Merge branch 'master' into upcoming/v4.16

- `InstaloaderContext.get_page_data()` loads a page as a logged-out visitor and returns the query results that the page embeds. Instagram only embeds them when the request looks like a page navigation, so the request sends the `Sec-Fetch-*` headers of one.
- `Profile.from_username()` reads the profile from its public page. Anonymously, `_normalize_profile_data()` completes the node.
- Logged in, `Profile.get_posts()` uses query `28975909992013618` (`PolarisProfilePostsTabContentQuery_connection`) with the variables that the web app sends. The response has the same shape as before.

When logged in, `from_username()` does not normalize the page's node. The page shows the profile to a logged-out visitor, so normalizing would set `followed_by_viewer` to `False`, and `download_profiles()` would refuse private profiles that the session follows. Instead, the GraphQL profile query in `_obtain_metadata()` fills in the missing fields when they are first read.

.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

@@ -8,22 +8,24 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: "Checkout Instaloader Repository"
-        uses: actions/checkout@v2
+        uses: actions/checkout@v7
         with:
           fetch-depth: 0  # needed for building docs
+          persist-credentials: false
       - name: "Setup Python"
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v7
         with:
-          python-version: 3.8
+          python-version: 3.15
+          cache: 'pipenv'
       - name: "Install Dependencies"
         run: |
-          python -m pip install pipenv==2023.2.4
+          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"
       - name: "Deploy Documentation"
         if: github.event_name == 'push' && github.ref == 'refs/heads/master'
-        uses: JamesIves/github-pages-deploy-action@v4.2.5
+        uses: JamesIves/github-pages-deploy-action@v4
         with:
           branch: master
           repository-name: instaloader/instaloader.github.io

.github/workflows/lint.yml

@@ -9,17 +9,20 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.10", "3.11", "3.12", "3.13", "3.14", "3.15"]
     steps:
       - name: Checkout Instaloader Repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v7
+        with:
+          persist-credentials: false
       - name: Setup Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v7
         with:
           python-version: ${{ matrix.python-version }}
+          cache: 'pipenv'
       - name: Install Dependencies
         run: |
-          python -m pip install pipenv==2023.2.4
+          python -m pip install pipenv==2026.8.0
           pipenv --python `python --version | grep -Eo '3\.[0-9]+'` sync --dev
       - name: PyLint
         run: pipenv --python `python --version | grep -Eo '3\.[0-9]+'` run pylint instaloader

.github/workflows/packages.yml

@@ -11,21 +11,25 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: "Checkout Repository"
-        uses: actions/checkout@v2
-      - name: "Setup Python"
-        uses: actions/setup-python@v2
+        uses: actions/checkout@v7
         with:
-          python-version: 3.8
+          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_REF: ${{ github.ref }}
-        run: echo ::set-output name=VERSION::${GITHUB_REF/refs\/tags\/v/}
+        run: echo "VERSION=${GITHUB_REF/refs\/tags\/v/}" >> $GITHUB_OUTPUT
         shell: bash
+      - name: "Install Dependencies"
+        run: python -m pip install -U setuptools wheel build
       - name: "Generate Python Package"
-        run: python setup.py sdist
+        run: python -m build
       - name: "Publish Distribution to PyPI"
-        uses: pypa/gh-action-pypi-publish@master
+        uses: pypa/gh-action-pypi-publish@release/v1
         with:
           password: ${{ secrets.PYPI_PASSWORD }}
       - name: "Publish Distribution to AUR"

.github/workflows/stale.yml

@@ -2,7 +2,7 @@ name: Mark stale issues and pull requests
 
 on:
   schedule:
-  - cron: "10 14 * * *"
+  - cron: "55 7 * * *"
 
 jobs:
   stale:
@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     
     steps:
-    - uses: actions/stale@v3
+    - uses: actions/stale@v11
       with:
         repo-token: ${{ secrets.GITHUB_TOKEN }}
         only-labels: 'question'
@@ -21,14 +21,14 @@ jobs:
         days-before-stale: 21
         days-before-close: -1
         remove-stale-when-updated: false
-    - uses: actions/stale@v1
+    - 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.'
         stale-pr-message: 'There has been no activity on this Pull Request for an extended period of time. This Pull Request will be closed after further 14 days of inactivity.'
         stale-issue-label: 'stale'
         stale-pr-label: 'stale'
-        exempt-issue-label: 'leave open'
-        exempt-pr-label: 'leave open'
+        exempt-issue-labels: 'leave open'
+        exempt-pr-labels: 'leave open'
         days-before-stale: 189
         days-before-close: 14

.github/workflows/windows_exe.yml

@@ -8,41 +8,34 @@ jobs:
     runs-on: windows-latest
     steps:
       - name: Checkout Instaloader repository
-        uses: actions/checkout@v2
-      - name: Setup Python
-        uses: actions/setup-python@v2
+        uses: actions/checkout@v7
         with:
-          python-version: "3.9"
+          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
         id: get_version
         env:
           GITHUB_REF: ${{ github.ref }}
-        run: echo ::set-output name=VERSION::${GITHUB_REF/refs\/tags\/v/}
+        run: echo "VERSION=${GITHUB_REF/refs\/tags\/v/}" >> $GITHUB_OUTPUT
         shell: bash
       - name: Run custom python script for EXE creation
         env:
           VERSION_TAG: v${{ steps.get_version.outputs.VERSION }}
         run: python deploy/windows/create_exe.py
-      - name: Create draft release
+      - 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: actions/create-release@v1
+        uses: softprops/action-gh-release@v3
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         with:
           tag_name: v${{ steps.get_version.outputs.VERSION }}
-          release_name: Version ${{ steps.get_version.outputs.VERSION }}
+          name: Version ${{ steps.get_version.outputs.VERSION }}
           draft: true
           prerelease: contains(steps.get_version.outputs.VERSION, 'a') || contains(steps.get_version.outputs.VERSION, 'b') || contains(steps.get_version.outputs.VERSION, 'c')
-      - name: Upload EXE as release asset
-        if: github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v')
-        id: upload-release-asset
-        uses: actions/upload-release-asset@v1
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          upload_url: ${{ steps.create_release.outputs.upload_url }}
-          asset_path: ./instaloader-v${{ steps.get_version.outputs.VERSION }}-windows-standalone.zip
-          asset_name: instaloader-v${{ steps.get_version.outputs.VERSION }}-windows-standalone.zip
-          asset_content_type: application/zip
+          files: ./instaloader-v${{ steps.get_version.outputs.VERSION }}-windows-standalone.zip

.pylintrc

@@ -351,7 +351,7 @@ single-line-if-stmt=no
 allow-any-import-level=
 
 # Allow explicit reexports by alias from a package __init__.
-allow-reexport-from-package=no
+allow-reexport-from-package=yes
 
 # Allow wildcard imports from modules that define __all__.
 allow-wildcard-with-all=no
@@ -433,6 +433,7 @@ disable=bad-inline-option,
         too-many-instance-attributes,
         too-many-lines,
         too-many-locals,
+        too-many-positional-arguments,
         too-many-public-methods,
         too-many-statements,
         unnecessary-lambda-assignment,

AUTHORS.md

@@ -6,4 +6,5 @@ Instaloader is written by
 - Alexander Graf (@aandergr)
 - André Koch-Kramer (@Thammus)
 - Lars Lindqvist (@e5150)
+- Eduardo M Kalinowksi (@ekalin)
 - ... and many more, see https://github.com/instaloader/instaloader/graphs/contributors

Pipfile

@@ -6,18 +6,17 @@ verify_ssl = true
 [dev-packages]
 pylint = "*"
 mypy = "*"
-sphinx = "~=2.3"
+sphinx = "*"
 pyinstaller = "*"
-pefile = "*"
-pywin32-ctypes = "*"
 psutil = "*"
-typing-extensions = "*"
 types-requests = "*"
-typed-ast = "*"
-jinja2 = "~=3.0.1"
-wrapt = "*"  # Needed for Python<3.11
-tomli = "*"  # Needed for Python<3.11
-dill = "*"  # Needed for Python<3.11
+sphinx-autodoc-typehints = "*"
+sphinxcontrib-jquery = "*"
+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
 
 [packages]
 requests = "*"
+browser-cookie3 = "*"

README.rst

@@ -53,7 +53,7 @@
 ::
 
     instaloader [--comments] [--geotags]
-                [--stories] [--highlights] [--tagged] [--igtv]
+                [--stories] [--highlights] [--tagged] [--reels] [--igtv]
                 [--login YOUR-USERNAME] [--fast-update]
                 profile | "#hashtag" | :stories | :feed | :saved
 
@@ -124,12 +124,30 @@ Supporters
 .. current-sponsors-start
 
 | Instaloader is proudly sponsored by
-|  `@rocketapi-io <https://github.com/rocketapi-io>`__
-|  `@socialmethod <https://github.com/socialmethod>`__
+
+.. list-table::
+  :align: center
+
+  * - |socialapis|
+  * - `SocialAPIs <https://socialapis.io/?utm_source=github&utm_medium=sponsor&utm_campaign=instaloader>`__
+
+|
+
+.. list-table::
+  :align: center
+
+  * - `@rocketapi-io <https://github.com/rocketapi-io>`__
+
+|
 
 See `Alex' GitHub Sponsors <https://github.com/sponsors/aandergr>`__ page for
 how you can sponsor the development of Instaloader!
 
+.. |socialapis| image:: ./.sponsor-logos/socialapis.png
+   :alt: SocialAPIs
+   :target: https://socialapis.io/?utm_source=github&utm_medium=sponsor&utm_campaign=instaloader
+   :height: 96px
+
 .. current-sponsors-end
 
 It is a pleasure for us to share our Instaloader to the world, and we are proud

deploy/arch/.SRCINFO.template

@@ -5,9 +5,13 @@ pkgbase = instaloader
 	url = https://instaloader.github.io/
 	arch = any
 	license = MIT
+	makedepends = python-build
+	makedepends = python-installer
 	makedepends = python-setuptools
-	depends = python>=3.8
-	depends = python-requests>=2.4
+	makedepends = python-wheel
+	depends = python
+	depends = python-requests
+	optdepends = python-browser-cookie3: Import session cookies from browser
 	options = !emptydirs
 	source = instaloader-{{version}}.tar.gz::https://codeload.github.com/instaloader/instaloader/tar.gz/v{{version}}
 	sha512sums = {{hash}}

deploy/arch/PKGBUILD.template

@@ -8,20 +8,30 @@ arch=('any')
 url="https://instaloader.github.io/"
 license=('MIT')
 groups=()
-depends=('python>=3.8' 'python-requests>=2.4')
-makedepends=('python-setuptools')
+depends=(
+  python
+  python-requests
+)
+makedepends=(
+  python-build
+  python-installer
+  python-setuptools
+  python-wheel
+)
+optdepends=(
+  'python-browser-cookie3: Import session cookies from browser'
+)
 options=('!emptydirs')
 source=($pkgname-$pkgver.tar.gz::https://codeload.github.com/instaloader/instaloader/tar.gz/v$pkgver)
 sha512sums=('{{hash}}')
 
 build() {
 	cd "$srcdir/$pkgname-$pkgver"
-	python setup.py clean --all
-	python setup.py build
+	python -m build --wheel --no-isolation
 }
 
 package() {
 	cd "$srcdir/$pkgname-$pkgver"
 	install -Dm644 LICENSE "$pkgdir"/usr/share/licenses/$pkgname/LICENSE
-	python setup.py install --root "$pkgdir/" --skip-build
+	python -m installer --destdir="$pkgdir" dist/*.whl
 }

deploy/windows/create_exe.py

@@ -44,7 +44,7 @@ with open('__main__.py', 'w+') as f:
     f.writelines(lines)
 
 # install dependencies and invoke PyInstaller
-commands = ["pip install pipenv==2023.2.4",
+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"]
 

