Release of Version 4.12

Fix GitHub Actions Node.js deprecation warnings.

Use actions/setup-python cache where appropriate.

.github/workflows/documentation.yml

@@ -8,22 +8,23 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: "Checkout Instaloader Repository"
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
         with:
           fetch-depth: 0  # needed for building docs
       - name: "Setup Python"
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
         with:
-          python-version: 3.8
+          python-version: 3.12
+          cache: 'pipenv'
       - name: "Install Dependencies"
         run: |
-          python -m pip install pipenv==2022.1.8
-          pipenv sync --dev
+          python -m pip install pipenv==2023.12.1
+          pipenv --python `python --version | grep -Eo '3\.[0-9]+'` sync --dev
       - name: "Build Documentation"
-        run: pipenv run make -C docs html SPHINXOPTS="-W -n"
+        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

@@ -7,20 +7,22 @@ jobs:
     name: PyLint and MyPy
     runs-on: ubuntu-latest
     strategy:
+      fail-fast: false
       matrix:
-        python-version: ["3.6", "3.7", "3.8", "3.9", "3.10"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
     steps:
       - name: Checkout Instaloader Repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
       - name: Setup Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
+          cache: 'pipenv'
       - name: Install Dependencies
         run: |
-          python -m pip install pipenv==2022.1.8
-          pipenv sync --dev
+          python -m pip install pipenv==2023.12.1
+          pipenv --python `python --version | grep -Eo '3\.[0-9]+'` sync --dev
       - name: PyLint
-        run: pipenv run pylint instaloader
+        run: pipenv --python `python --version | grep -Eo '3\.[0-9]+'` run pylint instaloader
       - name: MyPy
-        run: pipenv run mypy -m instaloader
+        run: pipenv --python `python --version | grep -Eo '3\.[0-9]+'` run mypy -m instaloader

.github/workflows/packages.yml

@@ -11,17 +11,19 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: "Checkout Repository"
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
       - name: "Setup Python"
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
         with:
-          python-version: 3.8
+          python-version: 3.12
       - 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 setuptools
       - name: "Generate Python Package"
         run: python setup.py sdist
       - name: "Publish Distribution to PyPI"

.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:
@@ -11,24 +11,24 @@ jobs:
     runs-on: ubuntu-latest
     
     steps:
-    - uses: actions/stale@v3
+    - uses: actions/stale@v9
       with:
         repo-token: ${{ secrets.GITHUB_TOKEN }}
         only-labels: 'question'
         stale-issue-message: 'There has been no activity on this question for an extended period of time. This issue will be closed after further 14 days of inactivity.'
         stale-issue-label: 'stale'
         exempt-issue-labels: 'leave open'
-        days-before-stale: 15
+        days-before-stale: 21
         days-before-close: -1
         remove-stale-when-updated: false
-    - uses: actions/stale@v1
+    - uses: actions/stale@v9
       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'
-        days-before-stale: 135
+        exempt-issue-labels: 'leave open'
+        exempt-pr-labels: 'leave open'
+        days-before-stale: 189
         days-before-close: 14

.github/workflows/windows_exe.yml

@@ -8,17 +8,18 @@ jobs:
     runs-on: windows-latest
     steps:
       - name: Checkout Instaloader repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
       - name: Setup Python
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v5
         with:
-          python-version: "3.9"
+          python-version: "3.12"
+          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:

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

@@ -6,14 +6,17 @@ verify_ssl = true
 [dev-packages]
 pylint = "*"
 mypy = "*"
-sphinx = "~=2.3"
+sphinx = "*"
 pyinstaller = "*"
-pefile = "*"
-pywin32-ctypes = "*"
 psutil = "*"
-typing-extensions = "*"
 types-requests = "*"
-typed-ast = "*"
+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

@@ -2,11 +2,7 @@
 
 .. badges-start
 
-|travis| |pypi| |pyversion| |license| |aur| |contributors| |downloads|
-
-.. |travis| image:: https://img.shields.io/travis/instaloader/instaloader/master.svg
-   :alt: Travis-CI Build Status
-   :target: https://travis-ci.org/instaloader/instaloader
+|pypi| |pyversion| |license| |aur| |contributors| |downloads|
 
 .. |pypi| image:: https://img.shields.io/pypi/v/instaloader.svg
    :alt: Instaloader PyPI Project Page
@@ -127,6 +123,9 @@ Supporters
 
 .. current-sponsors-start
 
+| Instaloader is proudly sponsored by
+|  `@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!
 

deploy/arch/.SRCINFO.template

@@ -6,7 +6,7 @@ pkgbase = instaloader
 	arch = any
 	license = MIT
 	makedepends = python-setuptools
-	depends = python>=3.6
+	depends = python>=3.8
 	depends = python-requests>=2.4
 	options = !emptydirs
 	source = instaloader-{{version}}.tar.gz::https://codeload.github.com/instaloader/instaloader/tar.gz/v{{version}}

deploy/arch/PKGBUILD.template

@@ -8,7 +8,7 @@ arch=('any')
 url="https://instaloader.github.io/"
 license=('MIT')
 groups=()
-depends=('python>=3.6' 'python-requests>=2.4')
+depends=('python>=3.8' 'python-requests>=2.4')
 makedepends=('python-setuptools')
 options=('!emptydirs')
 source=($pkgname-$pkgver.tar.gz::https://codeload.github.com/instaloader/instaloader/tar.gz/v$pkgver)

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==2022.1.8",
+commands = ["pip install pipenv==2023.12.1",
             f"pipenv --python {sys.version_info.major}.{sys.version_info.minor} sync --dev",
             "pipenv run pyinstaller --log-level=DEBUG instaloader.spec"]
 

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.
@@ -102,23 +102,23 @@ Instaloader supports the following targets:
    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
@@ -140,7 +140,7 @@ 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`.
@@ -255,7 +255,7 @@ 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 +307,47 @@ 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
 
@@ -183,6 +183,7 @@ 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 +193,32 @@ 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
+
+   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.
+
+   In subsequent runs, you can just use :option:`--login` to reuse the
+   same session, which is saved by Instaloader.
+
+   .. versionadded:: 4.11
+
+.. option:: --cookiefile COOKIE-FILE, -B COOKIE-FILE
+
+   Cookie file path of a browser profile to load cookies from.
+
+  .. versionadded:: 4.11
+
 .. option:: --sessionfile SESSIONFILE, -f SESSIONFILE
 
    Path for loading and storing session key file.  Defaults to
@@ -281,7 +304,7 @@ 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/120 on Linux.
 
