First Beta Release for Version 4.16

PyLint 4 removed it.

.github/dependabot.yml

@@ -0,0 +1,15 @@
+version: 2
+updates:
+  - package-ecosystem: pip
+    directory: "/"
+    schedule:
+      interval: monthly
+    cooldown:
+      default-days: 7
+
+  - package-ecosystem: github-actions
+    directory: "/"
+    schedule:
+      interval: monthly
+    cooldown:
+      default-days: 7

.github/pull_request_template.md

@@ -2,17 +2,23 @@
 
 <!--
 Thanks for your willingness to contribute to Instaloader! Please briefly
-describe
+describe:
 
 - A motivation for this change, e.g.
   - Fixes # .
-  - More general: What problem does the pull request solve?
+  - What problem does the pull request solve?
 
 - The changes proposed in this pull request
+  - Keep the PR focused: avoid bundling independent fixes or refactorings.
 
 - The completeness of this change
-  - Is it just a proof of concept?
   - Is the documentation updated (if appropriate)?
-  - Do you consider it ready to be merged or is it a draft?
+  - How has it been tested?
+  - Do you consider it ready to be merged or is it a draft / proof of concept?
   - Can we help you at some point?
+
+- Further considerations
+  - Is it based on master (bugfix), upcoming/v4.X (new feature), or another pull request?
+  - Does it preserve backward compatibility and existing behavior?
+
 -->

.github/workflows/documentation.yml

@@ -8,17 +8,18 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: "Checkout Instaloader Repository"
-        uses: actions/checkout@v4
+        uses: actions/checkout@v7
         with:
           fetch-depth: 0  # needed for building docs
+          persist-credentials: false
       - name: "Setup Python"
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v7
         with:
-          python-version: 3.14
+          python-version: 3.15
           cache: 'pipenv'
       - name: "Install Dependencies"
         run: |
-          python -m pip install pipenv==2025.0.4
+          python -m pip install pipenv==2026.8.0
           pipenv --python `python --version | grep -Eo '3\.[0-9]+'` sync --dev
       - name: "Build Documentation"
         run: pipenv --python `python --version | grep -Eo '3\.[0-9]+'` run make -C docs html SPHINXOPTS="-W -n"

.github/workflows/lint.yml

@@ -9,21 +9,22 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13", "3.14"]
+        python-version: ["3.10", "3.11", "3.12", "3.13", "3.14", "3.15"]
     steps:
       - name: Checkout Instaloader Repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v7
+        with:
+          persist-credentials: false
       - name: Setup Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v7
         with:
           python-version: ${{ matrix.python-version }}
           cache: 'pipenv'
       - name: Install Dependencies
         run: |
-          python -m pip install pipenv==2025.0.4
+          python -m pip install pipenv==2026.8.0
           pipenv --python `python --version | grep -Eo '3\.[0-9]+'` sync --dev
       - name: PyLint
-        if: matrix.python-version != '3.9'
         run: pipenv --python `python --version | grep -Eo '3\.[0-9]+'` run pylint instaloader
       - name: MyPy
         run: pipenv --python `python --version | grep -Eo '3\.[0-9]+'` run mypy -m instaloader

.github/workflows/packages.yml

@@ -11,11 +11,13 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: "Checkout Repository"
-        uses: actions/checkout@v4
+        uses: actions/checkout@v7
-      - name: "Setup Python"
-        uses: actions/setup-python@v5
         with:
-          python-version: 3.14
+          persist-credentials: false
+      - name: "Setup Python"
+        uses: actions/setup-python@v7
+        with:
+          python-version: 3.15
       - name: "Get the tagged version"
         id: get_version
         env:

.github/workflows/stale.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     
     steps:
-    - uses: actions/stale@v9
+    - uses: actions/stale@v11
       with:
         repo-token: ${{ secrets.GITHUB_TOKEN }}
         only-labels: 'question'
@@ -21,7 +21,7 @@ jobs:
         days-before-stale: 21
         days-before-close: -1
         remove-stale-when-updated: false
-    - uses: actions/stale@v9
+    - uses: actions/stale@v11
       with:
         repo-token: ${{ secrets.GITHUB_TOKEN }}
         stale-issue-message: 'There has been no activity on this issue for an extended period of time. This issue will be closed after further 14 days of inactivity.'

.github/workflows/windows_exe.yml

@@ -8,11 +8,13 @@ jobs:
     runs-on: windows-latest
     steps:
       - name: Checkout Instaloader repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v7
-      - name: Setup Python
-        uses: actions/setup-python@v5
         with:
-          python-version: "3.14"
+          persist-credentials: false
+      - name: Setup Python
+        uses: actions/setup-python@v7
+        with:
+          python-version: 3.15
           cache: 'pipenv'
           architecture: x64
       - name: Get the tagged version
@@ -28,7 +30,7 @@ jobs:
       - name: Create draft release and upload EXE as release asset
         if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v')
         id: create_release
-        uses: softprops/action-gh-release@v2
+        uses: softprops/action-gh-release@v3
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:

.pylintrc

@@ -93,10 +93,6 @@ py-version=3.8
 # Discover python modules and packages in the file system subtree.
 recursive=no
 
-# When enabled, pylint would attempt to guess common misconfiguration and emit
-# user-friendly hints instead of false-positive error messages.
-suggestion-mode=yes
-
 # Allow loading of arbitrary C extensions. Extensions are imported into the
 # active Python interpreter and may run arbitrary code.
 unsafe-load-any-extension=no

Pipfile

@@ -16,6 +16,7 @@ tomli = "*"           # Needed for Pylint for "python_version < '3.11'"
 dill = "*"            # Needed for Pylint for "python_version < '3.11'"
 pywin32-ctypes = "*"  # Needed for pyinstaller on Windows
 pefile = "*"          # Needed for pyinstaller on Windows
+pip-licenses = "*"
 
 [packages]
 requests = "*"

deploy/windows/GPL-3.0.txt

@@ -0,0 +1,674 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <https://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 <https://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
+<https://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
+<https://www.gnu.org/licenses/why-not-lgpl.html>.

deploy/windows/NOTICE.txt

@@ -0,0 +1,16 @@
+instaloader.exe is a standalone executable built with PyInstaller. Besides Instaloader itself
+(see ../LICENSE.txt), it contains the following third-party software:
+
+- Python, its standard library and the libraries it is built with, see Python.txt and
+  Python-incorporated-software.txt.
+- The Python packages listed in third-party.txt, along with their license texts.
+
+browser-cookie3 is licensed under the GNU Lesser General Public License version 3, whose text is
+included in third-party.txt. It refers to the GNU General Public License version 3, see GPL-3.0.txt.
+certifi is licensed under the Mozilla Public License 2.0, whose text is included in third-party.txt.
+Their source code, in the versions listed in third-party.txt, is available at
+https://pypi.org/project/browser-cookie3/#history and https://pypi.org/project/certifi/#history.
+
+You may build instaloader.exe with modified versions of these packages: the source code of
+Instaloader, including the script used to build instaloader.exe (deploy/windows/create_exe.py),
+is published along with each release at https://github.com/instaloader/instaloader/releases.

deploy/windows/create_exe.py

@@ -1,9 +1,12 @@
 import hashlib
+import json
 import os
+import platform
 import re
 import shutil
 import subprocess
 import sys
+import urllib.request
 
 # copy the required files into repo root
 shutil.copy('docs/favicon.ico', '.')
@@ -43,10 +46,18 @@ with open('instaloader/__main__.py', 'r') as f:
 with open('__main__.py', 'w+') as f:
     f.writelines(lines)
 
