Release of version 4.15.2

When Instagram returns {"data": null} for a shortcode metadata query (e.g. under
rate limiting, or for an unavailable post), response["data"]["xdt_shortcode_media"]
raised a raw TypeError before the existing `if pic_json is None` check could run.
Guard the intermediate "data" so the clean BadResponseException is raised instead,
which the download loop already handles.

.github/workflows/documentation.yml

@@ -14,11 +14,11 @@ jobs:
       - name: "Setup Python"
         uses: actions/setup-python@v5
         with:
-          python-version: 3.12
+          python-version: 3.14
           cache: 'pipenv'
       - name: "Install Dependencies"
         run: |
-          python -m pip install pipenv==2023.12.1
+          python -m pip install pipenv==2025.0.4
           pipenv --python `python --version | grep -Eo '3\.[0-9]+'` sync --dev
       - name: "Build Documentation"
         run: pipenv --python `python --version | grep -Eo '3\.[0-9]+'` run make -C docs html SPHINXOPTS="-W -n"

.github/workflows/lint.yml

@@ -9,7 +9,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13", "3.14"]
     steps:
       - name: Checkout Instaloader Repository
         uses: actions/checkout@v4
@@ -20,9 +20,10 @@ jobs:
           cache: 'pipenv'
       - name: Install Dependencies
         run: |
-          python -m pip install pipenv==2023.12.1
+          python -m pip install pipenv==2025.0.4
           pipenv --python `python --version | grep -Eo '3\.[0-9]+'` sync --dev
       - name: PyLint
+        if: matrix.python-version != '3.9'
         run: pipenv --python `python --version | grep -Eo '3\.[0-9]+'` run pylint instaloader
       - name: MyPy
         run: pipenv --python `python --version | grep -Eo '3\.[0-9]+'` run mypy -m instaloader

.github/workflows/packages.yml

@@ -15,7 +15,7 @@ jobs:
       - name: "Setup Python"
         uses: actions/setup-python@v5
         with:
-          python-version: 3.12
+          python-version: 3.14
       - name: "Get the tagged version"
         id: get_version
         env:
@@ -23,11 +23,11 @@ jobs:
         run: echo "VERSION=${GITHUB_REF/refs\/tags\/v/}" >> $GITHUB_OUTPUT
         shell: bash
       - name: "Install Dependencies"
-        run: python -m pip install setuptools
+        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/windows_exe.yml

@@ -12,7 +12,7 @@ jobs:
       - name: Setup Python
         uses: actions/setup-python@v5
         with:
-          python-version: "3.12"
+          python-version: "3.14"
           cache: 'pipenv'
           architecture: x64
       - name: Get the tagged version
@@ -25,25 +25,15 @@ jobs:
         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@v2
         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,

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
 
@@ -124,11 +124,30 @@ Supporters
 .. current-sponsors-start
 
 | Instaloader is proudly sponsored by
-|  `@rocketapi-io <https://github.com/rocketapi-io>`__
+
+.. 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==2023.12.1",
+commands = ["pip install pipenv==2025.0.4",
             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/basic-usage.rst

@@ -92,11 +92,14 @@ 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
@@ -122,7 +125,8 @@ Instaloader supports the following targets:
 
 - ``-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
 
@@ -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)

docs/cli-options.rst

@@ -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.
@@ -202,22 +208,24 @@ Instead of :option:`--login`, it is possible to use
 
 .. option:: --load-cookies BROWSER-NAME, -b BROWSER-NAME
 
-   Use Instagram cookie in your browser to login.
-   This feature requires the browser_cookie3 library.
-   Compatible with :option:`--cookiefile` if you want to load cookies from browser profiles.
-   Incompatible with :option:`--login` due to potential username mismatch between user input and browser login.
-   Supported browsers: Brave, Chrome, Chromium, Edge, Firefox, LibreWolf, Opera, Opera_GX, Safari and Vivaldi.
+   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`.
 
-   In subsequent runs, you can just use :option:`--login` to reuse the
-   same session, which is saved by Instaloader.
+   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
 
-   Cookie file path of a browser profile to load cookies from.
+   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
+   .. versionadded:: 4.11
 
 .. option:: --sessionfile SESSIONFILE, -f SESSIONFILE
 
@@ -304,7 +312,7 @@ How to Download
 .. option:: --user-agent USER_AGENT
 
    User Agent to use for HTTP requests. Per default, Instaloader pretends being
-   Chrome/120 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/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/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
 

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
 

instaloader/__init__.py

@@ -1,7 +1,7 @@
 """Download pictures (or videos) along with their captions and other metadata from Instagram."""
 