 .. option:: --max-connection-attempts N
 

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/installation.rst

@@ -8,7 +8,7 @@ Install Instaloader
 To **install Instaloader**,
 
 #. Ensure that you have `Python <https://www.python.org/>`__, at least
-   version 3.6, and `pip <https://pypi.python.org/pypi/pip>`__
+   version 3.8, and `pip <https://pypi.python.org/pypi/pip>`__
    installed.
 
 #. Then, install Instaloader using::

docs/module/exceptions.rst

@@ -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/nodeiterator.rst

@@ -30,7 +30,7 @@ Iterator :class:`NodeIterator` and a context manager
 
    It can be serialized and deserialized with :func:`save_structure_to_file`
    and :func:`load_structure_from_file`, as well as with :mod:`json` and
-   :mod:`pickle` thanks to being a :func:`~collections.namedtuple`.
+   :mod:`pickle` thanks to being a :class:`~typing.NamedTuple`.
 
 ``resumable_iteration``
 """""""""""""""""""""""

docs/module/structures.rst

@@ -71,6 +71,14 @@ TopSearchResults
 
    .. versionadded:: 4.3
 
+TitlePic
+""""""""
+
+.. autoclass:: TitlePic
+   :no-show-inheritance:
+
+   .. versionadded:: 4.8
+
 Loading and Saving
 """"""""""""""""""
 

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__ = '4.9.3'
+__version__ = '4.12'
 
 
 try:
@@ -18,5 +18,6 @@ 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,
+                         Profile, Story, StoryItem, TopSearchResults, TitlePic,
+                         load_structure_from_file, save_structure_to_file,
                          load_structure, get_json_structure)

instaloader/__main__.py

@@ -6,16 +6,31 @@ 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])
@@ -45,7 +60,6 @@ def filterstr_to_filterfunc(filter_str: str, item_type: type):
 
     class TransformFilterAst(ast.NodeTransformer):
         def visit_Name(self, node: ast.Name):
-            # pylint:disable=no-self-use
             if not isinstance(node.ctx, ast.Load):
                 raise InvalidArgumentException("Invalid filter: Modifying variables ({}) not allowed.".format(node.id))
             if node.id == "datetime":
@@ -68,6 +82,56 @@ def filterstr_to_filterfunc(filter_str: str, item_type: type):
     return filterfunc
 
 
+def get_cookies_from_instagram(domain, browser, cookie_file='', cookie_name=''):
+    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 succesfully in {browser}?")
+
+    if cookie_name:
+        return cookies.get(cookie_name, {})
+    else:
+        return cookies
+
+
+def import_session(browser, instaloader, cookiefile):
+    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,
@@ -79,7 +143,9 @@ def _main(instaloader: Instaloader, targetlist: List[str],
           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
@@ -94,6 +160,11 @@ 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):
@@ -109,6 +180,10 @@ 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: ")
@@ -118,14 +193,19 @@ 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:
@@ -216,7 +296,7 @@ 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.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,
@@ -231,8 +311,10 @@ def _main(instaloader: Instaloader, targetlist: List[str],
                                                    latest_stamps=latest_stamps)
     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)
@@ -244,6 +326,8 @@ 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():
@@ -259,17 +343,17 @@ 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]",
@@ -300,11 +384,11 @@ 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',
@@ -318,11 +402,11 @@ 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('--igtv', action='store_true',
@@ -354,9 +438,14 @@ 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>"))
@@ -417,15 +506,15 @@ 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
@@ -435,15 +524,18 @@ 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
@@ -468,25 +560,37 @@ 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_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

@@ -77,7 +77,7 @@ 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
 
@@ -221,8 +221,8 @@ class Instaloader:
                  download_comments: bool = False,
                  save_metadata: bool = True,
                  compress_json: bool = True,
-                 post_metadata_txt_pattern: str = None,
-                 storyitem_metadata_txt_pattern: str = None,
+                 post_metadata_txt_pattern: Optional[str] = None,
+                 storyitem_metadata_txt_pattern: Optional[str] = None,
                  max_connection_attempts: int = 3,
                  request_timeout: float = 300.0,
                  rate_controller: Optional[Callable[[InstaloaderContext], RateController]] = None,
@@ -447,7 +447,7 @@ class Instaloader:
         """Updates picture caption / Post metadata info"""
         def _elliptify(caption):
             pcaption = caption.replace('\n', ' ').strip()
-            return '[' + ((pcaption[:29] + u"\u2026") if len(pcaption) > 31 else pcaption) + ']'
+            return '[' + ((pcaption[:29] + "\u2026") if len(pcaption) > 31 else pcaption) + ']'
         filename += '.txt'
         caption += '\n'
         pcaption = _elliptify(caption)
@@ -524,7 +524,7 @@ class Instaloader:
         .. versionadded:: 4.3"""
 
         http_response = self.context.get_raw(url)
-        date_object = None  # type: Optional[datetime]
+        date_object: Optional[datetime] = None
         if 'Last-Modified' in http_response.headers:
             date_object = datetime.strptime(http_response.headers["Last-Modified"], '%a, %d %b %Y %H:%M:%S GMT')
             date_object = date_object.replace(tzinfo=timezone.utc)
@@ -585,6 +585,23 @@ class Instaloader:
         .. versionadded:: 4.4"""
         self.download_title_pic(hashtag.profile_pic_url, '#' + hashtag.name, 'profile_pic', None)
 