-# install dependencies and invoke PyInstaller
+# packages bundled into the executable, whose licenses have to be shipped along with it
-commands = ["pip install pipenv==2025.0.4",
+with open('Pipfile.lock') as f:
+    locked_packages = json.load(f)['default']
+bundled_packages = ' '.join(list(locked_packages) + ['psutil', 'pyinstaller'])
+os.makedirs('dist/licenses', exist_ok=True)
+
+# install dependencies, invoke PyInstaller and collect licenses
+commands = ["pip install pipenv==2026.8.0",
             f"pipenv --python {sys.version_info.major}.{sys.version_info.minor} sync --dev",
-            "pipenv run pyinstaller --log-level=DEBUG instaloader.spec"]
+            "pipenv run pyinstaller --log-level=DEBUG instaloader.spec",
+            f"pipenv run pip-licenses --packages {bundled_packages} --with-license-file "
+            "--with-notice-file --no-license-path --format=plain-vertical --output-file dist/licenses/third-party.txt"]
 
 for command in commands:
     print()
@@ -67,5 +78,13 @@ with open('dist/instaloader.exe', 'rb') as f:
 with open('dist/instaloader.exe.md5', 'w+') as f:
     f.write('{} *instaloader.exe\n'.format(hash_md5.hexdigest()))
 
+# include the remaining license texts
+shutil.copy('LICENSE', 'dist/LICENSE.txt')
+shutil.copy('deploy/windows/NOTICE.txt', 'dist/licenses/NOTICE.txt')
+shutil.copy('deploy/windows/GPL-3.0.txt', 'dist/licenses/GPL-3.0.txt')
+shutil.copy(os.path.join(sys.base_prefix, 'LICENSE.txt'), 'dist/licenses/Python.txt')
+urllib.request.urlretrieve('https://raw.githubusercontent.com/python/cpython/v{}/Doc/license.rst'
+                           .format(platform.python_version()), 'dist/licenses/Python-incorporated-software.txt')
+
 # Create ZIP file
 shutil.make_archive('instaloader-{}-windows-standalone'.format(os.getenv('VERSION_TAG')), 'zip', 'dist')

deploy/windows/instaloader.spec

@@ -9,7 +9,7 @@ a = Analysis(['__main__.py'],
              hiddenimports=[],
              hookspath=[],
              runtime_hooks=[],
-             excludes=[],
+             excludes=['setuptools', 'pkg_resources', '_distutils_hack', 'packaging'],
              win_no_prefer_redirects=False,
              win_private_assemblies=False,
              cipher=block_cipher)

docs/README.md

@@ -7,9 +7,10 @@ https://instaloader.github.io/
 
 ## Build
 
-The documentation is created with [Sphinx](http://www.sphinx-doc.org/). To build it, use
+The documentation is created with [Sphinx](http://www.sphinx-doc.org/). To build it, use (in the top-level directory
+of the Instaloader source tree):
 
 ```
-pip3 install -r requirements.txt
+pipenv sync --dev
-make html
+make -C docs html
 ```

docs/codesnippets/615_import_firefox_session.py

@@ -14,8 +14,13 @@ def get_cookiefile():
     default_cookiefile = {
         "Windows": "~/AppData/Roaming/Mozilla/Firefox/Profiles/*/cookies.sqlite",
         "Darwin": "~/Library/Application Support/Firefox/Profiles/*/cookies.sqlite",
-    }.get(system(), "~/.mozilla/firefox/*/cookies.sqlite")
+    }.get(system(), None)
-    cookiefiles = glob(expanduser(default_cookiefile))
+    if default_cookiefile:
+        cookiefiles = glob(expanduser(default_cookiefile))
+    else:
+        # Check Firefox 147+ XDG path, then legacy
+        cookiefiles = glob(expanduser("~/.config/mozilla/firefox/*/cookies.sqlite")) or \
+                      glob(expanduser("~/.mozilla/firefox/*/cookies.sqlite"))
     if not cookiefiles:
         raise SystemExit("No Firefox cookies.sqlite file found. Use -c COOKIEFILE.")
     return cookiefiles[0]

docs/contributing.rst

@@ -74,6 +74,14 @@ Improvements of the Instaloader source or its documentation can be proposed as a
     - a bug fix that does require thorough testing before being released to a
       final version.
 
+- Keep Pull Requests focused: address a single problem or feature in a
+  self-contained change. Avoid bundling multiple independent fixes, refactorings,
+  or architectural changes into one pull request, as this makes it hard to
+  review, validate, or selectively merge them.
+
+- Be mindful of backward compatibility: changes should preserve existing intended
+  behavior whenever possible.
+
 - All Pull Requests are analyzed by `Pylint <https://www.pylint.org/>`__ for
   error and syntax checking of the source and
   `Mypy <https://github.com/python/mypy>`__ for type checking. You can run them

docs/requirements.txt

@@ -1,2 +0,0 @@
-requests
-sphinx~=2.3

instaloader/__init__.py

@@ -1,7 +1,7 @@
 """Download pictures (or videos) along with their captions and other metadata from Instagram."""
 
 
-__version__ = '4.15.3'
+__version__ = '4.16b1'
 
 
 try:

instaloader/__main__.py

@@ -16,7 +16,7 @@ from .instaloader import (get_default_session_filename, get_default_stamps_filen
 from .instaloadercontext import default_user_agent
 from .lateststamps import LatestStamps
 try:
-    import browser_cookie3
+    import browser_cookie3  # type: ignore[import-untyped]
     bc3_library = True
 except ImportError:
     bc3_library = False

instaloader/instaloader.py

@@ -12,7 +12,7 @@ from datetime import datetime, timezone
 from functools import wraps
 from io import BytesIO
 from pathlib import Path
-from typing import Any, Callable, IO, Iterator, List, Optional, Set, Union, cast
+from typing import Any, Callable, Dict, IO, Iterator, List, Optional, Set, Union, cast
 from urllib.parse import urlparse
 
 import requests
@@ -85,31 +85,36 @@ def _requires_login(func: Callable) -> Callable:
 def _retry_on_connection_error(func: Callable) -> Callable:
     """Decorator to retry the function max_connection_attempts number of times.
 
-    Herewith-decorated functions need an ``_attempt`` keyword argument.
-
     This is to decorate functions that do network requests that may fail. Note that
     :meth:`.get_json`, :meth:`.get_iphone_json`, :meth:`.graphql_query` and :meth:`.graphql_node_list` already have
     their own logic for retrying, hence functions that only use these for network access must not be decorated with this
-    decorator."""
+    decorator.
+
+    .. versionchanged:: 4.16
+       Decorated functions no longer need to accept an ``_attempt`` keyword argument.
+    """
     @wraps(func)
-    def call(instaloader, *args, **kwargs):
+    def call(instaloader, *args, **kwargs) -> Any:
-        try:
+        # The failure we are currently retrying, if any. It tells us whether a ^C means "skip this
-            return func(instaloader, *args, **kwargs)
+        # download" rather than "abort everything", and whether to sleep before the next attempt.
-        except (urllib3.exceptions.HTTPError, requests.exceptions.RequestException, ConnectionException) as err:
+        pending_error_string: Optional[str] = None
-            error_string = "{}({}): {}".format(func.__name__, ', '.join([repr(arg) for arg in args]), err)
+        for attempt in range(1, instaloader.context.max_connection_attempts + 1):
-            if (kwargs.get('_attempt') or 1) == instaloader.context.max_connection_attempts:
-                raise ConnectionException(error_string) from None
-            instaloader.context.error(error_string + " [retrying; skip with ^C]", repeat_at_end=False)
             try:
-                if kwargs.get('_attempt'):
+                if pending_error_string is not None:
-                    kwargs['_attempt'] += 1
+                    instaloader.context.do_sleep()
-                else:
+                return func(instaloader, *args, **kwargs)
-                    kwargs['_attempt'] = 2
+            except (urllib3.exceptions.HTTPError, requests.exceptions.RequestException, ConnectionException) as err:
-                instaloader.context.do_sleep()
+                error_string = "{}({}): {}".format(func.__name__, ', '.join([repr(arg) for arg in args]), err)
-                return call(instaloader, *args, **kwargs)
+                if attempt == instaloader.context.max_connection_attempts:
+                    raise ConnectionException(error_string) from None
+                instaloader.context.error(error_string + " [retrying; skip with ^C]", repeat_at_end=False)
+                pending_error_string = error_string
             except KeyboardInterrupt:
+                if pending_error_string is None:
+                    raise
                 instaloader.context.error("[skipped by user]", repeat_at_end=False)
-                raise ConnectionException(error_string) from None
+                raise ConnectionException(pending_error_string) from None
+        raise AssertionError("_retry_on_connection_error() retry loop exited without result")
     return call
 