 
-__version__ = '4.12'
+__version__ = '4.15.2'
 
 
 try:
@@ -13,11 +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, TitlePic,
-                         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

@@ -37,7 +37,7 @@ def usage_string():
     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), '')
@@ -82,7 +82,7 @@ def filterstr_to_filterfunc(filter_str: str, item_type: type):
     return filterfunc
 
 
-def get_cookies_from_instagram(domain, browser, cookie_file='', cookie_name=''):
+def get_cookies_from_instagram(domain: str, browser: str, cookie_file: Optional[str] = None):
     supported_browsers = {
         "brave": browser_cookie3.brave,
         "chrome": browser_cookie3.chrome,
@@ -112,15 +112,12 @@ def get_cookies_from_instagram(domain, browser, cookie_file='', cookie_name=''):
         print(f"Cookies loaded successfully from {browser}")
     else:
         raise LoginException(f"No cookies found for Instagram in {browser}, "
-                             f"Are you logged in succesfully in {browser}?")
+                             f"Are you logged in successfully in {browser}?")
 
-    if cookie_name:
-        return cookies.get(cookie_name, {})
-    else:
-        return cookies
+    return cookies
 
 
-def import_session(browser, instaloader, cookiefile):
+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)
@@ -139,6 +136,7 @@ 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,
@@ -258,11 +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:
@@ -272,8 +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:
@@ -297,18 +296,35 @@ def _main(instaloader: Instaloader, targetlist: List[str],
         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: 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.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
@@ -409,6 +425,8 @@ def main():
                         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.')
 
@@ -570,6 +588,7 @@ def main():
                           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,

instaloader/instaloader.py

@@ -83,7 +83,7 @@ def _requires_login(func: Callable) -> Callable:
 
 
 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.
 
@@ -722,7 +722,7 @@ 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]
@@ -737,19 +737,20 @@ 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
@@ -866,8 +867,9 @@ 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
@@ -1214,6 +1216,7 @@ 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,
@@ -1280,6 +1283,32 @@ 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:
@@ -1409,7 +1438,9 @@ 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.
@@ -1426,6 +1457,8 @@ 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
 
@@ -1434,6 +1467,12 @@ class Instaloader:
 
         .. versionchanged:: 4.8
            Add `latest_stamps` parameter.
+
+        .. versionchanged:: 4.13
+           Add `max_count` parameter.
+
+        .. versionchanged:: 4.14
+           Add `reels` parameter.
         """
 
         @contextmanager
@@ -1477,6 +1516,12 @@ 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)):
@@ -1499,7 +1544,7 @@ 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, possibly_pinned=3)
+                                             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)

instaloader/instaloadercontext.py

@@ -1,4 +1,3 @@
-import hashlib
 import json
 import os
 import pickle
@@ -33,15 +32,15 @@ def copy_session(session: requests.Session, request_timeout: Optional[float] = N
 
 def default_user_agent() -> str:
     return ('Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 '
-            '(KHTML, like Gecko) Chrome/120.0.0.0 Safari/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',
@@ -94,7 +93,6 @@ 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()
@@ -104,7 +102,7 @@ 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
@@ -387,31 +385,45 @@ class InstaloaderContext:
 
     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 = ""
@@ -438,6 +450,15 @@ class InstaloaderContext:
                 response_headers.clear()
                 response_headers.update(resp.headers)
             if resp.status_code == 400:
+                with suppress(json.decoder.JSONDecodeError):
+                    if resp.json().get("message") in [
+                        "feedback_required",
+                        "checkpoint_required",
+                        "challenge_required",
+                    ]:
+                        # Raise AbortDownloadException in case of substantial Instagram
+                        # requirements to stop producing more requests
+                        raise AbortDownloadException(self._response_error(resp))
                 raise QueryReturnedBadRequestException(self._response_error(resp))
             if resp.status_code == 404:
                 raise QueryReturnedNotFoundException(self._response_error(resp))
@@ -462,6 +483,8 @@ 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:
@@ -473,14 +496,48 @@ 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))
+            del tmpsession.headers['Connection']
+            del tmpsession.headers['Content-Length']
+            tmpsession.headers['authority'] = 'www.instagram.com'
+            tmpsession.headers['scheme'] = 'https'
+            tmpsession.headers['accept'] = '*/*'
+            if referer is not None:
+                tmpsession.headers['referer'] = urllib.parse.quote(referer)
+
+            variables_json = json.dumps(variables, separators=(',', ':'))
+
+            resp_json = self.get_json('graphql/query',
+                                      params={'query_hash': query_hash,
+                                              'variables': variables_json},
+                                      session=tmpsession)
+        if 'status' not in resp_json:
+            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.
         """
         with copy_session(self._session, self.request_timeout) as tmpsession:
@@ -495,16 +552,12 @@ 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},
-                                      session=tmpsession)
+                                      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
@@ -512,7 +565,7 @@ class InstaloaderContext:
     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.
@@ -524,7 +577,7 @@ 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:
@@ -673,17 +726,6 @@ class InstaloaderContext:
                 raise QueryReturnedNotFoundException(self._response_error(resp))
             raise ConnectionException(self._response_error(resp))
 