+    @_requires_login
+    def save_session(self) -> dict:
+        """Saves internally stored :class:`requests.Session` object to :class:`dict`.
+
+        :raises LoginRequiredException: If called without being logged in.
+
+        .. versionadded:: 4.10
+        """
+        return self.context.save_session()
+
+    def load_session(self, username: str, session_data: dict) -> None:
+        """Internally stores :class:`requests.Session` object from :class:`dict`.
+
+        .. versionadded:: 4.10
+        """
+        self.context.load_session(username, session_data)
+
     @_requires_login
     def save_session_to_file(self, filename: Optional[str] = None) -> None:
         """Saves internally stored :class:`requests.Session` object.
@@ -626,11 +643,16 @@ 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:
@@ -712,7 +734,7 @@ class Instaloader:
                             post.get_sidecar_nodes(self.slide_start, self.slide_end),
                             start=self.slide_start % post.mediacount + 1
                     ):
-                        suffix = str(edge_number)  # type: Optional[str]
+                        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):
@@ -878,13 +900,18 @@ class Instaloader:
         filename_template = os.path.join(dirname, self.format_filename(item, target=target))
         filename = self.__prepare_filename(filename_template, lambda: item.url)
         downloaded = False
-        if not item.is_video or self.download_video_thumbnails is True:
+        video_url_fetch_failed = False
+        if item.is_video and self.download_videos is True:
+            video_url = item.video_url
+            if video_url:
+                filename = self.__prepare_filename(filename_template, lambda: str(video_url))
+                downloaded |= (not _already_downloaded(filename + ".mp4") and
+                               self.download_pic(filename=filename, url=video_url, mtime=date_local))
+            else:
+                video_url_fetch_failed = True
+        if video_url_fetch_failed or not item.is_video or self.download_video_thumbnails is True:
             downloaded = (not _already_downloaded(filename + ".jpg") and
                           self.download_pic(filename=filename, url=item.url, mtime=date_local))
-        if item.is_video and self.download_videos is True:
-            filename = self.__prepare_filename(filename_template, lambda: str(item.video_url))
-            downloaded |= (not _already_downloaded(filename + ".mp4") and
-                           self.download_pic(filename=filename, url=item.video_url, mtime=date_local))
         # Save caption if desired
         metadata_string = _ArbitraryItemFormatter(item).format(self.storyitem_metadata_txt_pattern).strip()
         if metadata_string:
@@ -940,11 +967,11 @@ class Instaloader:
         """
         for user_highlight in self.get_highlights(user):
             name = user_highlight.owner_username
-            highlight_target = (filename_target
+            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)))  # type: Union[str, Path]
+                                                                       self.sanitize_paths)))
             self.context.log("Retrieving highlights \"{}\" from profile {}".format(user_highlight.title, name))
             self.download_highlight_cover(user_highlight, highlight_target)
             totalcount = user_highlight.itemcount
@@ -969,7 +996,8 @@ 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.
 
@@ -981,6 +1009,9 @@ 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`.
@@ -989,6 +1020,8 @@ 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)
@@ -1010,7 +1043,7 @@ 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
@@ -1044,7 +1077,7 @@ 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
@@ -1075,7 +1108,7 @@ class Instaloader:
                                                'has_stories': False})["data"]
 
     @_requires_login
-    def download_feed_posts(self, max_count: int = None, fast_update: bool = False,
+    def download_feed_posts(self, max_count: Optional[int] = None, fast_update: bool = False,
                             post_filter: Optional[Callable[[Post], bool]] = None) -> None:
         """
         Download pictures from the user's feed.
@@ -1096,7 +1129,7 @@ class Instaloader:
         self.posts_download_loop(self.get_feed_posts(), ":feed", fast_update, post_filter, max_count=max_count)
 
     @_requires_login
-    def download_saved_posts(self, max_count: int = None, fast_update: bool = False,
+    def download_saved_posts(self, max_count: Optional[int] = None, fast_update: bool = False,
                              post_filter: Optional[Callable[[Post], bool]] = None) -> None:
         """Download user's saved pictures.
 
@@ -1432,7 +1465,7 @@ 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):
@@ -1466,7 +1499,7 @@ 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)
                     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)
@@ -1554,11 +1587,16 @@ 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:
@@ -1577,3 +1615,10 @@ 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

@@ -3,13 +3,13 @@ import json
 import os
 import pickle
 import random
-import re
 import shutil
 import sys
 import textwrap
 import time
 import urllib.parse
-from contextlib import contextmanager
+import uuid
+from contextlib import contextmanager, suppress
 from datetime import datetime, timedelta
 from functools import partial
 from typing import Any, Callable, Dict, Iterator, List, Optional, Union
@@ -24,16 +24,44 @@ def copy_session(session: requests.Session, request_timeout: Optional[float] = N
     """Duplicates a requests.Session."""
     new = requests.Session()
     new.cookies = requests.utils.cookiejar_from_dict(requests.utils.dict_from_cookiejar(session.cookies))
-    new.headers = session.headers.copy()
+    new.headers = session.headers.copy()  # type: ignore
     # Override default timeout behavior.
     # Need to silence mypy bug for this. See: https://github.com/python/mypy/issues/2427
-    new.request = partial(new.request, timeout=request_timeout) # type: ignore
+    new.request = partial(new.request, timeout=request_timeout)  # type: ignore
     return new
 
 
 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/120.0.0.0 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+',
+            'x-ads-opt-out': '1',
+            'x-bloks-is-panorama-enabled': 'true',
+            'x-bloks-version-id': '01507c21540f73e2216b6f62a11a5b5e51aa85491b72475c080da35b1228ddd6',
+            'x-fb-client-ip': 'True',
+            'x-fb-connection-type': 'wifi',
+            'x-fb-http-engine': 'Liger',
+            'x-fb-server-cluster': 'True',
+            'x-fb': '1',
+            'x-ig-abr-connection-speed-kbps': '2',
+            'x-ig-app-id': '124024574287414',
+            'x-ig-app-locale': 'en-US',
+            'x-ig-app-startup-country': 'US',
+            'x-ig-bandwidth-speed-kbps': '0.000',
+            'x-ig-capabilities': '36r/F/8=',
+            'x-ig-connection-speed': '{}kbps'.format(random.randint(1000, 20000)),
+            'x-ig-connection-type': 'WiFi',
+            'x-ig-device-locale': 'en-US',
+            'x-ig-mapped-locale': 'en-US',
+            'x-ig-timezone-offset': str((datetime.now().astimezone().utcoffset() or timedelta(seconds=0)).seconds),
+            'x-ig-www-claim': '0',
+            'x-pigeon-session-id': str(uuid.uuid4()),
+            'x-tigon-is-retry': 'False',
+            'x-whatsapp': '0'}
 
 
 class InstaloaderContext:
@@ -61,6 +89,7 @@ class InstaloaderContext:
         self.request_timeout = request_timeout
         self._session = self.get_anonymous_session()
         self.username = None
+        self.user_id = None
         self.sleep = sleep
         self.quiet = quiet
         self.max_connection_attempts = max_connection_attempts
@@ -68,9 +97,10 @@ class InstaloaderContext:
         self._root_rhx_gis = None
         self.two_factor_auth_pending = None
         self.iphone_support = iphone_support
+        self.iphone_headers = default_iphone_headers()
 
