
+                "normalizer": {
+                    "to_lower": {
+                        "type": "custom",
+                        "filter": ["lowercase"]
+                    }
+                }
+            },
+            "number_of_replicas": 0
+        }
+    }
+]
+
+
+class ElasticIndex:
+    """
+    handle mapping and settings on elastic search for a given index
+    """
+
+    CONFIG = AppConfig().config
+    ES_URL = CONFIG['application']['es_url']
+    HEADERS = {'Content-type': 'application/json'}
+
+    def __init__(self, index_name, expected_map, expected_set):
+        self.index_name = index_name
+        self.expected_map = expected_map
+        self.expected_set = expected_set
+        self.exists, self.details = self.index_exists()
+
+    def index_exists(self):
+        """ check if index already exists and return mapping if it does """
+        index_name = self.index_name
+        url = f'{self.ES_URL}/ta_{index_name}'
+        response = requests.get(url)
+        exists = response.ok
+
+        if exists:
+            details = response.json()[f'ta_{index_name}']
+        else:
+            details = False
+
+        return exists, details
+
+    def validate(self):
+        """
+        check if all expected mappings and settings match
+        returns True when rebuild is needed
+        """
+
+        if self.expected_map:
+            rebuild = self.validate_mappings()
+            if rebuild:
+                return rebuild
+
+        if self.expected_set:
+            rebuild = self.validate_settings()
+            if rebuild:
+                return rebuild
+
+        return False
+
+    def validate_mappings(self):
+        """ check if all mappings are as expected """
+
+        expected_map = self.expected_map
+        now_map = self.details['mappings']['properties']
+
+        for key, value in expected_map.items():
+            # nested
+            if list(value.keys()) == ['properties']:
+                for key_n, value_n in value['properties'].items():
+                    if key_n not in now_map[key]['properties'].keys():
+                        print(key_n, value_n)
+                        return True
+                    if not value_n == now_map[key]['properties'][key_n]:
+                        print(key_n, value_n)
+                        return True
+
+                continue
+
+            # not nested
+            if key not in now_map.keys():
+                print(key, value)
+                return True
+            if not value == now_map[key]:
+                print(key, value)
+                return True
+
+        return False
+
+    def validate_settings(self):
+        """ check if all settings are as expected """
+
+        now_set = self.details['settings']['index']
+
+        for key, value in self.expected_set.items():
+            if key not in now_set.keys():
+                print(key, value)
+                return True
+
+            if not value == now_set[key]:
+                print(key, value)
+                return True
+
+        return False
+
+    def rebuild_index(self):
+        """ rebuild with new mapping """
+        # backup
+        self.reindex('backup')
+        # delete original
+        self.delete_index(backup=False)
+        # create new
+        self.create_blank()
+        self.reindex('restore')
+        # delete backup
+        self.delete_index()
+
+    def reindex(self, method):
+        """ create on elastic search """
+        index_name = self.index_name
+        if method == 'backup':
+            source = f'ta_{index_name}'
+            destination = f'ta_{index_name}_backup'
+        elif method == 'restore':
+            source = f'ta_{index_name}_backup'
+            destination = f'ta_{index_name}'
+
+        query = {
+            "source": {
+                "index": source
+            },
+            "dest": {
+                "index": destination
+            }
+        }
+        data = json.dumps(query)
+        url = self.ES_URL + '/_reindex?refresh=true'
+        response = requests.post(url=url, data=data, headers=self.HEADERS)
+        if not response.ok:
+            print(response.text)
+
+    def delete_index(self, backup=True):
+        """ delete index passed as argument """
+        if backup:
+            url = f'{self.ES_URL}/ta_{self.index_name}_backup'
+        else:
+            url = f'{self.ES_URL}/ta_{self.index_name}'
+        response = requests.delete(url)
+        if not response.ok:
+            print(response.text)
+
+    def create_blank(self):
+        """ apply new mapping and settings for blank new index """
+        expected_map = self.expected_map
+        expected_set = self.expected_set
+        # stich payload
+        payload = {}
+        if expected_set:
+            payload.update({"settings": expected_set})
+        if expected_map:
+            payload.update({"mappings": {"properties": expected_map}})
+        # create
+        url = f'{self.ES_URL}/ta_{self.index_name}'
+        data = json.dumps(payload)
+        response = requests.put(url=url, data=data, headers=self.HEADERS)
+        if not response.ok:
+            print(response.text)
+
+
+class ElasticBackup:
+    """ dump index to nd-json files for later bulk import """
+
+    def __init__(self, index_config):
+        self.config = AppConfig().config
+        self.index_config = index_config
+        self.timestamp = datetime.now().strftime('%Y%m%d')
+
+    def get_all_documents(self, index_name):
+        """ export all documents of a single index """
+        headers = {'Content-type': 'application/json'}
+        es_url = self.config['application']['es_url']
+        # get PIT ID
+        url = f'{es_url}/ta_{index_name}/_pit?keep_alive=1m'
+        response = requests.post(url)
+        json_data = json.loads(response.text)
+        pit_id = json_data['id']
+        # build query
+        data = {
+            "query": {"match_all": {}},
+            "size": 100, "pit": {"id": pit_id, "keep_alive": "1m"},
+            "sort": [ {"_id": {"order": "asc"}} ]
+        }
+        query_str = json.dumps(data)
+        url = es_url + '/_search'
+        # loop until nothing left
+        all_results = []
+        while True:
+            response = requests.get(url, data=query_str, headers=headers)
+            json_data = json.loads(response.text)
+            all_hits = json_data['hits']['hits']
+            if all_hits:
+                for hit in all_hits:
+                    search_after = hit['sort']
+                    all_results.append(hit)
+                # update search_after with last hit data
+                data['search_after'] = search_after
+                query_str = json.dumps(data)
+            else:
+                break
+        # clean up PIT
+        query_str = json.dumps({"id": pit_id})
+        requests.delete(es_url + '/_pit', data=query_str, headers=headers)
+
+        return all_results
+
+    @staticmethod
+    def build_bulk(all_results):
+        """ build bulk query data from all_results """
+        bulk_list = []
+
+        for document in all_results:
+            document_id = document['_id']
+            es_index = document['_index']
+            action = { "index" : { "_index": es_index, "_id": document_id } }
+            source = document['_source']
+            bulk_list.append(json.dumps(action))
+            bulk_list.append(json.dumps(source))
+
+        # add last newline
+        bulk_list.append('\n')
+        file_content = '\n'.join(bulk_list)
+
+        return file_content
+
+    def write_json_file(self, file_content, index_name):
+        """ write json file to disk """
+        cache_dir = self.config['application']['cache_dir']
+        file_name = f'ta_{index_name}-{self.timestamp}.json'
+        file_path = os.path.join(cache_dir, file_name)
+        with open(file_path, 'w', encoding='utf-8') as f:
+            f.write(file_content)
+
+    def post_bulk_restore(self, file_name):
+        """ send bulk to es """
+        cache_dir = self.config['application']['cache_dir']
+        es_url = self.config['application']['es_url']
+        headers = {'Content-type': 'application/x-ndjson'}
+        file_path = os.path.join(cache_dir, file_name)
+
+        with open(file_path, 'r', encoding='utf-8') as f:
+            query_str = f.read()
+
+        url = es_url + '/_bulk'
+        request = requests.post(url, data=query_str, headers=headers)
+        if not request.ok:
+            print(request.text)
+
+    def restore_from_file(self):
+        """ restore all available backup files """
+        cache_dir = self.config['application']['cache_dir']
+        all_available_backups = [
+            i for i in os.listdir(cache_dir) if
+            i.startswith('ta_') and i.endswith('.json')
+        ]
+        for file_name in all_available_backups:
+            self.post_bulk_restore(file_name)
+
+
+def backup_all_indexes():
+    """ backup all es indexes to disk """
+    backup_handler = ElasticBackup(INDEX_CONFIG)
+
+    for index in backup_handler.index_config:
+        index_name = index['index_name']
+        all_results = backup_handler.get_all_documents(index_name)
+        file_content = backup_handler.build_bulk(all_results)
+        backup_handler.write_json_file(file_content, index_name)
+
+
+def restore_from_backup():
+    """ restore indexes from backup file """
+    # delete
+    index_check(force_restore=True)
+    # recreate
+    backup_handler = ElasticBackup(INDEX_CONFIG)
+    backup_handler.restore_from_file()
+
+
+def index_check(force_restore=False):
+    """ check if all indexes are created and have correct mapping """
+    for index in INDEX_CONFIG:
+        index_name = index['index_name']
+        expected_map = index['expected_map']
+        expected_set = index['expected_set']
+        handler = ElasticIndex(index_name, expected_map, expected_set)
+        # force restore
+        if force_restore:
+            handler.delete_index(backup=False)
+            handler.create_blank()
+            continue
+
+        # create new
+        if not handler.exists:
+            print(f'create new blank index with name ta_{index_name}...')
+            handler.create_blank()
+            continue
+
+        # validate index
+        rebuild = handler.validate()
+        if rebuild:
+            print(f'applying new mappings to index ta_{index_name}...')
+            handler.rebuild_index()
+            continue
+
+        # else all good
+        print(f'ta_{index_name} index is created and up to date...')

tubearchivist/home/src/reindex.py

@@ -0,0 +1,347 @@
+"""
+Functionality:
+- reindexing old documents
+- syncing updated values between indexes
+- scan the filesystem to delete or index
+"""
+
+import json
+import os
+from datetime import datetime
+from time import sleep
+from math import ceil
+
+import requests
+
+from home.src.download import ChannelSubscription, PendingList
+from home.src.config import AppConfig
+from home.src.index import (
+    YoutubeChannel,
+    YoutubeVideo,
+    index_new_video
+)
+from home.src.helper import get_total_hits, clean_string, set_message
+
+
+class Reindex:
+    """ check for outdated documents and refresh data from youtube """
+
+    def __init__(self):
+        self.video_daily, self.channel_daily = self.get_daily()
+        self.all_youtube_ids = False
+        self.all_channel_ids = False
+        # config
+        config = AppConfig().config
+        self.sleep_interval = config['downloads']['sleep_interval']
+        self.es_url = config['application']['es_url']
+        self.refresh_interval = 90
+
+    def get_daily(self):
+        """ get daily refresh values """
+        total_videos = get_total_hits(
+            'ta_video', self.es_url, 'active'
+        )
+        video_daily = ceil(total_videos / self.refresh_interval * 1.2)
+        total_channels = get_total_hits(
+            'ta_channel', self.es_url, 'channel_active'
+        )
+        channel_daily = ceil(total_channels / self.refresh_interval * 1.2)
+        return (video_daily, channel_daily)
+
+    def get_outdated_vids(self):
+        """ get daily videos to refresh """
+        headers = {'Content-type': 'application/json'}
+        now = int(datetime.now().strftime("%s"))
+        now_3m = now - 3 * 30 * 24 * 60 * 60
+        size = self.video_daily
+        data = {
+            "size": size,
+            "query": {
+                "bool": {
+                    "must": [
+                        {"match": {"active": True}},
+                        {"range": {"vid_last_refresh": {"lte": now_3m}}}
+                    ]
+                }
+            },
+            "sort": [{"vid_last_refresh": {"order": "asc"}}], "_source": False
+        }
+        query_str = json.dumps(data)
+        url = self.es_url + '/ta_video/_search'
+        response = requests.get(url, data=query_str, headers=headers)
+        if not response.ok:
+            print(response.text)
+        response_dict = json.loads(response.text)
+        all_youtube_ids = [i['_id'] for i in response_dict['hits']['hits']]
+        return all_youtube_ids
+
+    def get_outdated_channels(self):
+        """ get daily channels to refresh """
+        headers = {'Content-type': 'application/json'}
+        now = int(datetime.now().strftime("%s"))
+        now_3m = now - 3 * 30 * 24 * 60 * 60
+        size = self.channel_daily
+        data = {
+            "size": size,
+            "query": {
+                "bool": {
+                    "must": [
+                        {"match": {"channel_active": True}},
+                        {"range": {"channel_last_refresh": {"lte": now_3m}}}
+                    ]
+                }
+            },
+            "sort": [{"channel_last_refresh": {"order": "asc"}}],
+            "_source": False
+        }
+        query_str = json.dumps(data)
+        url = self.es_url + '/ta_channel/_search'
+        response = requests.get(url, data=query_str, headers=headers)
+        if not response.ok:
+            print(response.text)
+        response_dict = json.loads(response.text)
+        all_channel_ids = [i['_id'] for i in response_dict['hits']['hits']]
+        return all_channel_ids
+
+    def check_outdated(self):
+        """ add missing vids and channels """
+        self.all_youtube_ids = self.get_outdated_vids()
+        self.all_channel_ids = self.get_outdated_channels()
+
+    def rescrape_all_channels(self):
+        """ sync new data from channel to all matching videos """
+        sleep_interval = self.sleep_interval
+        channel_sub_handler = ChannelSubscription()
+        all_channels = channel_sub_handler.get_channels(
+            subscribed_only=False
+        )
+        all_channel_ids = [i['channel_id'] for i in all_channels]
+
+        counter = 1
+        for channel_id in all_channel_ids:
+            message = f'Progress: {counter}/{len(all_channels)}'
+            mess_dict = {
+                "status": "scraping",
+                "level": "info",
+                "title": "Scraping all youtube channels",
+                "message": message
+            }
+            set_message('progress:download', mess_dict)
+            channel_index = YoutubeChannel(channel_id)
+            subscribed = channel_index.channel_dict['channel_subscribed']
+            channel_index.channel_dict = channel_index.build_channel_dict(
+                scrape=True
+            )
+            channel_index.channel_dict['channel_subscribed'] = subscribed
+            channel_index.upload_to_es()
+            channel_index.sync_to_videos()
+            counter = counter + 1
+            if sleep_interval:
+                sleep(sleep_interval)
+
+    @staticmethod
+    def reindex_single_video(youtube_id):
+        """ refresh data for single video """
+        vid_handler = YoutubeVideo(youtube_id)
+        if not vid_handler.vid_dict:
+            # stop if deactivated
+            vid_handler.deactivate()
+            return
+
+        es_vid_dict = vid_handler.get_es_data()
+        player = es_vid_dict['_source']['player']
+        date_downloaded = es_vid_dict['_source']['date_downloaded']
+        channel_dict = es_vid_dict['_source']['channel']
+        channel_name = channel_dict['channel_name']
+        vid_handler.build_file_path(channel_name)
+        # add to vid_dict
+        vid_handler.vid_dict['player'] = player
+        vid_handler.vid_dict['date_downloaded'] = date_downloaded
+        vid_handler.vid_dict['channel'] = channel_dict
+        # update
+        vid_handler.upload_to_es()
+        vid_handler.delete_cache()
+
+    @staticmethod
+    def reindex_single_channel(channel_id):
+        """ refresh channel data and sync to videos """
+        channel_handler = YoutubeChannel(channel_id)
+        subscribed = channel_handler.channel_dict['channel_subscribed']
+        channel_handler.channel_dict = channel_handler.build_channel_dict(
+            scrape=True
+        )
+        channel_handler.channel_dict['channel_subscribed'] = subscribed
+        channel_handler.upload_to_es()
+        channel_handler.sync_to_videos()
+        channel_handler.clear_cache()
+
+    def reindex(self):
+        """ reindex what's needed """
+        # videos
+        for youtube_id in self.all_youtube_ids:
+            self.reindex_single_video(youtube_id)
+            if self.sleep_interval:
+                sleep(self.sleep_interval)
+        # channels
+        for channel_id in self.all_channel_ids:
+            self.reindex_single_channel(channel_id)
+            if self.sleep_interval:
+                sleep(self.sleep_interval)
+
+
+class FilesystemScanner:
+    """ handle scanning and fixing from filesystem """
+
+    CONFIG = AppConfig().config
+    ES_URL = CONFIG['application']['es_url']
+    VIDEOS = CONFIG['application']['videos']
+
+    def __init__(self):
+        self.all_downloaded = self.get_all_downloaded()
+        self.all_indexed = self.get_all_indexed()
+        self.missmatch = None
+        self.to_rename = None
+        self.to_index = None
+        self.to_delete = None
+
+    def get_all_downloaded(self):
+        """ get a list of all video files downloaded """
+        all_channels = os.listdir(self.VIDEOS)
+        all_channels.sort()
+        all_downloaded = []
+        for channel_name in all_channels:
+            channel_path = os.path.join(self.VIDEOS, channel_name)
+            for video in os.listdir(channel_path):
+                youtube_id = video[9:20]
+                all_downloaded.append((channel_name, video, youtube_id))
+
+        return all_downloaded
+
+    @staticmethod
+    def get_all_indexed():
+        """ get a list of all indexed videos """
+        index_handler = PendingList()
+        all_indexed_raw = index_handler.get_all_indexed()
+        all_indexed = []
+        for video in all_indexed_raw:
+            youtube_id = video['_id']
+            media_url = video['_source']['media_url']
+            published = video['_source']['published']
+            title = video['_source']['title']
+            all_indexed.append((youtube_id, media_url, published, title))
+        return all_indexed
+
+    def list_comarison(self):
+        """ compare the lists to figure out what to do """
+        self.find_unindexed()
+        self.find_missing()
+        self.find_bad_media_url()
+
+    def find_unindexed(self):
+        """ find video files without a matching document indexed """
+        all_indexed_ids = [i[0] for i in self.all_indexed]
+        to_index = []
+        for downloaded in self.all_downloaded:
+            if downloaded[2] not in all_indexed_ids:
+                to_index.append(downloaded)
+
+        self.to_index = to_index
+
+    def find_missing(self):
+        """ find indexed videos without matching media file """
+        all_downloaded_ids = [i[2] for i in self.all_downloaded]
+        to_delete = []
+        for video in self.all_indexed:
+            youtube_id = video[0]
+            if youtube_id not in all_downloaded_ids:
+                to_delete.append(video)
+
+        self.to_delete = to_delete
+
+    def find_bad_media_url(self):
+        """ rename media files not matching the indexed title """
+        to_fix = []
+        to_rename = []
+        for downloaded in self.all_downloaded:
+            channel, filename, downloaded_id = downloaded
+            # find in indexed
+            for indexed in self.all_indexed:
+                indexed_id, media_url, published, title = indexed
+                if indexed_id == downloaded_id:
+                    # found it
+                    title_c = clean_string(title)
+                    pub = published.replace('-', '')
+                    expected_filename = f'{pub}_{indexed_id}_{title_c}.mp4'
+                    new_url = os.path.join(channel, expected_filename)
+                    if expected_filename != filename:
+                        # file to rename
+                        to_rename.append(
+                            (channel, filename, expected_filename)
+                        )
+                    if media_url != new_url:
+                        # media_url to update in es
+                        to_fix.append((indexed_id, new_url))
+
+                    break
+
+        self.missmatch = to_fix
+        self.to_rename = to_rename
+
+    def rename_files(self):
+        """ rename media files as identified by find_bad_media_url """
+        for bad_filename in self.to_rename:
+            channel, filename, expected_filename = bad_filename
+            old_path = os.path.join(self.VIDEOS, channel, filename)
+            new_path = os.path.join(self.VIDEOS, channel, expected_filename)
+            os.rename(old_path, new_path)
+
+    def send_missmatch_bulk(self):
+        """ build bulk update """
+        bulk_list = []
+        for video_missmatch in self.missmatch:
+            youtube_id, media_url = video_missmatch
+            action = {"update": {"_id": youtube_id, "_index": 'ta_video'}}
+            source = {"doc": {"media_url": media_url}}
+            bulk_list.append(json.dumps(action))
+            bulk_list.append(json.dumps(source))
+        # add last newline
+        bulk_list.append('\n')
+        query_str = '\n'.join(bulk_list)
+        # make the call
+        headers = {'Content-type': 'application/x-ndjson'}
+        url = self.ES_URL + '/_bulk'
+        request = requests.post(url, data=query_str, headers=headers)
+        if not request.ok:
+            print(request.text)
+
+    def delete_from_index(self):
+        """ find indexed but deleted mediafile """
+        for indexed in self.to_delete:
+            youtube_id, _ = indexed
+            url = self.ES_URL + '/ta_video/_doc/' + youtube_id
+            request = requests.delete(url)
+            if not request.ok:
+                print(request.text)
+
+
+def scan_filesystem():
+    """ grouped function to delete and update index """
+    filesystem_handler = FilesystemScanner()
+    filesystem_handler.list_comarison()
+    if filesystem_handler.to_rename:
+        filesystem_handler.rename_files()
+    if filesystem_handler.missmatch:
+        filesystem_handler.send_missmatch_bulk()
+    if filesystem_handler.to_delete:
+        filesystem_handler.delete_from_index()
+    if filesystem_handler.to_index:
+        for missing_vid in filesystem_handler.to_index:
+            youtube_id = missing_vid[2]
+            index_new_video(youtube_id)
+
+
+def reindex_old_documents():
+    """ daily refresh of old documents """
+    reindex_handler = Reindex()
+    reindex_handler.check_outdated()
+    reindex_handler.reindex()