docs/.sponsor-logos

@@ -0,0 +1 @@
+../.sponsor-logos

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
-make html
+pipenv sync --dev
+make -C docs html
 ```

docs/_templates/layout.html

@@ -21,7 +21,7 @@
 {% block header %}
   <nav class="navbar navbar-light navbar-expand bg-light border-bottom">
     <a class="navbar-brand" href="{{ pathto(master_doc) }}">
-      <img src="{{ pathto('_static/' + logo, 1) }}" width="30" height="30" class="d-inline-block align-top" alt="logo">
+      <img src="{{ pathto('_static/logo.png', 1) }}" width="30" height="30" class="d-inline-block align-top" alt="logo">
       <span class="ml-3">Instaloader</span>
     </a>
     <ul class="navbar-nav mr-auto">

docs/basic-usage.rst

@@ -75,7 +75,7 @@ What to Download
 Instaloader supports the following targets:
 
 - ``profile``
-   Public profile, or private profile with :option:`--login`.
+   Public profile, or private profile with :ref:`login<login>`.
 
    If an already-downloaded profile has been renamed, Instaloader automatically
    finds it by its unique ID and renames the folder accordingly.
@@ -92,37 +92,41 @@ Instaloader supports the following targets:
    - :option:`--tagged`
       to **download posts where the user is tagged**, and
 
+   - :option:`--reels`
+      to **download Reels videos**.
+
    - :option:`--igtv`
       to **download IGTV videos**.
 
 - ``"#hashtag"``
-   Posts with a certain **hashtag** (the quotes are usually necessary).
+   Posts with a certain **hashtag** (the quotes are usually necessary). Requires :ref:`login<login>`.
 
 - ``%location id``
    Posts tagged with a given location; the location ID is the numerical ID
    Instagram labels a location with (e.g.
    \https://www.instagram.com/explore/locations/**362629379**/plymouth-naval-memorial/).
-   Requires :option:`--login`.
+   Requires :ref:`login<login>`.
 
    .. versionadded:: 4.2
 
 - ``:stories``
    The currently-visible **stories** of your followees (requires
-   :option:`--login`).
+   :ref:`login<login>`).
 
 - ``:feed``
-   Your **feed** (requires :option:`--login`).
+   Your **feed** (requires :ref:`login<login>`).
 
 - ``:saved``
-   Posts which are marked as **saved** (requires :option:`--login`).
+   Posts which are marked as **saved** (requires :ref:`login<login>`).
 
 - ``@profile``
    All profiles that are followed by ``profile``, i.e. the *followees* of
-   ``profile`` (requires :option:`--login`).
+   ``profile`` (requires :ref:`login<login>`).
 
 - ``-post``
    Replace **post** with the post's shortcode to download single post. Must be preceded by ``--`` in
-   the argument list to not be mistaken as an option flag::
+   the argument list to not be mistaken as an option flag.  For example, to download the post
+   https://www.instagram.com/p/**B_K4CykAOtf**, run the command::
 
     instaloader -- -B_K4CykAOtf
 
@@ -140,7 +144,7 @@ downloads the pictures and videos and their captions. You can specify
 
 - :option:`--geotags`
    **download geotags** of each post and save them as
-   Google Maps link (requires :option:`--login`),
+   Google Maps link (requires :ref:`login<login>`),
 
 For a reference of all supported command line options, see
 :ref:`command-line-options`.
@@ -231,7 +235,7 @@ The filter string must be a
 where the attributes from :class:`Post` or
 :class:`StoryItem` respectively are defined.
 
-Id est, the following attributes can be used with both
+The following attributes can be used with both
 :option:`--post-filter` and :option:`--storyitem-filter`:
 
 - :attr:`~Post.owner_username` (str), :attr:`~Post.owner_id` (int)
@@ -255,7 +259,7 @@ Id est, the following attributes can be used with both
 As :option:`--post-filter`, the following attributes can be used additionally:
 
 - :attr:`~Post.viewer_has_liked` (bool)
-   Whether user (with :option:`--login`) has liked given post. To download the
+   Whether user (with :ref:`login<login>`) has liked given post. To download the
    pictures from your feed that you have liked::
 
       instaloader --login=your_username --post-filter=viewer_has_liked :feed
@@ -307,13 +311,47 @@ the post's caption::
 
    instaloader --post-metadata-txt="{likes} likes." <target>
 
-Note that with this feature, it is possible to easily and fastly extract
+Note that with this feature, it is possible to easily and quickly extract
 additional metadata of already-downloaded posts, by reimporting their JSON
 files. Say, you now also want to export the number of comments the Posts had
 when they were downloaded::
 
    instaloader --post-metadata-txt="{likes} likes, {comments} comments." <target>/*.json.xz
 
+.. _exit_codes:
+
+Exit codes
+^^^^^^^^^^
+
+Different exit codes are used to indicate different kinds of error:
+
+0
+  No error, all downloads were successful.
+
+1
+  A non-fatal error happened. One or more posts, or even one or more
+  profiles could not be downloaded, but execution was not stopped. The
+  errors are repeated at the end of the log for easy access.
+
+2
+  Command-line error. An unrecognized option was passed, or an invalid
+  combination of options, for example. No interaction with Instagram
+  was made.
+
+3
+  Login error. It was not possible to login. Downloads were not
+  attempted.
+
+4
+  Fatal download error. Downloads were interrupted and no further
+  attempts were made. Happens when a response with one of the status
+  codes in the :option:`--abort-on` option were passed, or when
+  Instagram logs the user out during downloads.
+
+5
+  Interrupted by the user. Happens when the user presses Control-C or
+  sends SIGINT to the process.
+
 .. _instaloader-as-cronjob:
 
 Instaloader as Cronjob

docs/cli-options.rst

@@ -26,7 +26,7 @@ Targets
 ^^^^^^^
 
 Specify a list of targets. For each of these, Instaloader creates a folder and
-stores all posts along with the pictures's captions there.
+stores all posts along with the pictures' captions there.
 
 .. include:: basic-usage.rst
    :start-after: targets-start
@@ -61,13 +61,13 @@ What to Download of each Post
 
    Download geotags when available. Geotags are stored as a text file with
    the location's name and a Google Maps link. This requires an additional
-   request to the Instagram server for each picture. Requires :option:`--login`.
+   request to the Instagram server for each picture. Requires :ref:`login<login>`.
 
 .. option:: --comments, -C
 
    Download and update comments for each post. This requires an additional
    request to the Instagram server for each post, which is why it is disabled by
-   default.
+   default. Requires :ref:`login<login>`.
 
 .. option:: --no-captions
 
@@ -116,12 +116,12 @@ What to Download of each Profile
 .. option:: --stories, -s
 
    Also download stories of each profile that is downloaded. Requires
-   :option:`--login`.
+   :ref:`login<login>`.
 
 .. option:: --highlights
 
    Also download highlights of each profile that is downloaded. Requires
-   :option:`--login`.
+   :ref:`login<login>`.
 
    .. versionadded:: 4.1
 
@@ -131,6 +131,12 @@ What to Download of each Profile
 
    .. versionadded:: 4.1
 
+.. option:: --reels
+
+   Also download Reels videos.
+
+   .. versionadded:: 4.14
+
 .. option:: --igtv
 
    Also download IGTV videos.
@@ -183,6 +189,7 @@ Which Posts to Download
    Do not attempt to download more than COUNT posts.  Applies to
    ``#hashtag``, ``%location_id``, ``:feed``, and ``:saved``.
 
+.. _login:
 
 Login (Download Private Profiles)
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@@ -192,10 +199,34 @@ profiles. To login, pass the :option:`--login` option. Your session cookie (not
 password!) will be saved to a local file to be reused next time you want
 Instaloader to login.
 
+Instead of :option:`--login`, it is possible to use
+:option:`--load-cookies` to import a session from a browser.
+
 .. option:: --login YOUR-USERNAME, -l YOUR-USERNAME
 
    Login name (profile name) for your Instagram account.
 
+.. option:: --load-cookies BROWSER-NAME, -b BROWSER-NAME
+
+   Load Instagram session cookies from a browser instead of using Instaloader's own login mechanism.
+   This method requires the `browser_cookie3 <https://github.com/borisbabic/browser_cookie3>`__ library.
+   By default, cookies are loaded from the browser's main profile, but you can specify a custom cookie file using :option:`--cookiefile`.
+
+   Since :option:`--load-cookies` and :option:`--login` are alternative ways to acquire a session, they cannot be used together when initially acquiring a session.
+
+   Supported browsers: Arc, Brave, Chrome, Chromium, Edge, Firefox, LibreWolf, Opera, Opera_GX, Safari, and Vivaldi.
+
+   Once logged in via browser cookies, Instaloader saves the session, allowing you to use :option:`--login` in subsequent runs.
+
+   .. versionadded:: 4.11
+
+.. option:: --cookiefile COOKIE-FILE, -B COOKIE-FILE
+
+   Specifies a cookie file path for :option:`--load-cookies` to load cookies from a particular browser profile.
+   This option must be used together with :option:`--load-cookies` and does not work on its own.
+
+   .. versionadded:: 4.11
+
 .. option:: --sessionfile SESSIONFILE, -f SESSIONFILE
 
    Path for loading and storing session key file.  Defaults to
@@ -281,7 +312,7 @@ How to Download
 .. option:: --user-agent USER_AGENT
 
    User Agent to use for HTTP requests. Per default, Instaloader pretends being
-   Chrome/92 on Linux.
+   Chrome/142 on Linux.
 
 .. option:: --max-connection-attempts N
 

docs/codesnippets/113_only_one_per_user.py

@@ -2,7 +2,7 @@ import instaloader
 
 L = instaloader.Instaloader()
 
-posts = instaloader.Hashtag.from_name(L.context, 'urbanphotography').get_posts()
+posts = instaloader.Hashtag.from_name(L.context, 'urbanphotography').get_posts_resumable()
 
 users = set()
 

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")
-    cookiefiles = glob(expanduser(default_cookiefile))
+    }.get(system(), None)
+    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/codesnippets/666_historical_hashtag_data.py

@@ -3,7 +3,7 @@ import instaloader
 
 L = instaloader.Instaloader()
 
-posts = instaloader.Hashtag.from_name(L.context, "urbanphotography").get_posts()
+posts = instaloader.Hashtag.from_name(L.context, "urbanphotography").get_posts_resumable()
 
 SINCE = datetime(2020, 5, 10)  # further from today, inclusive
 UNTIL = datetime(2020, 5, 11)  # closer to today, not inclusive

docs/conf.py

@@ -1,56 +1,84 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
+# Configuration file for the Sphinx documentation builder.
 #
-# Instaloader documentation build configuration file, created by
-# sphinx-quickstart on Fri Aug 25 15:38:26 2017.
-#
-# This file is execfile()d with the current directory set to its
-# containing dir.
-#
-# Note that not all possible configuration values are present in this
-# autogenerated file.
-#
-# All configuration values have a default; values that are commented out
-# serve to show the default.
+# For the full list of built-in configuration values, see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
 
-# If extensions (or modules to document with autodoc) are in another directory,
-# add these directories to sys.path here. If the directory is relative to the
-# documentation root, use os.path.abspath to make it absolute, like shown here.
-#
 import os
 import platform
 import subprocess
 import sys
-import typing
 
 sys.path.insert(0, os.path.abspath('..'))
 
-import docs.sphinx_autodoc_typehints as sphinx_autodoc_typehints
 
-# -- General configuration ------------------------------------------------
+# -- Project information -----------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
 
-# If your documentation needs a minimal Sphinx version, state it here.
-#
-# needs_sphinx = '1.0'
+project = 'Instaloader'
+copyright = '2023, Alexander Graf and Andre Koch-Kramer'
+author = 'Alexander Graf and Andre Koch-Kramer'
+
+# -- General configuration ---------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
 
-# Add any Sphinx extension module names here, as strings. They can be
-# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
-# ones.
 extensions = [
-    'sphinx.ext.autodoc',
-    'sphinx.ext.githubpages',
-    'sphinx.ext.intersphinx',
-    'sphinx.ext.extlinks'
+    "sphinx.ext.autodoc",
+    "sphinx.ext.extlinks",
+    "sphinx.ext.githubpages",
+    "sphinx.ext.intersphinx",
+    "sphinxcontrib.jquery",
 ]
 
-autodoc_default_flags = ['show-inheritance', 'members', 'undoc-members']
+# autodoc options
 
-autodoc_member_order = 'bysource'
+autodoc_default_options = {
+    'show-inheritance': True,
+    'members': True,
+    'undoc-members': True,
+}
 
-intersphinx_mapping = {'python': ('https://docs.python.org/3', None),
-                       'requests': ('https://requests.readthedocs.io/en/latest/', None)}
+# extlinks options
 
-nitpick_ignore = [('py:class', 'typing.Tuple')]
+extlinks = {
+    'issue': (
+        'https://github.com/instaloader/instaloader/issues/%s',
+        'Issue #%s'
+    ),
+    'example': (
+        'https://raw.githubusercontent.com/instaloader/instaloader/master/docs/codesnippets/%s',
+        'Example %s'
+    ),
+}
+
+# intersphinx options
+
+intersphinx_mapping = {
+    'python': ('https://docs.python.org/3', None),
+    'requests': ('https://requests.readthedocs.io/en/latest/', None),
+}
+
+# other options
+
+templates_path = ['_templates']
+exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+
+# ignore TypeVar as it is currently unsupported by Sphinx
+nitpick_ignore = [('py:class', 'instaloader.nodeiterator.T')]
+
+# -- Options for HTML output -------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
+
+pygments_style = 'fruity'
+
+html_theme = 'basic'
+html_static_path = ['_static']
+
+html_logo = "logo.png"
+
+html_css_files = ['instaloaderdoc.css']
+html_js_files = ['instaloaderdoc.js']
+
+# get release number
 
 current_release = subprocess.check_output(["git", "describe", "--abbrev=0"]).decode("ascii")[1:-1]
 date_format = "%e %b %Y" if platform.system() != "Windows" else "%d %b %Y"
@@ -58,322 +86,3 @@ current_release_date = subprocess.check_output(
     ["git", "log", "-1", "--tags", "--format=%ad", "--date=format:"+date_format]).decode("ascii")[:-1]
 
 html_context = {'current_release': current_release, 'current_release_date': current_release_date}
-
-extlinks = {
-    'issue': (
-        'https://github.com/instaloader/instaloader/issues/%s',
-        'Issue #'
-    ),
-    'example': (
-        'https://raw.githubusercontent.com/instaloader/instaloader/master/docs/codesnippets/%s',
-        'Example '
-    ),
-}
-
-# Add any paths that contain templates here, relative to this directory.
-templates_path = ['_templates']
-
-# The suffix(es) of source filenames.
-# You can specify multiple suffix as a list of string:
-#
-# source_suffix = ['.rst', '.md']
-source_suffix = '.rst'
-
-# The encoding of source files.
-#
-# source_encoding = 'utf-8-sig'
-
-# The master toctree document.
-master_doc = 'index'
-
-# General information about the project.
-project = 'Instaloader'
-copyright = '2017-2020, Alexander Graf and Andre Koch-Kramer'
-author = 'Alexander Graf and Andre Koch-Kramer'
-
-# The version info for the project you're documenting, acts as replacement for
-# |version| and |release|, also used in various other places throughout the
-# built documents.
-#
-# The short X.Y version.
-#version = '3.0'
-# The full version, including alpha/beta/rc tags.
-#release = '3.0rc0'
-
-# The language for content autogenerated by Sphinx. Refer to documentation
-# for a list of supported languages.
-#
-# This is also used if you do content translation via gettext catalogs.
-# Usually you set "language" from the command line for these cases.
-language = "en"
-
-# There are two options for replacing |today|: either, you set today to some
-# non-false value, then it is used:
-#
-# today = ''
-#
-# Else, today_fmt is used as the format for a strftime call.
-#
-# today_fmt = '%B %d, %Y'
-
-# List of patterns, relative to source directory, that match files and
-# directories to ignore when looking for source files.
-# This patterns also effect to html_static_path and html_extra_path
-exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
-
-# The reST default role (used for this markup: `text`) to use for all
-# documents.
-#
-# default_role = None
-
-# If true, '()' will be appended to :func: etc. cross-reference text.
-#
-# add_function_parentheses = True
-
-# If true, the current module name will be prepended to all description
-# unit titles (such as .. function::).
-#
-add_module_names = False
-
-# If true, sectionauthor and moduleauthor directives will be shown in the
-# output. They are ignored by default.
-#
-# show_authors = False
-
-# The name of the Pygments (syntax highlighting) style to use.
-pygments_style = 'fruity'
-
-# A list of ignored prefixes for module index sorting.
-# modindex_common_prefix = []
-
-# If true, keep warnings as "system message" paragraphs in the built documents.
-# keep_warnings = False
-
-# If true, `todo` and `todoList` produce output, else they produce nothing.
-todo_include_todos = False
-
-
-# -- Options for HTML output ----------------------------------------------
-
-# The theme to use for HTML and HTML Help pages.  See the documentation for
-# a list of builtin themes.
-#
-html_theme = 'basic'
-
-# Add any paths that contain custom themes here, relative to this directory.
-# html_theme_path = []
-
-# The name for this set of Sphinx documents.
-# "<project> v<release> documentation" by default.
-#
-# html_title = 'Instaloader v3.0rc0'
-
-# A shorter title for the navigation bar.  Default is the same as html_title.
-#
-# html_short_title = None
-
-# The name of an image file (relative to this directory) to place at the top
-# of the sidebar.
-#
-html_logo = "logo.png"
-
-# The name of an image file (relative to this directory) to use as a favicon of
-# the docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
-# pixels large.
-#
-html_favicon = "favicon.ico"
-
-# Add any paths that contain custom static files (such as style sheets) here,
-# relative to this directory. They are copied after the builtin static files,
-# so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
-
-# Add any extra paths that contain custom files (such as robots.txt or
-# .htaccess) here, relative to this directory. These files are copied
-# directly to the root of the documentation.
-#
-# html_extra_path = []
-
-# If not None, a 'Last updated on:' timestamp is inserted at every page
-# bottom, using the given strftime format.
-# The empty string is equivalent to '%b %d, %Y'.
-#
-# html_last_updated_fmt = None
-
-# If true, SmartyPants will be used to convert quotes and dashes to
-# typographically correct entities.
-#
-# html_use_smartypants = True
-
-# Custom sidebar templates, maps document names to template names.
-#
-#html_sidebars = {'**': ["relations.html", "links.html"] }
-html_sidebars = {}
-
-# Additional templates that should be rendered to pages, maps page names to
-# template names.
-#
-# html_additional_pages = {}
-
-# If false, no module index is generated.
-#
-html_domain_indices = False
-
-# If false, no index is generated.
-#
-html_use_index = True
-
-# If true, the index is split into individual pages for each letter.
-#
-# html_split_index = False
-
-# If true, links to the reST sources are added to the pages.
-#
-html_show_sourcelink = False
-
-# If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
-#
-html_show_sphinx = False
-
-# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
-#
-html_show_copyright = False
-
-# If true, an OpenSearch description file will be output, and all pages will
-# contain a <link> tag referring to it.  The value of this option must be the
-# base URL from which the finished HTML is served.
-#
-# html_use_opensearch = ''
-
-# This is the file name suffix for HTML files (e.g. ".xhtml").
-# html_file_suffix = None
-
-# Language to be used for generating the HTML full-text search index.
-# Sphinx supports the following languages:
-#   'da', 'de', 'en', 'es', 'fi', 'fr', 'h', 'it', 'ja'
-#   'nl', 'no', 'pt', 'ro', 'r', 'sv', 'tr', 'zh'
-#
-# html_search_language = 'en'
-
-# A dictionary with options for the search language support, empty by default.
-# 'ja' uses this config value.
-# 'zh' user can custom change `jieba` dictionary path.
-#
-# html_search_options = {'type': 'default'}
-
-# The name of a javascript file (relative to the configuration directory) that
-# implements a search results scorer. If empty, the default will be used.
-#
-# html_search_scorer = 'scorer.js'
-
-# Output file base name for HTML help builder.
-htmlhelp_basename = 'Instaloaderdoc'
-
-# -- Options for LaTeX output ---------------------------------------------
-
-latex_elements = {
-     # The paper size ('letterpaper' or 'a4paper').
-     #
-     # 'papersize': 'letterpaper',
-
-     # The font size ('10pt', '11pt' or '12pt').
-     #
-     # 'pointsize': '10pt',
-
-     # Additional stuff for the LaTeX preamble.
-     #
-     # 'preamble': '',
-
-     # Latex figure (float) alignment
-     #
-     # 'figure_align': 'htbp',
-}
-
-# Grouping the document tree into LaTeX files. List of tuples
-# (source start file, target name, title,
-#  author, documentclass [howto, manual, or own class]).
-latex_documents = [
-    (master_doc, 'Instaloader.tex', 'Instaloader Documentation',
-     'Alexander Graf, André Koch-Kramer', 'manual'),
-]
-
-# The name of an image file (relative to this directory) to place at the top of
-# the title page.
-#
-# latex_logo = None
-
-# For "manual" documents, if this is true, then toplevel headings are parts,