         # error log, filled with error() and printed at the end of Instaloader.main()
-        self.error_log = []                      # type: List[str]
+        self.error_log: List[str] = []
 
         self._rate_controller = rate_controller(self) if rate_controller is not None else RateController(self)
 
@@ -81,20 +111,26 @@ class InstaloaderContext:
         self.fatal_status_codes = fatal_status_codes or []
 
         # Cache profile from id (mapping from id to Profile)
-        self.profile_id_cache = dict()           # type: Dict[int, Any]
+        self.profile_id_cache: Dict[int, Any] = dict()
 
     @contextmanager
     def anonymous_copy(self):
         session = self._session
         username = self.username
+        user_id = self.user_id
+        iphone_headers = self.iphone_headers
         self._session = self.get_anonymous_session()
         self.username = None
+        self.user_id = None
+        self.iphone_headers = default_iphone_headers()
         try:
             yield self
         finally:
             self._session.close()
             self.username = username
             self._session = session
+            self.user_id = user_id
+            self.iphone_headers = iphone_headers
 
     @property
     def is_logged_in(self) -> bool:
@@ -115,6 +151,13 @@ class InstaloaderContext:
         if repeat_at_end:
             self.error_log.append(msg)
 
+    @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:
@@ -170,35 +213,56 @@ class InstaloaderContext:
         session.request = partial(session.request, timeout=self.request_timeout) # type: ignore
         return session
 
-    def save_session_to_file(self, sessionfile):
-        """Not meant to be used directly, use :meth:`Instaloader.save_session_to_file`."""
-        pickle.dump(requests.utils.dict_from_cookiejar(self._session.cookies), sessionfile)
+    def save_session(self):
+        """Not meant to be used directly, use :meth:`Instaloader.save_session`."""
+        return requests.utils.dict_from_cookiejar(self._session.cookies)
 
-    def load_session_from_file(self, username, sessionfile):
-        """Not meant to be used directly, use :meth:`Instaloader.load_session_from_file`."""
+    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()
-        session.cookies = requests.utils.cookiejar_from_dict(pickle.load(sessionfile))
+        session.cookies = requests.utils.cookiejar_from_dict(sessiondata)
         session.headers.update(self._default_http_header())
         session.headers.update({'X-CSRFToken': session.cookies.get_dict()['csrftoken']})
         # 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
+        session.request = partial(session.request, timeout=self.request_timeout)  # type: ignore
         self._session = session
         self.username = username
 
+    def save_session_to_file(self, sessionfile):
+        """Not meant to be used directly, use :meth:`Instaloader.save_session_to_file`."""
+        pickle.dump(self.save_session(), sessionfile)
+
+    def load_session_from_file(self, username, sessionfile):
+        """Not meant to be used directly, use :meth:`Instaloader.load_session_from_file`."""
+        self.load_session(username, pickle.load(sessionfile))
+
     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
@@ -211,20 +275,25 @@ 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'):
@@ -236,35 +305,37 @@ 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
         self.username = user
+        self.user_id = resp_json['userId']
 
     def two_factor_login(self, two_factor_code):
         """Second step of login if 2FA is enabled.
@@ -297,8 +368,26 @@ 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) -> Dict[str, Any]:
+                 session: Optional[requests.Session] = None, _attempt=1,
+                 response_headers: Optional[Dict[str, Any]] = None) -> Dict[str, Any]:
         """JSON request to Instagram.
 
         :param path: URL, relative to the given domain which defaults to www.instagram.com/
@@ -325,55 +414,41 @@ class InstaloaderContext:
             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 ""
-                raise AbortDownloadException("Query to https://{}/{} responded with \"{} {}\"{}".format(
-                    host, path, resp.status_code, resp.reason, redirect
+                body = ""
+                if resp.headers['Content-Type'].startswith('application/json'):
+                    body = ': ' + resp.text[:500] + ('…' if len(resp.text) > 501 else '')
+                raise AbortDownloadException("Query to https://{}/{} responded with \"{} {}\"{}{}".format(
+                    host, path, resp.status_code, resp.reason, redirect, body
                 ))
             while resp.is_redirect:
                 redirect_url = resp.headers['location']
                 self.log('\nHTTP redirect from https://{0}/{1} to {2}'.format(host, path, redirect_url))
-                if redirect_url.startswith('https://www.instagram.com/accounts/login'):
+                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.")
-                    # alternate rate limit exceeded behavior
-                    raise TooManyRequestsException("Redirected to 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)):
                     resp = sess.get(redirect_url if redirect_url.endswith('/') else redirect_url + '/',
                                     params=params, allow_redirects=False)
                 else:
                     break
+            if response_headers is not None:
+                response_headers.clear()
+                response_headers.update(resp.headers)
             if resp.status_code == 400:
-                raise QueryReturnedBadRequestException("400 Bad Request")
+                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:
-                match = re.search(r'window\._sharedData = (.*);</script>', resp.text)
-                if match is None:
-                    raise QueryReturnedNotFoundException("Could not find \"window._sharedData\" in html response.")
-                resp_json = json.loads(match.group(1))
-                entry_data = resp_json.get('entry_data')
-                post_or_profile_page = list(entry_data.values())[0] if entry_data is not None else None
-                if post_or_profile_page is None:
-                    raise ConnectionException("\"window._sharedData\" does not contain required keys.")
-                # If GraphQL data is missing in `window._sharedData`, search for it in `__additionalDataLoaded`.
-                if 'graphql' not in post_or_profile_page[0]:
-                    match = re.search(r'window\.__additionalDataLoaded\(.*?({.*"graphql":.*})\);</script>',
-                                      resp.text)
-                    if match is not None:
-                        post_or_profile_page[0]['graphql'] = json.loads(match.group(1))['graphql']
-                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)
@@ -391,7 +466,8 @@ class InstaloaderContext:
                         self._rate_controller.handle_429('iphone')
                     if is_other_query:
                         self._rate_controller.handle_429('other')
-                return self.get_json(path=path, params=params, host=host, session=sess, _attempt=_attempt + 1)
+                return self.get_json(path=path, params=params, host=host, session=sess, _attempt=_attempt + 1,
+                                     response_headers=response_headers)
             except KeyboardInterrupt:
                 self.error("[skipped by user]", repeat_at_end=False)
                 raise ConnectionException(error_string) from err
@@ -481,11 +557,57 @@ class InstaloaderContext:
 