 
@@ -330,9 +335,12 @@ class Instaloader:
     def __exit__(self, *args):
         self.close()
 
+    def __repr__(self):
+        return f"<Instaloader context={self.context}>"
+
     @_retry_on_connection_error
     def download_pic(self, filename: str, url: str, mtime: datetime,
-                     filename_suffix: Optional[str] = None, _attempt: int = 1) -> bool:
+                     filename_suffix: Optional[str] = None) -> bool:
         """Downloads and saves picture with given url under given directory with given timestamp.
         Returns true, if file was actually downloaded, i.e. updated."""
         if filename_suffix is not None:
@@ -516,8 +524,9 @@ class Instaloader:
                                 '{0}_{1}_{2}.{3}'.format(target, identifier, name_suffix, extension))
 
     @_retry_on_connection_error
-    def download_title_pic(self, url: str, target: Union[str, Path], name_suffix: str, owner_profile: Optional[Profile],
+    def download_title_pic(
-                           _attempt: int = 1) -> None:
+            self, url: str, target: Union[str, Path], name_suffix: str, owner_profile: Optional[Profile]
+    ) -> None:
         """Downloads and saves a picture that does not have an association with a Post or StoryItem, such as a
         Profile picture or a Highlight cover picture. Modification time is taken from the HTTP response headers.
 
@@ -960,6 +969,11 @@ class Instaloader:
         .. versionchanged:: 4.3
            Also downloads and saves the Highlight's cover pictures.
 
+        .. versionchanged:: 4.16
+           Add progress output for highlight retrieval, displaying a counter of the current
+           highlight number and the total number of highlights being processed. This provides
+           feedback similar to the per-item download counter already present in this function.
+
         :param user: ID or Profile of the user whose highlights should get downloaded.
         :param fast_update: If true, abort when first already-downloaded picture is encountered
         :param filename_target: Replacement for {target} in dirname_pattern and filename_pattern
@@ -967,14 +981,20 @@ class Instaloader:
         :param storyitem_filter: function(storyitem), which returns True if given StoryItem should be downloaded
         :raises LoginRequiredException: If called without being logged in.
         """
-        for user_highlight in self.get_highlights(user):
+        user_highlights = list(self.get_highlights(user))
+        hl_size = len(user_highlights)
+        for hl_number, user_highlight in enumerate(user_highlights, start=1):
             name = user_highlight.owner_username
             highlight_target: Union[str, Path] = (filename_target
                                 if filename_target
                                 else (Path(_PostPathFormatter.sanitize_path(name, self.sanitize_paths)) /
                                       _PostPathFormatter.sanitize_path(user_highlight.title,
                                                                        self.sanitize_paths)))
-            self.context.log("Retrieving highlights \"{}\" from profile {}".format(user_highlight.title, name))
+            self.context.log(
+                "[{0:{w}d}/{1:{w}d}] Retrieving highlights \"{2}\" from profile {3}".format(
+                    hl_number, hl_size, user_highlight.title, name, w=len(str(hl_size))
+                )
+            )
             self.download_highlight_cover(user_highlight, highlight_target)
             totalcount = user_highlight.itemcount
             count = 1
@@ -1092,22 +1112,16 @@ class Instaloader:
         :raises LoginRequiredException: If called without being logged in.
         """
 
-        data = self.context.graphql_query("d6f4427fbe92d846298cf93df0b937d3", {})["data"]
+        params: Dict[str, Any] = {}
-
         while True:
-            feed = data["user"]["edge_web_feed_timeline"]
+            data = self.context.get_json("api/v1/feed/timeline/", params=params)
-            for edge in feed["edges"]:
+            for item in data.get("feed_items", []):
-                node = edge["node"]
+                media = item.get("media_or_ad")
-                if node.get("__typename") in Post.supported_graphql_types() and node.get("shortcode") is not None:
+                if media and media.get("code") and media.get("ad_id") is None:
-                    yield Post(self.context, node)
+                    yield Post.from_iphone_struct(self.context, media)
-            if not feed["page_info"]["has_next_page"]:
+            if not (data.get("more_available") and data.get("next_max_id")):
                 break
-            data = self.context.graphql_query("d6f4427fbe92d846298cf93df0b937d3",
+            params = {"max_id": data["next_max_id"]}
-                                              {'fetch_media_item_count': 12,
-                                               'fetch_media_item_cursor': feed["page_info"]["end_cursor"],
-                                               'fetch_comment_count': 4,
-                                               'fetch_like': 10,
-                                               'has_stories': False})["data"]
 
     @_requires_login
     def download_feed_posts(self, max_count: Optional[int] = None, fast_update: bool = False,

instaloader/instaloadercontext.py

@@ -2,6 +2,7 @@ import json
 import os
 import pickle
 import random
+import re
 import shutil
 import sys
 import textwrap
@@ -30,6 +31,19 @@ def copy_session(session: requests.Session, request_timeout: Optional[float] = N
     return new
 
 
+def _embedded_query_data(obj: Any) -> Iterator[Dict[str, Any]]:
+    """Yield the data of each GraphQL query result in JSON that a page of www.instagram.com embeds."""
+    if isinstance(obj, dict):
+        result = obj['__bbox'].get('result') if isinstance(obj.get('__bbox'), dict) else None
+        if isinstance(result, dict) and isinstance(result.get('data'), dict):
+            yield result['data']
+        for value in obj.values():
+            yield from _embedded_query_data(value)
+    elif isinstance(obj, list):
+        for value in obj:
+            yield from _embedded_query_data(value)
+
+
 def default_user_agent() -> str:
     return ('Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 '
             '(KHTML, like Gecko) Chrome/142.0.0.0 Safari/537.36')
@@ -87,7 +101,7 @@ class InstaloaderContext:
         self.user_agent = user_agent if user_agent is not None else default_user_agent()
         self.request_timeout = request_timeout
         self._session = self.get_anonymous_session()
-        self.username = None
+        self.username: Optional[str] = None
         self.user_id = None
         self.sleep = sleep
         self.quiet = quiet
@@ -111,6 +125,9 @@ class InstaloaderContext:
         # Cache profile from id (mapping from id to Profile)
         self.profile_id_cache: Dict[int, Any] = dict()
 
+        # Tokens of the logged-in web page for api/graphql queries, by sessionid cookie
+        self._web_api_tokens_cache: Dict[str, Dict[str, str]] = dict()
+
     @contextmanager
     def anonymous_copy(self):
         session = self._session
@@ -149,6 +166,9 @@ class InstaloaderContext:
         if repeat_at_end:
             self.error_log.append(msg)
 
+    def __repr__(self):
+        return f"<InstaloaderContext is_logged_in={self.is_logged_in}>"
+
     @property
     def has_stored_errors(self) -> bool:
         """Returns whether any error has been reported and stored to be repeated at program termination.
@@ -384,8 +404,102 @@ class InstaloaderContext:
             f" when accessing {resp.url}"
         )
 