-# not chapters.
-#
-# latex_use_parts = False
-
-# If true, show page references after internal links.
-#
-# latex_show_pagerefs = False
-
-# If true, show URL addresses after external links.
-#
-# latex_show_urls = False
-
-# Documents to append as an appendix to all manuals.
-#
-# latex_appendices = []
-
-# It false, will not define \strong, \code, 	itleref, \crossref ... but only
-# \sphinxstrong, ..., \sphinxtitleref, ... To help avoid clash with user added
-# packages.
-#
-# latex_keep_old_macro_names = True
-
-# If false, no module index is generated.
-#
-# latex_domain_indices = True
-
-
-# -- Options for manual page output ---------------------------------------
-
-# One entry per manual page. List of tuples
-# (source start file, name, description, authors, manual section).
-man_pages = [
-    (master_doc, 'instaloader', 'Instaloader Documentation',
-     [author], 1)
-]
-
-# If true, show URL addresses after external links.
-#
-# man_show_urls = False
-
-
-# -- Options for Texinfo output -------------------------------------------
-
-# Grouping the document tree into Texinfo files. List of tuples
-# (source start file, target name, title, author,
-#  dir menu entry, description, category)
-texinfo_documents = [
-    (master_doc, 'Instaloader', 'Instaloader Documentation',
-     author, 'Instaloader', 'One line description of project.',
-     'Miscellaneous'),
-]
-
-# Documents to append as an appendix to all manuals.
-#
-# texinfo_appendices = []
-
-# If false, no module index is generated.
-#
-# texinfo_domain_indices = True
-
-# How to display URL addresses: 'footnote', 'no', or 'inline'.
-#
-# texinfo_show_urls = 'footnote'
-
-# If true, do not generate a @detailmenu in the "Top" node's menu.
-#
-# texinfo_no_detailmenu = False
-
-
-def setup(app):
-    typing.TYPE_CHECKING = True
-    app.add_stylesheet("instaloaderdoc.css")
-    app.connect('autodoc-process-signature', sphinx_autodoc_typehints.process_signature)
-    app.connect('autodoc-process-docstring', sphinx_autodoc_typehints.process_docstring)

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/index.rst

@@ -48,7 +48,7 @@ See :ref:`install` for more options on how to install Instaloader.
 ::
 
     instaloader [--comments] [--geotags]
-                [--stories] [--highlights] [--tagged] [--igtv]
+                [--stories] [--highlights] [--tagged] [--reels] [--igtv]
                 [--login YOUR-USERNAME] [--fast-update]
                 profile | "#hashtag" | %location_id |
                 :stories | :feed | :saved

docs/module/exceptions.rst

@@ -2,7 +2,7 @@ Exceptions
 ^^^^^^^^^^
 
 .. module:: instaloader
-   :noindex:
+   :no-index:
 
 .. highlight:: python
 
@@ -27,16 +27,26 @@ Exceptions
 
 .. autoexception:: LoginRequiredException
 
+.. autoexception:: LoginException
+
+   .. versionadded:: 4.12
+
 .. autoexception:: TwoFactorAuthRequiredException
 
    .. versionadded:: 4.2
 
+   .. versionchanged:: 4.12
+      Inherits LoginException
+
 .. autoexception:: InvalidArgumentException
 
 .. autoexception:: BadResponseException
 
 .. autoexception:: BadCredentialsException
 
+   .. versionchanged:: 4.12
+      Inherits LoginException
+
 .. autoexception:: PostChangedException
 
 .. autoexception:: QueryReturnedNotFoundException

docs/module/instaloader.rst

@@ -2,7 +2,7 @@
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 .. module:: instaloader
-   :noindex:
+   :no-index:
 
 .. highlight:: python
 

docs/module/instaloadercontext.rst

@@ -2,7 +2,7 @@
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 .. module:: instaloader
-   :noindex:
+   :no-index:
 
 .. highlight:: python
 

docs/module/nodeiterator.rst

@@ -2,7 +2,7 @@ Resumable Iterations
 ^^^^^^^^^^^^^^^^^^^^
 
 .. module:: instaloader
-   :noindex:
+   :no-index:
 
 .. highlight:: python
 

docs/module/structures.rst

@@ -2,7 +2,7 @@ Instagram Structures
 ^^^^^^^^^^^^^^^^^^^^
 
 .. module:: instaloader
-   :noindex:
+   :no-index:
 
 .. highlight:: python
 
@@ -71,6 +71,14 @@ TopSearchResults
 
    .. versionadded:: 4.3
 
+TitlePic
+""""""""
+
+.. autoclass:: TitlePic
+   :no-show-inheritance:
+
+   .. versionadded:: 4.8
+
 Loading and Saving
 """"""""""""""""""
 

docs/requirements.txt

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

docs/sphinx_autodoc_typehints.py

@@ -1,251 +0,0 @@
-# sphinx_autodoc_typehints from Nov 20 2018 (version 1.5.2).
-#  https://github.com/agronholm/sphinx-autodoc-typehints
-# (slightly modified to fix class links, maybe related to agronholm/sphinx-autodoc-typehints#38)
-#
-# This is the MIT license: http://www.opensource.org/licenses/mit-license.php
-#
-# Copyright (c) Alex Grönholm
-#
-# Permission is hereby granted, free of charge, to any person obtaining a copy of this
-# software and associated documentation files (the "Software"), to deal in the Software
-# without restriction, including without limitation the rights to use, copy, modify, merge,
-# publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons
-# to whom the Software is furnished to do so, subject to the following conditions:
-#
-# The above copyright notice and this permission notice shall be included in all copies or
-# substantial portions of the Software.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
-# INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR
-# PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE
-# FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
-# OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
-# DEALINGS IN THE SOFTWARE.
-#
-
-
-import inspect
-from typing import get_type_hints, TypeVar, Any, AnyStr, Generic, Union
-
-from sphinx.util import logging
-from sphinx.util.inspect import Signature
-
-try:
-    from inspect import unwrap
-except ImportError:
-    def unwrap(func, *, stop=None):
-        """This is the inspect.unwrap() method copied from Python 3.5's standard library."""
-        if stop is None:
-            def _is_wrapper(f):
-                return hasattr(f, '__wrapped__')
-        else:
-            def _is_wrapper(f):
-                return hasattr(f, '__wrapped__') and not stop(f)
-        f = func  # remember the original func for error reporting
-        memo = {id(f)}  # Memoise by id to tolerate non-hashable objects
-        while _is_wrapper(func):
-            func = func.__wrapped__
-            id_func = id(func)
-            if id_func in memo:
-                raise ValueError('wrapper loop when unwrapping {!r}'.format(f))
-            memo.add(id_func)
-        return func
-
-logger = logging.getLogger(__name__)
-
-
-def format_annotation(annotation):
-    if inspect.isclass(annotation) and annotation.__module__ == 'builtins':
-        if annotation.__qualname__ == 'NoneType':
-            return '``None``'
-        else:
-            return ':py:class:`{}`'.format(annotation.__qualname__)
-
-    annotation_cls = annotation if inspect.isclass(annotation) else type(annotation)
-    class_name = None
-    if annotation_cls.__module__ == 'typing':
-        params = None
-        prefix = ':py:class:'
-        module = 'typing'
-        extra = ''
-
-        if inspect.isclass(getattr(annotation, '__origin__', None)):
-            annotation_cls = annotation.__origin__
-            try:
-                if Generic in annotation_cls.mro():
-                    module = annotation_cls.__module__
-            except TypeError:
-                pass  # annotation_cls was either the "type" object or typing.Type
-
-        if annotation is Any:
-            return ':py:data:`~typing.Any`'
-        elif annotation is AnyStr:
-            return ':py:data:`~typing.AnyStr`'
-        elif isinstance(annotation, TypeVar):
-            return '\\%r' % annotation
-        elif (annotation is Union or getattr(annotation, '__origin__', None) is Union or
-              hasattr(annotation, '__union_params__')):
-            prefix = ':py:data:'
-            class_name = 'Union'
-            if hasattr(annotation, '__union_params__'):
-                params = annotation.__union_params__
-            elif hasattr(annotation, '__args__'):
-                params = annotation.__args__
-
-            if params and len(params) == 2 and (hasattr(params[1], '__qualname__') and
-                                                params[1].__qualname__ == 'NoneType'):
-                class_name = 'Optional'
-                params = (params[0],)
-        elif annotation_cls.__qualname__ == 'Tuple' and hasattr(annotation, '__tuple_params__'):
-            params = annotation.__tuple_params__
-            if annotation.__tuple_use_ellipsis__:
-                params += (Ellipsis,)
-        elif annotation_cls.__qualname__ == 'Callable':
-            prefix = ':py:data:'
-            arg_annotations = result_annotation = None
-            if hasattr(annotation, '__result__'):
-                arg_annotations = annotation.__args__
-                result_annotation = annotation.__result__
-            elif getattr(annotation, '__args__', None):
-                arg_annotations = annotation.__args__[:-1]
-                result_annotation = annotation.__args__[-1]
-
-            if arg_annotations in (Ellipsis, (Ellipsis,)):
-                params = [Ellipsis, result_annotation]
-            elif arg_annotations is not None:
-                params = [
-                    '\\[{}]'.format(
-                        ', '.join(format_annotation(param) for param in arg_annotations)),
-                    result_annotation
-                ]
-        elif hasattr(annotation, 'type_var'):
-            # Type alias
-            class_name = annotation.name
-            params = (annotation.type_var,)
-        elif getattr(annotation, '__args__', None) is not None:
-            params = annotation.__args__
-        elif hasattr(annotation, '__parameters__'):
-            params = annotation.__parameters__
-
-        if params:
-            extra = '\\[{}]'.format(', '.join(format_annotation(param) for param in params))
-
-        if not class_name:
-            class_name = annotation_cls.__qualname__.title()
-
-        return '{}`~{}.{}`{}'.format(prefix, module, class_name, extra)
-    elif annotation is Ellipsis:
-        return '...'
-    elif inspect.isclass(annotation) or inspect.isclass(getattr(annotation, '__origin__', None)):
-        if not inspect.isclass(annotation):
-            annotation_cls = annotation.__origin__
-
-        extra = ''
-        if Generic in annotation_cls.mro():
-            params = (getattr(annotation, '__parameters__', None) or
-                      getattr(annotation, '__args__', None))
-            extra = '\\[{}]'.format(', '.join(format_annotation(param) for param in params))
-
-        module = annotation.__module__.split('.')[0]    # hack to 'fix' class linking for Instaloader project
-        return ':py:class:`~{}.{}`{}'.format(module, annotation_cls.__qualname__,
-                                             extra)
-
-    return str(annotation)
-
-
-def process_signature(app, what: str, name: str, obj, options, signature, return_annotation):
-    if not callable(obj):
-        return
-
-    if what in ('class', 'exception'):
-        obj = getattr(obj, '__init__', getattr(obj, '__new__', None))
-
-    if not getattr(obj, '__annotations__', None):
-        return
-
-    obj = unwrap(obj)
-    signature = Signature(obj)
-    parameters = [
-        param.replace(annotation=inspect.Parameter.empty)
-        for param in signature.signature.parameters.values()
-    ]
-
-    if parameters:
-        if what in ('class', 'exception'):
-            del parameters[0]
-        elif what == 'method':
-            outer = inspect.getmodule(obj)
-            for clsname in obj.__qualname__.split('.')[:-1]:
-                outer = getattr(outer, clsname)
-
-            method_name = obj.__name__
-            if method_name.startswith("__") and not method_name.endswith("__"):
-                # If the method starts with double underscore (dunder)
-                # Python applies mangling so we need to prepend the class name.
-                # This doesn't happen if it always ends with double underscore.
-                class_name = obj.__qualname__.split('.')[-2]
-                method_name = "_{c}{m}".format(c=class_name, m=method_name)
-
-            method_object = outer.__dict__[method_name]
-            if not isinstance(method_object, (classmethod, staticmethod)):
-                del parameters[0]
-
-    signature.signature = signature.signature.replace(
-        parameters=parameters,
-        return_annotation=inspect.Signature.empty)
-
-    return signature.format_args().replace('\\', '\\\\'), None
-
-
-def process_docstring(app, what, name, obj, options, lines):
-    if isinstance(obj, property):
-        obj = obj.fget
-
-    if callable(obj):
-        if what in ('class', 'exception'):
-            obj = getattr(obj, '__init__')
-
-        obj = unwrap(obj)
-        try:
-            type_hints = get_type_hints(obj)
-        except (AttributeError, TypeError):
-            # Introspecting a slot wrapper will raise TypeError
-            return
-        except NameError as exc:
-            logger.warning('Cannot resolve forward reference in type annotations of "%s": %s',
-                           name, exc)
-            type_hints = obj.__annotations__
-
-        for argname, annotation in type_hints.items():
-            if argname.endswith('_'):
-                argname = '{}\\_'.format(argname[:-1])
-
-            formatted_annotation = format_annotation(annotation)
-
-            if argname == 'return':
-                if what in ('class', 'exception'):
-                    # Don't add return type None from __init__()
-                    continue
-
-                insert_index = len(lines)
-                for i, line in enumerate(lines):
-                    if line.startswith(':rtype:'):
-                        insert_index = None
-                        break
-                    elif line.startswith(':return:') or line.startswith(':returns:'):
-                        insert_index = i
-
-                if insert_index is not None:
-                    if insert_index == len(lines):
-                        # Ensure that :rtype: doesn't get joined with a paragraph of text, which
-                        # prevents it being interpreted.
-                        lines.append('')
-                        insert_index += 1
-
-                    lines.insert(insert_index, ':rtype: {}'.format(formatted_annotation))
-            else:
-                searchfor = ':param {}:'.format(argname)
-                for i, line in enumerate(lines):
-                    if line.startswith(searchfor):
-                        lines.insert(i, ':type {}: {}'.format(argname, formatted_annotation))
-                        break

docs/troubleshooting.rst

@@ -33,7 +33,7 @@ happen under normal conditions, consider adjusting the
 There have been observations that services, that in their nature offer
 promiscuous IP addresses, such as cloud, VPN and public proxy services, might be
 subject to significantly stricter limits for anonymous access. However,
-logged-in accesses (see :option:`--login`) do not seem to be affected.
+:ref:`logged-in accesses<login>` do not seem to be affected.
 
 Instaloader allows to adjust the rate controlling behavior by overriding
 :class:`instaloader.RateController`.

instaloader/__init__.py

@@ -1,7 +1,7 @@
 """Download pictures (or videos) along with their captions and other metadata from Instagram."""
 
 
-__version__ = '4.10'
+__version__ = '4.15.4'
 
 
 try:
@@ -13,10 +13,26 @@ else:
     win_unicode_console.enable()
 
 from .exceptions import *
-from .instaloader import Instaloader
-from .instaloadercontext import InstaloaderContext, RateController
-from .lateststamps import LatestStamps
-from .nodeiterator import NodeIterator, FrozenNodeIterator, resumable_iteration
-from .structures import (Hashtag, Highlight, Post, PostSidecarNode, PostComment, PostCommentAnswer, PostLocation,
-                         Profile, Story, StoryItem, TopSearchResults, load_structure_from_file, save_structure_to_file,
-                         load_structure, get_json_structure)
+from .instaloader import Instaloader as Instaloader
+from .instaloadercontext import (InstaloaderContext as InstaloaderContext,
+                                 RateController as RateController)
+from .lateststamps import LatestStamps as LatestStamps
+from .nodeiterator import (NodeIterator as NodeIterator,
+                           FrozenNodeIterator as FrozenNodeIterator,
+                           resumable_iteration as resumable_iteration)
+from .structures import (Hashtag as Hashtag,
+                         Highlight as Highlight,
+                         Post as Post,
+                         PostSidecarNode as PostSidecarNode,
+                         PostComment as PostComment,
+                         PostCommentAnswer as PostCommentAnswer,
+                         PostLocation as PostLocation,
+                         Profile as Profile,
+                         Story as Story,
+                         StoryItem as StoryItem,
+                         TopSearchResults as TopSearchResults,
+                         TitlePic as TitlePic,
+                         load_structure_from_file as load_structure_from_file,
+                         save_structure_to_file as save_structure_to_file,
+                         load_structure as load_structure,
+                         get_json_structure as get_json_structure)

instaloader/__main__.py

@@ -6,23 +6,38 @@ import os
 import re
 import sys
 from argparse import ArgumentParser, ArgumentTypeError, SUPPRESS
+from enum import IntEnum
 from typing import List, Optional
 
 from . import (AbortDownloadException, BadCredentialsException, Instaloader, InstaloaderException,
-               InvalidArgumentException, Post, Profile, ProfileNotExistsException, StoryItem,
+               InvalidArgumentException, LoginException, Post, Profile, ProfileNotExistsException, StoryItem,
                TwoFactorAuthRequiredException, __version__, load_structure_from_file)
 from .instaloader import (get_default_session_filename, get_default_stamps_filename)
 from .instaloadercontext import default_user_agent
 from .lateststamps import LatestStamps
+try:
+    import browser_cookie3
+    bc3_library = True
+except ImportError:
+    bc3_library = False
 
 
+class ExitCode(IntEnum):
+    SUCCESS = 0
+    NON_FATAL_ERROR = 1
+    INIT_FAILURE = 2
+    LOGIN_FAILURE = 3
+    DOWNLOAD_ABORTED = 4
+    USER_ABORTED = 5
+    UNEXPECTED_ERROR = 99
+
 def usage_string():
     # NOTE: duplicated in README.rst and docs/index.rst
     argv0 = os.path.basename(sys.argv[0])
     argv0 = "instaloader" if argv0 == "__main__.py" else argv0
     return """
 {0} [--comments] [--geotags]
-{2:{1}} [--stories] [--highlights] [--tagged] [--igtv]
+{2:{1}} [--stories] [--highlights] [--tagged] [--reels] [--igtv]
 {2:{1}} [--login YOUR-USERNAME] [--fast-update]
 {2:{1}} profile | "#hashtag" | %%location_id | :stories | :feed | :saved
 {0} --help""".format(argv0, len(argv0), '')
@@ -67,6 +82,53 @@ def filterstr_to_filterfunc(filter_str: str, item_type: type):
     return filterfunc
 
 
+def get_cookies_from_instagram(domain: str, browser: str, cookie_file: Optional[str] = None):
+    supported_browsers = {
+        "brave": browser_cookie3.brave,
+        "chrome": browser_cookie3.chrome,
+        "chromium": browser_cookie3.chromium,
+        "edge": browser_cookie3.edge,
+        "firefox": browser_cookie3.firefox,
+        "librewolf": browser_cookie3.librewolf,
+        "opera": browser_cookie3.opera,
+        "opera_gx": browser_cookie3.opera_gx,
+        "safari": browser_cookie3.safari,
+        "vivaldi": browser_cookie3.vivaldi,
+    }
+
+    if browser not in supported_browsers:
+        raise InvalidArgumentException("Loading cookies from the specified browser failed\n"
+                                       "Supported browsers are Brave, Chrome, Chromium, Edge, Firefox, LibreWolf, "
+                                       "Opera, Opera_GX, Safari and Vivaldi")
+
+    cookies = {}
+    browser_cookies = list(supported_browsers[browser](cookie_file=cookie_file))
+
+    for cookie in browser_cookies:
+        if domain in cookie.domain:
+            cookies[cookie.name] = cookie.value
+
+    if cookies:
+        print(f"Cookies loaded successfully from {browser}")
+    else:
+        raise LoginException(f"No cookies found for Instagram in {browser}, "
+                             f"Are you logged in successfully in {browser}?")
+
+    return cookies
+
+
+def import_session(browser: str, instaloader: Instaloader, cookiefile: Optional[str]):
+    cookie = get_cookies_from_instagram('instagram', browser, cookiefile)
+    if cookie is not None:
+        instaloader.context.update_cookies(cookie)
+        username = instaloader.test_login()
+        if not username:
+            raise LoginException(f"Not logged in. Are you logged in successfully in {browser}?")
+        instaloader.context.username = username
+        print(f"{username} has been successfully logged in.")
+        print(f"Next time use --login={username} to reuse the same session.")
+
+
 def _main(instaloader: Instaloader, targetlist: List[str],
           username: Optional[str] = None, password: Optional[str] = None,
           sessionfile: Optional[str] = None,
@@ -74,11 +136,14 @@ def _main(instaloader: Instaloader, targetlist: List[str],
           download_stories: bool = False,
           download_highlights: bool = False,
           download_tagged: bool = False,