         .. versionadded:: 4.2.1"""
         with copy_session(self._session, self.request_timeout) as tempsession:
-            tempsession.headers['User-Agent'] = 'Instagram 146.0.0.27.125 (iPhone12,1; iOS 13_3; en_US; en-US; ' \
-                                                'scale=2.00; 1656x3584; 190542906)'
-            for header in ['Host', 'Origin', 'X-Instagram-AJAX', 'X-Requested-With']:
+            # Set headers to simulate an API request from iPad
+            tempsession.headers['ig-intended-user-id'] = str(self.user_id)
+            tempsession.headers['x-pigeon-rawclienttime'] = '{:.6f}'.format(time.time())
+
+            # Add headers obtained from previous iPad request
+            tempsession.headers.update(self.iphone_headers)
+
+            # Extract key information from cookies if we haven't got it already from a previous request
+            header_cookies_mapping = {'x-mid': 'mid',
+                                     'ig-u-ds-user-id': 'ds_user_id',
+                                     'x-ig-device-id': 'ig_did',
+                                     'x-ig-family-device-id': 'ig_did',
+                                     'family_device_id': 'ig_did'}
+
+            # Map the cookie value to the matching HTTP request header
+            cookies = tempsession.cookies.get_dict().copy()
+            for key, value in header_cookies_mapping.items():
+                if value in cookies:
+                    if key not in tempsession.headers:
+                        tempsession.headers[key] = cookies[value]
+                    else:
+                        # Remove the cookie value if it's already specified as a header
+                        tempsession.cookies.pop(value, None)
+
+            # Edge case for ig-u-rur header due to special string encoding in cookie
+            if 'rur' in cookies:
+                if 'ig-u-rur' not in tempsession.headers:
+                    tempsession.headers['ig-u-rur'] = cookies['rur'].strip('\"').encode('utf-8') \
+                                                                    .decode('unicode_escape')
+                else:
+                    tempsession.cookies.pop('rur', None)
+
+            # Remove headers specific to Desktop version
+            for header in ['Host', 'Origin', 'X-Instagram-AJAX', 'X-Requested-With', 'Referer']:
                 tempsession.headers.pop(header, None)
-            return self.get_json(path, params, 'i.instagram.com', tempsession)
+
+            # No need for cookies if we have a bearer token
+            if 'authorization' in tempsession.headers:
+                tempsession.cookies.clear()
+
+            response_headers = dict()    # type: Dict[str, Any]
+            response = self.get_json(path, params, 'i.instagram.com', tempsession, response_headers=response_headers)
+
+            # Extract the ig-set-* headers and use them in the next request
+            for key, value in response_headers.items():
+                if key.startswith('ig-set-'):
+                    self.iphone_headers[key.replace('ig-set-', '')] = value
+                elif key.startswith('x-ig-set-'):
+                    self.iphone_headers[key.replace('x-ig-set-', 'x-ig-')] = value
+
+            return response
 
     def write_raw(self, resp: Union[bytes, requests.Response], filename: str) -> None:
         """Write raw response data into a file.
@@ -515,11 +637,11 @@ 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.
@@ -545,11 +667,11 @@ 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))
 
     @property
     def root_rhx_gis(self) -> Optional[str]:
@@ -581,7 +703,7 @@ class RateController:
 
     def __init__(self, context: InstaloaderContext):
         self._context = context
-        self._query_timestamps = dict()  # type: Dict[str, List[float]]
+        self._query_timestamps: Dict[str, List[float]] = dict()
         self._earliest_next_request_time = 0.0
         self._iphone_earliest_next_request_time = 0.0
 
@@ -589,7 +711,6 @@ class RateController:
         """Wait given number of seconds."""
         # Not static, to allow for the behavior of this method to depend on context-inherent properties, such as
         # whether we are logged in.
-        # pylint:disable=no-self-use
         time.sleep(secs)
 
     def _dump_query_timestamps(self, current_time: float, failed_query_type: str):
@@ -613,7 +734,6 @@ class RateController:
         control."""
         # Not static, to allow for the count_per_sliding_window to depend on context-inherent properties, such as
         # whether we are logged in.
-        # pylint:disable=no-self-use
         return 75 if query_type == 'other' else 200
 
     def _reqs_in_sliding_window(self, query_type: Optional[str], current_time: float, window: float) -> List[float]:

instaloader/lateststamps.py

@@ -1,6 +1,8 @@
 import configparser
 from datetime import datetime, timezone
 from typing import Optional
+from os.path import dirname
+from os import makedirs
 
 
 class LatestStamps:
@@ -25,6 +27,8 @@ class LatestStamps:
         self.data.read(latest_stamps_file)
 
     def _save(self):
+        if dn := dirname(self.file):
+            makedirs(dn, exist_ok=True)
         with open(self.file, 'w') as f:
             self.data.write(f)
 

instaloader/nodeiterator.py

@@ -10,15 +10,15 @@ from typing import Any, Callable, Dict, Iterable, Iterator, NamedTuple, Optional
 from .exceptions import AbortDownloadException, InvalidArgumentException, QueryReturnedBadRequestException
 from .instaloadercontext import InstaloaderContext
 