+    @staticmethod
+    def _rate_limit_key(path: str, params: Dict[str, Any], host: str) -> str:
+        """Determine the :class:`RateController` bucket that a request is accounted to."""
+        if 'graphql/query' in path or path == 'api/graphql':
+            if 'query_hash' in params:
+                return params['query_hash']
+            if 'doc_id' in params:
+                return params['doc_id']
+        if host == 'i.instagram.com':
+            return 'iphone'
+        return 'other'
+
+    def _raise_if_fatal_status(self, resp: requests.Response, host: str, path: str) -> None:
+        if resp.status_code not in self.fatal_status_codes:
+            return
+        redirect = " redirect to {}".format(resp.headers['location']) if 'location' in resp.headers else ""
+        body = ""
+        if resp.headers.get('Content-Type', '').startswith('application/json'):
+            body = ': ' + resp.text[:500] + ('…' if len(resp.text) > 501 else '')
+        raise AbortDownloadException("Query to https://{}/{} responded with \"{} {}\"{}{}".format(
+            host, path, resp.status_code, resp.reason, redirect, body
+        ))
+
+    def _raise_if_login_redirect(self, resp: requests.Response) -> None:
+        """Turn a redirect to the login page into a meaningful exception.
+
+        Instagram answers requests it will not serve anonymously with a redirect to the login page
+        rather than with an error status, so this needs to be checked wherever we do not follow
+        redirects automatically.
+        """
+        if not resp.is_redirect:
+            return
+        redirect_url = resp.headers.get('location', '')
+        if not (redirect_url.startswith('https://www.instagram.com/accounts/login') or
+                redirect_url.startswith('https://i.instagram.com/accounts/login')):
+            return
+        if not self.is_logged_in:
+            raise LoginRequiredException("Redirected to login page. Use --login or --load-cookies.")
+        raise AbortDownloadException("Redirected to login page. You've been logged out, please wait " +
+                                     "some time, recreate the session and try again")
+
+    def _follow_redirects(self, sess: requests.Session, resp: requests.Response,
+                          host: str, path: str, params: Dict[str, Any], use_post: bool) -> requests.Response:
+        """Follow redirects that stay on *host*, and reject those to the login page."""
+        # Redirects are followed with GET. For a POST request, `params` is the request body and must not be
+        # turned into query arguments.
+        redirect_params = None if use_post else params
+        while resp.is_redirect:
+            redirect_url = resp.headers['location']
+            self.log('\nHTTP redirect from https://{0}/{1} to {2}'.format(host, path, redirect_url))
+            self._raise_if_login_redirect(resp)
+            if not redirect_url.startswith('https://{}/'.format(host)):
+                break
+            resp = sess.get(redirect_url if redirect_url.endswith('/') else redirect_url + '/',
+                            params=redirect_params, allow_redirects=False)
+        return resp
+
+    def _raise_for_status(self, resp: requests.Response) -> None:
+        """Translate an unsuccessful HTTP status code into the corresponding exception."""
+        if resp.status_code == 400:
+            with suppress(json.decoder.JSONDecodeError):
+                if resp.json().get("message") in [
+                    "feedback_required",
+                    "checkpoint_required",
+                    "challenge_required",
+                ]:
+                    # Raise AbortDownloadException in case of substantial Instagram
+                    # requirements to stop producing more requests
+                    raise AbortDownloadException(self._response_error(resp))
+            raise QueryReturnedBadRequestException(self._response_error(resp))
+        if resp.status_code == 404:
+            raise QueryReturnedNotFoundException(self._response_error(resp))
+        if resp.status_code == 429:
+            raise TooManyRequestsException(self._response_error(resp))
+        if resp.status_code != 200:
+            raise ConnectionException(self._response_error(resp))
+
+    def _raise_for_download_status(self, resp: requests.Response) -> None:
+        """Translate an unsuccessful status code of an anonymous download request into an exception.
+
+        This is deliberately a different policy from :meth:`_raise_for_status`, which applies to the
+        JSON API: a download may be answered with 403 for an invalid URL signature, and is never
+        answered with the 400 or 429 that the API uses.
+        """
+        if resp.status_code == 200:
+            return
+        if resp.status_code == 403:
+            # suspected invalid URL signature
+            raise QueryReturnedForbiddenException(self._response_error(resp))
+        if resp.status_code == 404:
+            # 404 not worth retrying.
+            raise QueryReturnedNotFoundException(self._response_error(resp))
+        raise ConnectionException(self._response_error(resp))
+
     def get_json(self, path: str, params: Dict[str, Any], host: str = 'www.instagram.com',
-                 session: Optional[requests.Session] = None, _attempt=1,
+                 session: Optional[requests.Session] = None,
                  response_headers: Optional[Dict[str, Any]] = None,
                  use_post: bool = False) -> Dict[str, Any]:
         """JSON request to Instagram.
@@ -405,96 +519,110 @@ class InstaloaderContext:
 