+          download_reels: bool = False,
           download_igtv: bool = False,
           fast_update: bool = False,
           latest_stamps_file: Optional[str] = None,
           max_count: Optional[int] = None, post_filter_str: Optional[str] = None,
-          storyitem_filter_str: Optional[str] = None) -> None:
+          storyitem_filter_str: Optional[str] = None,
+          browser: Optional[str] = None,
+          cookiefile: Optional[str] = None) -> ExitCode:
     """Download set of profiles, hashtags etc. and handle logging in and session files if desired."""
     # Parse and generate filter function
     post_filter = None
@@ -93,6 +158,11 @@ def _main(instaloader: Instaloader, targetlist: List[str],
     if latest_stamps_file is not None:
         latest_stamps = LatestStamps(latest_stamps_file)
         instaloader.context.log(f"Using latest stamps from {latest_stamps_file}.")
+    # load cookies if browser is not None
+    if browser and bc3_library:
+        import_session(browser.lower(), instaloader, cookiefile)
+    elif browser and not bc3_library:
+        raise InvalidArgumentException("browser_cookie3 library is needed to load cookies from browsers")
     # Login, if desired
     if username is not None:
         if not re.match(r"^[A-Za-z0-9._]+$", username):
@@ -108,6 +178,10 @@ def _main(instaloader: Instaloader, targetlist: List[str],
                 try:
                     instaloader.login(username, password)
                 except TwoFactorAuthRequiredException:
+                    # https://github.com/instaloader/instaloader/issues/1217
+                    instaloader.context.error("Warning: There have been reports of 2FA currently not working. "
+                                              "Consider importing session cookies from your browser with "
+                                              "--load-cookies.")
                     while True:
                         try:
                             code = input("Enter 2FA verification code: ")
@@ -117,14 +191,19 @@ def _main(instaloader: Instaloader, targetlist: List[str],
                             print(err, file=sys.stderr)
                             pass
             else:
-                instaloader.interactive_login(username)
+                try:
+                    instaloader.interactive_login(username)
+                except KeyboardInterrupt:
+                    print("\nInterrupted by user.", file=sys.stderr)
+                    return ExitCode.USER_ABORTED
         instaloader.context.log("Logged in as %s." % username)
     # since 4.2.9 login is required for geotags
     if instaloader.download_geotags and not instaloader.context.is_logged_in:
-        instaloader.context.error("Warning: Use --login to download geotags of posts.")
+        instaloader.context.error("Warning: Login is required to download geotags of posts.")
     # Try block for KeyboardInterrupt (save session on ^C)
     profiles = set()
     anonymous_retry_profiles = set()
+    exit_code = ExitCode.SUCCESS
     try:
         # Generate set of profiles, already downloading non-profile targets
         for target in targetlist:
@@ -177,11 +256,13 @@ def _main(instaloader: Instaloader, targetlist: List[str],
                     instaloader.download_saved_posts(fast_update=fast_update, max_count=max_count,
                                                      post_filter=post_filter)
                 elif re.match(r"^[A-Za-z0-9._]+$", target):
+                    download_profile_content = download_posts or download_tagged or download_reels or download_igtv
                     try:
                         profile = instaloader.check_profile_id(target, latest_stamps)
                         if instaloader.context.is_logged_in and profile.has_blocked_viewer:
-                            if download_profile_pic or ((download_posts or download_tagged or download_igtv)
-                                                        and not profile.is_private):
+                            if download_profile_pic or (
+                                download_profile_content and not profile.is_private
+                            ):
                                 raise ProfileNotExistsException("{} blocked you; But we download her anonymously."
                                                                 .format(target))
                             else:
@@ -191,8 +272,7 @@ def _main(instaloader: Instaloader, targetlist: List[str],
                     except ProfileNotExistsException as err:
                         # Not only our profile.has_blocked_viewer condition raises ProfileNotExistsException,
                         # check_profile_id() also does, since access to blocked profile may be responded with 404.
-                        if instaloader.context.is_logged_in and (download_profile_pic or download_posts or
-                                                                 download_tagged or download_igtv):
+                        if instaloader.context.is_logged_in and (download_profile_pic or download_profile_content):
                             instaloader.context.log(err)
                             instaloader.context.log("Trying again anonymously, helps in case you are just blocked.")
                             with instaloader.anonymous_copy() as anonymous_loader:
@@ -215,23 +295,42 @@ def _main(instaloader: Instaloader, targetlist: List[str],
                                                                          ' '.join([p.username for p in profiles])))
         if instaloader.context.iphone_support and profiles and (download_profile_pic or download_posts) and \
            not instaloader.context.is_logged_in:
-            instaloader.context.log("Hint: Use --login to download higher-quality versions of pictures.")
-        instaloader.download_profiles(profiles,
-                                      download_profile_pic, download_posts, download_tagged, download_igtv,
-                                      download_highlights, download_stories,
-                                      fast_update, post_filter, storyitem_filter, latest_stamps=latest_stamps)
+            instaloader.context.log("Hint: Login to download higher-quality versions of pictures.")
+        instaloader.download_profiles(
+            profiles,
+            download_profile_pic,
+            download_posts,
+            download_tagged,
+            download_igtv,
+            download_highlights,
+            download_stories,
+            fast_update,
+            post_filter,
+            storyitem_filter,
+            latest_stamps=latest_stamps,
+            reels=download_reels,
+        )
         if anonymous_retry_profiles:
             instaloader.context.log("Downloading anonymously: {}"
                                     .format(' '.join([p.username for p in anonymous_retry_profiles])))
             with instaloader.anonymous_copy() as anonymous_loader:
-                anonymous_loader.download_profiles(anonymous_retry_profiles,
-                                                   download_profile_pic, download_posts, download_tagged, download_igtv,
-                                                   fast_update=fast_update, post_filter=post_filter,
-                                                   latest_stamps=latest_stamps)
+                anonymous_loader.download_profiles(
+                    anonymous_retry_profiles,
+                    download_profile_pic,
+                    download_posts,
+                    download_tagged,
+                    download_igtv,
+                    fast_update=fast_update,
+                    post_filter=post_filter,
+                    latest_stamps=latest_stamps,
+                    reels=download_reels
+                )
     except KeyboardInterrupt:
         print("\nInterrupted by user.", file=sys.stderr)
+        exit_code = ExitCode.USER_ABORTED
     except AbortDownloadException as exc:
         print("\nDownload aborted: {}.".format(exc), file=sys.stderr)
+        exit_code = ExitCode.DOWNLOAD_ABORTED
     # Save session if it is useful
     if instaloader.context.is_logged_in:
         instaloader.save_session_to_file(sessionfile)
@@ -243,6 +342,8 @@ def _main(instaloader: Instaloader, targetlist: List[str],
         else:
             # Instaloader did not do anything
             instaloader.context.log("usage:" + usage_string())
+            exit_code = ExitCode.INIT_FAILURE
+    return exit_code
 
 
 def main():
@@ -258,17 +359,17 @@ def main():
                            help="Download profile. If an already-downloaded profile has been renamed, Instaloader "
                                 "automatically finds it by its unique ID and renames the folder likewise.")
     g_targets.add_argument('_at_profile', nargs='*', metavar="@profile",
-                           help="Download all followees of profile. Requires --login. "
+                           help="Download all followees of profile. Requires login. "
                                 "Consider using :feed rather than @yourself.")
     g_targets.add_argument('_hashtag', nargs='*', metavar='"#hashtag"', help="Download #hashtag.")
     g_targets.add_argument('_location', nargs='*', metavar='%location_id',
-                           help="Download %%location_id. Requires --login.")
+                           help="Download %%location_id. Requires login.")
     g_targets.add_argument('_feed', nargs='*', metavar=":feed",
-                           help="Download pictures from your feed. Requires --login.")
+                           help="Download pictures from your feed. Requires login.")
     g_targets.add_argument('_stories', nargs='*', metavar=":stories",
-                           help="Download the stories of your followees. Requires --login.")
+                           help="Download the stories of your followees. Requires login.")
     g_targets.add_argument('_saved', nargs='*', metavar=":saved",
-                           help="Download the posts that you marked as saved. Requires --login.")
+                           help="Download the posts that you marked as saved. Requires login.")
     g_targets.add_argument('_singlepost', nargs='*', metavar="-- -shortcode",
                            help="Download the post with the given shortcode")
     g_targets.add_argument('_json', nargs='*', metavar="filename.json[.xz]",
@@ -299,11 +400,11 @@ def main():
                         help='Download geotags when available. Geotags are stored as a '
                              'text file with the location\'s name and a Google Maps link. '
                              'This requires an additional request to the Instagram '
-                             'server for each picture. Requires --login.')
+                             'server for each picture. Requires login.')
     g_post.add_argument('-C', '--comments', action='store_true',
                         help='Download and update comments for each post. '
                              'This requires an additional request to the Instagram '
-                             'server for each post, which is why it is disabled by default.')
+                             'server for each post, which is why it is disabled by default. Requires login.')
     g_post.add_argument('--no-captions', action='store_true',
                         help='Do not create txt files.')
     g_post.add_argument('--post-metadata-txt', action='append',
@@ -317,13 +418,15 @@ def main():
     g_post.add_argument('--no-compress-json', action='store_true',
                         help='Do not xz compress JSON files, rather create pretty formatted JSONs.')
     g_prof.add_argument('-s', '--stories', action='store_true',
-                        help='Also download stories of each profile that is downloaded. Requires --login.')
+                        help='Also download stories of each profile that is downloaded. Requires login.')
     g_prof.add_argument('--stories-only', action='store_true',
                         help=SUPPRESS)
     g_prof.add_argument('--highlights', action='store_true',
-                        help='Also download highlights of each profile that is downloaded. Requires --login.')
+                        help='Also download highlights of each profile that is downloaded. Requires login.')
     g_prof.add_argument('--tagged', action='store_true',
                         help='Also download posts where each profile is tagged.')
+    g_prof.add_argument('--reels', action='store_true',
+                        help='Also download Reels videos.')
     g_prof.add_argument('--igtv', action='store_true',
                         help='Also download IGTV videos.')
 
@@ -353,9 +456,14 @@ def main():
                                         'Instaloader can login to Instagram. This allows downloading private profiles. '
                                         'To login, pass the --login option. Your session cookie (not your password!) '
                                         'will be saved to a local file to be reused next time you want Instaloader '
-                                        'to login.')
+                                        'to login. Instead of --login, the --load-cookies option can be used to '
+                                        'import a session from a browser.')
     g_login.add_argument('-l', '--login', metavar='YOUR-USERNAME',
                          help='Login name (profile name) for your Instagram account.')
+    g_login.add_argument('-b', '--load-cookies', metavar='BROWSER-NAME',
+                         help='Browser name to load cookies from Instagram')
+    g_login.add_argument('-B', '--cookiefile', metavar='COOKIE-FILE',
+                         help='Cookie file of a profile to load cookies')
     g_login.add_argument('-f', '--sessionfile',
                          help='Path for loading and storing session key file. '
                               'Defaults to ' + get_default_session_filename("<login_name>"))
@@ -416,15 +524,15 @@ def main():
 
     args = parser.parse_args()
     try:
-        if args.login is None and (args.stories or args.stories_only):
-            print("--login=USERNAME required to download stories.", file=sys.stderr)
+        if (args.login is None and args.load_cookies is None) and (args.stories or args.stories_only):
+            print("Login is required to download stories.", file=sys.stderr)
             args.stories = False
             if args.stories_only:
-                raise SystemExit(1)
+                raise InvalidArgumentException()
 
         if ':feed-all' in args.profile or ':feed-liked' in args.profile:
-            raise SystemExit(":feed-all and :feed-liked were removed. Use :feed as target and "
-                             "eventually --post-filter=viewer_has_liked.")
+            raise InvalidArgumentException(":feed-all and :feed-liked were removed. Use :feed as target and "
+                                           "eventually --post-filter=viewer_has_liked.")
 
         post_metadata_txt_pattern = '\n'.join(args.post_metadata_txt) if args.post_metadata_txt else None
         storyitem_metadata_txt_pattern = '\n'.join(args.storyitem_metadata_txt) if args.storyitem_metadata_txt else None
@@ -434,15 +542,18 @@ def main():
                 post_metadata_txt_pattern = ''
                 storyitem_metadata_txt_pattern = ''
             else:
-                raise SystemExit("--no-captions and --post-metadata-txt or --storyitem-metadata-txt given; "
-                                 "That contradicts.")
+                raise InvalidArgumentException("--no-captions and --post-metadata-txt or --storyitem-metadata-txt "
+                                               "given; That contradicts.")
 
         if args.no_resume and args.resume_prefix:
-            raise SystemExit("--no-resume and --resume-prefix given; That contradicts.")
+            raise InvalidArgumentException("--no-resume and --resume-prefix given; That contradicts.")
         resume_prefix = (args.resume_prefix if args.resume_prefix else 'iterator') if not args.no_resume else None
 
         if args.no_pictures and args.fast_update:
-            raise SystemExit('--no-pictures and --fast-update cannot be used together.')
+            raise InvalidArgumentException('--no-pictures and --fast-update cannot be used together.')
+
+        if args.login and args.load_cookies:
+            raise InvalidArgumentException('--load-cookies and --login cannot be used together.')
 
         # Determine what to download
         download_profile_pic = not args.no_profile_pic or args.profile_pic_only
@@ -467,25 +578,38 @@ def main():
                              iphone_support=not args.no_iphone,
                              title_pattern=args.title_pattern,
                              sanitize_paths=args.sanitize_paths)
-        _main(loader,
-              args.profile,
-              username=args.login.lower() if args.login is not None else None,
-              password=args.password,
-              sessionfile=args.sessionfile,
-              download_profile_pic=download_profile_pic,
-              download_posts=download_posts,
-              download_stories=download_stories,
-              download_highlights=args.highlights,
-              download_tagged=args.tagged,
-              download_igtv=args.igtv,
-              fast_update=args.fast_update,
-              latest_stamps_file=args.latest_stamps,
-              max_count=int(args.count) if args.count is not None else None,
-              post_filter_str=args.post_filter,
-              storyitem_filter_str=args.storyitem_filter)
+        exit_code = _main(loader,
+                          args.profile,
+                          username=args.login.lower() if args.login is not None else None,
+                          password=args.password,
+                          sessionfile=args.sessionfile,
+                          download_profile_pic=download_profile_pic,
+                          download_posts=download_posts,
+                          download_stories=download_stories,
+                          download_highlights=args.highlights,
+                          download_tagged=args.tagged,
+                          download_reels=args.reels,
+                          download_igtv=args.igtv,
+                          fast_update=args.fast_update,
+                          latest_stamps_file=args.latest_stamps,
+                          max_count=int(args.count) if args.count is not None else None,
+                          post_filter_str=args.post_filter,
+                          storyitem_filter_str=args.storyitem_filter,
+                          browser=args.load_cookies,
+                          cookiefile=args.cookiefile)
         loader.close()
+        if loader.has_stored_errors:
+            exit_code = ExitCode.NON_FATAL_ERROR
+    except InvalidArgumentException as err:
+        print(err, file=sys.stderr)
+        exit_code = ExitCode.INIT_FAILURE
+    except LoginException as err:
+        print(err, file=sys.stderr)
+        exit_code = ExitCode.LOGIN_FAILURE
     except InstaloaderException as err:
-        raise SystemExit("Fatal error: %s" % err) from err
+        print("Fatal error: %s" % err)
+        exit_code = ExitCode.UNEXPECTED_ERROR
+    sys.exit(exit_code)
 
 
 if __name__ == "__main__":

instaloader/exceptions.py

@@ -33,7 +33,11 @@ class LoginRequiredException(InstaloaderException):
     pass
 
 
-class TwoFactorAuthRequiredException(InstaloaderException):
+class LoginException(InstaloaderException):
+    pass
+
+
+class TwoFactorAuthRequiredException(LoginException):
     pass
 
 
@@ -45,7 +49,7 @@ class BadResponseException(InstaloaderException):
     pass
 
 
-class BadCredentialsException(InstaloaderException):
+class BadCredentialsException(LoginException):
     pass
 
 

instaloader/instaloader.py

@@ -77,13 +77,13 @@ def _requires_login(func: Callable) -> Callable:
     @wraps(func)
     def call(instaloader, *args, **kwargs):
         if not instaloader.context.is_logged_in:
-            raise LoginRequiredException("--login=USERNAME required.")
+            raise LoginRequiredException("Login required.")
         return func(instaloader, *args, **kwargs)
     return call
 
 
 def _retry_on_connection_error(func: Callable) -> Callable:
-    """Decorator to retry the function max_connection_attemps number of times.
+    """Decorator to retry the function max_connection_attempts number of times.
 
     Herewith-decorated functions need an ``_attempt`` keyword argument.
 
@@ -330,6 +330,9 @@ 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:
@@ -643,11 +646,16 @@ class Instaloader:
     def login(self, user: str, passwd: str) -> None:
         """Log in to instagram with given username and password and internally store session object.
 
-        :raises InvalidArgumentException: If the provided username does not exist.
         :raises BadCredentialsException: If the provided password is wrong.
-        :raises ConnectionException: If connection to Instagram failed.
         :raises TwoFactorAuthRequiredException: First step of 2FA login done, now call
-           :meth:`Instaloader.two_factor_login`."""
+           :meth:`Instaloader.two_factor_login`.
+        :raises LoginException: An error happened during login (for example, an invalid response was received).
+           Or if the provided username does not exist.
+
+        .. versionchanged:: 4.12
+           Raises LoginException instead of ConnectionException when an error happens.