-FrozenNodeIterator = NamedTuple('FrozenNodeIterator',
-                                [('query_hash', str),
-                                 ('query_variables', Dict),
-                                 ('query_referer', Optional[str]),
-                                 ('context_username', Optional[str]),
-                                 ('total_index', int),
-                                 ('best_before', Optional[float]),
-                                 ('remaining_data', Optional[Dict]),
-                                 ('first_node', Optional[Dict])])
+class FrozenNodeIterator(NamedTuple):
+    query_hash: str
+    query_variables: Dict
+    query_referer: Optional[str]
+    context_username: Optional[str]
+    total_index: int
+    best_before: Optional[float]
+    remaining_data: Optional[Dict]
+    first_node: Optional[Dict]
 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."""
@@ -77,7 +77,7 @@ class NodeIterator(Iterator[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], bool]] = None):
+                 is_first: Optional[Callable[[T, Optional[T]], bool]] = None):
         self._context = context
         self._query_hash = query_hash
         self._edge_extractor = edge_extractor
@@ -95,7 +95,7 @@ class NodeIterator(Iterator[T]):
         self._is_first = is_first
 
     def _query(self, after: Optional[str] = None) -> Dict:
-        pagination_variables = {'first': NodeIterator._graphql_page_length}  # type: Dict[str, Any]
+        pagination_variables: Dict[str, Any] = {'first': NodeIterator._graphql_page_length}
         if after is not None:
             pagination_variables['after'] = after
         try:
@@ -131,13 +131,13 @@ class NodeIterator(Iterator[T]):
                 raise
             item = self._node_wrapper(node)
             if self._is_first is not None:
-                if self._is_first(item):
+                if self._is_first(item, self.first_item):
                     self._first_node = node
             else:
                 if self._first_node is None:
                     self._first_node = node
             return item
-        if self._data['page_info']['has_next_page']:
+        if self._data.get('page_info', {}).get('has_next_page'):
             query_response = self._query(self._data['page_info']['end_cursor'])
             if self._data['edges'] != query_response['edges'] and len(query_response['edges']) > 0:
                 page_index, data = self._page_index, self._data
@@ -184,6 +184,10 @@ 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
@@ -289,7 +293,7 @@ def resumable_iteration(context: InstaloaderContext,
             is_resuming = True
             start_index = iterator.total_index
             context.log("Resuming from {}.".format(resume_file_path))
-        except (InvalidArgumentException, LZMAError, json.decoder.JSONDecodeError) as exc:
+        except (InvalidArgumentException, LZMAError, json.decoder.JSONDecodeError, EOFError) as exc:
             context.error("Warning: Not resuming from {}: {}".format(resume_file_path, exc))
     try:
         yield is_resuming, start_index

instaloader/sectioniterator.py

@@ -29,7 +29,7 @@ class SectionIterator(Iterator[T]):
     def _query(self, max_id: Optional[str] = None) -> Dict[str, Any]:
         pagination_variables = {"max_id": max_id} if max_id is not None else {}
         return self._sections_extractor(
-            self._context.get_json(self._query_path, params={"__a": 1, **pagination_variables})
+            self._context.get_json(self._query_path, params={"__a": 1, "__d": "dis", **pagination_variables})
         )
 
     def __next__(self) -> T:

instaloader/structures.py

@@ -2,12 +2,11 @@ import json
 import lzma
 import re
 from base64 import b64decode, b64encode
-from collections import namedtuple
 from contextlib import suppress
 from datetime import datetime
 from itertools import islice
 from pathlib import Path
-from typing import Any, Callable, Dict, Iterable, Iterator, List, Optional, Tuple, Union
+from typing import Any, Callable, Dict, Iterable, Iterator, List, NamedTuple, Optional, Tuple, Union
 from unicodedata import normalize
 
 from . import __version__
@@ -16,25 +15,129 @@ from .instaloadercontext import InstaloaderContext
 from .nodeiterator import FrozenNodeIterator, NodeIterator
 from .sectioniterator import SectionIterator
 
-PostSidecarNode = namedtuple('PostSidecarNode', ['is_video', 'display_url', 'video_url'])
-PostSidecarNode.__doc__ = "Item of a Sidecar Post."
+
+class PostSidecarNode(NamedTuple):
+    """Item of a Sidecar Post."""
+    is_video: bool
+    display_url: str
+    video_url: str
+
+
 PostSidecarNode.is_video.__doc__ = "Whether this node is a video."
 PostSidecarNode.display_url.__doc__ = "URL of image or video thumbnail."
 PostSidecarNode.video_url.__doc__ = "URL of video or None."
 
-PostCommentAnswer = namedtuple('PostCommentAnswer', ['id', 'created_at_utc', 'text', 'owner', 'likes_count'])
+
+class PostCommentAnswer(NamedTuple):
+    id: int
+    created_at_utc: datetime
+    text: str
+    owner: 'Profile'
+    likes_count: int
+
+
 PostCommentAnswer.id.__doc__ = "ID number of comment."
 PostCommentAnswer.created_at_utc.__doc__ = ":class:`~datetime.datetime` when comment was created (UTC)."
 PostCommentAnswer.text.__doc__ = "Comment text."
 PostCommentAnswer.owner.__doc__ = "Owner :class:`Profile` of the comment."
 PostCommentAnswer.likes_count.__doc__ = "Number of likes on comment."
 
-PostComment = namedtuple('PostComment', (*PostCommentAnswer._fields, 'answers')) # type: ignore
-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." # type: ignore
 
-PostLocation = namedtuple('PostLocation', ['id', 'name', 'slug', 'has_public_page', 'lat', 'lng'])
+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,
+        )
+
+    @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
+    name: str
+    slug: str
+    has_public_page: Optional[bool]
+    lat: Optional[float]
+    lng: Optional[float]
+
+
 PostLocation.id.__doc__ = "ID number of location."
 PostLocation.name.__doc__ = "Location name."
 PostLocation.slug.__doc__ = "URL friendly variant of location name."
@@ -42,6 +145,22 @@ PostLocation.has_public_page.__doc__ = "Whether location has a public page."
 PostLocation.lat.__doc__ = "Latitude (:class:`float` or None)."
 PostLocation.lng.__doc__ = "Longitude (:class:`float` or None)."
 