         .. versionchanged:: 4.13
            Added `use_post` parameter.
+
+        .. versionchanged:: 4.16
+           Removed the internal `_attempt` parameter; retries are no longer implemented by recursion.
         """
-        is_graphql_query = 'query_hash' in params and 'graphql/query' in path
+        sess = session or self._session
-        is_doc_id_query = 'doc_id' in params and 'graphql/query' in path
+        rate_limit_key = self._rate_limit_key(path, params, host)
-        is_iphone_query = host == 'i.instagram.com'
+        url = 'https://{0}/{1}'.format(host, path)
-        is_other_query = not is_graphql_query and not is_doc_id_query and host == "www.instagram.com"
+
-        sess = session if session else self._session
+        # The failure we are currently retrying, if any. It drives the 429 backoff performed before the
-        try:
+        # next attempt, and tells us whether a ^C means "skip this query" rather than "abort everything".
-            self.do_sleep()
+        pending_error: Optional[BaseException] = None
-            if is_graphql_query:
+        pending_error_string = ""
-                self._rate_controller.wait_before_query(params['query_hash'])
+
-            if is_doc_id_query:
+        for attempt in range(1, self.max_connection_attempts + 1):
-                self._rate_controller.wait_before_query(params['doc_id'])
-            if is_iphone_query:
-                self._rate_controller.wait_before_query('iphone')
-            if is_other_query:
-                self._rate_controller.wait_before_query('other')
-            if use_post:
-                resp = sess.post('https://{0}/{1}'.format(host, path), data=params, allow_redirects=False)
-            else:
-                resp = sess.get('https://{0}/{1}'.format(host, path), params=params, allow_redirects=False)
-            if resp.status_code in self.fatal_status_codes:
-                redirect = " redirect to {}".format(resp.headers['location']) if 'location' in resp.headers else ""
-                body = ""
-                if resp.headers['Content-Type'].startswith('application/json'):
-                    body = ': ' + resp.text[:500] + ('…' if len(resp.text) > 501 else '')
-                raise AbortDownloadException("Query to https://{}/{} responded with \"{} {}\"{}{}".format(
-                    host, path, resp.status_code, resp.reason, redirect, body
-                ))
-            while resp.is_redirect:
-                redirect_url = resp.headers['location']
-                self.log('\nHTTP redirect from https://{0}/{1} to {2}'.format(host, path, redirect_url))
-                if (redirect_url.startswith('https://www.instagram.com/accounts/login') or
-                    redirect_url.startswith('https://i.instagram.com/accounts/login')):
-                    if not self.is_logged_in:
-                        raise LoginRequiredException("Redirected to login page. Use --login or --load-cookies.")
-                    raise AbortDownloadException("Redirected to login page. You've been logged out, please wait " +
-                                                 "some time, recreate the session and try again")
-                if redirect_url.startswith('https://{}/'.format(host)):
-                    resp = sess.get(redirect_url if redirect_url.endswith('/') else redirect_url + '/',
-                                    params=params, allow_redirects=False)
-                else:
-                    break
-            if response_headers is not None:
-                response_headers.clear()
-                response_headers.update(resp.headers)
-            if resp.status_code == 400:
-                with suppress(json.decoder.JSONDecodeError):
-                    if resp.json().get("message") in [
-                        "feedback_required",
-                        "checkpoint_required",
-                        "challenge_required",
-                    ]:
-                        # Raise AbortDownloadException in case of substantial Instagram
-                        # requirements to stop producing more requests
-                        raise AbortDownloadException(self._response_error(resp))
-                raise QueryReturnedBadRequestException(self._response_error(resp))
-            if resp.status_code == 404:
-                raise QueryReturnedNotFoundException(self._response_error(resp))
-            if resp.status_code == 429:
-                raise TooManyRequestsException(self._response_error(resp))
-            if resp.status_code != 200:
-                raise ConnectionException(self._response_error(resp))
-            else:
-                resp_json = resp.json()
-            if 'status' in resp_json and resp_json['status'] != "ok":
-                raise ConnectionException(self._response_error(resp))
-            return resp_json
-        except (ConnectionException, json.decoder.JSONDecodeError, requests.exceptions.RequestException) as err:
-            error_string = "JSON Query to {}: {}".format(path, err)
-            if _attempt == self.max_connection_attempts:
-                if isinstance(err, QueryReturnedNotFoundException):
-                    raise QueryReturnedNotFoundException(error_string) from err
-                else:
-                    raise ConnectionException(error_string) from err
-            self.error(error_string + " [retrying; skip with ^C]", repeat_at_end=False)
             try:
-                if isinstance(err, TooManyRequestsException):
+                if isinstance(pending_error, TooManyRequestsException):
-                    if is_graphql_query:
+                    self._rate_controller.handle_429(rate_limit_key)
-                        self._rate_controller.handle_429(params['query_hash'])
+                self.do_sleep()
-                    if is_doc_id_query:
+                self._rate_controller.wait_before_query(rate_limit_key)
-                        self._rate_controller.handle_429(params['doc_id'])
+
-                    if is_iphone_query:
+                if use_post:
-                        self._rate_controller.handle_429('iphone')
+                    resp = sess.post(url, data=params, allow_redirects=False)
-                    if is_other_query:
+                else:
-                        self._rate_controller.handle_429('other')
+                    resp = sess.get(url, params=params, allow_redirects=False)
-                return self.get_json(path=path, params=params, host=host, session=sess, _attempt=_attempt + 1,
+
-                                     response_headers=response_headers)
+                self._raise_if_fatal_status(resp, host, path)
+                resp = self._follow_redirects(sess, resp, host, path, params, use_post)
+
+                if response_headers is not None:
+                    response_headers.clear()
+                    response_headers.update(resp.headers)
+
+                self._raise_for_status(resp)
+                resp_json = resp.json()
+                if 'status' in resp_json and resp_json['status'] != "ok":
+                    raise ConnectionException(self._response_error(resp))
+                return resp_json
+            except (ConnectionException, json.decoder.JSONDecodeError, requests.exceptions.RequestException) as err:
+                error_string = "JSON Query to {}: {}".format(path, err)
+                if attempt == self.max_connection_attempts:
+                    if isinstance(err, QueryReturnedNotFoundException):
+                        raise QueryReturnedNotFoundException(error_string) from err
+                    raise ConnectionException(error_string) from err
+                self.error(error_string + " [retrying; skip with ^C]", repeat_at_end=False)
+                pending_error, pending_error_string = err, error_string
             except KeyboardInterrupt:
+                if pending_error is None:
+                    raise
                 self.error("[skipped by user]", repeat_at_end=False)
-                raise ConnectionException(error_string) from err
+                raise ConnectionException(pending_error_string) from pending_error
+
+        raise AssertionError("get_json() retry loop exited without result")
+
+    @contextmanager
+    def _graphql_session(self, referer: Optional[str], csrf: Optional[str] = None,
+                         lsd: Optional[str] = None) -> Iterator[requests.Session]:
+        """Short-lived session carrying the headers that the GraphQL endpoint expects.
+
+        Pass the page's `lsd` token for the web app's ``api/graphql`` endpoint."""
+        with copy_session(self._session, self.request_timeout) as tmpsession:
+            tmpsession.headers.update(self._default_http_header(empty_session_only=True))
+            del tmpsession.headers['Connection']
+            del tmpsession.headers['Content-Length']
+            tmpsession.headers['authority'] = 'www.instagram.com'
+            tmpsession.headers['scheme'] = 'https'
+            tmpsession.headers['accept'] = '*/*'
+            if csrf is not None:
+                tmpsession.headers['x-csrftoken'] = csrf
+            if referer is not None:
+                tmpsession.headers['referer'] = urllib.parse.quote(referer)
+            if lsd is not None:
+                tmpsession.headers.update({'x-fb-lsd': lsd, 'sec-fetch-dest': 'empty', 'sec-fetch-mode': 'cors',
+                                           'sec-fetch-site': 'same-origin'})
+            yield tmpsession
+
+    def _csrf_token(self) -> str:
+        """The csrftoken cookie value, requesting the start page once if we do not have one yet."""
+        def token_from_cookies() -> Optional[str]:
+            return next((c.value for c in self._session.cookies if c.name == 'csrftoken' and c.value), None)
+        csrf = token_from_cookies()
+        if csrf:
+            return csrf
+        self._session.get('https://www.instagram.com/', timeout=self.request_timeout)
+        return token_from_cookies() or ''
+
+    def _web_api_tokens(self) -> Dict[str, str]:
+        """The tokens that the web app sends along with its api/graphql queries, from the logged-in start page."""
+        sessionid = self._session.cookies.get_dict().get("sessionid", "")
+        if sessionid not in self._web_api_tokens_cache:
+            html = self._get_page(self._session, "")
+            tokens = {}
+            for name, pattern in [
+                ("fb_dtsg", r'"DTSGInitialData",\[\],\{[^{}]*"token":"([^"]+)"'),
+                ("lsd", r'"LSD",\[\],\{[^{}]*"token":"([^"]+)"'),
+                ("av", r'"IG_USER_EIMU":"?(\d+)'),
+            ]:
+                match = re.search(pattern, html)
+                if match is None:
+                    raise BadResponseException(
+                        "The start page did not contain the token {}.".format(name)
+                    )
+                tokens[name] = match.group(1)
+            self._web_api_tokens_cache[sessionid] = tokens
+        return self._web_api_tokens_cache[sessionid]
 
     def graphql_query(self, query_hash: str, variables: Dict[str, Any],
                       referer: Optional[str] = None) -> Dict[str, Any]:
@@ -509,18 +637,8 @@ class InstaloaderContext:
         .. versionchanged:: 4.13.1
            Removed the `rhx_gis` parameter.
         """
-        with copy_session(self._session, self.request_timeout) as tmpsession:
+        variables_json = json.dumps(variables, separators=(',', ':'))
-            tmpsession.headers.update(self._default_http_header(empty_session_only=True))
+        with self._graphql_session(referer) as tmpsession:
-            del tmpsession.headers['Connection']
-            del tmpsession.headers['Content-Length']
-            tmpsession.headers['authority'] = 'www.instagram.com'
-            tmpsession.headers['scheme'] = 'https'
-            tmpsession.headers['accept'] = '*/*'
-            if referer is not None:
-                tmpsession.headers['referer'] = urllib.parse.quote(referer)
-
-            variables_json = json.dumps(variables, separators=(',', ':'))
-
             resp_json = self.get_json('graphql/query',
                                       params={'query_hash': query_hash,
                                               'variables': variables_json},
@@ -530,7 +648,7 @@ class InstaloaderContext:
         return resp_json
 
     def doc_id_graphql_query(self, doc_id: str, variables: Dict[str, Any],
-                             referer: Optional[str] = None) -> Dict[str, Any]:
+                             referer: Optional[str] = None, web_api: bool = False) -> Dict[str, Any]:
         """
         Do a doc_id-based GraphQL Query using method POST.
 
@@ -539,35 +657,23 @@ class InstaloaderContext:
         :param doc_id: doc_id for the query.
         :param variables: Variables for the Query.
         :param referer: HTTP Referer, or None.
+        :param web_api: Query the web app's ``api/graphql`` endpoint, as the web app does, rather than
+           ``graphql/query``. Requires login.
         :return: The server's response dictionary.
+
+        .. versionchanged:: 4.16
+           Added `web_api` parameter.
         """
-        csrf = next((c.value for c in self._session.cookies
+        variables_json = json.dumps(variables, separators=(',', ':'))
-                     if c.name == 'csrftoken' and c.value), None)
+        params = {'variables': variables_json,
-        if not csrf:
+                  'doc_id': doc_id,
-            self._session.get('https://www.instagram.com/', timeout=self.request_timeout)
+                  'server_timestamps': 'true',
-            csrf = next((c.value for c in self._session.cookies
+                  **(self._web_api_tokens() if web_api else {})}
-                         if c.name == 'csrftoken' and c.value), '')
+        with self._graphql_session(referer, csrf=self._csrf_token(), lsd=params.get('lsd')) as tmpsession:
-
+            resp_json = self.get_json('api/graphql' if web_api else 'graphql/query', params=params,
-        with copy_session(self._session, self.request_timeout) as tmpsession:
+                                      session=tmpsession, use_post=True)
-            tmpsession.headers.update(self._default_http_header(empty_session_only=True))
+        # api/graphql does not respond with a "status" field.
-            del tmpsession.headers['Connection']
+        if not web_api and 'status' not in resp_json:
-            del tmpsession.headers['Content-Length']
-            tmpsession.headers['authority'] = 'www.instagram.com'
-            tmpsession.headers['scheme'] = 'https'
-            tmpsession.headers['accept'] = '*/*'
-            tmpsession.headers['x-csrftoken'] = csrf
-            if referer is not None:
-                tmpsession.headers['referer'] = urllib.parse.quote(referer)
-
-            variables_json = json.dumps(variables, separators=(',', ':'))
-
-            resp_json = self.get_json('graphql/query',
-                                      params={'variables': variables_json,
-                                              'doc_id': doc_id,
-                                              'server_timestamps': 'true'},
-                                      session=tmpsession,
-                                      use_post=True)
-        if 'status' not in resp_json:
             self.error("GraphQL response did not contain a \"status\" field.")
         return resp_json
 