+           Raises LoginException instead of InvalidArgumentException when the username does not exist.
+        """
         self.context.login(user, passwd)
 
     def two_factor_login(self, two_factor_code) -> None:
@@ -717,7 +725,7 @@ class Instaloader:
         # Download the image(s) / video thumbnail and videos within sidecars if desired
         downloaded = True
         if post.typename == 'GraphSidecar':
-            if self.download_pictures or self.download_videos:
+            if (self.download_pictures or self.download_videos) and post.mediacount > 0:
                 if not _all_already_downloaded(
                         filename_template, enumerate(
                             (post.get_is_videos()[i]
@@ -732,19 +740,20 @@ class Instaloader:
                         suffix: Optional[str] = str(edge_number)
                         if '{filename}' in self.filename_pattern:
                             suffix = None
-                        if self.download_pictures and (not sidecar_node.is_video or self.download_video_thumbnails):
+                        video_url = sidecar_node.video_url
+                        if self.download_pictures and (video_url is None or self.download_video_thumbnails):
                             # pylint:disable=cell-var-from-loop
                             sidecar_filename = self.__prepare_filename(filename_template,
                                                                        lambda: sidecar_node.display_url)
                             # Download sidecar picture or video thumbnail (--no-pictures implies --no-video-thumbnails)
                             downloaded &= self.download_pic(filename=sidecar_filename, url=sidecar_node.display_url,
                                                             mtime=post.date_local, filename_suffix=suffix)
-                        if sidecar_node.is_video and self.download_videos:
+                        if video_url is not None and self.download_videos:
                             # pylint:disable=cell-var-from-loop
                             sidecar_filename = self.__prepare_filename(filename_template,
-                                                                       lambda: sidecar_node.video_url)
+                                                                       lambda: video_url)
                             # Download sidecar video if desired
-                            downloaded &= self.download_pic(filename=sidecar_filename, url=sidecar_node.video_url,
+                            downloaded &= self.download_pic(filename=sidecar_filename, url=video_url,
                                                             mtime=post.date_local, filename_suffix=suffix)
                 else:
                     downloaded = False
@@ -861,8 +870,9 @@ class Instaloader:
                 last_scraped = latest_stamps.get_last_story_timestamp(name)
                 scraped_timestamp = datetime.now().astimezone()
             for item in user_story.get_items():
-                if latest_stamps is not None and item.date_local <= last_scraped:
-                    break
+                if latest_stamps is not None:
+                    if item.date_local <= last_scraped:
+                        break
                 if storyitem_filter is not None and not storyitem_filter(item):
                     self.context.log("<{} skipped>".format(item), flush=True)
                     continue
@@ -953,6 +963,11 @@ 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
@@ -960,14 +975,20 @@ 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
@@ -991,7 +1012,8 @@ class Instaloader:
                             max_count: Optional[int] = None,
                             total_count: Optional[int] = None,
                             owner_profile: Optional[Profile] = None,
-                            takewhile: Optional[Callable[[Post], bool]] = None) -> None:
+                            takewhile: Optional[Callable[[Post], bool]] = None,
+                            possibly_pinned: int = 0) -> None:
         """
         Download the Posts returned by given Post Iterator.
 
@@ -1003,6 +1025,9 @@ class Instaloader:
         .. versionchanged:: 4.8
            Add `takewhile` parameter.
 
+        .. versionchanged:: 4.10.3
+           Add `possibly_pinned` parameter.
+
         :param posts: Post Iterator to loop through.
         :param target: Target name.
         :param fast_update: :option:`--fast-update`.
@@ -1011,6 +1036,8 @@ class Instaloader:
         :param total_count: Total number of posts returned by given iterator.
         :param owner_profile: Associated profile, if any.
         :param takewhile: Expression evaluated for each post. Once it returns false, downloading stops.
+        :param possibly_pinned: Number of posts that might be pinned. These posts do not cause download
+               to stop even if they've already been downloaded.
         """
         displayed_count = (max_count if total_count is None or max_count is not None and max_count < total_count
                            else total_count)
@@ -1032,7 +1059,7 @@ class Instaloader:
         ) as (is_resuming, start_index):
             for number, post in enumerate(posts, start=start_index + 1):
                 should_stop = not takewhile(post)
-                if should_stop and post.is_pinned:
+                if should_stop and number <= possibly_pinned:
                     continue
                 if (max_count is not None and number > max_count) or should_stop:
                     break
@@ -1066,7 +1093,7 @@ class Instaloader:
                         except PostChangedException:
                             post_changed = True
                             continue
-                    if fast_update and not downloaded and not post_changed and not post.is_pinned:
+                    if fast_update and not downloaded and not post_changed and number > possibly_pinned:
                         # disengage fast_update for first post when resuming
                         if not is_resuming or number > 0:
                             break
@@ -1203,6 +1230,7 @@ class Instaloader:
            Use :meth:`Hashtag.get_posts_resumable`."""
         return Hashtag.from_name(self.context, hashtag).get_posts_resumable()
 
+    @_requires_login
     def download_hashtag(self, hashtag: Union[Hashtag, str],
                          max_count: Optional[int] = None,
                          post_filter: Optional[Callable[[Post], bool]] = None,
@@ -1269,6 +1297,32 @@ class Instaloader:
         if latest_stamps is not None and tagged_posts.first_item is not None:
             latest_stamps.set_last_tagged_timestamp(profile.username, tagged_posts.first_item.date_local)
 
+    def download_reels(self, profile: Profile, fast_update: bool = False,
+                      post_filter: Optional[Callable[[Post], bool]] = None,
+                      latest_stamps: Optional[LatestStamps] = None) -> None:
+        """Download reels videos of a profile.
+
+        .. versionadded:: 4.14.0
+
+        """
+        self.context.log("Retrieving reels videos for profile {}.".format(profile.username))
+        posts_takewhile: Optional[Callable[[Post], bool]] = None
+        if latest_stamps is not None:
+            last_scraped = latest_stamps.get_last_reels_timestamp(profile.username)
+            posts_takewhile = lambda p: p.date_local > last_scraped
+        reels = profile.get_reels()
+        self.posts_download_loop(
+            reels,
+            profile.username,
+            fast_update,
+            post_filter,
+            owner_profile=profile,
+            takewhile=posts_takewhile,
+            possibly_pinned=3,
+        )
+        if latest_stamps is not None and reels.first_item is not None:
+            latest_stamps.set_last_reels_timestamp(profile.username, reels.first_item.date_local)
+
     def download_igtv(self, profile: Profile, fast_update: bool = False,
                       post_filter: Optional[Callable[[Post], bool]] = None,
                       latest_stamps: Optional[LatestStamps] = None) -> None:
@@ -1398,7 +1452,9 @@ class Instaloader:
                           post_filter: Optional[Callable[[Post], bool]] = None,
                           storyitem_filter: Optional[Callable[[Post], bool]] = None,
                           raise_errors: bool = False,
-                          latest_stamps: Optional[LatestStamps] = None):
+                          latest_stamps: Optional[LatestStamps] = None,
+                          max_count: Optional[int] = None,
+                          reels: bool = False):
         """High-level method to download set of profiles.
 
         :param profiles: Set of profiles to download.
@@ -1415,6 +1471,8 @@ class Instaloader:
            Whether :exc:`LoginRequiredException` and :exc:`PrivateProfileNotFollowedException` should be raised or
            catched and printed with :meth:`InstaloaderContext.error_catcher`.
         :param latest_stamps: :option:`--latest-stamps`.
+        :param max_count: Maximum count of posts to download.
+        :param reels: :option:`--reels`.
 
         .. versionadded:: 4.1
 
@@ -1423,6 +1481,12 @@ class Instaloader:
 
         .. versionchanged:: 4.8
            Add `latest_stamps` parameter.
+
+        .. versionchanged:: 4.13
+           Add `max_count` parameter.
+
+        .. versionchanged:: 4.14
+           Add `reels` parameter.
         """
 
         @contextmanager
@@ -1454,7 +1518,7 @@ class Instaloader:
                 if tagged or igtv or highlights or posts:
                     if (not self.context.is_logged_in and
                             profile.is_private):
-                        raise LoginRequiredException("--login=USERNAME required.")
+                        raise LoginRequiredException("Login required.")
                     if (self.context.username != profile.username and
                             profile.is_private and
                             not profile.followed_by_viewer):
@@ -1466,6 +1530,12 @@ class Instaloader:
                         self.download_tagged(profile, fast_update=fast_update, post_filter=post_filter,
                                              latest_stamps=latest_stamps)
 
+                # Download reels, if requested
+                if reels:
+                    with self.context.error_catcher('Download reels of {}'.format(profile_name)):
+                        self.download_reels(profile, fast_update=fast_update, post_filter=post_filter,
+                                           latest_stamps=latest_stamps)
+
                 # Download IGTV, if requested
                 if igtv:
                     with self.context.error_catcher('Download IGTV of {}'.format(profile_name)):
@@ -1488,7 +1558,7 @@ class Instaloader:
                     posts_to_download = profile.get_posts()
                     self.posts_download_loop(posts_to_download, profile_name, fast_update, post_filter,
                                              total_count=profile.mediacount, owner_profile=profile,
-                                             takewhile=posts_takewhile)
+                                             takewhile=posts_takewhile, possibly_pinned=3, max_count=max_count)
                     if latest_stamps is not None and posts_to_download.first_item is not None:
                         latest_stamps.set_last_post_timestamp(profile_name,
                                                               posts_to_download.first_item.date_local)
@@ -1576,11 +1646,16 @@ class Instaloader:
     def interactive_login(self, username: str) -> None:
         """Logs in and internally stores session, asking user for password interactively.
 
-        :raises LoginRequiredException: when in quiet mode.
-        :raises InvalidArgumentException: If the provided username does not exist.
-        :raises ConnectionException: If connection to Instagram failed."""
+        :raises InvalidArgumentException: when in quiet mode.
+        :raises LoginException: If the provided username does not exist.
+        :raises ConnectionException: If connection to Instagram failed.
+
+        .. versionchanged:: 4.12
+           Raises InvalidArgumentException instead of LoginRequiredException when in quiet mode.
+           Raises LoginException instead of InvalidArgumentException when the username does not exist.
+        """
         if self.context.quiet:
-            raise LoginRequiredException("Quiet mode requires given password or valid session file.")
+            raise InvalidArgumentException("Quiet mode requires given password or valid session file.")
         try:
             password = None
             while password is None:
@@ -1599,3 +1674,10 @@ class Instaloader:
                 except BadCredentialsException as err:
                     print(err, file=sys.stderr)
                     pass
+
+    @property
+    def has_stored_errors(self) -> bool:
+        """Returns whether any error has been reported and stored to be repeated at program termination.
+
+        .. versionadded: 4.12"""
+        return self.context.has_stored_errors

instaloader/instaloadercontext.py

@@ -1,4 +1,3 @@
-import hashlib
 import json
 import os
 import pickle
@@ -10,7 +9,7 @@ import textwrap
 import time
 import urllib.parse
 import uuid
-from contextlib import contextmanager
+from contextlib import contextmanager, suppress
 from datetime import datetime, timedelta
 from functools import partial
 from typing import Any, Callable, Dict, Iterator, List, Optional, Union
@@ -32,17 +31,30 @@ 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/92.0.4515.131 Safari/537.36'
+    return ('Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 '
+            '(KHTML, like Gecko) Chrome/142.0.0.0 Safari/537.36')
 
 
 def default_iphone_headers() -> Dict[str, Any]:
-    return {'User-Agent': 'Instagram 273.0.0.16.70 (iPad13,8; iOS 16_3; en_US; en-US; ' \
-                          'scale=2.00; 2048x2732; 452417278) AppleWebKit/420+',
+    return {'User-Agent': 'Instagram 361.0.0.35.82 (iPad13,8; iOS 18_0; en_US; en-US; ' \
+                          'scale=2.00; 2048x2732; 674117118) AppleWebKit/420+',
             'x-ads-opt-out': '1',
             'x-bloks-is-panorama-enabled': 'true',
-            'x-bloks-version-id': '01507c21540f73e2216b6f62a11a5b5e51aa85491b72475c080da35b1228ddd6',
+            'x-bloks-version-id': '16b7bd25c6c06886d57c4d455265669345a2d96625385b8ee30026ac2dc5ed97',
             'x-fb-client-ip': 'True',
             'x-fb-connection-type': 'wifi',
             'x-fb-http-engine': 'Liger',
@@ -95,7 +107,6 @@ class InstaloaderContext:
         self.quiet = quiet
         self.max_connection_attempts = max_connection_attempts
         self._graphql_page_length = 50
-        self._root_rhx_gis = None
         self.two_factor_auth_pending = None
         self.iphone_support = iphone_support
         self.iphone_headers = default_iphone_headers()
@@ -105,7 +116,7 @@ class InstaloaderContext:
 
         self._rate_controller = rate_controller(self) if rate_controller is not None else RateController(self)
 
-        # Can be set to True for testing, disables supression of InstaloaderContext._error_catcher
+        # Can be set to True for testing, disables suppression of InstaloaderContext._error_catcher
         self.raise_all_errors = False
 
         # HTTP status codes that should cause an AbortDownloadException
@@ -152,6 +163,16 @@ 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.
+
+        .. versionadded: 4.12"""
+        return bool(self.error_log)
+
     def close(self):
         """Print error log and close session"""
         if self.error_log and not self.quiet:
@@ -187,7 +208,8 @@ class InstaloaderContext:
                   'Referer': 'https://www.instagram.com/',
                   'User-Agent': self.user_agent,
                   'X-Instagram-AJAX': '1',
-                  'X-Requested-With': 'XMLHttpRequest'}
+                  'X-Requested-With': 'XMLHttpRequest',
+                  'x-ig-app-id': '936619743392459'}
         if empty_session_only:
             del header['Host']
             del header['Origin']
@@ -211,6 +233,10 @@ class InstaloaderContext:
         """Not meant to be used directly, use :meth:`Instaloader.save_session`."""
         return requests.utils.dict_from_cookiejar(self._session.cookies)
 
+    def update_cookies(self, cookie):
+        """.. versionadded:: 4.11"""
+        self._session.cookies.update(cookie)
+
     def load_session(self, username, sessiondata):
         """Not meant to be used directly, use :meth:`Instaloader.load_session`."""
         session = requests.Session()
@@ -233,17 +259,26 @@ class InstaloaderContext:
 
     def test_login(self) -> Optional[str]:
         """Not meant to be used directly, use :meth:`Instaloader.test_login`."""
-        data = self.graphql_query("d6f4427fbe92d846298cf93df0b937d3", {})
-        return data["data"]["user"]["username"] if data["data"]["user"] is not None else None
+        try:
+            data = self.graphql_query("d6f4427fbe92d846298cf93df0b937d3", {})
+            return data["data"]["user"]["username"] if data["data"]["user"] is not None else None
+        except (AbortDownloadException, ConnectionException) as err:
+            self.error(f"Error when checking if logged in: {err}")
+            return None
 
     def login(self, user, passwd):
         """Not meant to be used directly, use :meth:`Instaloader.login`.
 
-        :raises InvalidArgumentException: If the provided username does not exist.
         :raises BadCredentialsException: If the provided password is wrong.
-        :raises ConnectionException: If connection to Instagram failed.
         :raises TwoFactorAuthRequiredException: First step of 2FA login done, now call
-           :meth:`Instaloader.two_factor_login`."""
+           :meth:`Instaloader.two_factor_login`.
+        :raises LoginException: An error happened during login (for example, and invalid response).
+           Or if the provided username does not exist.
+
+        .. versionchanged:: 4.12
+           Raises LoginException instead of ConnectionException when an error happens.
+           Raises LoginException instead of InvalidArgumentException when the username does not exist.
+        """
         # pylint:disable=import-outside-toplevel
         import http.client
         # pylint:disable=protected-access
@@ -256,20 +291,25 @@ class InstaloaderContext:
         # Override default timeout behavior.
         # Need to silence mypy bug for this. See: https://github.com/python/mypy/issues/2427
         session.request = partial(session.request, timeout=self.request_timeout) # type: ignore
-        csrf_json = self.get_json('accounts/login/', {}, session=session)
-        csrf_token = csrf_json['config']['csrf_token']
+
+        # Make a request to Instagram's root URL, which will set the session's csrftoken cookie
+        # Not using self.get_json() here, because we need to access the cookie
+        session.get('https://www.instagram.com/')
+        # Add session's csrftoken cookie to session headers
+        csrf_token = session.cookies.get_dict()['csrftoken']
         session.headers.update({'X-CSRFToken': csrf_token})
-        # Not using self.get_json() here, because we need to access csrftoken cookie
+
         self.do_sleep()
         # Workaround credits to pgrimaud.
         # See: https://github.com/pgrimaud/instagram-user-feed/commit/96ad4cf54d1ad331b337f325c73e664999a6d066
         enc_password = '#PWD_INSTAGRAM_BROWSER:0:{}:{}'.format(int(datetime.now().timestamp()), passwd)
-        login = session.post('https://www.instagram.com/accounts/login/ajax/',
+        login = session.post('https://www.instagram.com/api/v1/web/accounts/login/ajax/',
                              data={'enc_password': enc_password, 'username': user}, allow_redirects=True)
         try:
             resp_json = login.json()
+
         except json.decoder.JSONDecodeError as err:
-            raise ConnectionException(
+            raise LoginException(
                 "Login error: JSON decode fail, {} - {}.".format(login.status_code, login.reason)
             ) from err
         if resp_json.get('two_factor_required'):
@@ -281,31 +321,32 @@ class InstaloaderContext:
                                             resp_json['two_factor_info']['two_factor_identifier'])
             raise TwoFactorAuthRequiredException("Login error: two-factor authentication required.")
         if resp_json.get('checkpoint_url'):
-            raise ConnectionException("Login: Checkpoint required. Point your browser to "
-                                      "https://www.instagram.com{} - "
-                                      "follow the instructions, then retry.".format(resp_json.get('checkpoint_url')))
+            raise LoginException(
+                f"Login: Checkpoint required. Point your browser to {resp_json.get('checkpoint_url')} - "
+                f"follow the instructions, then retry."
+            )
         if resp_json['status'] != 'ok':
             if 'message' in resp_json:
-                raise ConnectionException("Login error: \"{}\" status, message \"{}\".".format(resp_json['status'],
-                                                                                               resp_json['message']))
+                raise LoginException("Login error: \"{}\" status, message \"{}\".".format(resp_json['status'],
+                                                                                          resp_json['message']))