tubearchivist/home/src/searching.py

@@ -0,0 +1,237 @@
+"""
+Functionality:
+- handle search to populate results to view
+- cache youtube video thumbnails and channel artwork
+- parse values in hit_cleanup for frontend
+- calculate pagination values
+"""
+
+import math
+import os
+import urllib.parse
+
+from datetime import datetime
+
+import requests
+
+from PIL import Image
+
+from home.src.config import AppConfig
+
+
+class SearchHandler:
+    """ search elastic search """
+
+    CONFIG = AppConfig().config
+    CACHE_DIR = CONFIG['application']['cache_dir']
+
+    def __init__(self, url, data, cache=True):
+        self.max_hits = None
+        self.url = url
+        self.data = data
+        self.cache = cache
+
+    def get_data(self):
+        """ get the data """
+        if self.data:
+            response = requests.get(self.url, json=self.data).json()
+        else:
+            response = requests.get(self.url).json()
+
+        if 'hits' in response.keys():
+            self.max_hits = response['hits']['total']['value']
+            return_value = response['hits']['hits']
+        else:
+            # simulate list for single result to reuse rest of class
+            return_value = [response]
+
+        # stop if empty
+        if not return_value:
+            return False
+
+        all_videos = []
+        all_channels = []
+        for idx, hit in enumerate(return_value):
+            return_value[idx] = self.hit_cleanup(hit)
+            if hit['_index'] == 'ta_video':
+                video_dict, channel_dict = self.vid_cache_link(hit)
+                if video_dict not in all_videos:
+                    all_videos.append(video_dict)
+                if channel_dict not in all_channels:
+                    all_channels.append(channel_dict)
+            elif hit['_index'] == 'ta_channel':
+                channel_dict = self.channel_cache_link(hit)
+                if channel_dict not in all_channels:
+                    all_channels.append(channel_dict)
+        if self.cache:
+            # validate cache
+            self.cache_dl_vids(all_videos)
+            self.cache_dl_chan(all_channels)
+
+        return return_value
+
+    @staticmethod
+    def vid_cache_link(hit):
+        """ download thumbnails into chache """
+        vid_thumb = hit['source']['vid_thumb_url']
+        youtube_id = hit['source']['youtube_id']
+        channel_id_hit = hit['source']['channel']['channel_id']
+        chan_thumb = hit['source']['channel']['channel_thumb_url']
+        try:
+            chan_banner = hit['source']['channel']['channel_banner_url']
+        except KeyError:
+            chan_banner = False
+        video_dict = {
+            'youtube_id': youtube_id,
+            'vid_thumb': vid_thumb
+        }
+        channel_dict = {
+            'channel_id': channel_id_hit,
+            'chan_thumb': chan_thumb,
+            'chan_banner': chan_banner
+        }
+        return video_dict, channel_dict
+
+    @staticmethod
+    def channel_cache_link(hit):
+        """ build channel thumb links """
+        channel_id_hit = hit['source']['channel_id']
+        chan_thumb = hit['source']['channel_thumb_url']
+        try:
+            chan_banner = hit['source']['channel_banner_url']
+        except KeyError:
+            chan_banner = False
+        channel_dict = {
+            'channel_id': channel_id_hit,
+            'chan_thumb': chan_thumb,
+            'chan_banner': chan_banner
+        }
+        return channel_dict
+
+    def cache_dl_vids(self, all_videos):
+        """ video thumbs links for cache """
+        vid_cache = os.path.join(self.CACHE_DIR, 'videos')
+        all_vid_cached = os.listdir(vid_cache)
+        # videos
+        for video_dict in all_videos:
+            youtube_id = video_dict['youtube_id']
+            if not youtube_id + '.jpg' in all_vid_cached:
+                cache_path = os.path.join(vid_cache, youtube_id + '.jpg')
+                thumb_url = video_dict['vid_thumb']
+                img_raw = requests.get(thumb_url, stream=True).raw
+                img = Image.open(img_raw)
+                width, height = img.size
+                if not width / height == 16 / 9:
+                    new_height = width / 16 * 9
+                    offset = (height - new_height) / 2
+                    img = img.crop((0, offset, width, height - offset))
+                img.save(cache_path)
+
+    def cache_dl_chan(self, all_channels):
+        """ download channel thumbs """
+        chan_cache = os.path.join(self.CACHE_DIR, 'channels')
+        all_chan_cached = os.listdir(chan_cache)
+        for channel_dict in all_channels:
+            channel_id_cache = channel_dict['channel_id']
+            channel_banner_url = channel_dict['chan_banner']
+            channel_banner = channel_id_cache + '_banner.jpg'
+            channel_thumb_url = channel_dict['chan_thumb']
+            channel_thumb = channel_id_cache + '_thumb.jpg'
+            # thumb
+            if channel_thumb_url and channel_thumb not in all_chan_cached:
+                cache_path = os.path.join(chan_cache, channel_thumb)
+                img_raw = requests.get(channel_thumb_url, stream=True).content
+                with open(cache_path, 'wb') as f:
+                    f.write(img_raw)
+            # banner
+            if channel_banner_url and channel_banner not in all_chan_cached:
+                cache_path = os.path.join(chan_cache, channel_banner)
+                img_raw = requests.get(channel_banner_url, stream=True).content
+                with open(cache_path, 'wb') as f:
+                    f.write(img_raw)
+
+    @staticmethod
+    def hit_cleanup(hit):
+        """ clean up and parse data from a single hit """
+        hit['source'] = hit.pop('_source')
+        hit_keys = hit['source'].keys()
+        if 'media_url' in hit_keys:
+            parsed_url = urllib.parse.quote(hit['source']['media_url'])
+            hit['source']['media_url'] = parsed_url
+
+        if 'published' in hit_keys:
+            published = hit['source']['published']
+            date_pub = datetime.strptime(published, "%Y-%m-%d")
+            date_str = datetime.strftime(date_pub, "%d %b, %Y")
+            hit['source']['published'] = date_str
+
+        if 'vid_last_refresh' in hit_keys:
+            vid_last_refresh = hit['source']['vid_last_refresh']
+            date_refresh = datetime.fromtimestamp(vid_last_refresh)
+            date_str = datetime.strftime(date_refresh, "%d %b, %Y")
+            hit['source']['vid_last_refresh'] = date_str
+
+        if 'channel_last_refresh' in hit_keys:
+            refreshed = hit['source']['channel_last_refresh']
+            date_refresh = datetime.fromtimestamp(refreshed)
+            date_str = datetime.strftime(date_refresh, "%d %b, %Y")
+            hit['source']['channel_last_refresh'] = date_str
+
+        if 'channel' in hit_keys:
+            channel_keys = hit['source']['channel'].keys()
+            if 'channel_last_refresh' in channel_keys:
+                refreshed = hit['source']['channel']['channel_last_refresh']
+                date_refresh = datetime.fromtimestamp(refreshed)
+                date_str = datetime.strftime(date_refresh, "%d %b, %Y")
+                hit['source']['channel']['channel_last_refresh'] = date_str
+
+        return hit
+
+
+class Pagination:
+    """
+    figure out the pagination based on page size and total_hits
+    """
+
+    def __init__(self, page_get, search_get=False):
+        config = AppConfig().config
+        self.page_size = config['archive']['page_size']
+        self.page_get = page_get
+        self.search_get = search_get
+        self.pagination = self.first_guess()
+
+    def first_guess(self):
+        """ build first guess before api call """
+        page_get = self.page_get
+        if page_get in [0, 1]:
+            page_from = 0
+            prev_pages = False
+        elif page_get > 1:
+            page_from = (page_get - 1) * self.page_size
+            prev_pages = [
+                i for i in range(page_get - 1, page_get - 6, -1) if i > 1
+            ]
+            prev_pages.reverse()
+        pagination = {
+            "page_size": self.page_size,
+            "page_from": page_from,
+            "prev_pages": prev_pages,
+            "current_page": page_get
+        }
+        if self.search_get:
+            pagination.update({"search_get": self.search_get})
+        return pagination
+
+    def validate(self, total_hits):
+        """ validate pagination with total_hits after making api call """
+        page_get = self.page_get
+        max_pages = math.ceil(total_hits / self.page_size)
+        if page_get < max_pages and max_pages > 1:
+            self.pagination['last_page'] = max_pages
+        else:
+            self.pagination['last_page'] = False
+        next_pages = [
+            i for i in range(page_get + 1, page_get + 6) if 1 < i < max_pages
+        ]
+
+        self.pagination['next_pages'] = next_pages

tubearchivist/home/tasks.py

@@ -0,0 +1,68 @@
+"""
+Functionality:
+- initiate celery app
+- collect tasks
+"""
+
+import os
+
+from celery import Celery, shared_task
+
+from home.src.download import (
+    PendingList,
+    ChannelSubscription,
+    VideoDownloader
+)
+from home.src.config import AppConfig
+
+
+CONFIG = AppConfig().config
+LIMIT_COUNT = CONFIG['downloads']['limit_count']
+REDIS_HOST = CONFIG['application']['REDIS_HOST']
+
+os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'home.settings')
+app = Celery('tasks', broker='redis://' + REDIS_HOST)
+app.config_from_object('django.conf:settings', namespace='CELERY')
+app.autodiscover_tasks()
+
+
+@shared_task
+def update_subscribed():
+    """ look for missing videos and add to pending """
+    channel_handler = ChannelSubscription()
+    missing_videos = channel_handler.find_missing()
+    if missing_videos:
+        pending_handler = PendingList()
+        pending_handler.add_to_pending(missing_videos)
+
+
+@shared_task
+def download_pending():
+    """ download latest pending videos """
+    pending_handler = PendingList()
+    pending_vids = pending_handler.get_all_pending()[0]
+    pending = [i['youtube_id'] for i in pending_vids]
+    pending.reverse()
+    if LIMIT_COUNT:
+        to_download = pending[:LIMIT_COUNT]
+    else:
+        to_download = pending
+    if to_download:
+        download_handler = VideoDownloader(to_download)
+        download_handler.download_list()
+
+
+@shared_task
+def download_single(youtube_id):
+    """ start download single video now """
+    to_download = [youtube_id]
+    download_handler = VideoDownloader(to_download)
+    download_handler.download_list()
+
+
+@shared_task
+def extrac_dl(youtube_ids):
+    """ parse list passed and add to pending """
+    pending_handler = PendingList()
+    missing_videos = pending_handler.parse_url_list(youtube_ids)
+    pending_handler.add_to_pending(missing_videos)

tubearchivist/home/templates/home/about.html

@@ -0,0 +1,38 @@
+{% extends "home/base.html" %}
+{% load static %}
+{% block content %}
+<div class="title-bar">
+    <h1>About The Tube Archivist</h1>
+</div>
+<div class="about-section">
+    <h2>Getting started</h2>
+    <ol>
+        <li>Before adding some videos to the download queue, take a look at the download format settings on your <a href="{% url 'settings' %}#format">settings</a> page and set your desired download quality.</li>
+        <li>While at the settings page also set the value for the Subscriptions <a href="{% url 'settings' %}#subscriptions">page size</a>. This will define the max amount of videos that will get added once you run <i>Rescan Subscriptions</i>. yt-dlp by default uses 50 video page size. Any value higher than that will significantly slow down the scanning process.</li>
+        <li>Subscribe to some of your favourite youtube channels in the <a href="{% url 'channel' %}">channel</a> page. To subscribe to a channel you have a few options:
+            <ul>
+                <li>Enter the Youtube channel ID, a 25 character alphanumeric string. For example <span class="settings-current">UCBa659QWEk1AI4Tg--mrJ2A</span></li>
+                <li>Enter the url to the channel page on youtube. For example <span class="settings-current">https://www.youtube.com/channel/UCBa659QWEk1AI4Tg--mrJ2A</span></li>
+                <li>Enter the video url for any video and let <i>Tube Archivist</i> extract the channel ID for you. For example <span class="settings-current">https://www.youtube.com/watch?v=2tdiKTSdE9Y</span></li>
+            </ul>
+        </li>
+        <li>After that head over to the <a href="{% url 'downloads' %}">Downloads</a> Page. Once you click on the <i>Rescan Subscriptions</i> button, Tube Archivist will go through all your subscribed channels and look for new videos. Initially these are the latest videos depending on the page size as described above.</li>
+        <li>Click on <span class="settings-current">ignore</span> for any video you don't want to download or on <span class="settings-current">Download now</span> for any video you want to start downloading now independently from the queue.</li>
+        <li>Click on the <span class="settings-current">Download queue</span> button to start downloading. Tube Archivist will then start the queue from the bottom and download as many videos as defined in <a href="{% url 'settings' %}#downloads">download limit</a>. There is currently no good way to cancel the download process.</li>
+    </ol>
+</div>
+<div class="about-section">
+    <h2>Additional</h2>
+    <ul>
+        <li>You can manually add videos to the queue on the <a href="{% url 'downloads' %}">download page</a> by clicking on <i>Add to download queue</i> and then entering a list of videos. Add one link per line. You have a few options:
+            <ul>
+                <li>Add a link to a Youtube video. For example <span class="settings-current">https://www.youtube.com/watch?v=2tdiKTSdE9Y</span>.</li>
+                <li>Add a Youtube video ID. For example <span class="settings-current">2tdiKTSdE9Y</span>.</li>
+                <li>Add a link to a Youtube video by providing the shortened url, for example <span class="settings-current">https://youtu.be/2tdiKTSdE9Y</span>.</li>
+                <li>Add a Channel ID or Channel Url to add every available video to the download queue. This will ignore the page size as described above. You can still ignore selected videos before starting the download.</li>
+            </ul>
+        </li>
+        <li>As you watch videos, mark them as watched by clicking on the unseen icon <span class="about-icon"><img src="{% static 'img/icon-unseen.svg' %}" alt="unseen-icon" class="unseen-icon"></span>. Once marked as watched, the icon will change to <span class="about-icon"><img src="{% static 'img/icon-seen.svg' %}" alt="seen-icon" class="seen-icon"></span>.</li>
+    </ul>
+</div>
+{% endblock content %}