@@ -671,6 +777,44 @@ class InstaloaderContext:
 
             return response
 
+    def _get_page(self, session: requests.Session, path: str) -> str:
+        """Load a page of ``www.instagram.com`` and return its HTML."""
+        self.do_sleep()
+        self._rate_controller.wait_before_query('other')
+        url = 'https://www.instagram.com/{0}'.format(path)
+        # Instagram only embeds the data when the request looks like a browser's page navigation.
+        headers = {'Accept': 'text/html', 'Sec-Fetch-Dest': 'document', 'Sec-Fetch-Mode': 'navigate',
+                   'Sec-Fetch-Site': 'none'}
+        try:
+            resp = session.get(url, headers=headers, allow_redirects=False)
+        except requests.exceptions.RequestException as err:
+            raise ConnectionException("Page request to {}: {}".format(url, err)) from err
+        self._raise_if_login_redirect(resp)
+        if resp.status_code == 404:
+            raise QueryReturnedNotFoundException(self._response_error(resp))
+        if resp.status_code != 200:
+            raise ConnectionException(self._response_error(resp))
+        return resp.text
+
+    def get_page_data(self, path: str) -> List[Dict[str, Any]]:
+        """Load a page of ``www.instagram.com`` as a logged-out visitor and return the data it embeds.
+
+        Instagram renders public profile and post pages with the results of their GraphQL queries
+        embedded in the HTML, even when it refuses anonymous API requests for the same data.
+
+        :param path: URL, relative to ``www.instagram.com/``
+        :return: The ``data`` object of each query result that the page embeds, in page order.
+        :raises QueryReturnedNotFoundException: When the server responds with a 404.
+        :raises ConnectionException: When the request failed.
+        """
+        with self.get_anonymous_session() as anonymous_session:
+            html = self._get_page(anonymous_session, path)
+        data: List[Dict[str, Any]] = []
+        for script in re.finditer(r'<script type="application/json"[^>]*>(.*?)</script>', html, re.DOTALL):
+            with suppress(json.decoder.JSONDecodeError):
+                data.extend(_embedded_query_data(json.loads(script.group(1))))
+        return data
+
     def write_raw(self, resp: Union[bytes, requests.Response], filename: str) -> None:
         """Write raw response data into a file.
 
@@ -683,27 +827,26 @@ class InstaloaderContext:
                 file.write(resp)
         os.replace(filename + '.temp', filename)
 
-    def get_raw(self, url: str, _attempt=1) -> requests.Response:
+    def get_raw(self, url: str) -> requests.Response:
         """Downloads a file anonymously.
 
+        This does not retry on its own; callers that need retrying are decorated with
+        ``_retry_on_connection_error``.
+
         :raises QueryReturnedNotFoundException: When the server responds with a 404.
         :raises QueryReturnedForbiddenException: When the server responds with a 403.
         :raises ConnectionException: When download failed.
 
-        .. versionadded:: 4.2.1"""
+        .. versionadded:: 4.2.1
+
+        .. versionchanged:: 4.16
+           Removed the `_attempt` parameter.
+        """
         with self.get_anonymous_session() as anonymous_session:
             resp = anonymous_session.get(url, stream=True)
-        if resp.status_code == 200:
+        self._raise_for_download_status(resp)
-            resp.raw.decode_content = True
+        resp.raw.decode_content = True
-            return resp
+        return resp
-        else:
-            if resp.status_code == 403:
-                # suspected invalid URL signature
-                raise QueryReturnedForbiddenException(self._response_error(resp))
-            if resp.status_code == 404:
-                # 404 not worth retrying.
-                raise QueryReturnedNotFoundException(self._response_error(resp))
-            raise ConnectionException(self._response_error(resp))
 
     def get_and_write_raw(self, url: str, filename: str) -> None:
         """Downloads and writes anonymously-requested raw data into a file.
@@ -724,16 +867,8 @@ class InstaloaderContext:
         """
         with self.get_anonymous_session() as anonymous_session:
             resp = anonymous_session.head(url, allow_redirects=allow_redirects)
-        if resp.status_code == 200:
+        self._raise_for_download_status(resp)
-            return resp
+        return resp
-        else:
-            if resp.status_code == 403:
-                # suspected invalid URL signature
-                raise QueryReturnedForbiddenException(self._response_error(resp))
-            if resp.status_code == 404:
-                # 404 not worth retrying.
-                raise QueryReturnedNotFoundException(self._response_error(resp))
-            raise ConnectionException(self._response_error(resp))
 
 
 class RateController:

instaloader/nodeiterator.py

@@ -69,6 +69,9 @@ class NodeIterator(Iterator[T]):
 
     .. versionchanged: 4.13
        Included support for `doc_id`-based queries (using POST method).
+
+    .. versionchanged: 4.16
+       Added `web_api` parameter, see :meth:`InstaloaderContext.doc_id_graphql_query`.
     """
 
     _graphql_page_length = 12
@@ -83,10 +86,12 @@ class NodeIterator(Iterator[T]):
                  query_referer: Optional[str] = None,
                  first_data: Optional[Dict[str, Any]] = None,
                  is_first: Optional[Callable[[T, Optional[T]], bool]] = None,
-                 doc_id: Optional[str] = None):
+                 doc_id: Optional[str] = None,
+                 web_api: bool = False):
         self._context = context
         self._query_hash = query_hash
         self._doc_id = doc_id
+        self._web_api = web_api
         self._edge_extractor = edge_extractor
         self._node_wrapper = node_wrapper
         self._query_variables = query_variables if query_variables is not None else {}
@@ -117,7 +122,7 @@ class NodeIterator(Iterator[T]):
             pagination_variables['last'] = None
         data = self._edge_extractor(
             self._context.doc_id_graphql_query(
-                doc_id, {**self._query_variables, **pagination_variables}, self._query_referer
+                doc_id, {**self._query_variables, **pagination_variables}, self._query_referer, self._web_api
             )
         )
         self._best_before = datetime.now() + NodeIterator._shelf_life

instaloader/structures.py

@@ -999,22 +999,30 @@ class Profile:
         :param username: Username
         :raises: :class:`ProfileNotExistsException`
         """
-        # Resolve the profile through the web_profile_info endpoint, which works both
+        # Resolve the profile through its public web page, which Instagram renders with the
-        # anonymously and when logged in and returns the complete profile node
+        # profile embedded. The web_profile_info endpoint previously used here is refused
-        # (including the first page of posts). The GraphQL fbsearch query previously
+        # with HTTP 400 for some professional profiles, and with HTTP 401 or 429 for some
-        # used here started responding with HTTP 400.
+        # sessions, both anonymously and when logged in.
         try:
-            data = context.get_json(
+            page = context.get_page_data("{0}/".format(username.lower()))
-                "api/v1/users/web_profile_info/", params={"username": username.lower()}
-            ).get("data")
         except QueryReturnedNotFoundException:
-            data = None
+            page = []
-        if data and data.get("user"):
+        # The page embeds two queries for the profile: one for its details and one for its
-            profile = cls(context, data["user"])
+        # posts.
-            profile._has_full_metadata = True
+        user: Dict[str, Any] = {}
-            return profile
+        for data in page:
-
+            user.update(data.get("xig_user_by_username") or {})
-        raise ProfileNotExistsException("Profile {} does not exist.".format(username))
+        if not user.get("pk"):
+            raise ProfileNotExistsException("Profile {} does not exist.".format(username))
+        user.pop("polaris_ordered_timeline_connection", None)
+        # The page's "id" is not the user ID, which is "pk".
+        node = dict(user, id=user["pk"])
+        if context.is_logged_in:
+            # The page shows the profile as a logged-out visitor sees it. Leave the missing
+            # fields, notably the viewer's relationship to the profile, such as
+            # followed_by_viewer, to the GraphQL profile query in _obtain_metadata().
+            return cls(context, node)
+        return cls(context, cls._normalize_profile_data(node))
 