             else:
-                raise ConnectionException("Login error: \"{}\" status.".format(resp_json['status']))
+                raise LoginException("Login error: \"{}\" status.".format(resp_json['status']))
         if 'authenticated' not in resp_json:
             # Issue #472
             if 'message' in resp_json:
-                raise ConnectionException("Login error: Unexpected response, \"{}\".".format(resp_json['message']))
+                raise LoginException("Login error: Unexpected response, \"{}\".".format(resp_json['message']))
             else:
-                raise ConnectionException("Login error: Unexpected response, this might indicate a blocked IP.")
+                raise LoginException("Login error: Unexpected response, this might indicate a blocked IP.")
         if not resp_json['authenticated']:
             if resp_json['user']:
                 # '{"authenticated": false, "user": true, "status": "ok"}'
                 raise BadCredentialsException('Login error: Wrong password.')
             else:
                 # '{"authenticated": false, "user": false, "status": "ok"}'
-                # Raise InvalidArgumentException rather than BadCredentialException, because BadCredentialException
+                # Raise LoginException rather than BadCredentialException, because BadCredentialException
                 # triggers re-asking of password in Instaloader.interactive_login(), which makes no sense if the
                 # username is invalid.
-                raise InvalidArgumentException('Login error: User {} does not exist.'.format(user))
+                raise LoginException('Login error: User {} does not exist.'.format(user))
         # '{"authenticated": true, "user": true, "userId": ..., "oneTapPrompt": false, "status": "ok"}'
         session.headers.update({'X-CSRFToken': login.cookies['csrftoken']})
         self._session = session
@@ -343,33 +384,64 @@ class InstaloaderContext:
         if self.sleep:
             time.sleep(min(random.expovariate(0.6), 15.0))
 
+    @staticmethod
+    def _response_error(resp: requests.Response) -> str:
+        extra_from_json: Optional[str] = None
+        with suppress(json.decoder.JSONDecodeError):
+            resp_json = resp.json()
+            if "status" in resp_json:
+                extra_from_json = (
+                    f"\"{resp_json['status']}\" status, message \"{resp_json['message']}\""
+                    if "message" in resp_json
+                    else f"\"{resp_json['status']}\" status"
+                )
+        return (
+            f"{resp.status_code} {resp.reason}"
+            f"{f' - {extra_from_json}' if extra_from_json is not None else ''}"
+            f" when accessing {resp.url}"
+        )
+
     def get_json(self, path: str, params: Dict[str, Any], host: str = 'www.instagram.com',
                  session: Optional[requests.Session] = None, _attempt=1,
-                 response_headers: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
+                 response_headers: Optional[Dict[str, Any]] = None,
+                 use_post: bool = False) -> Dict[str, Any]:
         """JSON request to Instagram.
 
         :param path: URL, relative to the given domain which defaults to www.instagram.com/
-        :param params: GET parameters
+        :param params: request parameters
         :param host: Domain part of the URL from where to download the requested JSON; defaults to www.instagram.com
         :param session: Session to use, or None to use self.session
+        :param use_post: Use POST instead of GET to make the request
         :return: Decoded response dictionary
-        :raises QueryReturnedBadRequestException: When the server responds with a 400.
+        :raises AbortDownloadException: When the server responds with
+            'feedback_required'/'checkpoint_required'/'challenge_required'
+        :raises QueryReturnedBadRequestException: When the server responds with a 400 (and not
+            'feedback_required'/'checkpoint_required'/'challenge_required').
         :raises QueryReturnedNotFoundException: When the server responds with a 404.
         :raises ConnectionException: When query repeatedly failed.
+
+        .. versionchanged:: 4.13
+           Added `use_post` parameter.
         """
         is_graphql_query = 'query_hash' in params and 'graphql/query' in path
+        is_doc_id_query = 'doc_id' in params and 'graphql/query' in path
         is_iphone_query = host == 'i.instagram.com'
-        is_other_query = not is_graphql_query and host == "www.instagram.com"
+        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
         try:
             self.do_sleep()
             if is_graphql_query:
                 self._rate_controller.wait_before_query(params['query_hash'])
+            if is_doc_id_query:
+                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')
-            resp = sess.get('https://{0}/{1}'.format(host, path), params=params, allow_redirects=False)
+            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 = ""
@@ -384,7 +456,7 @@ class InstaloaderContext:
                 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.")
+                        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)):
@@ -396,31 +468,26 @@ class InstaloaderContext:
                 response_headers.clear()
                 response_headers.update(resp.headers)
             if resp.status_code == 400:
-                raise QueryReturnedBadRequestException("400 Bad Request")
+                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("404 Not Found")
+                raise QueryReturnedNotFoundException(self._response_error(resp))
             if resp.status_code == 429:
-                raise TooManyRequestsException("429 Too Many Requests")
+                raise TooManyRequestsException(self._response_error(resp))
             if resp.status_code != 200:
-                raise ConnectionException("HTTP error code {}.".format(resp.status_code))
-            is_html_query = not is_graphql_query and not "__a" in params and host == "www.instagram.com"
-            if is_html_query:
-                # Extract JSON from HTML response
-                match = re.search('(?<={"raw":").*?(?<!\\\\)(?=")', resp.text)
-                if match is None:
-                    raise QueryReturnedNotFoundException("Could not find JSON data in html response.")
-                # Unescape escaped JSON string
-                unescaped_string = match.group(0).encode("utf-8").decode("unicode_escape")
-                resp_json = json.loads(unescaped_string)
-                return resp_json
+                raise ConnectionException(self._response_error(resp))
             else:
                 resp_json = resp.json()
             if 'status' in resp_json and resp_json['status'] != "ok":
-                if 'message' in resp_json:
-                    raise ConnectionException("Returned \"{}\" status, message \"{}\".".format(resp_json['status'],
-                                                                                               resp_json['message']))
-                else:
-                    raise ConnectionException("Returned \"{}\" status.".format(resp_json['status']))
+                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)
@@ -434,6 +501,8 @@ class InstaloaderContext:
                 if isinstance(err, TooManyRequestsException):
                     if is_graphql_query:
                         self._rate_controller.handle_429(params['query_hash'])
+                    if is_doc_id_query:
+                        self._rate_controller.handle_429(params['doc_id'])
                     if is_iphone_query:
                         self._rate_controller.handle_429('iphone')
                     if is_other_query:
@@ -445,15 +514,17 @@ class InstaloaderContext:
                 raise ConnectionException(error_string) from err
 
     def graphql_query(self, query_hash: str, variables: Dict[str, Any],
-                      referer: Optional[str] = None, rhx_gis: Optional[str] = None) -> Dict[str, Any]:
+                      referer: Optional[str] = None) -> Dict[str, Any]:
         """
         Do a GraphQL Query.
 
         :param query_hash: Query identifying hash.
         :param variables: Variables for the Query.
         :param referer: HTTP Referer, or None.
-        :param rhx_gis: 'rhx_gis' variable as somewhere returned by Instagram, needed to 'sign' request
         :return: The server's response dictionary.
+
+        .. versionchanged:: 4.13.1
+           Removed the `rhx_gis` parameter.
         """
         with copy_session(self._session, self.request_timeout) as tmpsession:
             tmpsession.headers.update(self._default_http_header(empty_session_only=True))
@@ -467,12 +538,6 @@ class InstaloaderContext:
 
             variables_json = json.dumps(variables, separators=(',', ':'))
 
-            if rhx_gis:
-                #self.log("rhx_gis {} query_hash {}".format(rhx_gis, query_hash))
-                values = "{}:{}".format(rhx_gis, variables_json)
-                x_instagram_gis = hashlib.md5(values.encode()).hexdigest()
-                tmpsession.headers['x-instagram-gis'] = x_instagram_gis
-
             resp_json = self.get_json('graphql/query',
                                       params={'query_hash': query_hash,
                                               'variables': variables_json},
@@ -481,10 +546,52 @@ class InstaloaderContext:
             self.error("GraphQL response did not contain a \"status\" field.")
         return resp_json
 
+    def doc_id_graphql_query(self, doc_id: str, variables: Dict[str, Any],
+                             referer: Optional[str] = None) -> Dict[str, Any]:
+        """
+        Do a doc_id-based GraphQL Query using method POST.
+
+        .. versionadded:: 4.13
+
+        :param doc_id: doc_id for the query.
+        :param variables: Variables for the Query.
+        :param referer: HTTP Referer, or None.
+        :return: The server's response dictionary.
+        """
+        csrf = next((c.value for c in self._session.cookies
+                     if c.name == 'csrftoken' and c.value), None)
+        if not csrf:
+            self._session.get('https://www.instagram.com/', timeout=self.request_timeout)
+            csrf = next((c.value for c in self._session.cookies
+                         if c.name == 'csrftoken' and c.value), '')
+
+        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'] = '*/*'
+            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
+
     def graphql_node_list(self, query_hash: str, query_variables: Dict[str, Any],
                           query_referer: Optional[str],
                           edge_extractor: Callable[[Dict[str, Any]], Dict[str, Any]],
-                          rhx_gis: Optional[str] = None,
+                          _rhx_gis: Optional[str] = None,
                           first_data: Optional[Dict[str, Any]] = None) -> Iterator[Dict[str, Any]]:
         """
         Retrieve a list of GraphQL nodes.
@@ -496,7 +603,7 @@ class InstaloaderContext:
         def _query():
             query_variables['first'] = self._graphql_page_length
             try:
-                return edge_extractor(self.graphql_query(query_hash, query_variables, query_referer, rhx_gis))
+                return edge_extractor(self.graphql_query(query_hash, query_variables, query_referer))
             except QueryReturnedBadRequestException:
                 new_page_length = int(self._graphql_page_length / 2)
                 if new_page_length >= 12:
@@ -581,6 +688,38 @@ class InstaloaderContext:
 
             return response
 
+    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.
+        """
+        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:
+            with self.get_anonymous_session() as anonymous_session:
+                resp = anonymous_session.get(url, headers=headers, allow_redirects=False)
+        except requests.exceptions.RequestException as err:
+            raise ConnectionException("Page request to {}: {}".format(url, err)) from err
+        if resp.status_code == 404:
+            raise QueryReturnedNotFoundException(self._response_error(resp))
+        if resp.status_code != 200:
+            raise ConnectionException(self._response_error(resp))
+        data: List[Dict[str, Any]] = []
+        for script in re.finditer(r'<script type="application/json"[^>]*>(.*?)</script>', resp.text, 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.
 
@@ -609,11 +748,11 @@ class InstaloaderContext:
         else:
             if resp.status_code == 403:
                 # suspected invalid URL signature
-                raise QueryReturnedForbiddenException("403 when accessing {}.".format(url))
+                raise QueryReturnedForbiddenException(self._response_error(resp))
             if resp.status_code == 404:
                 # 404 not worth retrying.
-                raise QueryReturnedNotFoundException("404 when accessing {}.".format(url))
-            raise ConnectionException("HTTP error code {}.".format(resp.status_code))
+                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.
@@ -639,22 +778,11 @@ class InstaloaderContext:
         else:
             if resp.status_code == 403:
                 # suspected invalid URL signature
-                raise QueryReturnedForbiddenException("403 when accessing {}.".format(url))
+                raise QueryReturnedForbiddenException(self._response_error(resp))
             if resp.status_code == 404:
                 # 404 not worth retrying.
-                raise QueryReturnedNotFoundException("404 when accessing {}.".format(url))
-            raise ConnectionException("HTTP error code {}.".format(resp.status_code))
-
-    @property
-    def root_rhx_gis(self) -> Optional[str]:
-        """rhx_gis string returned in the / query."""
-        if self.is_logged_in:
-            # At the moment, rhx_gis seems to be required for anonymous requests only. By returning None when logged
-            # in, we can save the root_rhx_gis lookup query.
-            return None
-        if self._root_rhx_gis is None:
-            self._root_rhx_gis = self.get_json('', {}).get('rhx_gis', '')
-        return self._root_rhx_gis or None
+                raise QueryReturnedNotFoundException(self._response_error(resp))
+            raise ConnectionException(self._response_error(resp))
 
 
 class RateController:

instaloader/lateststamps.py

@@ -18,6 +18,7 @@ class LatestStamps:
     POST_TIMESTAMP = 'post-timestamp'
     TAGGED_TIMESTAMP = 'tagged-timestamp'
     IGTV_TIMESTAMP = 'igtv-timestamp'
+    REELS_TIMESTAMP = 'reels-timestamp'
     STORY_TIMESTAMP = 'story-timestamp'
     ISO_FORMAT = '%Y-%m-%dT%H:%M:%S.%f%z'
 
@@ -87,6 +88,14 @@ class LatestStamps:
         """Sets timestamp of last download of a profile's tagged posts."""
         self._set_timestamp(profile_name, self.TAGGED_TIMESTAMP, timestamp)
 
+    def get_last_reels_timestamp(self, profile_name: str) -> datetime:
+        """Returns timestamp of last download of a profile's reels posts."""
+        return self._get_timestamp(profile_name, self.REELS_TIMESTAMP)
+
+    def set_last_reels_timestamp(self, profile_name: str, timestamp: datetime):
+        """Sets timestamp of last download of a profile's reels posts."""
+        self._set_timestamp(profile_name, self.REELS_TIMESTAMP, timestamp)
+
     def get_last_igtv_timestamp(self, profile_name: str) -> datetime:
         """Returns timestamp of last download of a profile's igtv posts."""
         return self._get_timestamp(profile_name, self.IGTV_TIMESTAMP)

instaloader/nodeiterator.py

@@ -7,11 +7,11 @@ from datetime import datetime, timedelta
 from lzma import LZMAError
 from typing import Any, Callable, Dict, Iterable, Iterator, NamedTuple, Optional, Tuple, TypeVar
 
-from .exceptions import AbortDownloadException, InvalidArgumentException, QueryReturnedBadRequestException
+from .exceptions import InvalidArgumentException
 from .instaloadercontext import InstaloaderContext
 
 class FrozenNodeIterator(NamedTuple):
-    query_hash: str
+    query_hash: Optional[str]
     query_variables: Dict
     query_referer: Optional[str]
     context_username: Optional[str]
@@ -19,6 +19,7 @@ class FrozenNodeIterator(NamedTuple):
     best_before: Optional[float]
     remaining_data: Optional[Dict]
     first_node: Optional[Dict]
+    doc_id: Optional[str]
 FrozenNodeIterator.query_hash.__doc__ = """The GraphQL ``query_hash`` parameter."""
 FrozenNodeIterator.query_variables.__doc__ = """The GraphQL ``query_variables`` parameter."""
 FrozenNodeIterator.query_referer.__doc__ = """The HTTP referer used for the GraphQL query."""
@@ -28,6 +29,7 @@ FrozenNodeIterator.best_before.__doc__ = """Date when parts of the stored nodes
 FrozenNodeIterator.remaining_data.__doc__ = \
     """The already-retrieved, yet-unprocessed ``edges`` and the ``page_info`` at time of freezing."""
 FrozenNodeIterator.first_node.__doc__ = """Node data of the first item, if an item has been produced."""
+FrozenNodeIterator.doc_id.__doc__ = """The GraphQL ``doc_id`` parameter."""
 
 T = TypeVar('T')
 
@@ -64,22 +66,27 @@ class NodeIterator(Iterator[T]):
     NodeIterators are matching if and only if they have the same magic.
 
     See also :func:`resumable_iteration` for a high-level context manager that handles a resumable iteration.
+
+    .. versionchanged: 4.13
+       Included support for `doc_id`-based queries (using POST method).
     """
 
-    _graphql_page_length = 50
+    _graphql_page_length = 12
     _shelf_life = timedelta(days=29)
 
     def __init__(self,
                  context: InstaloaderContext,
-                 query_hash: str,
+                 query_hash: Optional[str],
                  edge_extractor: Callable[[Dict[str, Any]], Dict[str, Any]],
                  node_wrapper: Callable[[Dict], T],
                  query_variables: Optional[Dict[str, Any]] = None,
                  query_referer: Optional[str] = None,
                  first_data: Optional[Dict[str, Any]] = None,
-                 is_first: Optional[Callable[[T, Optional[T]], bool]] = None):
+                 is_first: Optional[Callable[[T, Optional[T]], bool]] = None,
+                 doc_id: Optional[str] = None):
         self._context = context
         self._query_hash = query_hash
+        self._doc_id = doc_id
         self._edge_extractor = edge_extractor
         self._node_wrapper = node_wrapper
         self._query_variables = query_variables if query_variables is not None else {}
@@ -95,26 +102,38 @@ class NodeIterator(Iterator[T]):
         self._is_first = is_first
 
     def _query(self, after: Optional[str] = None) -> Dict:
+        if self._doc_id is not None:
+            return self._query_doc_id(self._doc_id, after)
+        else:
+            assert self._query_hash is not None
+            return self._query_query_hash(self._query_hash, after)
+
+    def _query_doc_id(self, doc_id: str, after: Optional[str] = None) -> Dict:
+        pagination_variables: Dict[str, Any] = {'__relay_internal__pv__PolarisFeedShareMenurelayprovider': False}
+        if after is not None:
+            pagination_variables['after'] = after
+            pagination_variables['before'] = None
+            pagination_variables['first'] = 12
+            pagination_variables['last'] = None
+        data = self._edge_extractor(
+            self._context.doc_id_graphql_query(
+                doc_id, {**self._query_variables, **pagination_variables}, self._query_referer
+            )
+        )
+        self._best_before = datetime.now() + NodeIterator._shelf_life
+        return data
+
+    def _query_query_hash(self, query_hash: str, after: Optional[str] = None) -> Dict:
         pagination_variables: Dict[str, Any] = {'first': NodeIterator._graphql_page_length}
         if after is not None:
             pagination_variables['after'] = after
-        try:
-            data = self._edge_extractor(
-                self._context.graphql_query(
-                    self._query_hash, {**self._query_variables, **pagination_variables}, self._query_referer
-                )
+        data = self._edge_extractor(
+            self._context.graphql_query(
+                query_hash, {**self._query_variables, **pagination_variables}, self._query_referer
             )
-            self._best_before = datetime.now() + NodeIterator._shelf_life
-            return data
-        except QueryReturnedBadRequestException:
-            new_page_length = int(NodeIterator._graphql_page_length / 2)
-            if new_page_length >= 12:
-                NodeIterator._graphql_page_length = new_page_length
-                self._context.error("HTTP Error 400 (Bad Request) on GraphQL Query. Retrying with shorter page length.",
-                                    repeat_at_end=False)
-                return self._query(after)
-            else:
-                raise
+        )
+        self._best_before = datetime.now() + NodeIterator._shelf_life
+        return data
 
     def __iter__(self):
         return self
@@ -184,6 +203,10 @@ class NodeIterator(Iterator[T]):
         """
         return self._node_wrapper(self._first_node) if self._first_node is not None else None
 
+    @staticmethod
+    def page_length() -> int:
+        return NodeIterator._graphql_page_length
+
     def freeze(self) -> FrozenNodeIterator:
         """Freeze the iterator for later resuming."""
         remaining_data = None
@@ -199,6 +222,7 @@ class NodeIterator(Iterator[T]):