tubearchivist/home/templates/home/base.html

@@ -0,0 +1,103 @@
+{% load static %}
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta http-equiv="X-UA-Compatible" content="IE=edge">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <link rel="stylesheet" type="text/css" href="{% static 'css/style.css' %}">
+    <link rel="shortcut icon" type="image/png" href="{% static 'favicon.ico' %}"/>
+    {% if title %}
+        <title>TA | {{ title }}</title>
+    {% else %}
+        <title>TubeArchivist</title>
+    {% endif %}
+    {% if colors == "dark" %}
+        <link rel="stylesheet" href="{% static 'css/dark.css' %}">
+    {% else %}
+        <link rel="stylesheet" href="{% static 'css/light.css' %}">
+    {% endif %}
+    <script type="text/javascript" src="{% static 'script.js' %}"></script>
+</head>
+<body>
+    <div class="boxed-content">
+        <div class="top-banner">
+            <a href="{% url 'home' %}">
+                {% if colors == 'dark' %}
+                    <img src="{% static 'img/banner-tube-archivist-dark.png' %}" alt="tube-archivist-banner">
+                {% endif %}
+                {% if colors == 'light' %}
+                    <img src="{% static 'img/banner-tube-archivist-light.png' %}" alt="tube-archivist-banner">
+                {% endif %}
+            </a>
+        </div>
+        <div class="top-nav">
+            <div class="nav-items">
+                <a href="{% url 'home' %}">
+                    <div class="nav-item">home</div>
+                </a>
+                <a href="{% url 'channel' %}">
+                    <div class="nav-item">channels</div>
+                </a>
+                <a href="{% url 'downloads' %}">
+                    <div class="nav-item">downloads</div>
+                </a>
+            </div>
+            <div class="nav-icons">
+                <a href="{% url 'about' %}">
+                    <img src="{% static 'img/icon-help.svg' %}" alt="help-icon">
+                </a>
+                <a href="{% url 'settings' %}">
+                    <img src="{% static 'img/icon-gear.svg' %}" alt="gear-icon">
+                </a>
+            </div>
+        </div>
+        {% block content %}{% endblock %}
+            <div class="pagination">
+                {% if pagination %}
+                    {% if pagination.current_page > 1 %}
+                        {% if pagination.search_get %}
+                        <a class="pagination-item" href="{{ request.path }}?search={{ pagination.search_get }}">First</a>
+                        {% else %}
+                        <a class="pagination-item" href="{{ request.path }}">First</a>
+                        {% endif %}
+                    {% endif %}
+                    {% if pagination.prev_pages %}
+                        {% for page in pagination.prev_pages %}
+                            {% if pagination.search_get %}
+                            <a class="pagination-item" href="?page={{ page }}&search={{ pagination.search_get }}">{{ page }}</a>
+                            {% else %}
+                            <a class="pagination-item" href="?page={{ page }}">{{ page }}</a>
+                            {% endif %}
+                        {% endfor %}
+                    {% endif %}
+                    {% if pagination.current_page %}
+                    <span>< Page {{ pagination.current_page }}</span>
+                    {% endif %}
+                    {% if pagination.next_pages %}
+                        <span> ></span>
+                        {% for page in pagination.next_pages %}
+                            {% if pagination.search_get %}
+                            <a class="pagination-item" href="?page={{ page }}&search={{ pagination.search_get }}">{{ page }}</a>
+                            {% else %}
+                            <a class="pagination-item" href="?page={{ page }}">{{ page }}</a>
+                            {% endif %}
+                        {% endfor %}
+                    {% endif %}
+                    {% if pagination.last_page > 0 %}
+                        {% if pagination.search_get %}
+                        <a class="pagination-item" href="?page={{ pagination.last_page }}&search={{ pagination.search_get }}">Last ({{ pagination.last_page }})</a>
+                        {% else %}
+                        <a class="pagination-item" href="?page={{ pagination.last_page }}">Last ({{ pagination.last_page }})</a>
+                        {% endif %}
+                    {% endif %}
+                {% endif %}
+            </div>
+    </div>
+    <div class="footer">
+        <div class="boxed-content">
+            <span>© 2021 | The Tube Archivist</span>
+        </div>
+    </div>
+</body>
+</html>

tubearchivist/home/templates/home/channel.html

@@ -0,0 +1,85 @@
+{% extends "home/base.html" %}
+{% load static %}
+{% load humanize %}
+{% block content %}
+<div class="title-bar">
+    <h1>Channels</h1>
+</div>
+<div class="two-col">
+    <div>
+        <h2>Subscribe to channel</h2>
+        <p>Input channel ID, channel URL or Video of a channel</p>
+        <form action="/channel/" method="post">
+            {% csrf_token %}
+            <input type="text" id="subscribe" name="subscribe" autocomplete="off">
+            <button type="submit">Subscribe</button>
+        </form>
+    </div>
+    <div class="search-form">
+        <form onSubmit="return channelRedirect();" id="search-box">
+            {% csrf_token %}
+            <input name="videoSearch" list="resultBox" type="text" id="searchInput" autocomplete="off" oninput="searchChannels(this.value)">
+            <datalist id="resultBox">
+            </datalist>
+        </form>
+        <div class="search-icon">
+            <img src="{% static 'img/icon-search.svg' %}" alt="search-icon" onclick="showSearch()">
+        </div>
+    </div>
+</div>
+<div class="padding-box">
+    <h2>Total matching channels: {{ max_hits }}</h2>
+    <span>Change show / hide subscribed only </span><span class="settings-current">{{ show_subed_only }}</span>
+    <select name="watched" id="watched" onchange="showSubscribedOnly(this.value)">
+        <option value="" disabled selected> -- change -- </option>
+        <option value="0">show all channels</option>
+        <option value="1">show subscribed channels only</option>
+    </select>
+</div>
+<div>
+    {% if channels %}
+        {% for channel in channels %}
+        <div class="channel-item">
+            {% if channel.source.channel_banner_url %}
+                <div class="channel-banner">
+                    <a href="{% url 'channel_id' channel.source.channel_id %}">
+                        <img src="/cache/channels/{{ channel.source.channel_id }}_banner.jpg" alt="{{ channel.source.channel_id }}-banner">
+                    </a>
+                </div>
+            {% endif %}
+            <div class="info-box info-box-2">
+                <div class="info-box-item">
+                    <div class="round-img">
+                        <a href="{% url 'channel_id' channel.source.channel_id %}">
+                            <img src="/cache/channels/{{ channel.source.channel_id }}_thumb.jpg" alt="channel-thumb">
+                        </a>
+                    </div>
+                    <div>
+                        <h3><a href="{% url 'channel_id' channel.source.channel_id %}">{{ channel.source.channel_name }}</a></h3>
+                        {% if channel.source.channel_subs >= 1000000 %}
+                            <p>Subscribers: {{ channel.source.channel_subs|intword }}</p>
+                        {% else %}
+                            <p>Subscribers: {{ channel.source.channel_subs|intcomma }}</p>
+                        {% endif %}
+                    </div>
+                </div>
+                <div class="info-box-item">
+                    <div>
+                        <p>Last refreshed: {{ channel.source.channel_last_refresh }}</p>
+                        <p>Subscribed: 
+                        {% if channel.source.channel_subscribed %}
+                            <button type="button" id="{{ channel.source.channel_id }}" onclick="unsubscribe(this.id)" title="Unsubscribe from {{ channel.source.channel_name }}">Unsubscribe</button>
+                        {% else %}
+                            false
+                        {% endif %}
+                        </p>
+                    </div>
+                </div>
+            </div>
+        </div>
+        {% endfor %}
+    {% else %}
+        <h2>No channels found...</h2>
+    {% endif %}
+</div>
+{% endblock content %}

tubearchivist/home/templates/home/channel_id.html

@@ -0,0 +1,99 @@
+{% extends "home/base.html" %}
+{% block content %}
+{% load static %}
+{% load humanize %}
+<div class="title-bar">
+    <h1>Channel: {{ channel_info.channel_name }}</h1>
+</div>
+<div class="channel-banner">
+    {% if channel_info.channel_banner_url %}
+        <a href="/channel/{{ channel_info.channel_id }}/"><img src="/cache/channels/{{ channel_info.channel_id }}_banner.jpg" alt="channel_banner"></a>
+    {% endif %}
+</div>
+<div class="info-box info-box-3 padding-box">
+    <div class="info-box-item">
+        <div class="round-img">
+            <a href="{% url 'channel_id' channel_info.channel_id %}">
+                <img src="/cache/channels/{{ channel_info.channel_id }}_thumb.jpg" alt="channel-thumb">
+            </a>
+        </div>
+        <div>
+            <h3><a href="{% url 'channel_id' channel_info.channel_id %}">{{ channel_info.channel_name }}</a></h3>
+            {% if channel_info.channel_subs >= 1000000 %}
+                <span>Subscribers: {{ channel_info.channel_subs|intword }}</span>
+            {% else %}
+                <span>Subscribers: {{ channel_info.channel_subs|intcomma }}</span>
+            {% endif %}
+        </div>
+    </div>
+    <div class="info-box-item">
+        <div>
+            <p>Last refreshed: {{ channel_info.channel_last_refresh }}</p>
+            <p>Subscribed: 
+            {% if channel_info.channel_subscribed %}
+                <button type="button" id="{{ channel_info.channel_id }}" onclick="unsubscribe(this.id)" title="Unsubscribe from {{ channel_info.channel_name }}">Unsubscribe</button>
+            {% else %}
+                false
+            {% endif %}
+            </p>
+        </div>
+    </div>
+    {% if videos %}
+    <div class="info-box-item">
+        <div>
+            {% if channel_info.channel_views >= 1000000 %}
+                <p>Channel views: {{ channel_info.channel_views|intword }}</p>
+            {% else %}
+                <p>Channel views: {{ channel_info.channel_views|intcomma }}</p>
+            {% endif %}
+            <p>Total Videos archived: {{ max_hits }}</p>
+            <p>Watched: <button title="Mark all videos from {{ channel_info.channel_name }} as watched" type="button" id="{{ channel_info.channel_id }}" onclick="isWatched(this.id)">Mark as watched</button></p>
+            <p>Channel id: {{ channel_info.channel_id }}</p>
+        </div>
+    </div>
+    {% endif %}
+</div>
+{% if channel_info.channel_description %}
+    <div class="info-box-item description-box">
+        <p>Description: <button onclick="textReveal()" id="text-reveal-button">Show</button></p>
+        <div id="text-reveal" class="description-text">
+            {{ channel_info.channel_description|linebreaks }}
+        </div>
+    </div>
+{% endif %}
+<div id="player" class="video-player"></div>
+<h2>Videos</h2>
+<div class="video-list">
+    {% if videos %}
+        {% for video in videos %}
+            <div class="video-item">
+                <a href="#player" data-src="/media/{{ video.source.media_url }}" data-thumb="/cache/videos/{{ video.source.youtube_id }}.jpg" data-title="{{ video.source.title }}" data-channel="{{ video.source.channel.channel_name }}" data-id="{{ video.source.youtube_id }}" onclick="createPlayer(this)">
+                    <div class="video-thumb-wrap">
+                        <div class="video-thumb">
+                            <img src="/cache/videos/{{ video.source.youtube_id }}.jpg" alt="video-thumb">
+                        </div>
+                        <div class="video-play">
+                            <img src="{% static 'img/icon-play.svg' %}" alt="play-icon">
+                        </div>
+                    </div>
+                </a>
+                <div class="video-desc">
+                    <div class="video-desc-player" id="video-info-{{ video.source.youtube_id }}">
+                        {% if video.source.player.watched %}
+                            <img src="{% static 'img/icon-seen.svg' %}" alt="seen-icon" id="{{ video.source.youtube_id }}" class="seen-icon">
+                        {% else %}
+                            <img src="{% static 'img/icon-unseen.svg' %}" alt="unseen-icon" id="{{ video.source.youtube_id }}" onclick="isWatched(this.id)" class="unseen-icon" title="Mark as watched.">
+                        {% endif %}
+                        <span>{{ video.source.published }} | {{ video.source.player.duration_str }}</span>
+                    </div>
+                    <div>
+                        <a class="video-more" href="{% url 'video' video.source.youtube_id %}"><h2>{{ video.source.title }}</h2></a>
+                    </div>
+                </div>
+            </div>
+        {% endfor %}
+    {% else %}
+        <h2>No videos found...</h2>
+    {% endif %}
+</div>
+{% endblock content %}

tubearchivist/home/templates/home/downloads.html

@@ -0,0 +1,56 @@
+{% extends "home/base.html" %}
+{% load static %}
+{% block content %}
+<div class="title-bar">
+    <h1>Downloads</h1>
+</div>
+<div id="downloadMessage"></div>
+<div class="info-box info-box-3 padding-box">
+    <div class="icon-text">
+        <img id="rescan-icon" onclick="rescanPending()" src="{% static 'img/icon-rescan.svg' %}" alt="rescan-icon">
+        <p>Rescan subscriptions</p>
+    </div>
+    <div class="icon-text">
+        <img id="download-icon" onclick="dlPending()" src="{% static 'img/icon-download.svg' %}" alt="download-icon">
+        <p>Download queue</p>
+    </div>
+    <div class="icon-text">
+        <img id="add-icon" onclick="showForm()" src="{% static 'img/icon-add.svg' %}" alt="add-icon">
+        <p>Add to download queue</p>
+        <div class="show-form">
+            <form id='hidden-form' action="/downloads/" method="post">
+                {% csrf_token %}
+                <textarea rows="4" placeholder="Enter Video Urls or IDs here..." id="vid-url" name="vid-url"></textarea>
+                <button type="submit">Add to download queue</button>
+            </form>
+        </div>
+    </div>
+</div>
+<h2>Download queue</h2>
+<div>
+    {% if pending %}
+        <h3>Total pending downloads: {{ pending|length }}</h3>
+        {% for video in pending %}
+            <div class="dl-item" id="dl-{{ video.youtube_id }}">
+                <div class="dl-thumb">
+                    <img src="{{ video.vid_thumb_url }}" alt="video_thumb">
+                </div>
+                <div class="dl-desc">
+                    <h3>{{ video.title }}</h3>
+                    {% if video.channel_indexed %}
+                        <a href="{% url 'channel_id' video.channel_id %}">{{ video.channel_name }}</a>
+                    {% else %}
+                        <span>{{ video.channel_name }}</span>
+                    {% endif %}
+                    <p>Published: {{ video.published }} | Duration: {{ video.duration }} | {{ video.youtube_id }}</p>
+                    <button data-id="{{ video.youtube_id }}" onclick="toIgnore(this)">Ignore</button>
+                    <button data-id="{{ video.youtube_id }}" onclick="downloadNow(this)">Download now</button>
+                </div>
+            </div>
+        {% endfor %}
+    {% else %}
+        <h3>No pending downloads</h3>
+    {% endif %}
+</div>
+<script type="text/javascript" src="{% static 'progress.js' %}"></script>
+{% endblock content %}