+# This regular expression is by MiguelX413
+_hashtag_regex = re.compile(r"(?:#)((?:\w){1,150})")
+
+# This regular expression is modified from jStassen, adjusted to use Python's \w to
+# 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)
+
+
+def _optional_normalize(string: Optional[str]) -> Optional[str]:
+    if string is not None:
+        return normalize("NFC", string)
+    else:
+        return None
+
 
 class Post:
     """
@@ -73,8 +192,8 @@ class Post:
         self._context = context
         self._node = node
         self._owner_profile = owner_profile
-        self._full_metadata_dict = None  # type: Optional[Dict[str, Any]]
-        self._location = None            # type: Optional[PostLocation]
+        self._full_metadata_dict: Optional[Dict[str, Any]] = None
+        self._location: Optional[PostLocation] = None
         self._iphone_struct_ = None
         if 'iphone_struct' in node:
             # if loaded from JSON with load_structure_from_file()
@@ -211,7 +330,7 @@ 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]
@@ -364,16 +483,10 @@ class Post:
     @property
     def caption(self) -> Optional[str]:
         """Caption."""
-        def _normalize(string: Optional[str]) -> Optional[str]:
-            if string is not None:
-                return normalize("NFC", string)
-            else:
-                return None
-
         if "edge_media_to_caption" in self._node and self._node["edge_media_to_caption"]["edges"]:
-            return _normalize(self._node["edge_media_to_caption"]["edges"][0]["node"]["text"])
+            return _optional_normalize(self._node["edge_media_to_caption"]["edges"][0]["node"]["text"])
         elif "caption" in self._node:
-            return _normalize(self._node["caption"])
+            return _optional_normalize(self._node["caption"])
         return None
 
     @property
@@ -381,22 +494,14 @@ class Post:
         """List of all lowercased hashtags (without preceeding #) that occur in the Post's caption."""
         if not self.caption:
             return []
-        # This regular expression is from jStassen, adjusted to use Python's \w to support Unicode
-        # http://blog.jstassen.com/2016/03/code-regex-for-instagram-username-and-hashtags/
-        hashtag_regex = re.compile(r"(?:#)(\w(?:(?:\w|(?:\.(?!\.))){0,28}(?:\w))?)")
-        return re.findall(hashtag_regex, self.caption.lower())
+        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 @."""
         if not self.caption:
             return []
-        # This regular expression is modified from jStassen, adjusted to use Python's \w to
-        # 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|_)(?:@)(\w(?:(?:\w|(?:\.(?!\.))){0,28}(?:\w))?)", re.ASCII)
-        return re.findall(mention_regex, self.caption.lower())
+        return _mention_regex.findall(self.caption.lower())
 
     @property
     def pcaption(self) -> str:
@@ -405,7 +510,7 @@ class Post:
         .. versionadded:: 4.2.6"""
         def _elliptify(caption):
             pcaption = ' '.join([s.replace('/', '\u2215') for s in caption.splitlines() if s]).strip()
-            return (pcaption[:30] + u"\u2026") if len(pcaption) > 31 else pcaption
+            return (pcaption[:30] + "\u2026") if len(pcaption) > 31 else pcaption
         return _elliptify(self.caption) if self.caption else ''
 
     @property
@@ -512,16 +617,77 @@ class Post:
         except KeyError:
             return self._field('edge_media_to_comment', 'count')
 
-    def get_comments(self) -> Iterable[PostComment]:
-        r"""Iterate over all comments of the post.
+    def _get_comments_via_iphone_endpoint(self) -> Iterable[PostComment]:
+        """
+        Iterate over all comments of the post via an iPhone endpoint.
 
-        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`])
+        .. 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]:
+        """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`])
         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']),
@@ -551,18 +717,24 @@ 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')
-        answers_count = sum([edge['node'].get('edge_threaded_comments', {}).get('count', 0) for edge in 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',
@@ -580,7 +752,7 @@ 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
@@ -625,7 +797,7 @@ class Post:
     @property
     def location(self) -> Optional[PostLocation]:
         """
-        If the Post has a location, returns PostLocation namedtuple with fields 'id', 'lat' and 'lng' and 'name'.
+        If the Post has a location, returns PostLocation NamedTuple with fields 'id', 'lat' and 'lng' and 'name'.
 
         .. versionchanged:: 4.2.9
            Require being logged in (as required by Instagram), return None if not logged-in.
@@ -638,14 +810,18 @@ class Post:
         location_id = int(loc['id'])
         if any(k not in loc for k in ('name', 'slug', 'has_public_page', 'lat', 'lng')):
             loc.update(self._context.get_json("explore/locations/{0}/".format(location_id),
-                                              params={'__a': 1})['native_location_data']['location_info'])
+                                              params={'__a': 1, '__d': 'dis'})['native_location_data']['location_info'])
         self._location = PostLocation(location_id, loc['name'], loc['slug'], loc['has_public_page'],
                                       loc.get('lat'), loc.get('lng'))
         return self._location
 
     @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'])
@@ -681,7 +857,7 @@ class Profile:
     def __init__(self, context: InstaloaderContext, node: Dict[str, Any]):
         assert 'username' in node
         self._context = context
-        self._has_public_story = None  # type: Optional[bool]
+        self._has_public_story: Optional[bool] = None
         self._node = node
         self._has_full_metadata = False
         self._iphone_struct_ = None
@@ -753,7 +929,7 @@ 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):
@@ -807,7 +983,7 @@ 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']
@@ -874,7 +1050,29 @@ class Profile:
 
     @property
     def biography(self) -> str:
-        return self._metadata('biography')
+        return normalize("NFC", self._metadata('biography'))
+
+    @property
+    def biography_hashtags(self) -> List[str]:
+        """
+        List of all lowercased hashtags (without preceeding #) that occur in the Profile's biography.
+
+        .. versionadded:: 4.10
+        """
+        if not self.biography:
+            return []
+        return _hashtag_regex.findall(self.biography.lower())
+
+    @property
+    def biography_mentions(self) -> List[str]:
+        """
+        List of all lowercased profiles that are mentioned in the Profile's biography, without preceeding @.
+
+        .. versionadded:: 4.10
+        """
+        if not self.biography:
+            return []
+        return _mention_regex.findall(self.biography.lower())
 
     @property
     def blocked_by_viewer(self) -> bool:
@@ -992,7 +1190,7 @@ 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,
@@ -1039,17 +1237,29 @@ class Profile:
         )
 