             best_before=self._best_before.timestamp() if self._best_before else None,
             remaining_data=remaining_data,
             first_node=self._first_node,
+            doc_id=self._doc_id,
         )
 
     def thaw(self, frozen: FrozenNodeIterator) -> None:
@@ -216,7 +240,8 @@ class NodeIterator(Iterator[T]):
         if (self._query_hash != frozen.query_hash or
                 self._query_variables != frozen.query_variables or
                 self._query_referer != frozen.query_referer or
-                self._context.username != frozen.context_username):
+                self._context.username != frozen.context_username or
+                self._doc_id != frozen.doc_id):
             raise InvalidArgumentException("Mismatching resume information.")
         if not frozen.best_before:
             raise InvalidArgumentException("\"best before\" date missing.")
@@ -293,7 +318,7 @@ def resumable_iteration(context: InstaloaderContext,
             context.error("Warning: Not resuming from {}: {}".format(resume_file_path, exc))
     try:
         yield is_resuming, start_index
-    except (KeyboardInterrupt, AbortDownloadException):
+    except (Exception, KeyboardInterrupt):
         if os.path.dirname(resume_file_path):
             os.makedirs(os.path.dirname(resume_file_path), exist_ok=True)
         save(iterator.freeze(), resume_file_path)

instaloader/structures.py

@@ -20,7 +20,7 @@ class PostSidecarNode(NamedTuple):
     """Item of a Sidecar Post."""
     is_video: bool
     display_url: str
-    video_url: str
+    video_url: Optional[str]
 
 
 PostSidecarNode.is_video.__doc__ = "Whether this node is a video."
@@ -43,19 +43,91 @@ PostCommentAnswer.owner.__doc__ = "Owner :class:`Profile` of the comment."
 PostCommentAnswer.likes_count.__doc__ = "Number of likes on comment."
 
 
-class PostComment(NamedTuple):
-    id: int
-    created_at_utc: datetime
-    text: str
-    owner: 'Profile'
-    likes_count: int
-    answers: Iterator[PostCommentAnswer]
+class PostComment:
+    def __init__(self, context: 'InstaloaderContext', node: Dict[str, Any],
+                 answers: Iterator['PostCommentAnswer'], post: 'Post'):
+        self._context = context
+        self._node = node
+        self._answers = answers
+        self._post = post
 
+    @classmethod
+    def from_iphone_struct(
+        cls,
+        context: "InstaloaderContext",
+        media: Dict[str, Any],
+        answers: Iterator["PostCommentAnswer"],
+        post: "Post",
+    ):
+        return cls(
+            context=context,
+            node={
+                "id": int(media["pk"]),
+                "created_at": media["created_at"],
+                "text": media["text"],
+                "edge_liked_by": {
+                    "count": media["comment_like_count"],
+                },
+                "iphone_struct": media,
+            },
+            answers=answers,
+            post=post,
+        )
 
-for field in PostCommentAnswer._fields:
-    getattr(PostComment, field).__doc__ = getattr(PostCommentAnswer, field).__doc__  # pylint: disable=no-member
-PostComment.answers.__doc__ = r"Iterator which yields all :class:`PostCommentAnswer`\ s for the comment."
+    @property
+    def id(self) -> int:
+        """ ID number of comment. """
+        return self._node['id']
 
+    @property
+    def created_at_utc(self) -> datetime:
+        """ :class:`~datetime.datetime` when comment was created (UTC). """
+        return datetime.utcfromtimestamp(self._node['created_at'])
+
+    @property
+    def text(self):
+        """ Comment text. """
+        return self._node['text']
+
+    @property
+    def owner(self) -> "Profile":
+        """ Owner :class:`Profile` of the comment. """
+        if "iphone_struct" in self._node:
+            return Profile.from_iphone_struct(
+                self._context, self._node["iphone_struct"]["user"]
+            )
+        return Profile(self._context, self._node["owner"])
+
+    @property
+    def likes_count(self):
+        """ Number of likes on comment. """
+        return self._node.get('edge_liked_by', {}).get('count', 0)
+
+    @property
+    def answers(self) -> Iterator['PostCommentAnswer']:
+        """ Iterator which yields all :class:`PostCommentAnswer` for the comment. """
+        return self._answers
+
+    @property
+    def likes(self) -> Iterable['Profile']:
+        """
+        Iterate over all likes of a comment. A :class:`Profile` instance of each like is yielded.
+
+        .. versionadded:: 4.11
+        """
+        if self.likes_count != 0:
+            return NodeIterator(
+                self._context,
+                '5f0b1f6281e72053cbc07909c8d154ae',
+                lambda d: d['data']['comment']['edge_liked_by'],
+                lambda n: Profile(self._context, n),
+                {'comment_id': self.id},
+                'https://www.instagram.com/p/{0}/'.format(self._post.shortcode),
+            )
+        return []
+
+    def __repr__(self):
+        return f'<PostComment {self.id} of {self._post.shortcode}>'
 
 class PostLocation(NamedTuple):
     id: int
@@ -80,7 +152,7 @@ _hashtag_regex = re.compile(r"(?:#)((?:\w){1,150})")
 # support Unicode and a word/beginning of string delimiter at the beginning to ensure
 # that no email addresses join the list of mentions.
 # http://blog.jstassen.com/2016/03/code-regex-for-instagram-username-and-hashtags/
-_mention_regex = re.compile(r"(?:^|[^\w\n]|_)(?:@)(\w(?:(?:\w|(?:\.(?!\.))){0,28}(?:\w))?)", re.ASCII)
+_mention_regex = re.compile(r"(?:^|\W|_)(?:@)(\w(?:(?:\w|(?:\.(?!\.))){0,28}(?:\w))?)", re.ASCII)
 
 
 def _optional_normalize(string: Optional[str]) -> Optional[str]:
@@ -108,7 +180,7 @@ class Post:
     This class unifies access to the properties associated with a post. It implements == and is
     hashable.
 
-    :param context: :attr:`Instaloader.context` used for additional queries if neccessary..
+    :param context: :attr:`Instaloader.context` used for additional queries if necessary..
     :param node: Node structure, as returned by Instagram.
     :param owner_profile: The Profile of the owner, if already known at creation.
     """
@@ -160,21 +232,126 @@ class Post:
             "title": media.get("title"),
             "viewer_has_liked": media["has_liked"],
             "edge_media_preview_like": {"count": media["like_count"]},
+            "accessibility_caption": media.get("accessibility_caption"),
+            "comments": media.get("comment_count"),
             "iphone_struct": media,
         }
         with suppress(KeyError):
             fake_node["display_url"] = media['image_versions2']['candidates'][0]['url']
-        with suppress(KeyError):
+        with suppress(KeyError, TypeError):
             fake_node["video_url"] = media['video_versions'][-1]['url']
             fake_node["video_duration"] = media["video_duration"]
             fake_node["video_view_count"] = media["view_count"]
-        with suppress(KeyError):
-            fake_node["edge_sidecar_to_children"] = {"edges": [{"node": {
-                "display_url": node['image_versions2']['candidates'][0]['url'],
-                "is_video": media_types[node["media_type"]] == "GraphVideo",
-            }} for node in media["carousel_media"]]}
+        with suppress(KeyError, TypeError):
+            fake_node["edge_sidecar_to_children"] = {"edges": [{"node":
+                Post._convert_iphone_carousel(node, media_types)}
+                for node in media["carousel_media"]]}
         return cls(context, fake_node, Profile.from_iphone_struct(context, media["user"]) if "user" in media else None)
 
+    @staticmethod
+    def _convert_iphone_carousel(iphone_node: Dict[str, Any], media_types: Dict[int, str]) -> Dict[str, Any]:
+        fake_node = {
+            "display_url": iphone_node["image_versions2"]["candidates"][0]["url"],
+            "is_video": media_types[iphone_node["media_type"]] == "GraphVideo",
+        }
+        if "video_versions" in iphone_node and iphone_node["video_versions"] is not None:
+            fake_node["video_url"] = iphone_node["video_versions"][0]["url"]
+        return fake_node
+
+    @staticmethod
+    def _fetch_play_count_from_clips(context: 'InstaloaderContext', user_id: str,
+                                     shortcode: str) -> Optional[int]:
+        """Fetch play_count for a reel via the clips connection endpoint as a fallback."""
+        try:
+            resp = context.doc_id_graphql_query(
+                "27234427476213202",
+                {"data": {"include_feed_video": True, "page_size": 12,
+                           "target_user_id": str(user_id)}},
+            )
+            edges = ((resp.get("data") or {})
+                     .get("xdt_api__v1__clips__user__connection_v2") or {})
+            for edge in edges.get("edges") or []:
+                media = (edge.get("node") or {}).get("media") or {}
+                if media.get("code") == shortcode:
+                    return media.get("play_count")
+        except (ConnectionException, BadResponseException):
+            pass
+        return None
+
+    @staticmethod
+    def _normalize_post_data(media: Dict[str, Any], context: 'InstaloaderContext') -> Dict[str, Any]:
+        """Normalize a Polaris media item to a legacy-compatible node, preserving the source structure."""
+        media_types = {1: "GraphImage", 2: "GraphVideo", 8: "GraphSidecar"}
+        media_type = media.get("media_type")
+        typename = None
+        if isinstance(media_type, int):
+            typename = media_types.get(media_type)
+        if not typename:
+            raise BadResponseException(f"Unknown media_type in metadata: {media_type}.")
+        pic_json: Dict[str, Any] = media.copy()
+        pic_json["shortcode"] = media["code"]
+        pic_json["id"] = media["pk"]
+        pic_json["__typename"] = typename
+        pic_json["is_video"] = media_type == 2
+        pic_json["taken_at_timestamp"] = media["taken_at"]
+        pic_json["owner"] = {
+            "id": media["user"]["pk"],
+            "username": media["user"].get("username", ""),
+            "full_name": media["user"].get("full_name", ""),
+        }
+        candidates = (media.get("image_versions2") or {}).get("candidates") or []
+        pic_json["display_url"] = candidates[0]["url"] if candidates else None
+        video_versions = media.get("video_versions") or []
+        pic_json["video_url"] = video_versions[0]["url"] if video_versions else None
+        pic_json["video_duration"] = media.get("video_duration")
+        pic_json["video_view_count"] = media.get("view_count")
+        pic_json["video_play_count"] = media.get("play_count")
+        if media_type == 2 and pic_json["video_view_count"] is None:
+            pic_json["video_play_count"] = Post._fetch_play_count_from_clips(
+                context, media["user"]["pk"], media["code"]
+            )
+        caption = media.get("caption")
+        caption_text = caption.get("text") if isinstance(caption, dict) else None
+        pic_json["edge_media_to_caption"] = (
+            {"edges": [{"node": {"text": caption_text}}]} if caption_text is not None
+            else {"edges": []}
+        )
+        pic_json["edge_media_preview_like"] = {"count": media.get("like_count") or 0}
+        pic_json["edge_media_to_parent_comment"] = {
+            "count": media.get("comment_count") or 0,
+            "edges": [],
+        }
+        if media.get("has_liked") is not None:
+            pic_json["viewer_has_liked"] = media["has_liked"]
+        carousel = media.get("carousel_media") or []
+        if carousel:
+            carousel_nodes = []
+            for item in carousel:
+                item_type = item.get("media_type", 1)
+                node: Dict[str, Any] = {
+                    "shortcode": item.get("code", ""),
+                    "__typename": media_types.get(item_type, "GraphImage"),
+                    "is_video": item_type == 2,
+                }
+                item_candidates = (item.get("image_versions2") or {}).get("candidates") or []
+                node["display_url"] = item_candidates[0]["url"] if item_candidates else ""
+                item_videos = item.get("video_versions") or []
+                node["video_url"] = item_videos[0]["url"] if item_videos else None
+                if item.get("accessibility_caption") is not None:
+                    node["accessibility_caption"] = item["accessibility_caption"]
+                carousel_nodes.append({"node": node})
+            pic_json["edge_sidecar_to_children"] = {"edges": carousel_nodes}
+        tagged = (media.get("usertags") or {}).get("in") or []
+        if tagged:
+            pic_json["edge_media_to_tagged_user"] = {
+                "edges": [
+                    {"node": {"user": {"username": t["user"]["username"].lower()}}}
+                    for t in tagged
+                    if (t.get("user") or {}).get("username")
+                ]
+            }
+        return pic_json
+
     @staticmethod
     def shortcode_to_mediaid(code: str) -> int:
         if len(code) > 11:
@@ -236,13 +413,18 @@ class Post:
 
     def _obtain_metadata(self):
         if not self._full_metadata_dict:
-            pic_json = self._context.graphql_query(
-                '2b0673e0dc4580674a88d426fe00ea90',
-                {'shortcode': self.shortcode}
+            resp = self._context.doc_id_graphql_query(
+                "27128499623469141",
+                {
+                    "shortcode": self.shortcode,
+                    "__relay_internal__pv__PolarisAIGMMediaWebLabelEnabledrelayprovider": False,
+                },
             )
-            self._full_metadata_dict = pic_json['data']['shortcode_media']
-            if self._full_metadata_dict is None:
+            web_info = (resp.get("data") or {}).get("xdt_api__v1__media__shortcode__web_info") or {}
+            items = web_info.get("items")
+            if not items:
                 raise BadResponseException("Fetching Post metadata failed.")
+            self._full_metadata_dict = Post._normalize_post_data(items[0], self._context)
             if self.shortcode != self._full_metadata_dict['shortcode']:
                 self._node.update(self._full_metadata_dict)
                 raise PostChangedException
@@ -258,7 +440,7 @@ class Post:
         if not self._context.iphone_support:
             raise IPhoneSupportDisabledException("iPhone support is disabled.")
         if not self._context.is_logged_in:
-            raise LoginRequiredException("--login required to access iPhone media info endpoint.")
+            raise LoginRequiredException("Login required to access iPhone media info endpoint.")
         if not self._iphone_struct_:
             data = self._context.get_iphone_json(path='api/v1/media/{}/info/'.format(self.mediaid), params={})
             self._iphone_struct_ = data['items'][0]
@@ -419,14 +601,14 @@ class Post:
 
     @property
     def caption_hashtags(self) -> List[str]:
-        """List of all lowercased hashtags (without preceeding #) that occur in the Post's caption."""
+        """List of all lowercased hashtags (without preceding #) that occur in the Post's caption."""
         if not self.caption:
             return []
         return _hashtag_regex.findall(self.caption.lower())
 
     @property
     def caption_mentions(self) -> List[str]:
-        """List of all lowercased profiles that are mentioned in the Post's caption, without preceeding @."""
+        """List of all lowercased profiles that are mentioned in the Post's caption, without preceding @."""
         if not self.caption:
             return []
         return _mention_regex.findall(self.caption.lower())
@@ -509,6 +691,15 @@ class Post:
             return self._field('video_view_count')
         return None
 
+    @property
+    def video_play_count(self) -> Optional[int]:
+        """Play count of the video, or None.
+
+        .. versionadded:: 4.14.3"""
+        if self.is_video:
+            return self._field('video_play_count')
+        return None
+
     @property
     def video_duration(self) -> Optional[float]:
         """Duration of the video in seconds, or None.
@@ -545,16 +736,77 @@ class Post:
         except KeyError:
             return self._field('edge_media_to_comment', 'count')
 
+    def _get_comments_via_iphone_endpoint(self) -> Iterable[PostComment]:
+        """
+        Iterate over all comments of the post via an iPhone endpoint.
+
+        .. versionadded:: 4.10.3
+           fallback for :issue:`2125`.
+        """
+        def _query(min_id=None):
+            pagination_params = {"min_id": min_id} if min_id is not None else {}
+            return self._context.get_iphone_json(
+                f"api/v1/media/{self.mediaid}/comments/",
+                {
+                    "can_support_threading": "true",
+                    "permalink_enabled": "false",
+                    **pagination_params,
+                },
+            )
+
+        def _answers(comment_node):
+            def _answer(child_comment):
+                return PostCommentAnswer(
+                    id=int(child_comment["pk"]),
+                    created_at_utc=datetime.utcfromtimestamp(child_comment["created_at"]),
+                    text=child_comment["text"],
+                    owner=Profile.from_iphone_struct(self._context, child_comment["user"]),
+                    likes_count=child_comment["comment_like_count"],
+                )
+
+            child_comment_count = comment_node["child_comment_count"]
+            if child_comment_count == 0:
+                return
+            preview_child_comments = comment_node["preview_child_comments"]
+            if child_comment_count == len(preview_child_comments):
+                yield from (
+                    _answer(child_comment) for child_comment in preview_child_comments
+                )
+                return
+            pk = comment_node["pk"]
+            answers_json = self._context.get_iphone_json(
+                f"api/v1/media/{self.mediaid}/comments/{pk}/child_comments/",
+                {"max_id": ""},
+            )
+            yield from (
+                _answer(child_comment) for child_comment in answers_json["child_comments"]
+            )
+
+        def _paginated_comments(comments_json):
+            for comment_node in comments_json.get("comments", []):
+                yield PostComment.from_iphone_struct(
+                    self._context, comment_node, _answers(comment_node), self
+                )
+
+            next_min_id = comments_json.get("next_min_id")
+            if next_min_id:
+                yield from _paginated_comments(_query(next_min_id))
+
+        return _paginated_comments(_query())
+
     def get_comments(self) -> Iterable[PostComment]:
-        r"""Iterate over all comments of the post.
+        """Iterate over all comments of the post.
 
         Each comment is represented by a PostComment NamedTuple with fields text (string), created_at (datetime),
-        id (int), owner (:class:`Profile`) and answers (:class:`~typing.Iterator`\ [:class:`PostCommentAnswer`])
+        id (int), owner (:class:`Profile`) and answers (:class:`~typing.Iterator` [:class:`PostCommentAnswer`])
         if available.
 
         .. versionchanged:: 4.7
            Change return type to ``Iterable``.
         """
+        if not self._context.is_logged_in:
+            raise LoginRequiredException("Login required to access comments of a post.")
+
         def _postcommentanswer(node):
             return PostCommentAnswer(id=int(node['id']),
                                      created_at_utc=datetime.utcfromtimestamp(node['created_at']),
@@ -584,18 +836,28 @@ class Post:
             )
 
         def _postcomment(node):
-            return PostComment(*_postcommentanswer(node),
-                               answers=_postcommentanswers(node))
+            return PostComment(context=self._context, node=node,
+                               answers=_postcommentanswers(node), post=self)
         if self.comments == 0:
             # Avoid doing additional requests if there are no comments
             return []
 
-        comment_edges = self._field('edge_media_to_comment', 'edges')
+        try:
+            comment_edges = self._field("edge_media_to_parent_comment", "edges")
+        except KeyError:
+            comment_edges = self._field("edge_media_to_comment", "edges")
+
         answers_count = sum(edge['node'].get('edge_threaded_comments', {}).get('count', 0) for edge in comment_edges)
 
         if self.comments == len(comment_edges) + answers_count:
             # If the Post's metadata already contains all parent comments, don't do GraphQL requests to obtain them
             return [_postcomment(comment['node']) for comment in comment_edges]
+
+        if self.comments > NodeIterator.page_length():
+            # comments pagination via our graphql query does not work reliably anymore (issue #2125), fallback to an
+            # iphone endpoint if needed.
+            return self._get_comments_via_iphone_endpoint()
+
         return NodeIterator(
             self._context,
             '97b41c52301f77ce508f55e66d17620e',
@@ -613,7 +875,7 @@ class Post:
            Require being logged in (as required by Instagram).
         """
         if not self._context.is_logged_in:
-            raise LoginRequiredException("--login required to access likes of a post.")
+            raise LoginRequiredException("Login required to access likes of a post.")
         if self.likes == 0:
             # Avoid doing additional requests if there are no comments
             return
@@ -678,7 +940,11 @@ class Post:
 
     @property
     def is_pinned(self) -> bool:
-        """True if this Post has been pinned by at least one user.
+        """
+        .. deprecated: 4.10.3
+           This information is not returned by IG anymore
+
+        Used to return True if this Post has been pinned by at least one user, now likely returns always false.
 
         .. versionadded: 4.9.2"""
         return 'pinned_for_users' in self._node and bool(self._node['pinned_for_users'])
@@ -712,7 +978,8 @@ class Profile:
     Also, this class implements == and is hashable.
     """
     def __init__(self, context: InstaloaderContext, node: Dict[str, Any]):
-        assert 'username' in node
+        assert "username" in node
+        assert "id" in node or "pk" in node
         self._context = context
         self._has_public_story: Optional[bool] = None
         self._node = node
@@ -732,10 +999,30 @@ class Profile:
         :param username: Username
         :raises: :class:`ProfileNotExistsException`
         """
-        # pylint:disable=protected-access
-        profile = cls(context, {'username': username.lower()})
-        profile._obtain_metadata()  # to raise ProfileNotExistsException now in case username is invalid
-        return profile
+        # Resolve the profile through its public web page, which Instagram renders with the
+        # profile embedded. The web_profile_info endpoint previously used here is refused
+        # with HTTP 400 for some professional profiles, and with HTTP 401 or 429 for some
+        # sessions, both anonymously and when logged in.
+        try:
+            page = context.get_page_data("{0}/".format(username.lower()))
+        except QueryReturnedNotFoundException:
+            page = []
+        # The page embeds two queries for the profile: one for its details and one for its
+        # posts.
+        user: Dict[str, Any] = {}
+        for data in page:
+            user.update(data.get("xig_user_by_username") or {})
+        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):
@@ -748,16 +1035,16 @@ class Profile:
         """
         if profile_id in context.profile_id_cache:
             return context.profile_id_cache[profile_id]
-        data = context.graphql_query('7c16654f22c819fb63d1183034a5162f',
-                                     {'user_id': str(profile_id),
-                                      'include_chaining': False,
-                                      'include_reel': True,
-                                      'include_suggested_users': False,
-                                      'include_logged_out_extras': False,
-                                      'include_highlight_reels': False},
-                                     rhx_gis=context.root_rhx_gis)['data']['user']
-        if data:
-            profile = cls(context, data['reel']['owner'])
+        # Resolve the current username from the user id, then load the full profile.
+        # The GraphQL user query previously used here started responding with HTTP 400.
+        try:
+            user = context.get_json(
+                "api/v1/users/{0}/info/".format(profile_id), params={}
+            ).get('user')
+        except QueryReturnedNotFoundException:
+            user = None
+        if user and user.get('username'):
+            profile = cls.from_username(context, user['username'])
         else:
             raise ProfileNotExistsException("No profile found, the user may have blocked you (ID: " +
                                             str(profile_id) + ").")
@@ -786,7 +1073,7 @@ class Profile:
 
         .. versionadded:: 4.5.2"""
         if not context.is_logged_in:
-            raise LoginRequiredException("--login required to access own profile.")
+            raise LoginRequiredException("Login required to access own profile.")
         return cls(context, context.graphql_query("d6f4427fbe92d846298cf93df0b937d3", {})["data"]["user"])
 
     def _asdict(self):
@@ -803,11 +1090,41 @@ class Profile:
     def _obtain_metadata(self):
         try:
             if not self._has_full_metadata:
-                metadata = self._context.get_iphone_json(f'api/v1/users/web_profile_info/?username={self.username}',
-                                                         params={})
-                if metadata['data']['user'] is None:
+                if not self._context.is_logged_in:
+                    # Anonymous access: the web_profile_info endpoint returns the full
+                    # node in the legacy format and still works, unlike the GraphQL
+                    # profile query.
+                    try:
+                        data = self._context.get_json(
+                            "api/v1/users/web_profile_info/",
+                            params={"username": self.username},
+                        ).get('data')
+                    except QueryReturnedNotFoundException as err:
+                        raise ProfileNotExistsException(
+                            'Profile {} does not exist.'.format(self.username)) from err
+                    user_data = data.get('user') if data else None
+                    if user_data is None:
+                        raise ProfileNotExistsException('Profile {} does not exist.'.format(self.username))
+                    self._node = user_data
+                    self._has_full_metadata = True
+                    return
+                user_id = self._node.get('id') or self._node.get('pk')
+                variables = {
+                    "id": str(user_id),
+                    "render_surface": "PROFILE",
+                    "__relay_internal__pv__PolarisCannesGuardianExperienceEnabledrelayprovider": True,
+                    "__relay_internal__pv__PolarisCASB976ProfileEnabledrelayprovider": False,
+                    "__relay_internal__pv__PolarisRepostsConsumptionEnabledrelayprovider": False,
+                    "__relay_internal__pv__PolarisWebSchoolsEnabledrelayprovider": False,
+                    "enable_integrity_filters": True,
+                }
+                data = self._context.doc_id_graphql_query('27937681195819736', variables)
+                if data is None:
+                    raise QueryReturnedNotFoundException('GraphQL query returned None')
+                user_data = data.get('data', {}).get('user')
+                if user_data is None:
                     raise ProfileNotExistsException('Profile {} does not exist.'.format(self.username))
-                self._node = metadata['data']['user']
+                self._node = self._normalize_profile_data(user_data)
                 self._has_full_metadata = True
         except (QueryReturnedNotFoundException, KeyError) as err:
             top_search_results = TopSearchResults(self._context, self.username)
@@ -822,6 +1139,45 @@ class Profile:
                                                         ', '.join(similar_profiles[0:5]))) from err
             raise ProfileNotExistsException('Profile {} does not exist.'.format(self.username)) from err
 
+    @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:
+            normalized['id'] = normalized['pk']
+        if 'edge_owner_to_timeline_media' not in normalized and 'media_count' in normalized:
+            normalized['edge_owner_to_timeline_media'] = {'count': normalized['media_count']}
+        if 'edge_felix_video_timeline' not in normalized:
+            normalized['edge_felix_video_timeline'] = {'count': 0}
+        if 'edge_followed_by' not in normalized and 'follower_count' in normalized:
+            normalized['edge_followed_by'] = {'count': normalized['follower_count']}
+        if 'edge_follow' not in normalized and 'following_count' in normalized:
+            normalized['edge_follow'] = {'count': normalized['following_count']}
+        if 'is_business_account' not in normalized and 'is_business' in normalized:
+            normalized['is_business_account'] = normalized['is_business']
+        if 'business_category_name' not in normalized and 'category' in normalized:
+            normalized['business_category_name'] = normalized['category']
+        friendship = normalized.get('friendship_status', {}) or {}
+        if 'followed_by_viewer' not in normalized:
+            normalized['followed_by_viewer'] = friendship.get('following', False)
+        if 'follows_viewer' not in normalized:
+            normalized['follows_viewer'] = friendship.get('followed_by', False)
+        if 'blocked_by_viewer' not in normalized:
+            normalized['blocked_by_viewer'] = friendship.get('blocking', False)
+        if 'has_blocked_viewer' not in normalized:
+            normalized['has_blocked_viewer'] = False
+        if 'has_requested_viewer' not in normalized:
+            normalized['has_requested_viewer'] = friendship.get('incoming_request', False)
+        if 'requested_by_viewer' not in normalized:
+            normalized['requested_by_viewer'] = friendship.get('outgoing_request', False)
+        if 'profile_pic_url_hd' not in normalized:
+            hd_info = normalized.get('hd_profile_pic_url_info')
+            if hd_info and 'url' in hd_info:
+                normalized['profile_pic_url_hd'] = hd_info['url']
+            elif 'profile_pic_url' in normalized:
+                normalized['profile_pic_url_hd'] = normalized['profile_pic_url']
+        return normalized
+
     def _metadata(self, *keys) -> Any:
         try:
             d = self._node
@@ -840,7 +1196,7 @@ class Profile:
         if not self._context.iphone_support:
             raise IPhoneSupportDisabledException("iPhone support is disabled.")
         if not self._context.is_logged_in:
-            raise LoginRequiredException("--login required to access iPhone profile info endpoint.")
+            raise LoginRequiredException("Login required to access iPhone profile info endpoint.")
         if not self._iphone_struct_:
             data = self._context.get_iphone_json(path='api/v1/users/{}/info/'.format(self.userid), params={})
             self._iphone_struct_ = data['user']
@@ -912,7 +1268,7 @@ class Profile:
     @property
     def biography_hashtags(self) -> List[str]:
         """
-        List of all lowercased hashtags (without preceeding #) that occur in the Profile's biography.
+        List of all lowercased hashtags (without preceding #) that occur in the Profile's biography.
 
         .. versionadded:: 4.10
         """
@@ -923,7 +1279,7 @@ class Profile:
     @property
     def biography_mentions(self) -> List[str]:
         """
-        List of all lowercased profiles that are mentioned in the Profile's biography, without preceeding @.
+        List of all lowercased profiles that are mentioned in the Profile's biography, without preceding @.
 
         .. versionadded:: 4.10
         """
@@ -1030,15 +1386,52 @@ class Profile:
 
         :rtype: NodeIterator[Post]"""
         self._obtain_metadata()
+        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"),
+            )
         return NodeIterator(
-            self._context,
-            '003056d32c2554def87228bc3fd9668a',
-            lambda d: d['data']['user']['edge_owner_to_timeline_media'],
-            lambda n: Post(self._context, n, self),
-            {'id': self.userid},
-            'https://www.instagram.com/{0}/'.format(self.username),
-            self._metadata('edge_owner_to_timeline_media'),
-            Profile._make_is_newest_checker()
+            context=self._context,
+            edge_extractor=lambda d: d["data"]["xdt_api__v1__feed__user_timeline_graphql_connection"],
+            node_wrapper=lambda n: Post.from_iphone_struct(self._context, n),
+            # The query and variables that the web app sends for a profile's posts tab
+            # (PolarisProfilePostsTabContentQuery_connection). Instagram answers the
+            # previous query, 7898261790222653, with "execution error".
+            query_variables={
+                "data": {
+                    "count": 12,
+                    "include_reel_media_seen_timestamp": True,
+                    "include_relationship_info": True,
+                    "latest_besties_reel_media": True,
+                    "latest_reel_media": True,
+                },
+                "first": 12,
+                "include_multi_captions": True,
+                "username": self.username,
+                "__relay_internal__pv__PolarisMultiCaptionCarouselEnabledrelayprovider": True,
+                "__relay_internal__pv__PolarisShortDramaEnabledrelayprovider": 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="28975909992013618",
+            query_hash=None,
         )
 
     def get_saved_posts(self) -> NodeIterator[Post]:
@@ -1047,7 +1440,7 @@ class Profile:
         :rtype: NodeIterator[Post]"""
 
         if self.username != self._context.username:
-            raise LoginRequiredException("--login={} required to get that profile's saved posts.".format(self.username))
+            raise LoginRequiredException(f"Login as {self.username} required to get that profile's saved posts.")
 
         return NodeIterator(
             self._context,
@@ -1075,6 +1468,30 @@ class Profile:
             is_first=Profile._make_is_newest_checker()
         )
 
+    def get_reels(self) -> NodeIterator[Post]:
+        """Retrieve all reels from a profile.
+
+        :rtype: NodeIterator[Post]
+
+        .. versionadded:: 4.14.0
+
+        """
+        self._obtain_metadata()
+        return NodeIterator(
+            context = self._context,
+            edge_extractor = lambda d: d['data']['xdt_api__v1__clips__user__connection_v2'],
+            # Reels post info is incomplete relative to regular posts so we create a Post from the shortcode
+            # and fetch the additional metadata with an additional API request per Reel
+            node_wrapper = lambda n: Post.from_shortcode(context=self._context, shortcode=n["media"]["code"]),
+            query_variables = {'data': {
+                'page_size': 12, 'include_feed_video': True, "target_user_id": str(self.userid)}},
+            query_referer = 'https://www.instagram.com/{0}/'.format(self.username),
+            is_first = Profile._make_is_newest_checker(),
+            # fb_api_req_friendly_name=PolarisProfileReelsTabContentQuery_connection
+            doc_id = '7845543455542541',
+            query_hash = None,
+        )
+
     def get_igtv_posts(self) -> NodeIterator[Post]:
         """Retrieve all IGTV posts.
 
@@ -1107,7 +1524,7 @@ class Profile:
         .. versionadded:: 4.10
         """
         if not self._context.is_logged_in:
-            raise LoginRequiredException("--login required to get a profile's followers.")
+            raise LoginRequiredException("Login required to get a profile's followers.")
         self._obtain_metadata()
         return NodeIterator(
             self._context,
@@ -1126,7 +1543,7 @@ class Profile:
         :rtype: NodeIterator[Profile]
         """
         if not self._context.is_logged_in:
-            raise LoginRequiredException("--login required to get a profile's followers.")
+            raise LoginRequiredException("Login required to get a profile's followers.")
         self._obtain_metadata()
         return NodeIterator(
             self._context,
@@ -1145,7 +1562,7 @@ class Profile:
         :rtype: NodeIterator[Profile]
         """
         if not self._context.is_logged_in:
-            raise LoginRequiredException("--login required to get a profile's followees.")
+            raise LoginRequiredException("Login required to get a profile's followees.")
         self._obtain_metadata()
         return NodeIterator(
             self._context,
@@ -1164,7 +1581,7 @@ class Profile:
         .. versionadded:: 4.4
         """
         if not self._context.is_logged_in:
-            raise LoginRequiredException("--login required to get a profile's similar accounts.")
+            raise LoginRequiredException("Login required to get a profile's similar accounts.")
         self._obtain_metadata()
         yield from (Profile(self._context, edge["node"]) for edge in
                     self._context.graphql_query("ad99dd9d3646cc3c0dda65debcd266a7",
@@ -1243,7 +1660,7 @@ class StoryItem:
         if not self._context.iphone_support:
             raise IPhoneSupportDisabledException("iPhone support is disabled.")
         if not self._context.is_logged_in:
-            raise LoginRequiredException("--login required to access iPhone media info endpoint.")
+            raise LoginRequiredException("Login required to access iPhone media info endpoint.")
         if not self._iphone_struct_:
             data = self._context.get_iphone_json(
                 path='api/v1/feed/reels_media/?reel_ids={}'.format(self.owner_id), params={}
@@ -1340,7 +1757,7 @@ class StoryItem:
     @property
     def caption_hashtags(self) -> List[str]:
         """
-        List of all lowercased hashtags (without preceeding #) that occur in the StoryItem's caption.
+        List of all lowercased hashtags (without preceding #) that occur in the StoryItem's caption.
 
         .. versionadded:: 4.10
         """
@@ -1351,7 +1768,7 @@ class StoryItem:
     @property
     def caption_mentions(self) -> List[str]:
         """
-        List of all lowercased profiles that are mentioned in the StoryItem's caption, without preceeding @.
+        List of all lowercased profiles that are mentioned in the StoryItem's caption, without preceding @.
 
         .. versionadded:: 4.10
         """
@@ -1650,11 +2067,11 @@ class Hashtag:
     @classmethod
     def from_name(cls, context: InstaloaderContext, name: str):
         """
-        Create a Hashtag instance from a given hashtag name, without preceeding '#'. Raises an Exception if there is no
+        Create a Hashtag instance from a given hashtag name, without preceding '#'. Raises an Exception if there is no
         hashtag with the given name.
 
         :param context: :attr:`Instaloader.context`
-        :param name: Hashtag, without preceeding '#'
+        :param name: Hashtag, without preceding '#'
         :raises: :class:`QueryReturnedNotFoundException`
         """
         # pylint:disable=protected-access
@@ -1664,11 +2081,13 @@ class Hashtag:
 
     @property
     def name(self):
-        """Hashtag name lowercased, without preceeding '#'"""
+        """Hashtag name lowercased, without preceding '#'"""
         return self._node["name"].lower()
 
     def _query(self, params):
-        json_response = self._context.get_json("explore/tags/{0}/".format(self.name), params)
+        json_response = self._context.get_iphone_json(
+            "api/v1/tags/web_info/", {**params, "tag_name": self.name}
+        )
         return json_response["graphql"]["hashtag"] if "graphql" in json_response else json_response["data"]
 
     def _obtain_metadata(self):
@@ -1991,7 +2410,7 @@ def load_structure(context: InstaloaderContext, json_structure: dict) -> JsonExp
     """Loads a :class:`Post`, :class:`Profile`, :class:`StoryItem`, :class:`Hashtag` or :class:`FrozenNodeIterator` from
     a json structure.
 
-    :param context: :attr:`Instaloader.context` linked to the new object, used for additional queries if neccessary.
+    :param context: :attr:`Instaloader.context` linked to the new object, used for additional queries if necessary.
     :param json_structure: Instaloader JSON structure
 
     .. versionadded:: 4.8
@@ -2021,7 +2440,7 @@ def load_structure_from_file(context: InstaloaderContext, filename: str) -> Json
     """Loads a :class:`Post`, :class:`Profile`, :class:`StoryItem`, :class:`Hashtag` or :class:`FrozenNodeIterator` from
     a '.json' or '.json.xz' file that has been saved by :func:`save_structure_to_file`.
 
-    :param context: :attr:`Instaloader.context` linked to the new object, used for additional queries if neccessary.
+    :param context: :attr:`Instaloader.context` linked to the new object, used for additional queries if necessary.
     :param filename: Filename, ends in '.json' or '.json.xz'
     """
     compressed = filename.endswith('.xz')

setup.py

@@ -18,10 +18,13 @@ def get_version():
     raise SystemExit("Could not find version string.")
 
 
-if sys.version_info < (3, 8):
-    sys.exit('Instaloader requires Python >= 3.8.')
+if sys.version_info < (3, 10):
+    sys.exit('Instaloader requires Python >= 3.10.')
 
-requirements = ['requests>=2.4']
+requirements = ['requests>=2.25']
+optional_requirements = {
+    'browser_cookie3': ['browser_cookie3>=0.19.1'],
+}
 
 keywords = (['instagram', 'instagram-scraper', 'instagram-client', 'instagram-feed', 'downloader', 'videos', 'photos',
              'pictures', 'instagram-user-photos', 'instagram-photos', 'instagram-metadata', 'instagram-downloader',
@@ -43,7 +46,8 @@ setup(
                 'from Instagram.',
     long_description=open(os.path.join(SRC, 'README.rst')).read(),
     install_requires=requirements,
-    python_requires='>=3.8',
+    python_requires='>=3.10',
+    extras_require=optional_requirements,
     entry_points={'console_scripts': ['instaloader=instaloader.__main__:main']},
     zip_safe=False,
     keywords=keywords,
@@ -54,10 +58,12 @@ setup(
         'Intended Audience :: Developers',
         'License :: OSI Approved :: MIT License',
         'Operating System :: OS Independent',
-        'Programming Language :: Python :: 3.8',
-        '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

@@ -1,214 +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
-
-
-if __name__ == '__main__':
-    unittest.main()