tubearchivist/home/templates/home/home.html

@@ -0,0 +1,71 @@
+{% extends "home/base.html" %}
+{% block content %}
+{% load static %}
+<div class="title-bar">
+    <h1>Recent Videos</h1>
+</div>
+<div class="two-col">
+    <div class="sort">
+        <div>
+            <p>Sort order from <span class="settings-current">{{ sortorder }}</span>
+            <select name="sort" id="sort" onchange="sortChange(this.value)">
+                <option value="" disabled selected> -- change sort order -- </option>
+                <option value="published">date published</option>
+                <option value="downloaded">date downloaded</option>
+            </select></p>
+        </div>
+        <div>
+            <p>Hide watched videos <span class="settings-current">{{ hide_watched }}</span>
+            <select name="watched" id="watched" onchange="hideWatched(this.value)">
+                <option value="" disabled selected> -- change hide watched -- </option>
+                <option value="0">show watched videos</option>
+                <option value="1">hide watched videos</option>
+            </select></p>
+        </div>
+    </div>
+    <div class="search-form">
+        <form action="/" method="POST" id="search-box">
+            {% csrf_token %}
+            <input name="videoSearch" list="resultBox" type="text" id="searchInput" autocomplete="off">
+        </form>
+        <div class="search-icon">
+            <img src="{% static 'img/icon-search.svg' %}" alt="search-icon" onclick="showSearch()">
+        </div>
+    </div>
+</div>
+<div id="player" class="video-player"></div>
+<div class="video-list">
+    {% if videos %}
+        {% for video in videos %}
+            <div class="video-item">
+                <a href="#player" data-src="/media/{{ video.source.media_url }}" data-thumb="/cache/videos/{{ video.source.youtube_id }}.jpg" data-title="{{ video.source.title }}" data-channel="{{ video.source.channel.channel_name }}" data-id="{{ video.source.youtube_id }}" onclick="createPlayer(this)">
+                    <div class="video-thumb-wrap">
+                        <div class="video-thumb">
+                            <img src="/cache/videos/{{ video.source.youtube_id }}.jpg" alt="video-thumb">
+                        </div>
+                        <div class="video-play">
+                            <img src="{% static 'img/icon-play.svg' %}" alt="play-icon">
+                        </div>
+                    </div>
+                </a>
+                <div class="video-desc">
+                    <div class="video-desc-player" id="video-info-{{ video.source.youtube_id }}">
+                        {% if video.source.player.watched %}
+                            <img src="{% static 'img/icon-seen.svg' %}" alt="seen-icon" id="{{ video.source.youtube_id }}" class="seen-icon">
+                        {% else %}
+                            <img src="{% static 'img/icon-unseen.svg' %}" alt="unseen-icon" id="{{ video.source.youtube_id }}" onclick="isWatched(this.id)" class="unseen-icon" title="Mark as watched.">
+                        {% endif %}
+                        <span>{{ video.source.published }} | {{ video.source.player.duration_str }}</span>
+                    </div>
+                    <div>
+                        <a href="{% url 'channel_id' video.source.channel.channel_id %}"><h3>{{ video.source.channel.channel_name }}</h3></a>
+                        <a class="video-more" href="{% url 'video' video.source.youtube_id %}"><h2>{{ video.source.title }}</h2></a>
+                    </div>
+                </div>
+            </div>
+        {% endfor %}
+    {% else %}
+        <h2>No videos found...</h2>
+    {% endif %}
+</div>
+{% endblock content %}

tubearchivist/home/templates/home/settings.html

@@ -0,0 +1,127 @@
+{% extends "home/base.html" %}
+{% block content %}
+<div class="title-bar">
+    <h1>Settings</h1>
+</div>
+<form action="/settings/" method="POST">
+    {% csrf_token %}
+    <div class="settings-group">
+        <h2>Color scheme</h2>
+        <div class="settings-item">
+            <p>Current color scheme: <span class="settings-current">{{ config.application.colors }}</span></p>
+            <i>Select yout prefered color scheme between dark and light mode.</i><br>
+            <select name="application.colors" id="application.colors">
+                <option value="" disabled selected> -- change color scheme -- </option>
+                <option value="dark">dark mode</option>
+                <option value="light">light mode</option>
+            </select>
+        </div>
+    </div>
+    <div class="settings-group">
+        <h2>Archive View</h2>
+        <div class="settings-item">
+            <p>Current default Sort: <span class="settings-current">{{ config.archive.sort }}</span></p>
+            <i>Change how the home view and channels view sorts by defaults.</i><br>
+            <select name="archive.sort" id="archive.sort"">
+                <option value="" disabled selected> -- change sort order -- </option>
+                <option value="published">date published</option>
+                <option value="downloaded">date downloaded</option>
+            </select>
+        </div>
+        <div class="settings-item">
+            <p>Current default hide watched: <span class="settings-current">{{ config.archive.hide_watched }}</span></p>
+            <i>Show or hide watched videos by default.</i><br>
+            <select name="archive.hide_watched" id="archive.hide_watched"">
+                <option value="" disabled selected> -- change visibility -- </option>
+                <option value="0">show watched</option>
+                <option value="1">hide watched</option>
+            </select>
+        </div>
+        <div class="settings-item">
+            <p>Current default show subscribed channels only: <span class="settings-current">{{ config.archive.show_subed_only }}</span></p>
+            <i>Show subscribed channels only by default.</i><br>
+            <select name="archive.show_subed_only" id="archive.show_subed_only"">
+                <option value="" disabled selected> -- change visibility -- </option>
+                <option value="0">show subscribed only</option>
+                <option value="1">hide not subscribed</option>
+            </select>
+        </div>
+        <div class="settings-item">
+            <p>Current page size: <span class="settings-current">{{ config.archive.page_size }}</span></p>
+            <i>Result of videos showing in archive page</i><br>
+            <input type="number" name="archive.page_size" id="archive.page_size">
+        </div>
+    </div>
+    <div class="settings-group">
+        <h2 id="subscriptions">Subscriptions</h2>
+        <div class="settings-item">
+            <p>Currend channel page size: <span class="settings-current">{{ config.subscriptions.channel_size }}</span></p>
+            <i>Recent videos to check on check pending, max recommended 50.</i><br>
+            <input type="number" name="subscriptions.channel_size" id="subscriptions.channel_size">
+        </div>
+        <div class="settings-item">
+            <p>Auto scan subscribed channels:</p>
+            <i>Coming soon</i>
+        </div>
+        <div class="settings-item">
+            <p>Auto download pending:</p>
+            <i>Coming soon</i>
+        </div>
+    </div>
+    <div class="settings-group">
+        <h2 id="downloads">Downloads</h2>
+        <div class="settings-item">
+            <p>Current download limit: <span class="settings-current">{{ config.downloads.limit_count }}</span></p>
+            <i>Limit the count of videos getting downloaded on every run. 0 (zero) to deactivate.</i><br>
+            <input type="number" name="downloads.limit_count" id="downloads.limit_count">
+        </div>
+        <div class="settings-item">
+            <p>Currend Download speed limit: <span class="settings-current">{{ config.downloads.limit_speed }}</span></p>
+            <i>Limit download speed. 0 (zero) to deactivate.</i><br>
+            <input type="number" name="downloads.limit_speed" id="downloads.limit_speed"><span>KB/sec</span>
+        </div>
+        <div class="settings-item">
+            <p>Current scraping sleep interval: <span class="settings-current">{{ config.downloads.sleep_interval }}</p>
+            <i>Seconds to sleep between calls to youtube. Might be necessary to avoid throttling. Recommended 3.</i><br>
+            <input type="number" name="downloads.sleep_interval" id="downloads.sleep_interval">
+        </div>
+        <div class="settings-item">
+            <p>External downloader:</p>
+            <i>Coming soon</i>
+        </div>
+    </div>
+    <div class="settings-group">
+        <h2 id="format">Download Format</h2>
+        <div class="settings-item">
+            <p>Video and audio quality format for yt-dlp.<br>
+                Currently: <span class="settings-current">{{ config.downloads.format }}</span>
+            </p>
+            <p>Example configurations:</p>
+            <ul>
+                <li><span class="settings-current">bestvideo[height<=720]+bestaudio/best[height<=720]</span>: best audio and max video height of 720p.</li>
+                <li><span class="settings-current">bestvideo[height<=1080]+bestaudio/best[height<=1080]</span>: best audio and max video height of 1080p.</li>
+                <li><span class="settings-current">0</span>: deactivate and download the best quality possible as decided by yt-dlp.</li>
+            </ul>
+            <i>Make sure your custom format gets merged into a single file. Check out the <a href="https://github.com/yt-dlp/yt-dlp#format-selection" target="_blank">documentation</a> for valid configurations.</i><br>
+            <input type="text" name="downloads.format" id="downloads.format">
+            <br>
+        </div>
+    </div>
+    <button type="submit">Update Settings</button>
+</form>
+<div class="title-bar">
+    <h1>Actions</h1>
+</div>
+<div class="settings-group">
+    <p>Rescan filesystem.</p>
+    <i>Coming soon</i>
+</div>
+<div class="settings-group">
+    <p>Manual media files import.</p>
+    <i>Coming soon</i>
+</div>
+<div class="settings-group">
+    <p>Backup database.</p>
+    <i>Coming soon</i>
+</div>
+{% endblock content %}

tubearchivist/home/templates/home/video.html

@@ -0,0 +1,67 @@
+{% extends "home/base.html" %}
+{% block content %}
+{% load static %}
+{% load humanize %}
+<div class="title-bar">
+    <h1>Video: {{ video.title }}</h1>
+</div>
+<div class="video-main">
+    <video 
+        src="/media/{{ video.media_url }}" 
+        poster="/cache/videos/{{ video.youtube_id }}.jpg" controls preload="false" 
+        type='video/mp4' width="100%">
+    </video>
+</div>
+<div class="info-box info-box-3 padding-box">
+    <div class="info-box-item">
+        <div class="round-img">
+            <a href="{% url 'channel_id' video.channel.channel_id %}">
+                <img src="/cache/channels/{{ video.channel.channel_id }}_thumb.jpg" alt="channel-thumb">
+            </a>
+        </div>
+        <div>
+            <h3><a href="{% url 'channel_id' video.channel.channel_id %}">{{ video.channel.channel_name }}</a></h3>
+            {% if video.channel.channel_subs >= 1000000 %}
+                <p>Subscribers: {{ video.channel.channel_subs|intword }}</p>
+            {% else %}
+                <p>Subscribers: {{ video.channel.channel_subs|intcomma }}</p>
+            {% endif %}
+        </div>
+    </div>
+    <div class="info-box-item">
+        <div>
+            <p>Published: {{ video.published }}</p>
+            <p>Last refreshed: {{ video.vid_last_refresh }}</p>
+            <p class="video-info-watched">Watched:
+                {% if video.player.watched %}
+                    <img src="{% static 'img/icon-seen.svg' %}" alt="seen-icon" class="seen-icon" id="{{ video.youtube_id }}">
+                {% else %}
+                    <img src="{% static 'img/icon-unseen.svg' %}" alt="unseen-icon" id="{{ video.youtube_id }}" onclick="isWatched(this.id)" class="unseen-icon" title="Mark as watched.">
+                {% endif %}
+            </p>
+            {% if video.active %}
+                <p>Youtube: Active</p>
+            {% else %}
+                <p>Youtube: Deactivated</p>
+            {% endif %}
+            <p>Video ID: {{ video.youtube_id }}</p>
+        </div>
+    </div>
+    <div class="info-box-item">
+        <div>
+            <p>Views: {{ video.stats.view_count|intcomma }}</p>
+            <p class="thumb-icon like"><img src="{% static 'img/icon-thumb.svg' %}" alt="thumbs-up">: {{ video.stats.like_count|intcomma }}</p>
+            <p class="thumb-icon dislike"><img src="{% static 'img/icon-thumb.svg' %}" alt="thumbs-down">: {{ video.stats.dislike_count|intcomma }}</p>
+            <p>Rating: {{ video.stats.average_rating }}</p>
+        </div>
+    </div>
+</div>
+{% if video.description %}
+    <div class="info-box-item description-box">
+        <p>Description: <button onclick="textReveal()" id="text-reveal-button">Show</button></p>
+        <div id="text-reveal" class="description-text">
+            {{ video.description|linebreaks }}
+        </div>
+    </div>
+{% endif %}
+{% endblock content %}

tubearchivist/home/tests.py

@@ -0,0 +1,3 @@
+from django.test import TestCase
+
+# Create your tests here.

tubearchivist/home/urls.py

@@ -0,0 +1,27 @@
+""" all home app urls """
+
+from django.urls import path
+
+from home.views import (
+    HomeView,
+    DownloadView,
+    ChannelView,
+    ChannelIdView,
+    VideoView,
+    SettingsView,
+    AboutView
+)
+
+from . import views
+
+urlpatterns = [
+    path('', HomeView.as_view(), name='home'),
+    path('about/', AboutView.as_view(), name='about'),
+    path('downloads/', DownloadView.as_view(), name='downloads'),
+    path('settings/', SettingsView.as_view(), name='settings'),
+    path('process/', views.process, name='process'),
+    path('downloads/progress', views.progress, name='progress'),
+    path('channel/', ChannelView.as_view(), name='channel'),
+    path('channel/<slug:channel_id_detail>/', ChannelIdView.as_view(), name='channel_id'),
+    path('video/<slug:video_id>/', VideoView.as_view(), name='video')
+]