     @classmethod
     def from_id(cls, context: InstaloaderContext, profile_id: int):
@@ -1131,7 +1139,8 @@ class Profile:
                                                         ', '.join(similar_profiles[0:5]))) from err
             raise ProfileNotExistsException('Profile {} does not exist.'.format(self.username)) from err
 
-    def _normalize_profile_data(self, user_data: Dict[str, Any]) -> Dict[str, Any]:
+    @staticmethod
+    def _normalize_profile_data(user_data: Dict[str, Any]) -> Dict[str, Any]:
         """Normalize PolarisProfilePageContentQuery response to match legacy format."""
         normalized = user_data.copy()
         if 'id' not in normalized and 'pk' in normalized:
@@ -1375,35 +1384,65 @@ class Profile:
     def get_posts(self) -> NodeIterator[Post]:
         """Retrieve all posts from a profile.
 
-        :rtype: NodeIterator[Post]"""
+        :rtype: NodeIterator[Post]
+        :raises PrivateProfileNotFollowedException: When logged in and the profile is private and not followed."""
         self._obtain_metadata()
-        logged_in = self._context.is_logged_in
+        if not self._context.is_logged_in:
+            return NodeIterator(
+                context=self._context,
+                edge_extractor=lambda d: d["data"]["user"]["edge_owner_to_timeline_media"],
+                node_wrapper=lambda n: Post(self._context, n, self),
+                query_variables={
+                    "data": {
+                        "count": 12,
+                        "include_relationship_info": True,
+                        "latest_besties_reel_media": True,
+                        "latest_reel_media": True,
+                    },
+                    "id": self.userid,
+                },
+                query_referer="https://www.instagram.com/{0}/".format(self.username),
+                is_first=Profile._make_is_newest_checker(),
+                doc_id="7950326061742207",
+                query_hash=None,
+                first_data=self._metadata("edge_owner_to_timeline_media"),
+            )
+        # Instagram answers with an empty timeline rather than an error in that case. Unlike followed_by_viewer,
+        # which defaults to False, friendship_status tells whether the follow state is actually known.
+        if (self.is_private and self.username != (self._context.username or '').lower() and
+                (self._node.get('friendship_status') or {}).get('following') is False):
+            raise PrivateProfileNotFollowedException("Profile {} is private but not followed.".format(self.username))
         return NodeIterator(
             context=self._context,
-            edge_extractor=(
+            edge_extractor=lambda d: d["data"]["xdt_api__v1__feed__user_timeline_graphql_connection"],
-                (lambda d: d["data"]["xdt_api__v1__feed__user_timeline_graphql_connection"])
+            node_wrapper=lambda n: Post.from_iphone_struct(self._context, n),
-                if logged_in
+            # The query and variables that the web app sends for a profile's posts tab
-                else (lambda d: d["data"]["user"]["edge_owner_to_timeline_media"])
+            # (PolarisProfilePostsTabContentQuery_connection). Instagram answers the
-            ),
+            # previous queries, 7898261790222653 ("execution error") and 28975909992013618
-            node_wrapper=(
+            # (400 "feedback_required"), with errors.
-                (lambda n: Post.from_iphone_struct(self._context, n))
+            # It must be sent to the web app's api/graphql endpoint.
-                if logged_in
-                else (lambda n: Post(self._context, n, self))
-            ),
             query_variables={
                 "data": {
                     "count": 12,
+                    "include_reel_media_seen_timestamp": True,
                     "include_relationship_info": True,
                     "latest_besties_reel_media": True,
                     "latest_reel_media": True,
                 },
-                **({"username": self.username} if logged_in else {"id": self.userid}),
+                "first": 12,
+                "include_multi_captions": True,
+                "username": self.username,
+                "__relay_internal__pv__PolarisMultiCaptionCarouselEnabledrelayprovider": True,
+                "__relay_internal__pv__PolarisShortDramaEnabledrelayprovider": True,
+                "__relay_internal__pv__PolarisSEOIsCrawlerrelayprovider": False,
+                "__relay_internal__pv__PolarisThreadsStyleCommentsEnabledrelayprovider": False,
+                "__relay_internal__pv__PolarisReelsRecoDebugOverlayEnabledrelayprovider": False,
             },
             query_referer="https://www.instagram.com/{0}/".format(self.username),
             is_first=Profile._make_is_newest_checker(),
-            doc_id="7898261790222653" if logged_in else "7950326061742207",
+            doc_id="29104886249145907",
             query_hash=None,
-            first_data=(None if logged_in else self._metadata("edge_owner_to_timeline_media")),
+            web_api=True,
         )
 
     def get_saved_posts(self) -> NodeIterator[Post]:

setup.py

@@ -18,8 +18,8 @@ def get_version():
     raise SystemExit("Could not find version string.")
 
 
-if sys.version_info < (3, 9):
+if sys.version_info < (3, 10):
-    sys.exit('Instaloader requires Python >= 3.9.')
+    sys.exit('Instaloader requires Python >= 3.10.')
 
 requirements = ['requests>=2.25']
 optional_requirements = {
@@ -46,7 +46,7 @@ setup(
                 'from Instagram.',
     long_description=open(os.path.join(SRC, 'README.rst')).read(),
     install_requires=requirements,
-    python_requires='>=3.9',
+    python_requires='>=3.10',
     extras_require=optional_requirements,
     entry_points={'console_scripts': ['instaloader=instaloader.__main__:main']},
     zip_safe=False,
@@ -58,12 +58,12 @@ setup(
         'Intended Audience :: Developers',
         'License :: OSI Approved :: MIT License',
         'Operating System :: OS Independent',
-        'Programming Language :: Python :: 3.9',
         'Programming Language :: Python :: 3.10',
         'Programming Language :: Python :: 3.11',
         'Programming Language :: Python :: 3.12',
         'Programming Language :: Python :: 3.13',
         'Programming Language :: Python :: 3.14',
+        'Programming Language :: Python :: 3.15',
         'Programming Language :: Python :: 3 :: Only',
         'Topic :: Internet',
         'Topic :: Multimedia :: Graphics'

test/README.md

@@ -0,0 +1,4 @@
+# Instaloader Tests
+
+Integration tests for Instaloader features that require Instagram access are maintained here:
+https://github.com/instaloader/instaloader-tests