     @staticmethod
-    def _make_is_newest_checker() -> Callable[[Post], bool]:
-        newest_date: Optional[datetime] = None
-        def is_newest(p: Post) -> bool:
-            nonlocal newest_date
-            post_date = p.date_local
-            if newest_date is None or post_date > newest_date:
-                newest_date = post_date
-                return True
-            else:
-                return False
-        return is_newest
+    def _make_is_newest_checker() -> Callable[[Post, Optional[Post]], bool]:
+        return lambda post, first: first is None or post.date_local > first.date_local
+
+    def get_followed_hashtags(self) -> NodeIterator['Hashtag']:
+        """
+        Retrieve list of hashtags followed by given profile.
+        To use this, one needs to be logged in and private profiles has to be followed.
+
+        :rtype: NodeIterator[Hashtag]
+
+        .. versionadded:: 4.10
+        """
+        if not self._context.is_logged_in:
+            raise LoginRequiredException("Login required to get a profile's followers.")
+        self._obtain_metadata()
+        return NodeIterator(
+            self._context,
+            'e6306cc3dbe69d6a82ef8b5f8654c50b',
+            lambda d: d["data"]["user"]["edge_following_hashtag"],
+            lambda n: Hashtag(self._context, n),
+            {'id': str(self.userid)},
+            'https://www.instagram.com/{0}/'.format(self.username),
+        )
 
     def get_followers(self) -> NodeIterator['Profile']:
         """
@@ -1059,7 +1269,7 @@ 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,
@@ -1078,7 +1288,7 @@ 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,
@@ -1097,7 +1307,7 @@ 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",
@@ -1176,7 +1386,7 @@ 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={}
@@ -1257,6 +1467,53 @@ class StoryItem:
         """Type of post, GraphStoryImage or GraphStoryVideo"""
         return self._node['__typename']
 
+    @property
+    def caption(self) -> Optional[str]:
+        """
+        Caption.
+
+        .. versionadded:: 4.10
+        """
+        if "edge_media_to_caption" in self._node and self._node["edge_media_to_caption"]["edges"]:
+            return _optional_normalize(self._node["edge_media_to_caption"]["edges"][0]["node"]["text"])
+        elif "caption" in self._node:
+            return _optional_normalize(self._node["caption"])
+        return None
+
+    @property
+    def caption_hashtags(self) -> List[str]:
+        """
+        List of all lowercased hashtags (without preceeding #) that occur in the StoryItem's caption.
+
+        .. versionadded:: 4.10
+        """
+        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 StoryItem's caption, without preceeding @.
+
+        .. versionadded:: 4.10
+        """
+        if not self.caption:
+            return []
+        return _mention_regex.findall(self.caption.lower())
+
+    @property
+    def pcaption(self) -> str:
+        """
+        Printable caption, useful as a format specifier for --filename-pattern.
+
+        .. versionadded:: 4.10
+        """
+        def _elliptify(caption):
+            pcaption = ' '.join([s.replace('/', '\u2215') for s in caption.splitlines() if s]).strip()
+            return (pcaption[:30] + "\u2026") if len(pcaption) > 31 else pcaption
+        return _elliptify(self.caption) if self.caption else ''
+
     @property
     def is_video(self) -> bool:
         """True if the StoryItem is a video."""
@@ -1322,9 +1579,9 @@ class Story:
     def __init__(self, context: InstaloaderContext, node: Dict[str, Any]):
         self._context = context
         self._node = node
-        self._unique_id = None      # type: Optional[str]
-        self._owner_profile = None  # type: Optional[Profile]
-        self._iphone_struct_ = None  # type: Optional[Dict[str, Any]]
+        self._unique_id: Optional[str] = None
+        self._owner_profile: Optional[Profile] = None
+        self._iphone_struct_: Optional[Dict[str, Any]] = None
 
     def __repr__(self):
         return '<Story by {} changed {:%Y-%m-%d_%H-%M-%S_UTC}>'.format(self.owner_username, self.latest_media_utc)
@@ -1440,8 +1697,8 @@ class Highlight(Story):
     def __init__(self, context: InstaloaderContext, node: Dict[str, Any], owner: Optional[Profile] = None):
         super().__init__(context, node)
         self._owner_profile = owner
-        self._items = None  # type: Optional[List[Dict[str, Any]]]
-        self._iphone_struct_ = None  # type: Optional[Dict[str, Any]]
+        self._items: Optional[List[Dict[str, Any]]] = None
+        self._iphone_struct_: Optional[Dict[str, Any]] = None
 
     def __repr__(self):
         return '<Highlight by {}: {}>'.format(self.owner_username, self.title)
@@ -1559,7 +1816,7 @@ class Hashtag:
 
     def _obtain_metadata(self):
         if not self._has_full_metadata:
-            self._node = self._query({"__a": 1})
+            self._node = self._query({"__a": 1, "__d": "dis"})
             self._has_full_metadata = True
 
     def _asdict(self):

setup.py

@@ -18,10 +18,13 @@ def get_version():
     raise SystemExit("Could not find version string.")
 
 
-if sys.version_info < (3, 6):
-    sys.exit('Instaloader requires Python >= 3.6.')
+if sys.version_info < (3, 8):
+    sys.exit('Instaloader requires Python >= 3.8.')
 
 requirements = ['requests>=2.4']
+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='>=3.6',
+    python_requires='>=3.8',
+    extras_require=optional_requirements,
     entry_points={'console_scripts': ['instaloader=instaloader.__main__:main']},
     zip_safe=False,
     keywords=keywords,
@@ -54,10 +58,11 @@ setup(
         'Intended Audience :: Developers',
         'License :: OSI Approved :: MIT License',
         'Operating System :: OS Independent',
-        'Programming Language :: Python :: 3.6',
-        'Programming Language :: Python :: 3.7',
         '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 :: Only',
         'Topic :: Internet',
         'Topic :: Multimedia :: Graphics'

test/instaloader_unittests.py

@@ -23,7 +23,7 @@ PRIVATE_PROFILE_ID = 1706625676
 EMPTY_PROFILE = "not_public"
 EMPTY_PROFILE_ID = 1928659031
 
-ratecontroller = None  # type: Optional[instaloader.RateController]
+ratecontroller: Optional[instaloader.RateController] = None
 
 
 class TestInstaloaderAnonymously(unittest.TestCase):