tubearchivist/home/views.py

@@ -0,0 +1,562 @@
+"""
+Functionality:
+- all views for home app
+- process post data recieved from frontend via ajax
+"""
+
+import urllib.parse
+import json
+
+from datetime import datetime
+from time import sleep
+
+import requests
+
+from django.shortcuts import render, redirect
+from django.http import JsonResponse
+from django.views import View
+from django.utils.http import urlencode
+
+from home.src.download import PendingList, ChannelSubscription
+from home.src.searching import SearchHandler, Pagination
+from home.src.config import AppConfig
+from home.src.helper import (
+    process_url_list,
+    get_dl_message,
+    get_message,
+    set_message
+)
+from home.tasks import (
+    update_subscribed,
+    download_pending,
+    extrac_dl,
+    download_single
+)
+
+
+class HomeView(View):
+    """ handle home page and video search post functionality """
+
+    CONFIG = AppConfig().config
+    ES_URL = CONFIG['application']['es_url']
+
+    def get(self, request):
+        """ return home search results """
+        colors, sort_order, hide_watched = self.read_config()
+        # handle search
+        search_get = request.GET.get('search', False)
+        if search_get:
+            search_encoded = urllib.parse.quote(search_get)
+        else:
+            search_encoded = False
+        # define page size
+        page_get = int(request.GET.get('page', 0))
+        pagination_handler = Pagination(page_get, search_encoded)
+
+        url = self.ES_URL + '/ta_video/_search'
+
+        data = self.build_data(
+            pagination_handler, sort_order, search_get, hide_watched
+        )
+
+        search = SearchHandler(url, data)
+        videos_hits = search.get_data()
+        max_hits = search.max_hits
+        pagination_handler.validate(max_hits)
+        context = {
+            'videos': videos_hits,
+            'pagination': pagination_handler.pagination,
+            'sortorder': sort_order,
+            'hide_watched': hide_watched,
+            'colors': colors
+        }
+        return render(request, 'home/home.html', context)
+
+    @staticmethod
+    def build_data(pagination_handler, sort_order, search_get, hide_watched):
+        """ build the data dict for the search query """
+        page_size = pagination_handler.pagination['page_size']
+        page_from = pagination_handler.pagination['page_from']
+        data = {
+            "size": page_size, "from": page_from, "query": {"match_all": {}},
+            "sort": [
+                {"published": {"order": "desc"}},
+                {"date_downloaded": {"order": "desc"}}
+            ]
+        }
+        # define sort
+        if sort_order == 'downloaded':
+            del data['sort'][0]
+        if search_get:
+            del data['sort']
+        if hide_watched:
+            data['query'] = {"term": {"player.watched": {"value": False}}}
+        if search_get:
+            query = {
+                "multi_match": {
+                    "query": search_get,
+                    "fields": ["title", "channel.channel_name", "tags"],
+                    "type": "cross_fields",
+                    "operator": "and"
+                }
+            }
+            data['query'] = query
+
+        return data
+
+    @staticmethod
+    def read_config():
+        """ read needed values from redis """
+        config_handler = AppConfig().config
+        colors = config_handler['application']['colors']
+        sort_order = get_message('sort_order')
+        hide_watched = get_message('hide_watched')
+        return colors, sort_order, hide_watched
+
+    @staticmethod
+    def post(request):
+        """ handle post from search form """
+        post_data = dict(request.POST)
+        search_query = post_data['videoSearch'][0]
+        search_url = '/?' + urlencode({'search': search_query})
+        return redirect(search_url, permanent=True)
+
+
+class AboutView(View):
+    """ resolves to /about/
+    show helpful how to information
+    """
+
+    @staticmethod
+    def get(request):
+        """ handle http get """
+        config = AppConfig().config
+        colors = config['application']['colors']
+        context = {
+            'title': 'About',
+            'colors': colors
+        }
+        return render(request, 'home/about.html', context)
+
+
+class DownloadView(View):
+    """
+    resolves to /download/
+    takes POST for downloading youtube links
+    """
+
+    @staticmethod
+    def get(request):
+        """ handle get requests """
+        config = AppConfig().config
+        colors = config['application']['colors']
+        pending_handler = PendingList()
+        all_pending, _ = pending_handler.get_all_pending()
+        context = {
+            'pending': all_pending,
+            'title': 'Downloads',
+            'colors': colors
+        }
+        return render(request, 'home/downloads.html', context)
+
+    @staticmethod
+    def post(request):
+        """ handle post requests """
+        download_post = dict(request.POST)
+        if 'vid-url' in download_post.keys():
+            url_str = download_post['vid-url']
+            print('adding to queue')
+            youtube_ids = process_url_list(url_str)
+            print(youtube_ids)
+            extrac_dl.delay(youtube_ids)
+
+        sleep(2)
+        return redirect('downloads', permanent=True)
+
+
+class ChannelIdView(View):
+    """ display single channel page from channel_id """
+
+    def get(self, request, channel_id_detail):
+        """ get method """
+        es_url, colors = self.read_config()
+        context = self.get_channel_videos(request, channel_id_detail, es_url)
+        context.update({'colors': colors})
+        return render(request, 'home/channel_id.html', context)
+
+    @staticmethod
+    def read_config():
+        """ read config file """
+        config = AppConfig().config
+        es_url = config['application']['es_url']
+        colors = config['application']['colors']
+        return es_url, colors
+
+    def get_channel_videos(self, request, channel_id_detail, es_url):
+        """ get channel from video index """
+        page_get = int(request.GET.get('page', 0))
+        pagination_handler = Pagination(page_get)
+        # get data
+        url = es_url + '/ta_video/_search'
+        data = self.build_data(pagination_handler, channel_id_detail)
+        search = SearchHandler(url, data)
+        videos_hits = search.get_data()
+        max_hits = search.max_hits
+        if max_hits:
+            channel_info = videos_hits[0]['source']['channel']
+            channel_name = channel_info['channel_name']
+            pagination_handler.validate(max_hits)
+            pagination = pagination_handler.pagination
+        else:
+            # get details from channel index when when no hits
+            channel_info, channel_name = self.get_channel_info(
+                channel_id_detail, es_url
+            )
+            videos_hits = False
+            pagination = False
+
+        context = {
+            'channel_info': channel_info,
+            'videos': videos_hits,
+            'max_hits': max_hits,
+            'pagination': pagination,
+            'title': 'Channel: ' + channel_name,
+        }
+
+        return context
+
+    @staticmethod
+    def build_data(pagination_handler, channel_id_detail):
+        """ build data dict for search """
+        page_size = pagination_handler.pagination['page_size']
+        page_from = pagination_handler.pagination['page_from']
+        data = {
+            "size": page_size, "from": page_from,
+            "query": {
+                "term": {"channel.channel_id": {"value": channel_id_detail}}
+            },
+            "sort": [
+                {"published": {"order": "desc"}},
+                {"date_downloaded": {"order": "desc"}}
+            ]
+        }
+        return data
+
+    @staticmethod
+    def get_channel_info(channel_id_detail, es_url):
+        """ get channel info from channel index if no videos """
+        url = f'{es_url}/ta_channel/_doc/{channel_id_detail}'
+        data = False
+        search = SearchHandler(url, data)
+        channel_data = search.get_data()
+        channel_info = channel_data[0]['source']
+        channel_name = channel_info['channel_name']
+        return channel_info, channel_name
+
+
+class ChannelView(View):
+    """ handle functionality for channel overview page """
+
+    def get(self, request):
+        """ handle http get requests """
+        es_url, colors = self.read_config()
+        page_get = int(request.GET.get('page', 0))
+        pagination_handler = Pagination(page_get)
+        page_size = pagination_handler.pagination['page_size']
+        page_from = pagination_handler.pagination['page_from']
+        # get
+        url = es_url + '/ta_channel/_search'
+        data = {
+            "size": page_size, "from": page_from, "query": {"match_all": {}},
+            "sort": [{"channel_name.keyword": {"order": "asc"}}]
+        }
+        show_subed_only = get_message('show_subed_only')
+        if show_subed_only:
+            data['query'] = {"term": {"channel_subscribed": {"value": True}}}
+        search = SearchHandler(url, data)
+        channel_hits = search.get_data()
+        max_hits = search.max_hits
+        pagination_handler.validate(search.max_hits)
+        context = {
+            'channels': channel_hits,
+            'max_hits': max_hits,
+            'pagination': pagination_handler.pagination,
+            'show_subed_only': show_subed_only,
+            'title': 'Channels',
+            'colors': colors
+        }
+        return render(request, 'home/channel.html', context)
+
+    @staticmethod
+    def read_config():
+        """ read config file """
+        config = AppConfig().config
+        es_url = config['application']['es_url']
+        colors = config['application']['colors']
+        return es_url, colors
+
+    @staticmethod
+    def post(request):
+        """ handle http post requests """
+        subscriptions_post = dict(request.POST)
+        print(subscriptions_post)
+        subscriptions_post = dict(request.POST)
+        if 'subscribe' in subscriptions_post.keys():
+            youtube_ids = process_url_list(subscriptions_post['subscribe'])
+            if youtube_ids[0]['type'] == 'video':
+                youtube_id = youtube_ids[0]['url']
+                vid_details = PendingList().get_youtube_details(youtube_id)
+                channel_id_sub = vid_details['channel_id']
+            else:
+                channel_id_sub = youtube_ids[0]['url']
+            ChannelSubscription().change_subscribe(
+                channel_id_sub, channel_subscribed=True
+            )
+            print('subscribed to: ' + channel_id_sub)
+
+        sleep(1)
+        return redirect('channel', permanent=True)
+
+
+class VideoView(View):
+    """ display details about a single video """
+
+    def get(self, request, video_id):
+        """ get single video """
+        es_url, colors = self.read_config()
+        url = f'{es_url}/ta_video/_doc/{video_id}'
+        data = None
+        look_up = SearchHandler(url, data)
+        video_hit = look_up.get_data()
+        video_data = video_hit[0]['source']
+        video_title = video_data['title']
+        context = {
+            'video': video_data,
+            'title': video_title,
+            'colors': colors
+        }
+        return render(request, 'home/video.html', context)
+
+    @staticmethod
+    def read_config():
+        """ read config file """
+        config = AppConfig().config
+        es_url = config['application']['es_url']
+        colors = config['application']['colors']
+        return es_url, colors
+
+
+class SettingsView(View):
+    """ handle the settings page """
+
+    @staticmethod
+    def get(request):
+        """ read and display current settings """
+        config = AppConfig().config
+        colors = config['application']['colors']
+
+        context = {
+            'title': 'Settings',
+            'config': config,
+            'colors': colors
+        }
+
+        return render(request, 'home/settings.html', context)
+
+    @staticmethod
+    def post(request):
+        """ handle form post to update settings """
+        form_post = dict(request.POST)
+        del form_post['csrfmiddlewaretoken']
+        print(form_post)
+        config_handler = AppConfig()
+        config_handler.update_config(form_post)
+
+        return redirect('settings', permanent=True)
+
+
+def progress(request):
+    # pylint: disable=unused-argument
+    """ endpoint for download progress ajax calls """
+    config = AppConfig().config
+    cache_dir = config['application']['cache_dir']
+    json_data = get_dl_message(cache_dir)
+    return JsonResponse(json_data)
+
+
+def process(request):
+    """ handle all the buttons calls via POST ajax """
+    if request.method == 'POST':
+        post_dict = json.loads(request.body.decode())
+        post_handler = PostData(post_dict)
+        if post_handler.to_do:
+            task_result = post_handler.run_task()
+            return JsonResponse(task_result)
+
+    return JsonResponse({'success': False})
+
+
+class PostData:
+    """ generic post handler from process route """
+
+    CONFIG = AppConfig().config
+    ES_URL = CONFIG['application']['es_url']
+
+    VALID_KEYS = [
+        "watched", "rescan_pending", "ignore", "dl_pending",
+        "unsubscribe", "sort_order", "hide_watched", "show_subed_only",
+        "channel-search", "video-search", "dlnow"
+    ]
+
+    def __init__(self, post_dict):
+        self.post_dict = post_dict
+        self.to_do = self.validate()
+
+    def validate(self):
+        """ validate the post_dict """
+        to_do = []
+        for key, value in self.post_dict.items():
+            if key in self.VALID_KEYS:
+                task_item = {'task': key, 'status': value}
+                print(task_item)
+                to_do.append(task_item)
+            else:
+                print(key + ' not a valid key')
+
+        return to_do
+
+    def run_task(self):
+        """ run through the tasks to do """
+        for item in self.to_do:
+            task = item['task']
+            if task == 'watched':
+                youtube_id = item['status']
+                self.parse_watched(youtube_id)
+            elif task == 'rescan_pending':
+                print('download pending videos')
+                update_subscribed.delay()
+            elif task == 'ignore':
+                print('ignore video')
+                handler = PendingList()
+                ignore_list = item['status']
+                handler.ignore_from_pending([ignore_list])
+            elif task == 'dl_pending':
+                print('download pending')
+                download_pending.delay()
+            elif task == 'vid-url':
+                status_str = item['status']
+                print(urllib.parse.quote(status_str))
+            elif task == 'unsubscribe':
+                channel_id_unsub = item['status']
+                print('unsubscribe from ' + channel_id_unsub)
+                ChannelSubscription().change_subscribe(
+                    channel_id_unsub, channel_subscribed=False
+                )
+            elif task == 'sort_order':
+                sort_order = item['status']
+                set_message('sort_order', sort_order, expire=False)
+            elif task == 'hide_watched':
+                hide_watched = bool(int(item['status']))
+                print(item['status'])
+                set_message('hide_watched', hide_watched, expire=False)
+            elif task == 'show_subed_only':
+                show_subed_only = bool(int(item['status']))
+                print(show_subed_only)
+                set_message('show_subed_only', show_subed_only, expire=False)
+            elif task == 'channel-search':
+                search_query = item['status']
+                print('searching for: ' + search_query)
+                search_results = self.search_channels(search_query)
+                return search_results
+            elif task == 'video-search':
+                search_query = item['status']
+                print('searching for: ' + search_query)
+                search_results = self.search_videos(search_query)
+                return search_results
+            elif task == 'dlnow':
+                youtube_id = item['status']
+                print('downloading: ' + youtube_id)
+                download_single(youtube_id)
+        return {'success': True}
+
+    def search_channels(self, search_query):
+        """ fancy searching channels as you type """
+        url = self.ES_URL + '/ta_channel/_search'
+        data = {
+            "size": 10,
+            "query": {
+                "multi_match": {
+                    "query": search_query,
+                    "type": "bool_prefix",
+                    "fields": [
+                        "channel_name.search_as_you_type",
+                        "channel_name._2gram",
+                        "channel_name._3gram"
+                    ]
+                }
+            }
+        }
+        look_up = SearchHandler(url, data, cache=False)
+        search_results = look_up.get_data()
+        return {'results': search_results}
+
+    def search_videos(self, search_query):
+        """ fancy searching videos as you type """
+        url = self.ES_URL + '/ta_video/_search'
+        data = {
+            "size": 10,
+            "query": {
+                "multi_match": {
+                    "query": search_query,
+                    "type": "bool_prefix",
+                    "fields": [
+                        "title.search_as_you_type",
+                        "title._2gram",
+                        "title._3gram"
+                    ]
+                }
+            }
+        }
+        look_up = SearchHandler(url, data, cache=False)
+        search_results = look_up.get_data()
+        return {'results': search_results}
+
+    def parse_watched(self, youtube_id):
+        """ marked as watched based on id type """
+        es_url = self.ES_URL
+        id_type = process_url_list([youtube_id])[0]['type']
+        stamp = int(datetime.now().strftime("%s"))
+        if id_type == 'video':
+            stamp = int(datetime.now().strftime("%s"))
+            url = self.ES_URL + '/ta_video/_update/' + youtube_id
+            source = {
+                "doc": {"player": {"watched": True, "watched_date": stamp}}
+            }
+            request = requests.post(url, json=source)
+            if not request.ok:
+                print(request.text)
+        elif id_type == 'channel':
+            headers = {'Content-type': 'application/json'}
+            data = {
+                "description": youtube_id,
+                "processors": [
+                    {"set": {"field": "player.watched", "value": True}},
+                    {"set": {"field": "player.watched_date", "value": stamp}}
+                ]
+            }
+            payload = json.dumps(data)
+            url = es_url + '/_ingest/pipeline/' + youtube_id
+            request = requests.put(url, data=payload, headers=headers)
+            if not request.ok:
+                print(request.text)
+            # apply pipeline
+            must_list = [
+                {"term": {"channel.channel_id": {"value": youtube_id}}},
+                {"term": {"player.watched": {"value": False}}}
+            ]
+            data = {"query": {"bool": {"must": must_list}}}
+            payload = json.dumps(data)
+            url = f'{es_url}/ta_video/_update_by_query?pipeline={youtube_id}'
+            request = requests.post(url, data=payload, headers=headers)
+            if not request.ok:
+                print(request.text)

tubearchivist/manage.py

@@ -0,0 +1,22 @@
+#!/usr/bin/env python
+"""Django's command-line utility for administrative tasks."""
+import os
+import sys
+
+
+def main():
+    """Run administrative tasks."""
+    os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'config.settings')
+    try:
+        from django.core.management import execute_from_command_line
+    except ImportError as exc:
+        raise ImportError(
+            "Couldn't import Django. Are you sure it's installed and "
+            "available on your PYTHONPATH environment variable? Did you "
+            "forget to activate a virtual environment?"
+        ) from exc
+    execute_from_command_line(sys.argv)
+
+
+if __name__ == '__main__':
+    main()

tubearchivist/requirements.txt

@@ -0,0 +1,9 @@
+requests==2.26.0
+redis==3.5.3
+yt_dlp==2021.8.10
+celery==5.1.2
+Django==3.2.6
+beautifulsoup4==4.9.3
+Pillow==8.3.1
+uWSGI==2.0.19.1
+whitenoise==5.3.0

tubearchivist/static/css/dark.css

@@ -0,0 +1,9 @@
+:root {
+    --main-bg: #00202f;
+    --highlight-bg: #00293b;
+    --highlight-bg-transparent: #00293baf;
+    --main-font: #eeeeee;
+    --accent-font-dark: #259485;
+    --accent-font-light: #97d4c8;
+    --img-filter: invert(50%) sepia(9%) saturate(2940%) hue-rotate(122deg) brightness(94%) contrast(90%);
+}

tubearchivist/static/css/light.css

@@ -0,0 +1,19 @@
+:root {
+    --main-bg: #eeeeee;
+    --highlight-bg: #d9e0d9;
+    --highlight-bg-transparent: #00293baf;
+    --main-font: #00202f;
+    --accent-font-dark: #259485;
+    --accent-font-light: #35b399;
+    --img-filter: invert(50%) sepia(9%) saturate(2940%) hue-rotate(122deg) brightness(94%) contrast(90%);
+}
+
+/* :root {
+    --main-bg: #00202f;
+    --highlight-bg: #00293b;
+    --highlight-bg-transparent: #00293baf;
+    --main-font: #eeeeee;
+    --accent-font-dark: #259485;
+    --accent-font-light: #97d4c8;
+    --img-filter: invert(50%) sepia(9%) saturate(2940%) hue-rotate(122deg) brightness(94%) contrast(90%);
+} */