-    @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
-
 
 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
@@ -203,6 +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:
@@ -220,7 +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.")
@@ -297,7 +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."
@@ -180,7 +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.
     """
@@ -232,21 +232,32 @@ 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 shortcode_to_mediaid(code: str) -> int:
         if len(code) > 11:
@@ -308,13 +319,25 @@ class Post:
 
     def _obtain_metadata(self):
         if not self._full_metadata_dict:
-            pic_json = self._context.graphql_query(
-                '2b0673e0dc4580674a88d426fe00ea90',
-                {'shortcode': self.shortcode}
+            response = self._context.doc_id_graphql_query(
+                "8845758582119845", {"shortcode": self.shortcode}
             )
-            self._full_metadata_dict = pic_json['data']['shortcode_media']
-            if self._full_metadata_dict is None:
+            data = (response or {}).get("data")
+            pic_json = data.get("xdt_shortcode_media") if data else None
+            if pic_json is None:
                 raise BadResponseException("Fetching Post metadata failed.")
+            try:
+                xdt_types = {
+                    "XDTGraphImage": "GraphImage",
+                    "XDTGraphVideo": "GraphVideo",
+                    "XDTGraphSidecar": "GraphSidecar",
+                }
+                pic_json["__typename"] = xdt_types[pic_json["__typename"]]
+            except KeyError as exc:
+                raise BadResponseException(
+                    f"Unknown __typename in metadata: {pic_json['__typename']}."
+                ) from exc
+            self._full_metadata_dict = pic_json
             if self.shortcode != self._full_metadata_dict['shortcode']:
                 self._node.update(self._full_metadata_dict)
                 raise PostChangedException
@@ -491,14 +514,14 @@ 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())
@@ -581,6 +604,15 @@ 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.
@@ -723,7 +755,11 @@ class Post:
             # 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:
@@ -855,7 +891,8 @@ 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
@@ -875,10 +912,13 @@ 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
+        data = context.doc_id_graphql_query("26347858941511777", {"hasQuery": True, "query": username})["data"]
+        if data:
+            for user in data["xdt_api__v1__fbsearch__non_profiled_serp"]["users"]:
+                if user["username"].lower() == username.lower():
+                    return cls(context, user)
+
+        raise ProfileNotExistsException("Profile {} does not exist.".format(username))
 
     @classmethod
     def from_id(cls, context: InstaloaderContext, profile_id: int):
@@ -897,8 +937,7 @@ class Profile:
                                       'include_reel': True,
                                       'include_suggested_users': False,
                                       'include_logged_out_extras': False,
-                                      'include_highlight_reels': False},
-                                     rhx_gis=context.root_rhx_gis)['data']['user']
+                                      'include_highlight_reels': False})['data']['user']
         if data:
             profile = cls(context, data['reel']['owner'])
         else:
@@ -946,11 +985,23 @@ 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:
+                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)
@@ -965,6 +1016,44 @@ class Profile:
                                                         ', '.join(similar_profiles[0:5]))) from err
             raise ProfileNotExistsException('Profile {} does not exist.'.format(self.username)) from err
 
+    def _normalize_profile_data(self, user_data: Dict[str, Any]) -> Dict[str, Any]:
+        """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
@@ -1055,7 +1144,7 @@ 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
         """
@@ -1066,7 +1155,7 @@ 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
         """
@@ -1173,15 +1262,33 @@ class Profile:
 
         :rtype: NodeIterator[Post]"""
         self._obtain_metadata()
+        logged_in = self._context.is_logged_in
         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"])
+                if logged_in
+                else (lambda d: d["data"]["user"]["edge_owner_to_timeline_media"])
+            ),
+            node_wrapper=(
+                (lambda n: Post.from_iphone_struct(self._context, n))
+                if logged_in
+                else (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,
+                },
+                **({"username": self.username} if logged_in else {"id": self.userid}),
+            },
+            query_referer="https://www.instagram.com/{0}/".format(self.username),
+            is_first=Profile._make_is_newest_checker(),
+            doc_id="7898261790222653" if logged_in else "7950326061742207",
+            query_hash=None,
+            first_data=(None if logged_in else self._metadata("edge_owner_to_timeline_media")),
         )
 
     def get_saved_posts(self) -> NodeIterator[Post]:
@@ -1218,6 +1325,30 @@ 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.
 
@@ -1483,7 +1614,7 @@ 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
         """
@@ -1494,7 +1625,7 @@ 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
         """
@@ -1793,11 +1924,11 @@ 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
@@ -1807,11 +1938,13 @@ 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):
@@ -2134,7 +2267,7 @@ 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
@@ -2164,7 +2297,7 @@ 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 +18,10 @@ 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, 9):
+    sys.exit('Instaloader requires Python >= 3.9.')
 
-requirements = ['requests>=2.4']
+requirements = ['requests>=2.25']
 optional_requirements = {
     'browser_cookie3': ['browser_cookie3>=0.19.1'],
 }
@@ -46,7 +46,7 @@ setup(
                 'from Instagram.',
     long_description=open(os.path.join(SRC, 'README.rst')).read(),
     install_requires=requirements,
-    python_requires='>=3.8',
+    python_requires='>=3.9',
     extras_require=optional_requirements,
     entry_points={'console_scripts': ['instaloader=instaloader.__main__:main']},
     zip_safe=False,
@@ -58,11 +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 :: Only',
         'Topic :: Internet',
         'Topic :: Multimedia :: Graphics'