test/instaloader_unittests.py

@@ -1,237 +0,0 @@
-"""Unit Tests for Instaloader"""
-
-import os
-import shutil
-import tempfile
-import unittest
-from itertools import islice
-from typing import Optional
-
-import instaloader
-
-PROFILE_WITH_HIGHLIGHTS = 325732271
-PUBLIC_PROFILE = "selenagomez"
-PUBLIC_PROFILE_ID = 460563723
-PUBLIC_PROFILE_WITH_IGTV = "natgeo"
-HASHTAG = "kitten"
-LOCATION = "362629379"
-OWN_USERNAME = "aandergr"
-NORMAL_MAX_COUNT = 2
-PAGING_MAX_COUNT = 15
-PRIVATE_PROFILE = "aandergr"
-PRIVATE_PROFILE_ID = 1706625676
-EMPTY_PROFILE = "not_public"
-EMPTY_PROFILE_ID = 1928659031
-
-ratecontroller: Optional[instaloader.RateController] = None
-
-
-class TestInstaloaderAnonymously(unittest.TestCase):
-
-    def setUp(self):
-        self.dir = tempfile.mkdtemp()
-        print("Testing in {}".format(self.dir))
-        os.chdir(self.dir)
-        self.L = instaloader.Instaloader(download_geotags=True,
-                                         download_comments=True,
-                                         save_metadata=True)
-        self.L.context.raise_all_errors = True
-        if ratecontroller is not None:
-            # pylint:disable=protected-access
-            ratecontroller._context = self.L.context
-            self.L.context._rate_controller = ratecontroller
-
-    def tearDown(self):
-        # pylint:disable=global-statement,protected-access
-        global ratecontroller
-        ratecontroller = self.L.context._rate_controller
-        self.L.close()
-        os.chdir('/')
-        print("Removing {}".format(self.dir))
-        shutil.rmtree(self.dir)
-
-    def post_paging_test(self, iterator):
-        previous_post = None
-        for post in islice(iterator, PAGING_MAX_COUNT):
-            print(post)
-            if previous_post:
-                self.assertTrue(post.date_utc < previous_post.date_utc)
-            previous_post = post
-
-    @unittest.skip('')
-    def test_public_profile_download(self):
-        profiles = {self.L.check_profile_id(PUBLIC_PROFILE)}
-        self.L.download_profiles(profiles, profile_pic=False, fast_update=True, raise_errors=True)
-        self.L.download_profiles(profiles, profile_pic=False, fast_update=True, raise_errors=True)
-
-    def test_public_profile_paging(self):
-        self.post_paging_test(instaloader.Profile.from_username(self.L.context, PUBLIC_PROFILE).get_posts())
-
-    def test_profile_pic_download(self):
-        self.L.download_profiles({self.L.check_profile_id(PUBLIC_PROFILE)}, posts=False, raise_errors=True)
-
-    def test_hashtag_download(self):
-        self.L.download_hashtag(HASHTAG, NORMAL_MAX_COUNT)
-
-    def test_hashtag_paging(self):
-        for count, post in enumerate(instaloader.Hashtag.from_name(self.L.context, HASHTAG).get_all_posts()):
-            print(post)
-            if count == PAGING_MAX_COUNT:
-                break
-
-    def test_get_id_by_username(self):
-        self.assertEqual(PUBLIC_PROFILE_ID,
-                         instaloader.Profile.from_username(self.L.context, PUBLIC_PROFILE).userid)
-
-    def test_get_username_by_id_private(self):
-        self.assertEqual(PRIVATE_PROFILE.lower(),
-                         instaloader.Profile.from_id(self.L.context, PRIVATE_PROFILE_ID).username)
-
-    def test_get_username_by_id_public(self):
-        self.assertEqual(PUBLIC_PROFILE.lower(),
-                         instaloader.Profile.from_id(self.L.context, PUBLIC_PROFILE_ID).username)
-
-    def test_get_username_by_id_empty(self):
-        self.assertEqual(EMPTY_PROFILE.lower(),
-                         instaloader.Profile.from_id(self.L.context, EMPTY_PROFILE_ID).username)
-
-    def test_get_username_by_name_empty(self):
-        self.assertEqual(EMPTY_PROFILE_ID,
-                         instaloader.Profile.from_username(self.L.context, EMPTY_PROFILE).userid)
-
-    def test_post_from_mediaid(self):
-        for post in instaloader.Profile.from_username(self.L.context, PUBLIC_PROFILE).get_posts():
-            post2 = instaloader.Post.from_mediaid(self.L.context, post.mediaid)
-            self.assertEqual(post, post2)
-            break
-
-    def test_public_profile_tagged_paging(self):
-        for post in islice(instaloader.Profile.from_username(self.L.context, PUBLIC_PROFILE).get_tagged_posts(),
-                           PAGING_MAX_COUNT):
-            print(post)
-
-    def test_public_profile_igtv(self):
-        for post in islice(instaloader.Profile.from_username(self.L.context, PUBLIC_PROFILE_WITH_IGTV).get_igtv_posts(),
-                           PAGING_MAX_COUNT):
-            print(post)
-
-
-class TestInstaloaderLoggedIn(TestInstaloaderAnonymously):
-
-    def setUp(self):
-        super().setUp()
-        self.L.load_session_from_file(OWN_USERNAME)
-
-    @unittest.skip('')
-    def test_stories_download(self):
-        self.L.download_stories()
-
-    @unittest.skip('')
-    def test_private_profile_download(self):
-        self.L.download_profiles({self.L.check_profile_id(PRIVATE_PROFILE)}, stories=True, raise_errors=True)
-
-    def test_stories_paging(self):
-        for user_story in self.L.get_stories():
-            print("profile {}.".format(user_story.owner_username))
-            for item in user_story.get_items():
-                print(item)
-
-    def test_highlights_paging(self):
-        for user_highlight in self.L.get_highlights(PROFILE_WITH_HIGHLIGHTS):
-            print("Retrieving {} highlights \"{}\" from profile {}".format(user_highlight.itemcount,
-                                                                           user_highlight.title,
-                                                                           user_highlight.owner_username))
-            for item in user_highlight.get_items():
-                print(item)
-
-    def test_private_profile_paging(self):
-        self.post_paging_test(instaloader.Profile.from_username(self.L.context, PRIVATE_PROFILE).get_posts())
-
-    def test_feed_download(self):
-        self.L.download_feed_posts(NORMAL_MAX_COUNT)
-
-    def test_feed_paging(self):
-        for count, post in enumerate(self.L.get_feed_posts()):
-            print(post)
-            if count == PAGING_MAX_COUNT:
-                break
-
-    def test_saved_download(self):
-        self.L.download_saved_posts(NORMAL_MAX_COUNT)
-
-    def test_saved_paging(self):
-        for count, post in enumerate(instaloader.Profile.from_username(self.L.context, OWN_USERNAME).get_saved_posts()):
-            print(post)
-            if count == PAGING_MAX_COUNT:
-                break
-
-    def test_test_login(self):
-        self.assertEqual(OWN_USERNAME, self.L.test_login())
-
-    def test_followees_and_stories(self):
-        profile = instaloader.Profile.from_username(self.L.context, OWN_USERNAME)
-        followees = set(islice(profile.get_followees(), PAGING_MAX_COUNT))
-        self.L.download_profiles(followees, profile_pic=False, stories=True, posts=False, raise_errors=True)
-
-    def test_get_followees(self):
-        profile = instaloader.Profile.from_username(self.L.context, OWN_USERNAME)
-        for f in profile.get_followees():
-            print(f.username)
-
-    def test_get_followers(self):
-        profile = instaloader.Profile.from_username(self.L.context, OWN_USERNAME)
-        for f in profile.get_followers():
-            print(f.username)
-
-    def test_get_similar_accounts(self):
-        profile = instaloader.Profile.from_username(self.L.context, OWN_USERNAME)
-        for f in profile.get_similar_accounts():
-            print(f.username)
-
-    def test_get_likes(self):
-        for post in instaloader.Profile.from_username(self.L.context, OWN_USERNAME).get_posts():
-            for like in post.get_likes():
-                print(like.username)
-            break
-
-    def test_explore_paging(self):
-        for count, post in enumerate(self.L.get_explore_posts()):
-            print(post)
-            if count == PAGING_MAX_COUNT:
-                break
-
-    def test_location_download(self):
-        self.L.download_location(LOCATION, NORMAL_MAX_COUNT)
-
-    def test_location_paging(self):
-        for count, post in enumerate(self.L.get_location_posts(LOCATION)):
-            print(post)
-            if count == PAGING_MAX_COUNT:
-                break
-
-
-class TestCaptionMentions(unittest.TestCase):
-    """Caption parsing, which requires no network access."""
-
-    @staticmethod
-    def _post_with_caption(caption: str) -> instaloader.Post:
-        return instaloader.Post(None, {"shortcode": "BhrEy4nBFVU", "caption": caption})
-
-    def test_caption_mentions(self):
-        for caption, expected in [
-                ("@alice at the beginning", ["alice"]),
-                ("preceded by a space @bob", ["bob"]),
-                ("preceded by a newline\n@carol", ["carol"]),
-                ("multiple lines\n@dave\n@erin", ["dave", "erin"]),
-                ("no mentions here", []),
-        ]:
-            with self.subTest(caption=caption):
-                self.assertEqual(self._post_with_caption(caption).caption_mentions, expected)
-
-    def test_caption_mentions_ignores_email_addresses(self):
-        post = self._post_with_caption("write to alice@example.com\ncontact @bob instead")
-        self.assertEqual(post.caption_mentions, ["bob"])
-
-
-if __name__ == '__main__':
-    unittest.main()