tubearchivist/static/css/style.css

@@ -0,0 +1,631 @@
+@font-face {
+font-family: 'Sen-Bold';
+    src:  url('../font/Sen-Bold.ttf.woff');
+    font-family: 'Sen-Bold';
+}
+
+@font-face {
+font-family: 'Sen-Regular';
+    src:  url('../font/Sen-Regular.ttf.woff');
+    font-family: 'Sen-Regular';
+}
+
+* {
+    margin: 0;
+    padding: 0;
+}
+
+html {
+    height: 100%;
+}
+
+body {
+    background-color: var(--main-bg);
+    min-height: 100%;
+    display: grid;
+    grid-template-rows: 1fr auto;
+}
+
+a {
+    font-family: Sen-Regular, sans-serif;
+    text-decoration: none;
+    color: var(--accent-font-light);
+}
+
+h1 {
+    font-family: Sen-Bold, sans-serif;
+    font-size: 2.3em;
+    color: var(--accent-font-light);
+}
+
+h2 {
+    font-size: 1.2em;
+    margin-bottom: 10px;
+    font-family: Sen-Bold, sans-serif;
+    color: var(--accent-font-dark);
+}
+
+h3 {
+    font-size: 1.1em;
+    margin-bottom: 7px;
+    font-family: Sen-Regular, sans-serif;
+    color: var(--accent-font-light);
+}
+
+p, i, li {
+    font-family: Sen-Regular, sans-serif;
+    margin-bottom: 10px;
+    color: var(--main-font);
+}
+
+ul {
+    margin-left: 20px;
+}
+
+td, span {
+    font-family: Sen-Regular, sans-serif;
+    color: var(--main-font);
+}
+
+select, input {
+    padding: 5px;
+    margin: 5px;
+    border-radius: 0;
+    color: var(--main-bg);
+    background-color: var(--accent-font-light);
+}
+
+select {
+    border: none;
+}
+
+input {
+    border: solid 1px var(--main-font);
+}
+
+textarea {
+    width: 100%;
+}
+
+button {
+    border-radius: 0;
+    padding: 5px 13px;
+    border: none;
+    cursor: pointer;
+    background-color: var(--accent-font-dark);
+    color: #ffffff;
+}
+
+button:hover {
+    background-color: var(--accent-font-light);
+    transform: scale(1.05);
+    color: var(--main-bg);
+}
+
+.boxed-content {
+    max-width: 1000px;
+    width: 80%;
+    margin: 0 auto;
+}
+
+.round-img img {
+    border-radius: 50%;
+}
+
+.settings-current {
+    color: var(--accent-font-light);
+}
+
+.top-banner {
+    text-align: center;
+    margin-top: 10px;
+}
+
+.top-banner img {
+    width: 100%;
+    max-width: 700px;
+}
+
+.footer {
+    margin: 0;
+    padding: 20px 0;
+    background-color: var(--accent-font-dark);
+    grid-row-start: 2;
+    grid-row-end: 3;
+}
+
+/* navigation */
+.top-nav {
+    display: block;
+    padding: 15px 0;
+    /* justify-content: space-around; */
+    position: relative;
+}
+
+.nav-items {
+    width: 100%;
+    display: flex;
+    justify-content: center;
+}
+
+.nav-item {
+    font-size: 1.3em;
+    padding: 10px 20px;
+    margin: 0 10px;
+    border-bottom: 2px solid;
+    color: var(--accent-font-dark);
+}
+
+.nav-icons {
+    width: auto;
+    display: inline-flex;
+    position: absolute;
+    top: 50%;
+    right: 0;
+    transform: translate(0,-50%);
+}
+
+.nav-icons img {
+    width: 40px;
+    padding: 0 10px;
+    filter: var(--img-filter);
+}
+
+/* top of page */
+.title-bar {
+    padding: 25px 0;
+}
+
+.sort {
+    display: flex;
+    flex-wrap: wrap;
+}
+
+.sort > div {
+    width: 100%;
+    display: inline;
+}
+
+.padding-box {
+    padding: 30px 0;
+}
+
+.two-col {
+    display: flex;
+}
+
+.two-col > div {
+    width: 50%;
+}
+
+.search-form {
+    display: flex;
+    flex-wrap: wrap;
+    align-items: center;
+    justify-content: flex-end;
+}
+
+.search-form input {
+    width: 90%;
+}
+
+.search-icon {
+    flex: 0 0 40px;
+}
+
+.search-icon img {
+    width: 100%;
+    cursor: pointer;
+    filter: var(--img-filter);
+}
+
+#search-box {
+    display: none;
+    flex: auto;
+    padding: 10px;
+}
+
+#hidden-form {
+    display: none;
+}
+
+#text-reveal {
+    height: 0px;
+    overflow: hidden;
+}
+
+
+/* video player */
+.video-player {
+    position: relative;
+    margin: 20px 0;
+}
+
+.video-player video {
+    max-height: 70vh;
+}
+
+.player-title img {
+    width: 30px;
+}
+
+.player-title:hover {
+    opacity: 1;
+}
+
+.player-title {
+    opacity: 0;
+    background-color: var(--highlight-bg-transparent);
+    position: absolute;
+    top: 0;
+    z-index: 1;
+    width: 100%;
+    padding: 20px 0;
+}
+
+.player-title > * {
+    margin-left: 20px;
+}
+
+
+/* video list */
+.video-list {
+    display: grid;
+    grid-template-columns: 1fr 1fr 1fr;
+    grid-gap: 1rem;
+}
+
+.video-item {
+    overflow: hidden;
+}
+
+.video-thumb img {
+    width: 100%;
+}
+
+.video-play img {
+    width: 40px;
+    filter: var(--img-filter);
+}
+
+.video-thumb-wrap {
+    position: relative;
+}
+
+.video-thumb-wrap:hover > .video-play {
+    opacity: 1;
+    padding: 15px;
+}
+
+.video-play {
+    opacity: 0;
+    transition: all 0.3s ease-in-out;
+    position: absolute;
+    top: 50%;
+    right: 50%;
+    transform: translate(50%,-50%);
+    background-color: var(--highlight-bg);
+    border-radius: 50%;
+    padding: 8px;
+}
+
+.video-desc {
+    padding: 10px;
+    height: 100%;
+    background-color: var(--highlight-bg);
+}
+
+.video-desc img {
+    width: 20px;
+    margin-right: 10px;
+}
+
+.video-desc a {
+    text-decoration: none;
+    text-align: left;
+}
+
+.video-desc h3 {
+    font-size: 0.9em;
+    text-transform: uppercase;
+}
+
+.video-desc-player {
+    margin-bottom: 8px;
+    display: flex;
+    align-items: center;
+}
+
+.unseen-icon,
+.close-button {
+    cursor: pointer;
+    filter: var(--img-filter);
+}
+
+.seen-icon {
+    filter: var(--img-filter);
+}
+
+.video-more {
+    text-decoration: underline;
+    text-align: right;
+}
+
+
+/* pagination */
+.pagination {
+    padding: 30px 0;
+    margin-left: auto;
+    margin-right: auto;
+    text-align: center;
+}
+
+.pagination-item {
+    padding: 5px;
+    border: 1px solid;
+}
+
+
+/* info box */
+.info-box {
+    display: grid;
+    grid-gap: 1rem;
+}
+
+.info-box-3 {
+    grid-template-columns: 1fr 1fr 1fr;
+}
+
+.info-box-2 {
+    grid-template-columns: 1fr 1fr;
+}
+
+.info-box img {
+    width: 80px;
+    margin: 0 15px;
+}
+
+.info-box-item {
+    display: flex;
+    align-items: center;
+    padding: 15px;
+    background-color: var(--highlight-bg);
+}
+
+.description-text {
+    width: 100%;
+}
+
+.description-text br {
+    margin-bottom: 10px;
+}
+
+/* video page */
+.video-main video {
+    max-height: 70vh;
+}
+.video-info-watched {
+    display: flex;
+    align-items: center;
+}
+
+.video-info-watched img {
+    width: 20px;
+    margin-left: 5px;
+}
+
+.thumb-icon img {
+    width: 20px;
+    margin: 0;
+    filter: var(--img-filter);
+}
+
+.thumb-icon.dislike img {
+    transform: rotate(180deg);
+}
+
+/* channel overview page */
+.channel-item {
+    padding: 20px 0;
+}
+
+.channel-banner img {
+    width: 100%;
+}
+
+
+/* download page */
+.icon-text {
+    background-color: var(--highlight-bg);
+    text-align: center;
+    padding: 15px;
+}
+
+.icon-text img {
+    filter: var(--img-filter);
+    cursor: pointer;
+}
+
+.dl-item {
+    display: flex;
+    margin: 15px 0;
+    align-items: center;
+    background-color: var(--highlight-bg);
+}
+
+.dl-check {
+    width: 30px;
+}
+
+.dl-thumb {
+    width: 25%;
+}
+
+.dl-item img {
+    width: 100%;
+}
+
+.dl-desc {
+    padding-left: 15px;
+    width: 75%;
+}
+
+
+/* status message */
+.download-progress {
+    background-color: var(--highlight-bg);
+    text-align: center;
+    padding: 30px 0 15px 0;
+}
+
+
+/* settings */
+.settings-group {
+    background-color: var(--highlight-bg);
+    padding: 20px;
+    margin: 20px 0;
+}
+
+.settings-item {
+    margin-top: 25px;
+}
+
+.settings-item input {
+    min-width: 300px;
+}
+
+/* about */
+.about-section {
+    padding: 20px 0;
+}
+
+.about-section ol {
+    margin-left: 20px;
+}
+
+.about-section ul {
+    margin-top: 15px;
+}
+
+.about-section li {
+    margin-bottom: 10px;
+}
+
+.about-icon img {
+    margin-left: 5px;
+    width: 20px;
+    cursor: unset;
+}
+
+/* animation */
+.rotate-img {
+    animation: rotation 4s infinite linear;
+}
+
+.bounce-img {
+    animation: bounce 1.5s infinite ease-in-out alternate;
+}
+
+.pulse-img {
+    animation: pulse 1.5s infinite ease-in-out alternate;
+}
+
+@keyframes rotation {
+    from {
+        transform: rotate(0deg);
+    }
+    to {
+        transform: rotate(359deg);
+    }
+}
+
+@keyframes bounce {
+    0% {
+        transform: translateY(-5%);
+    }
+    100% {
+        transform: translateY(5%);
+        scale: 1.15;
+    }
+}
+
+@keyframes pulse {
+    0% {
+        scale: 1;
+    }
+    100% {
+        scale: 1.15;
+    }
+}
+
+/* tablet */
+@media screen and (max-width: 1000px) {
+    .boxed-content {
+        width: 90%;
+    }
+    .video-list {
+        grid-template-columns: 1fr 1fr;
+    }
+    .two-col {
+        display: block;
+    }
+    .two-col > div {
+        width: 100%;
+    }
+}
+
+/* phone */
+@media screen and (max-width: 600px) {
+    * {
+        word-wrap: anywhere;
+    }
+    .video-list {
+        grid-template-columns: 1fr;
+    }
+    .boxed-content {
+        width: 95%;
+    }
+    .footer {
+        text-align: center;
+    }
+    .top-nav {
+        flex-wrap: wrap-reverse;
+        display: flex;
+    }
+    .nav-icons {
+        width: 100%;
+        justify-content: center;
+        position: unset;
+        transform: unset;
+    }
+    .nav-item {
+        padding: unset;
+        margin: 15px;
+    }
+    .sort {
+        display: block;
+    }
+    .sort > div {
+        display: block;
+    }
+    .sort select {
+        width: 100%;
+        margin: unset;
+    }
+    .info-box-2,
+    .info-box-3 {
+        grid-template-columns: 1fr;
+    }
+    .description-box {
+        display: block;
+    }
+    .dl-item {
+        display: block;
+    }
+    .dl-thumb {
+        width: 100%;
+    }
+    .dl-desc {
+        padding: 15px;
+    }
+}

tubearchivist/static/img/icon-add.svg

@@ -0,0 +1,71 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="500"
+   height="500"
+   viewBox="0 0 132.29197 132.29167"
+   version="1.1"
+   id="svg1303"
+   inkscape:version="0.92.4 (5da689c313, 2019-01-14)"
+   sodipodi:docname="Icon_add.svg">
+  <defs
+     id="defs1297" />
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="0.85859018"
+     inkscape:cx="-97.380081"
+     inkscape:cy="261.09215"
+     inkscape:document-units="mm"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     units="px"
+     inkscape:window-width="1920"
+     inkscape:window-height="1017"
+     inkscape:window-x="-8"
+     inkscape:window-y="-8"
+     inkscape:window-maximized="1"
+     showguides="true"
+     inkscape:guide-bbox="true">
+    <sodipodi:guide
+       position="-221.87586,143.2945"
+       orientation="1,0"
+       id="guide1072"
+       inkscape:locked="false" />
+  </sodipodi:namedview>
+  <metadata
+     id="metadata1300">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title></dc:title>
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Ebene 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(0,-164.70764)">
+    <path
+       style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke"
+       d="m 58.600542,170.62113 c -1.62283,1.61686 -2.626579,3.8573 -2.631447,6.33943 l -0.08037,43.5977 -43.597706,-0.0803 c -4.9648228,-0.009 -8.9691711,3.98046 -8.9784054,8.94536 l -0.00482,2.62846 c -0.00925,4.9649 3.9804459,8.96933 8.9452674,8.97832 l 43.597694,0.0805 -0.08027,43.59778 c -0.0093,4.96488 3.980368,8.96922 8.945263,8.9783 l 2.628471,0.005 c 4.964897,0.009 8.969245,-3.98054 8.978406,-8.94536 l 0.08035,-43.59771 43.597715,0.0803 c 4.96484,0.009 8.96917,-3.98046 8.9784,-8.94534 l 0.005,-2.62847 c 0.009,-4.96489 -3.98037,-8.96923 -8.94525,-8.97831 l -43.597784,-0.0805 0.08034,-43.59771 c 0.0093,-4.96481 -3.980379,-8.96923 -8.945267,-8.97831 l -2.628469,-0.005 c -2.482483,-0.005 -4.724106,0.98906 -6.346936,2.60592 z"
+       id="rect1073"
+       inkscape:connector-curvature="0" />
+  </g>
+</svg>

tubearchivist/static/img/icon-close.svg

@@ -0,0 +1,63 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="500"
+   height="500"
+   viewBox="0 0 132.29197 132.29167"
+   version="1.1"
+   id="svg1303"
+   inkscape:version="0.92.4 (5da689c313, 2019-01-14)"
+   sodipodi:docname="Icons_close.svg">
+  <defs
+     id="defs1297" />
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.4291625"
+     inkscape:cx="122.66624"
+     inkscape:cy="202.38142"
+     inkscape:document-units="mm"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     units="px"
+     inkscape:window-width="1920"
+     inkscape:window-height="1017"
+     inkscape:window-x="-8"
+     inkscape:window-y="-8"
+     inkscape:window-maximized="1" />
+  <metadata
+     id="metadata1300">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Ebene 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(0,-164.70764)">
+    <path
+       style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke"
+       d="m 115.5244,167.09017 c -3.04348,0 -6.08905,1.16742 -8.42111,3.49893 L 66.146003,211.54641 25.18874,170.5891 c -4.664143,-4.66413 -12.173961,-4.66413 -16.8382429,0 l -2.4692132,2.46935 c -4.664282,4.66413 -4.664282,12.17408 0,16.83807 l 40.9572491,40.9573 -40.9572491,40.95745 c -4.664282,4.66412 -4.664282,12.17393 0,16.83806 l 2.4692132,2.46935 c 4.6642819,4.66413 12.1740999,4.66413 16.8382429,0 l 40.957263,-40.9573 40.957287,40.9573 c 4.66413,4.66413 12.17393,4.66413 16.8382,0 l 2.46921,-2.46935 c 4.66427,-4.66413 4.66427,-12.17394 0,-16.83806 L 85.453463,230.85382 126.4107,189.89652 c 4.66427,-4.66399 4.66427,-12.17394 0,-16.83807 l -2.46921,-2.46935 c -2.33221,-2.33206 -5.37361,-3.49893 -8.41709,-3.49893 z"
+       id="rect1073"
+       inkscape:connector-curvature="0" />
+  </g>
+</svg>

tubearchivist/static/img/icon-download.svg

@@ -0,0 +1,63 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="500"
+   height="500"
+   viewBox="0 0 132.29197 132.29167"
+   version="1.1"
+   id="svg1303"
+   inkscape:version="0.92.4 (5da689c313, 2019-01-14)"
+   sodipodi:docname="Download.svg">
+  <defs
+     id="defs1297" />
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="0.71458126"
+     inkscape:cx="-376.84122"
+     inkscape:cy="260.65826"
+     inkscape:document-units="mm"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     units="px"
+     inkscape:window-width="1920"
+     inkscape:window-height="1017"
+     inkscape:window-x="-8"
+     inkscape:window-y="-8"
+     inkscape:window-maximized="1" />
+  <metadata
+     id="metadata1300">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title></dc:title>
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Ebene 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(0,-164.70764)">
+    <path
+       style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke"
+       d="M 249.89062 39.6875 L 249.88477 39.693359 C 229.11581 39.693359 212.39453 59.135896 212.39453 83.289062 L 212.39453 289.66016 L 159.20312 236.46875 L 127.63867 268.05469 L 218.74805 359.14258 L 218.73242 359.1582 L 249.93555 390.33789 L 281.52148 358.77344 L 372.36133 267.91211 L 341.1582 236.73047 L 287.37891 290.50977 L 287.37891 83.283203 C 287.37891 59.130339 270.65971 39.6875 249.89062 39.6875 z M 50.566406 407.88867 C 44.284822 407.88867 39.228516 412.94498 39.228516 419.22656 L 39.228516 444.62695 C 39.228516 450.90854 44.284822 455.96484 50.566406 455.96484 L 449.43359 455.96484 C 455.71518 455.96484 460.77148 450.90854 460.77148 444.62695 L 460.77148 419.22656 C 460.77148 412.94498 455.71518 407.88867 449.43359 407.88867 L 50.566406 407.88867 z "
+       transform="matrix(0.26458394,0,0,0.26458394,0,164.70749)"
+       id="rect1208" />
+  </g>
+</svg>

tubearchivist/static/img/icon-gear.svg

@@ -0,0 +1,63 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="500"
+   height="500"
+   viewBox="0 0 132.29197 132.29167"
+   version="1.1"
+   id="svg1303"
+   inkscape:version="0.92.4 (5da689c313, 2019-01-14)"
+   sodipodi:docname="Icons_Settings02.svg">
+  <defs
+     id="defs1297" />
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.0105705"
+     inkscape:cx="-25.63665"
+     inkscape:cy="191.7261"
+     inkscape:document-units="mm"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     units="px"
+     inkscape:window-width="1920"
+     inkscape:window-height="1017"
+     inkscape:window-x="-8"
+     inkscape:window-y="-8"
+     inkscape:window-maximized="1" />
+  <metadata
+     id="metadata1300">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Ebene 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(0,-164.70764)">
+    <path
+       style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke"
+       d="m 57.383938,165.28042 c -4.849506,0 -8.753067,3.9047 -8.753067,8.75416 v 9.09569 a 50.663505,50.95301 0 0 0 -15.06221,8.94072 l -8.089206,-4.6705 c -4.199751,-2.42477 -9.533198,-0.99601 -11.957934,3.20377 l -8.61619,14.92534 c -2.4247365,4.19977 -0.9959782,9.53208 3.2037853,11.95684 l 8.3097237,4.79724 a 50.663505,50.95301 0 0 0 -0.791619,8.56976 50.663505,50.95301 0 0 0 0.811977,8.72482 l -8.0405786,4.64225 c -4.1997499,2.42476 -5.6285156,7.75707 -3.2037853,11.95677 l 8.6161899,14.92541 c 2.424737,4.19978 7.758197,5.62854 11.95794,3.20377 l 7.930877,-4.57893 a 50.663505,50.95301 0 0 0 14.93103,8.81636 v 9.12958 c 0,4.84953 3.903561,8.75306 8.753067,8.75306 h 17.234564 c 4.849471,0 8.753032,-3.90353 8.753032,-8.75306 v -8.90228 a 50.663505,50.95301 0 0 0 15.393578,-8.94415 l 7.757848,4.47942 c 4.19982,2.42477 9.53324,0.99601 11.95796,-3.20377 l 8.61621,-14.92541 c 2.42472,-4.1997 0.99596,-9.53201 -3.20378,-11.95677 l -7.78614,-4.49524 a 50.663505,50.95301 0 0 0 0.84705,-8.87183 50.663505,50.95301 0 0 0 -0.81197,-8.72475 l 8.0405,-4.64225 c 4.19982,-2.42476 5.62859,-7.75707 3.20385,-11.95684 l -8.6162,-14.92534 c -2.42474,-4.19978 -7.75823,-5.62854 -11.95797,-3.20377 l -7.930861,4.57893 a 50.663505,50.95301 0 0 0 -15.510075,-9.02895 v -8.91589 c 0,-4.84946 -3.903561,-8.75416 -8.753032,-8.75416 z m 8.9068,28.59545 A 36.767228,36.977328 0 0 1 103.05797,230.85344 36.767228,36.977328 0 0 1 66.290738,267.83108 36.767228,36.977328 0 0 1 29.5235,230.85344 36.767228,36.977328 0 0 1 66.290738,193.87587 Z"
+       id="path981"
+       inkscape:connector-curvature="0" />
+  </g>
+</svg>

tubearchivist/static/img/icon-help.svg

@@ -0,0 +1,68 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="500"
+   height="500"
+   viewBox="0 0 132.29197 132.29167"
+   version="1.1"
+   id="svg1303"
+   inkscape:version="0.92.4 (5da689c313, 2019-01-14)"
+   sodipodi:docname="Icons_Help.svg">
+  <defs
+     id="defs1297" />
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.0105705"
+     inkscape:cx="58.993585"
+     inkscape:cy="143.32456"
+     inkscape:document-units="mm"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     units="px"
+     inkscape:window-width="1920"
+     inkscape:window-height="1017"
+     inkscape:window-x="-8"
+     inkscape:window-y="-8"
+     inkscape:window-maximized="1" />
+  <metadata
+     id="metadata1300">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Ebene 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(0,-164.70764)">
+    <g
+       transform="matrix(6.2585232,0,0,6.2585232,-555.66096,-762.59652)"
+       id="g1069"
+       style="fill:#000000">
+      <path
+         style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke"
+         d="M 99.35362,148.32944 A 10.406119,10.406119 0 0 0 88.947542,158.73553 10.406119,10.406119 0 0 0 99.35362,169.14162 10.406119,10.406119 0 0 0 109.7597,158.73553 10.406119,10.406119 0 0 0 99.35362,148.32944 Z m 0.022,2.79535 c 0.58489,0 1.12588,0.073 1.62304,0.2192 0.51178,0.14622 0.95018,0.37308 1.31574,0.68016 0.38018,0.30706 0.67262,0.70157 0.87734,1.18411 0.21933,0.46791 0.32933,1.02372 0.32933,1.6671 0,0.4533 -0.0809,0.86261 -0.24176,1.22816 -0.16084,0.35094 -0.3655,0.67987 -0.61408,0.98694 -0.23396,0.30706 -0.48991,0.60692 -0.76774,0.89936 -0.26321,0.27783 -0.51176,0.57027 -0.74571,0.87734 -0.21932,0.30707 -0.39436,0.63601 -0.52597,0.98694 -0.1316,0.33631 -0.17549,0.72394 -0.13163,1.16261 h -2.829714 c -0.07311,-0.49715 -0.0583,-0.95035 0.04406,-1.35979 0.116978,-0.40941 0.277739,-0.78965 0.482453,-1.14059 0.204712,-0.35093 0.431586,-0.67246 0.680164,-0.96491 0.263203,-0.29244 0.511747,-0.57062 0.745707,-0.83381 0.23395,-0.27783 0.4238,-0.54119 0.57002,-0.78977 0.16086,-0.26321 0.24123,-0.53344 0.24123,-0.81125 0,-0.4533 -0.13908,-0.79704 -0.41691,-1.03099 -0.2632,-0.23397 -0.61381,-0.35083 -1.052474,-0.35083 -0.409426,0 -0.774845,0.0952 -1.096536,0.28528 -0.307068,0.19009 -0.606919,0.43123 -0.899364,0.72368 l -1.7767,-1.62304 c 0.511782,-0.59952 1.118345,-1.08235 1.820217,-1.4479 0.716494,-0.36557 1.506571,-0.548 2.369287,-0.548 z m -0.307306,11.16414 c 0.555636,0 1.016256,0.19727 1.381816,0.59205 0.38018,0.38019 0.57003,0.86249 0.57003,1.44737 0,0.57028 -0.18985,1.05311 -0.57003,1.4479 -0.36556,0.38018 -0.82618,0.57002 -1.381816,0.57002 -0.555651,0 -1.016262,-0.18984 -1.38182,-0.57002 -0.36556,-0.39479 -0.548536,-0.87762 -0.548536,-1.4479 0,-0.58488 0.182976,-1.06718 0.548536,-1.44737 0.365558,-0.39478 0.826169,-0.59205 1.38182,-0.59205 z"
+         id="path1038"
+         inkscape:connector-curvature="0" />
+    </g>
+  </g>
+</svg>

tubearchivist/static/img/icon-play.svg

@@ -0,0 +1,75 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="500"
+   height="500"
+   viewBox="0 0 132.29197 132.29167"
+   version="1.1"
+   id="svg1303"
+   inkscape:version="0.92.4 (5da689c313, 2019-01-14)"
+   sodipodi:docname="Icons_play.svg">
+  <defs
+     id="defs1297" />
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="3.4343607"
+     inkscape:cx="51.709313"
+     inkscape:cy="230.85077"
+     inkscape:document-units="mm"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     units="px"
+     inkscape:window-width="1920"
+     inkscape:window-height="1017"
+     inkscape:window-x="-8"
+     inkscape:window-y="-8"
+     inkscape:window-maximized="1" />
+  <metadata
+     id="metadata1300">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Ebene 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(0,-164.70764)">
+    <path
+       sodipodi:type="star"
+       style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke"
+       id="path1206"
+       sodipodi:sides="3"
+       sodipodi:cx="-142.60593"
+       sodipodi:cy="272.75879"
+       sodipodi:r1="30.817924"
+       sodipodi:r2="15.408962"
+       sodipodi:arg1="0.52359878"
+       sodipodi:arg2="1.5707963"
+       inkscape:flatsided="false"
+       inkscape:rounded="-3.46945e-18"
+       inkscape:randomized="0"
+       d="m -115.91682,288.16775 -26.68911,0 -26.6891,0 13.34455,-23.11344 13.34455,-23.11345 13.34456,23.11345 z"
+       transform="matrix(0,1.7014617,-1.7014617,0,530.04498,473.492)"
+       inkscape:transform-center-x="-18.792756" />
+  </g>
+</svg>

tubearchivist/static/img/icon-rescan.svg

@@ -0,0 +1,63 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="500"
+   height="500"
+   viewBox="0 0 132.29197 132.29167"
+   version="1.1"
+   id="svg1303"
+   inkscape:version="0.92.4 (5da689c313, 2019-01-14)"
+   sodipodi:docname="Rescan Subscriptions.svg">
+  <defs
+     id="defs1297" />
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="0.85859018"
+     inkscape:cx="125.63373"
+     inkscape:cy="156.7016"
+     inkscape:document-units="mm"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     units="px"
+     inkscape:window-width="1920"
+     inkscape:window-height="1017"
+     inkscape:window-x="-8"
+     inkscape:window-y="-8"
+     inkscape:window-maximized="1" />
+  <metadata
+     id="metadata1300">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Ebene 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(0,-164.70764)">
+    <path
+       style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke"
+       d="M 240.35352 18.810547 L 240.35352 29.246094 A 221.29301 221.29301 0 0 0 64.912109 129.45898 L 95.701172 150.14453 A 184.02261 184.02261 0 0 1 240.35352 66.369141 L 240.35352 87.705078 L 270.18359 70.480469 L 300.01562 53.257812 L 270.18359 36.035156 L 240.35352 18.810547 z M 312.28516 37.798828 L 301.08398 73.353516 A 184.02261 184.02261 0 0 1 422.6875 187.33594 L 406.34375 192.03125 L 431.13281 215.94922 L 455.92188 239.86719 L 464.24219 206.44141 L 472.56055 173.01367 L 458.55078 177.03711 A 221.29301 221.29301 0 0 0 312.28516 37.798828 z M 73.375 144.88281 L 48.585938 168.80078 L 23.796875 192.71875 L 35.617188 196.11328 A 221.29301 221.29301 0 0 0 28.707031 250 A 221.29301 221.29301 0 0 0 77.992188 388.9375 L 107.99805 366.83789 A 184.02261 184.02261 0 0 1 65.976562 250 A 184.02261 184.02261 0 0 1 71.474609 206.41211 L 90.013672 211.73633 L 81.693359 178.30859 L 73.375 144.88281 z M 433.95312 248.4375 A 184.02261 184.02261 0 0 1 434.02344 250 A 184.02261 184.02261 0 0 1 367.40625 391.49219 L 358.92773 380.14844 L 345.34375 411.80469 L 331.75977 443.45898 L 365.9668 439.39648 L 400.17188 435.33203 L 389.71484 421.33984 A 221.29301 221.29301 0 0 0 471.29297 250 A 221.29301 221.29301 0 0 0 471.23047 248.77539 L 433.95312 248.4375 z M 94.9375 385.80273 L 108.97852 417.25781 L 123.02148 448.71289 L 131.60156 436.87891 A 221.29301 221.29301 0 0 0 250 471.29297 A 221.29301 221.29301 0 0 0 328.64648 456.57227 L 315.99023 421.74805 A 184.02261 184.02261 0 0 1 250 434.02344 A 184.02261 184.02261 0 0 1 153.63867 406.48047 L 163.45898 392.93555 L 129.19727 389.36914 L 94.9375 385.80273 z "
+       transform="matrix(0.26458394,0,0,0.26458394,0,164.70749)"
+       id="path826" />
+  </g>
+</svg>

tubearchivist/static/img/icon-search.svg

@@ -0,0 +1,64 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="500"
+   height="500"
+   viewBox="0 0 132.29197 132.29167"
+   version="1.1"
+   id="svg1303"
+   inkscape:version="0.92.4 (5da689c313, 2019-01-14)"
+   sodipodi:docname="Icons_Lupe.svg">
+  <defs
+     id="defs1297" />
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.0105705"
+     inkscape:cx="-23.955221"
+     inkscape:cy="207.58555"
+     inkscape:document-units="mm"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     units="px"
+     inkscape:window-width="1920"
+     inkscape:window-height="1017"
+     inkscape:window-x="-8"
+     inkscape:window-y="-8"
+     inkscape:window-maximized="1" />
+  <metadata
+     id="metadata1300">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Ebene 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(0,-164.70764)">
+    <path
+       style="opacity:1;fill:#002130;fill-opacity:1;stroke:none;stroke-width:0;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke"
+       d="m 15.593586,179.85791 c 18.094683,-18.09394 47.431291,-18.09355 65.52552,7.7e-4 16.496472,16.53809 18.102694,42.7696 3.747207,61.19678 17.821687,15.21024 24.490877,18.93088 42.171347,34.20969 4.41254,4.71717 4.29213,12.08299 -0.27223,16.65347 -4.57089,4.56126 -11.93421,4.68001 -16.65007,0.26874 l -8.4e-4,9.1e-4 -0.0173,-0.0152 C 94.335453,273.50898 90.211408,265.24542 76.792795,249.15281 58.360539,263.5048 32.12693,261.89037 15.593512,245.38662 c -18.0947127,-18.09455 -18.0947127,-47.43175 0,-65.52636 z m 7.908493,7.90846 c -13.7275962,13.72683 -13.7279739,35.98299 -8.23e-4,49.71019 13.72719,13.72714 35.983444,13.72678 49.710173,-8.2e-4 13.726834,-13.72692 13.726834,-35.98245 0,-49.70937 -13.726863,-13.72676 -35.982478,-13.72676 -49.70935,0 z"
+       id="rect826"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="ccccccccccccccccc" />
+  </g>
+</svg>

tubearchivist/static/img/icon-seen.svg

@@ -0,0 +1,63 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="500"
+   height="500"
+   viewBox="0 0 132.29197 132.29167"
+   version="1.1"
+   id="svg1303"
+   inkscape:version="0.92.4 (5da689c313, 2019-01-14)"
+   sodipodi:docname="Icons_seen-02.svg">
+  <defs
+     id="defs1297" />
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="1.0316211"
+     inkscape:cx="67.654116"
+     inkscape:cy="175.0818"
+     inkscape:document-units="mm"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     units="px"
+     inkscape:window-width="1920"
+     inkscape:window-height="1017"
+     inkscape:window-x="-8"
+     inkscape:window-y="-8"
+     inkscape:window-maximized="1" />
+  <metadata
+     id="metadata1300">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Ebene 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(0,-164.70764)">
+    <path
+       style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke"
+       d="M 9.4628906 4.9277344 C 6.9502624 4.9277344 4.9277344 6.6131716 4.9277344 8.7070312 L 4.9277344 491.29297 C 4.9277344 493.38683 6.9502624 495.07227 9.4628906 495.07227 L 490.53711 495.07227 C 493.04974 495.07227 495.07227 493.38683 495.07227 491.29297 L 495.07227 8.7070312 C 495.07227 6.6131716 493.04974 4.9277344 490.53711 4.9277344 L 9.4628906 4.9277344 z M 53.607422 49.070312 L 446.39258 49.070312 C 448.90521 49.070312 450.92969 50.757703 450.92969 52.851562 L 450.92969 447.14844 C 450.92969 449.2423 448.90521 450.92969 446.39258 450.92969 L 53.607422 450.92969 C 51.094794 450.92969 49.070313 449.2423 49.070312 447.14844 L 49.070312 52.851562 C 49.070312 50.757703 51.094794 49.070312 53.607422 49.070312 z M 394.99414 104.48242 C 392.62745 104.47692 390.27922 105.49181 388.64453 107.46484 L 212.35547 320.24414 L 111.90625 232.94141 C 108.46825 229.95328 103.29681 230.31403 100.30859 233.75195 L 73.150391 264.99805 C 70.162261 268.43605 70.524968 273.60942 73.962891 276.59766 L 212.05469 396.62109 C 214.1632 398.4537 216.92406 399.02085 219.43359 398.39648 C 221.58781 398.24033 223.67676 397.24363 225.16992 395.44141 L 249.54883 366.01758 L 250.8125 364.5625 C 251.04106 364.29953 251.24412 364.0237 251.43359 363.74219 L 433.18555 144.36914 C 436.09166 140.86148 435.60727 135.69713 432.09961 132.79102 L 400.2207 106.37891 C 398.68612 105.10748 396.8349 104.4867 394.99414 104.48242 z "
+       transform="matrix(0.26458394,0,0,0.26458394,0,164.70749)"
+       id="rect816" />
+  </g>
+</svg>

tubearchivist/static/img/icon-thumb.svg

@@ -0,0 +1,63 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="500"
+   height="500"
+   viewBox="0 0 132.29197 132.29167"
+   version="1.1"
+   id="svg1303"
+   inkscape:version="0.92.4 (5da689c313, 2019-01-14)"
+   sodipodi:docname="Icons_thumbs.svg">
+  <defs
+     id="defs1297" />
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="0.71458126"
+     inkscape:cx="-133.80736"
+     inkscape:cy="163.34297"
+     inkscape:document-units="mm"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     units="px"
+     inkscape:window-width="1920"
+     inkscape:window-height="1017"
+     inkscape:window-x="-8"
+     inkscape:window-y="-8"
+     inkscape:window-maximized="1" />
+  <metadata
+     id="metadata1300">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Ebene 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(0,-164.70764)">
+    <path
+       style="opacity:1;fill:#1a1a1a;fill-opacity:1;stroke:none;stroke-width:0;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke"
+       d="m 74.762046,169.84647 c -0.757275,-0.0266 -1.556205,0.0266 -2.398918,0.17006 -17.977757,2.9811 5.863528,29.19697 -15.075776,44.15933 -17.503229,14.60104 -23.870308,10.01972 -24.044759,14.80451 v 47.00292 c 2.623747,6.94761 20.093043,14.05087 38.660635,15.56434 18.567588,1.51346 44.529822,-2.41107 44.816272,-10.49357 0.15245,-7.31882 -4.01785,-7.48655 -4.01785,-7.48655 0,0 9.14077,-0.56532 9.44575,-8.4939 0.15212,-7.77626 -8.85445,-8.88809 -8.85445,-8.88809 0,0 11.53636,-0.3275 11.53636,-8.34902 0,-8.20546 -8.87381,-8.85175 -11.6189,-8.99092 1.70324,-0.10363 8.42562,-2.42967 8.3861,-10.53741 -0.0399,-8.37053 -12.87508,-7.67987 -35.956784,-9.20144 2.66326,-15.52873 4.52035,-48.76031 -10.87768,-49.26032 z m -63.387663,53.22425 c -2.167221,0 -3.911718,1.45375 -3.911718,3.25977 v 53.07599 c 0,1.80609 1.744497,3.25983 3.911718,3.25983 h 14.602385 c 2.167228,0 3.911725,-1.45374 3.911725,-3.25983 v -53.07599 c 0,-1.80602 -1.744497,-3.25977 -3.911725,-3.25977 z"
+       id="rect1278"
+       inkscape:connector-curvature="0" />
+  </g>
+</svg>

tubearchivist/static/img/icon-unseen.svg

@@ -0,0 +1,65 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<!-- Created with Inkscape (http://www.inkscape.org/) -->
+
+<svg
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="500"
+   height="500"
+   viewBox="0 0 132.29197 132.29167"
+   version="1.1"
+   id="svg1303"
+   inkscape:version="0.92.4 (5da689c313, 2019-01-14)"
+   sodipodi:docname="icon-unseen.svg">
+  <defs
+     id="defs1297" />
+  <sodipodi:namedview
+     id="base"
+     pagecolor="#ffffff"
+     bordercolor="#666666"
+     borderopacity="1.0"
+     inkscape:pageopacity="0.0"
+     inkscape:pageshadow="2"
+     inkscape:zoom="0.72946627"
+     inkscape:cx="216.49148"
+     inkscape:cy="168.6324"
+     inkscape:document-units="mm"
+     inkscape:current-layer="layer1"
+     showgrid="false"
+     units="px"
+     inkscape:window-width="1920"
+     inkscape:window-height="1017"
+     inkscape:window-x="-8"
+     inkscape:window-y="-8"
+     inkscape:window-maximized="1" />
+  <metadata
+     id="metadata1300">
+    <rdf:RDF>
+      <cc:Work
+         rdf:about="">
+        <dc:format>image/svg+xml</dc:format>
+        <dc:type
+           rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
+        <dc:title />
+      </cc:Work>
+    </rdf:RDF>
+  </metadata>
+  <g
+     inkscape:label="Ebene 1"
+     inkscape:groupmode="layer"
+     id="layer1"
+     transform="translate(0,-164.70764)">
+    <path
+       style="opacity:1;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0;stroke-linecap:round;stroke-linejoin:bevel;stroke-miterlimit:4;stroke-dasharray:none;stroke-dashoffset:0;stroke-opacity:1;paint-order:markers fill stroke"
+       d="m 9.6367188,5.1015625 c -2.5126284,0 -4.5351563,1.6854372 -4.5351563,3.7792969 V 491.11914 c 0,2.09386 2.022528,3.7793 4.5351563,3.7793 H 490.36328 c 2.51263,0 4.53516,-1.68544 4.53516,-3.7793 V 8.8808594 c 0,-2.0938597 -2.02253,-3.7792969 -4.53516,-3.7792969 z M 53.748047,49.212891 H 446.25195 c 2.51263,0 4.53516,1.685437 4.53516,3.779297 V 447.00781 c 0,2.09386 -2.02253,3.7793 -4.53516,3.7793 H 53.748047 c -2.512628,0 -4.535156,-1.68544 -4.535156,-3.7793 V 52.992188 c 0,-2.09386 2.022528,-3.779297 4.535156,-3.779297 z"
+       transform="matrix(0.26458394,0,0,0.26458394,0,164.70749)"
+       id="rect816"
+       inkscape:connector-curvature="0"
+       sodipodi:nodetypes="ssssssssssssssssss" />
+  </g>
+</svg>

tubearchivist/static/progress.js

@@ -0,0 +1,84 @@
+/**
+ * Handle progress bar on /download
+ * 
+ */
+
+
+setTimeout(function(){
+    checkMessage();
+}, 1000);
+
+// initial check for messages
+function checkMessage() {
+    var req = new XMLHttpRequest();
+    req.responseType = 'json';
+    req.open('GET', '/downloads/progress', true);
+    req.onload = function() {
+        var dlProgress = req.response;
+        if (dlProgress['status']) {
+            console.log('start interval');
+            buildDownloadMessage(dlProgress);
+            handleInterval();
+        };
+        console.log(JSON.stringify(dlProgress));
+    };
+    req.send();
+}
+
+// set interval until no more messages
+function handleInterval() {
+    var watchDownload = setInterval(function() {
+        var req = new XMLHttpRequest();
+        req.responseType = 'json';
+        req.open('GET', '/downloads/progress', true);
+        req.onload = function() {
+            var dlProgress = req.response;
+            if (dlProgress['status']) {
+                console.log('continue interval');
+                buildDownloadMessage(dlProgress);
+            } else {
+                console.log('stop interval');
+                clearInterval(watchDownload);
+                location.reload();
+            };
+            console.log(JSON.stringify(dlProgress));
+        };
+        req.send();
+    }, 3000);
+};
+
+// remove and set message
+function buildDownloadMessage(dlProgress) {
+    var box = document.getElementById('downloadMessage');
+    box.innerHTML = '';
+    var dlStatus = dlProgress['status'];
+    var dlTitle = dlProgress['title'];
+    var dlMessage = dlProgress['message'];
+    // animate
+    if (dlStatus === 'rescan') {
+        animate('rescan-icon', 'rotate-img');
+    } else if (dlStatus === 'downloading') {
+        animate('download-icon', 'bounce-img');
+    };
+    // div box
+    var box = document.getElementById('downloadMessage');
+    var message = document.createElement('div');
+    message.classList.add('download-progress');
+    message.id = 'progress';
+    message.setAttribute('data', dlStatus);
+    var title = document.createElement('h3');
+    title.innerHTML = dlTitle;
+    var messageText = document.createElement('p');
+    messageText.innerHTML = dlMessage;
+    message.appendChild(title);
+    message.appendChild(messageText);
+    box.appendChild(message);
+};
+
+function animate(elementId, animationClass) {
+    var toAnimate = document.getElementById(elementId);
+    if (toAnimate.className !== animationClass) {
+        toAnimate.className = animationClass;
+        console.log(elementId, animationClass);
+    }
+}

tubearchivist/static/script.js

@@ -0,0 +1,271 @@
+
+function sortChange(sortValue) {
+    var payload = JSON.stringify({'sort_order': sortValue});
+    sendPost(payload);
+    setTimeout(function(){
+        location.reload();
+        return false;
+    }, 500);
+}
+
+function hideWatched(hideValue) {
+    var payload = JSON.stringify({'hide_watched': hideValue});
+    sendPost(payload);
+    setTimeout(function(){
+        location.reload();
+        return false;
+    }, 500);
+}
+
+function showSubscribedOnly(showValue) {
+    var payload = JSON.stringify({'show_subed_only': showValue});
+    sendPost(payload);
+    setTimeout(function(){
+        location.reload();
+        return false;
+    }, 500);
+}
+
+function isWatched(youtube_id) {
+    var payload = JSON.stringify({'watched': youtube_id});
+    sendPost(payload);
+    var seenIcon = document.createElement('img');
+    seenIcon.setAttribute('src', "/static/img/icon-seen.svg");
+    seenIcon.setAttribute('alt', 'seen-icon');
+    seenIcon.setAttribute('id', youtube_id);
+    seenIcon.classList = 'seen-icon';
+    document.getElementById(youtube_id).replaceWith(seenIcon);
+}
+
+function unsubscribe(channel_id) {
+    var payload = JSON.stringify({'unsubscribe': channel_id});
+    sendPost(payload);
+    document.getElementById('sub-' + channel_id).remove();
+}
+
+// download page buttons
+function rescanPending() {
+    var payload = JSON.stringify({'rescan_pending': true});
+    animate('rescan-icon', 'rotate-img');
+    sendPost(payload);
+    setTimeout(function(){
+        handleInterval();
+    }, 500);
+}
+
+function dlPending() {
+    var payload = JSON.stringify({'dl_pending': true});
+    animate('download-icon', 'bounce-img');
+    sendPost(payload);
+    setTimeout(function(){
+        handleInterval();
+    }, 500);
+}
+
+function toIgnore(button) {
+    var youtube_id = button.getAttribute('data-id');
+    var payload = JSON.stringify({'ignore': youtube_id});
+    console.log(payload);
+    sendPost(payload);
+    document.getElementById('dl-' + youtube_id).remove();
+}
+
+function downloadNow(button) {
+    var youtube_id = button.getAttribute('data-id');
+    var payload = JSON.stringify({'dlnow': youtube_id});
+    animate('download-icon', 'bounce-img');
+    sendPost(payload);
+    setTimeout(function(){
+        handleInterval();
+    }, 500);
+}
+
+// player
+function createPlayer(button) {
+    var mediaUrl = button.getAttribute('data-src');
+    var mediaThumb = button.getAttribute('data-thumb');
+    var mediaTitle = button.getAttribute('data-title');
+    var mediaChannel = button.getAttribute('data-channel');
+    var dataId = button.getAttribute('data-id');
+    // get watched status
+    var playedStatus = document.createDocumentFragment();
+    playedStatus.appendChild(document.getElementById(dataId));
+    // create player
+    removePlayer();
+    var playerElement = document.getElementById('player');
+    playerElement.setAttribute('data-id', dataId);
+    // playerElement.innerHTML = '';
+    var videoPlayer = document.createElement('video');
+    videoPlayer.setAttribute('src', mediaUrl);
+    videoPlayer.setAttribute('controls', true);
+    videoPlayer.setAttribute('autoplay', true);
+    videoPlayer.setAttribute('width', '100%');
+    videoPlayer.setAttribute('poster', mediaThumb);
+    playerElement.appendChild(videoPlayer);
+    // title bar
+    var titleBar = document.createElement('div');
+    titleBar.className = 'player-title';
+    // close
+    var closeButton = document.createElement('img');
+    closeButton.className = 'close-button';
+    closeButton.setAttribute('src', "/static/img/icon-close.svg");
+    closeButton.setAttribute('alt', 'close-icon');
+    closeButton.setAttribute('data', dataId);
+    closeButton.setAttribute('onclick', "removePlayer()");
+    closeButton.setAttribute('title', 'Close player');
+    titleBar.appendChild(closeButton);
+    // played
+    titleBar.appendChild(playedStatus);
+    playerElement.appendChild(titleBar);
+    // title
+    var videoTitle = document.createElement('p');
+    videoTitle.innerText = mediaTitle;
+    titleBar.appendChild(videoTitle);
+    var videoChannel = document.createElement('p');
+    videoChannel.innerText = mediaChannel
+    titleBar.appendChild(videoChannel);
+    // button
+    var videoButton = document.createElement('button');
+    videoButton.innerText = 'Details';
+    videoButton.setAttribute('onclick', "window.location.href='/video/" + dataId + "/';");
+    titleBar.appendChild(videoButton);
+}
+
+function removePlayer() {
+    var playerElement = document.getElementById('player');
+    if (playerElement.hasChildNodes()) {
+        var youtubeId = playerElement.getAttribute('data-id');
+        var playedStatus = document.createDocumentFragment();
+        playedStatus.appendChild(document.getElementById(youtubeId));
+        playerElement.innerHTML = '';
+        // append played status
+        var videoInfo = document.getElementById('video-info-' + youtubeId);
+        videoInfo.insertBefore(playedStatus, videoInfo.firstChild);
+    };
+}
+
+// searching channels
+function searchChannels(query) {
+    var searchResultBox = document.getElementById('resultBox');
+    searchResultBox.innerHTML = '';
+    if (query.length > 1) {
+        var payload = JSON.stringify({'channel-search': query})
+        sendSearchAsYouType(payload);
+        console.log(payload);
+    };
+}
+
+
+function populateChannelResults(allResults) {
+    
+    var searchResultBox = document.getElementById('resultBox');
+    
+    for (let i = 0; i < allResults.length; i++) {
+        
+        var singleResult = allResults[i];
+        var source = singleResult['source'];
+        var channelName = source['channel_name'];
+        var channelId = source['channel_id'];
+        var optionElement = document.createElement('option');
+        optionElement.value = channelName;
+        optionElement.setAttribute('data', channelId);
+        searchResultBox.appendChild(optionElement);
+        console.log(channelId, channelName);
+
+    }
+
+}
+
+function channelRedirect(){
+    var response = document.getElementById('resultBox');
+    var firstChild = response.firstChild
+    if (firstChild) {
+        var redirectId = firstChild.getAttribute('data');
+        console.log('redirecting: ' + redirectId);
+        location = '/channel/' + redirectId;
+    }
+    return false;
+}
+
+
+function sendSearchAsYouType(payload) {
+    console.log(payload);
+    var http = new XMLHttpRequest();
+    
+    http.onreadystatechange = function() {
+        if (http.readyState === 4) {
+            allResults = JSON.parse(http.response)['results'];
+            populateChannelResults(allResults);
+        }
+    }
+
+    http.open("POST", "/process/", true);
+    http.setRequestHeader("X-CSRFToken", getCookie("csrftoken"));
+    http.setRequestHeader("Content-type", "application/json");
+    http.send(payload);
+}
+
+
+
+// generic
+function sendPost(payload) {
+    console.log(payload);
+    var http = new XMLHttpRequest();
+    http.open("POST", "/process/", true);
+    http.setRequestHeader("X-CSRFToken", getCookie("csrftoken"));
+    http.setRequestHeader("Content-type", "application/json");
+    http.send(payload);
+}
+
+
+function getCookie(c_name) {
+    if (document.cookie.length > 0) {
+        c_start = document.cookie.indexOf(c_name + "=");
+        if (c_start != -1) {
+            c_start = c_start + c_name.length + 1;
+            c_end = document.cookie.indexOf(";", c_start);
+            if (c_end == -1) c_end = document.cookie.length;
+            return unescape(document.cookie.substring(c_start,c_end));
+        };
+    };
+    return "";
+}
+
+
+// animations
+function textReveal() {
+    var textBox = document.getElementById('text-reveal');
+    var button = document.getElementById('text-reveal-button');
+    var textBoxHeight = textBox.style.height;
+    if (textBoxHeight === 'unset') {
+        textBox.style.height = '0px';
+        button.innerText = 'Show';
+    } else {
+        textBox.style.height = 'unset';
+        button.innerText = 'Hide';
+    };
+}
+
+function showSearch() {
+    var searchBox = document.getElementById('search-box');
+    var displayStyle = searchBox.style.display
+    if (displayStyle === "") {
+        searchBox.style.display = 'block';
+    } else {
+        searchBox.style.display = "";
+    }
+    var inputBox = document.getElementById('searchInput');
+    inputBox.focus();
+}
+
+function showForm() {
+    console.log('show hidden form');
+    var formElement = document.getElementById('hidden-form');
+    var displayStyle = formElement.style.display
+    if (displayStyle === "") {
+        formElement.style.display = 'block';
+        animate('add-icon', 'pulse-img');
+    } else {
+        formElement.style.display = "";
+    }
+}

uwsgi.ini

@@ -0,0 +1,8 @@
+[uwsgi]
+; chdir = /app
+module=config.wsgi:application
+master=True
+pidfile=/tmp/project-master.pid
+vacuum=True
+max-requests=5000
+socket = :8080