attempt to fix 2FA

Fixes #1905.

.github/workflows/documentation.yml

@@ -0,0 +1,31 @@
+name: "Documentation"
+
+on: [push, pull_request]
+
+jobs:
+  docs:
+    name: "Documentation"
+    runs-on: ubuntu-latest
+    steps:
+      - name: "Checkout Instaloader Repository"
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0  # needed for building docs
+      - name: "Setup Python"
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.8
+      - name: "Install Dependencies"
+        run: |
+          python -m pip install pipenv==2023.2.4
+          pipenv --python `python --version | grep -Eo '3\.[0-9]+'` sync --dev
+      - name: "Build Documentation"
+        run: pipenv --python `python --version | grep -Eo '3\.[0-9]+'` run make -C docs html SPHINXOPTS="-W -n"
+      - name: "Deploy Documentation"
+        if: github.event_name == 'push' && github.ref == 'refs/heads/master'
+        uses: JamesIves/github-pages-deploy-action@v4.2.5
+        with:
+          branch: master
+          repository-name: instaloader/instaloader.github.io
+          folder: docs/_build/html
+          token: ${{ secrets.PAGES_DEPLOYMENT_TOKEN }}

.github/workflows/lint.yml

@@ -7,25 +7,21 @@ jobs:
     name: PyLint and MyPy
     runs-on: ubuntu-latest
     strategy:
+      fail-fast: false
       matrix:
-        python-version: ["3.8", "3.9", "3.10"]
+        python-version: ["3.8", "3.9", "3.10", "3.11"]
     steps:
       - name: Checkout Instaloader Repository
         uses: actions/checkout@v2
-        with:
-          fetch-depth: 0  # needed for building docs
       - name: Setup Python
         uses: actions/setup-python@v2
         with:
           python-version: ${{ matrix.python-version }}
       - name: Install Dependencies
         run: |
-          python -m pip install pipenv==2020.11.15
+          python -m pip install pipenv==2023.2.4
-          pipenv sync --dev
+          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
-      - name: Build Documentation
-        if: matrix.python-version == '3.8'
-        run: pipenv run make -C docs html SPHINXOPTS="-W -n"

.github/workflows/packages.yml

@@ -0,0 +1,36 @@
+name: "Publish Packages"
+
+on:
+  push:
+    tags:
+      - v*
+
+jobs:
+  publish:
+    name: "Publish Package"
+    runs-on: ubuntu-latest
+    steps:
+      - name: "Checkout Repository"
+        uses: actions/checkout@v2
+      - name: "Setup Python"
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.8
+      - name: "Get the tagged version"
+        id: get_version
+        env:
+          GITHUB_REF: ${{ github.ref }}
+        run: echo ::set-output name=VERSION::${GITHUB_REF/refs\/tags\/v/}
+        shell: bash
+      - name: "Generate Python Package"
+        run: python setup.py sdist
+      - name: "Publish Distribution to PyPI"
+        uses: pypa/gh-action-pypi-publish@master
+        with:
+          password: ${{ secrets.PYPI_PASSWORD }}
+      - name: "Publish Distribution to AUR"
+        run: deploy/arch/deploy.sh $VERSION_TAG
+        env:
+          VERSION_TAG: v${{ steps.get_version.outputs.VERSION }}
+          AUR_KEY: ${{ secrets.AUR_KEY }}
+          AUR_IV: ${{ secrets.AUR_IV }}

.github/workflows/stale.yml

@@ -18,7 +18,7 @@ jobs:
         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
@@ -30,5 +30,5 @@ jobs:
         stale-pr-label: 'stale'
         exempt-issue-label: 'leave open'
         exempt-pr-label: 'leave open'
-        days-before-stale: 135
+        days-before-stale: 189
         days-before-close: 14

.travis.yml

@@ -1,35 +0,0 @@
-dist: xenial
-language: python
-python:
- - "3.6"
- - "3.7"
-install:
- - pipenv sync --dev
-script:
- - pylint instaloader
- - mypy -m instaloader
- - make -C docs html SPHINXOPTS="-W -n"
-addons:
-  ssh_known_hosts: aur.archlinux.org
-deploy:
-  - provider: pypi
-    user: aandergr
-    on:
-      tags: true
-      python: 3.6
-    password:
-      secure: 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
-  - provider: pages
-    skip-cleanup: true
-    github-token: $GITHUB_TOKEN
-    local-dir: docs/_build/html
-    repo: instaloader/instaloader.github.io
-    target-branch: master
-    on:
-      branch: master
-      python: 3.6
-  - provider: script
-    script: deploy/arch/deploy.sh $TRAVIS_TAG
-    on:
-      tags: true
-      python: 3.6

Pipfile

@@ -12,6 +12,12 @@ pefile = "*"
 pywin32-ctypes = "*"
 psutil = "*"
 typing-extensions = "*"
+types-requests = "*"
+typed-ast = "*"
+jinja2 = "~=3.0.1"
+wrapt = "*"  # Needed for Python<3.11
+tomli = "*"  # Needed for Python<3.11
+dill = "*"  # Needed for Python<3.11
 
 [packages]
 requests = "*"

README.rst

@@ -2,11 +2,7 @@
 
 .. badges-start
 
-|travis| |pypi| |pyversion| |license| |aur| |contributors| |downloads|
+|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| image:: https://img.shields.io/pypi/v/instaloader.svg
    :alt: Instaloader PyPI Project Page
@@ -127,6 +123,10 @@ Supporters
 
 .. current-sponsors-start
 
+| Instaloader is proudly sponsored by
+|  `@rocketapi-io <https://github.com/rocketapi-io>`__
+|  `@socialmethod <https://github.com/socialmethod>`__
+
 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/arch/deploy.sh

@@ -8,10 +8,12 @@ echo $VERSION | grep -qe "[abc]" && exit 0
 cd $(dirname $0)
 
 # decrypt and add ssh key
-openssl aes-256-cbc -K $encrypted_354637631c28_key -iv $encrypted_354637631c28_iv -in id_rsa_AUR.enc -out /tmp/AUR_openssh -d
+openssl aes-256-cbc -K $AUR_KEY -iv $AUR_IV -in id_rsa_AUR.enc -out /tmp/AUR_openssh -d
 eval "$(ssh-agent -s)"
 chmod 600 /tmp/AUR_openssh
 ssh-add /tmp/AUR_openssh
+mkdir -p ~/.ssh
+ssh-keyscan -t rsa aur.archlinux.org >> ~/.ssh/known_hosts
 
 # clone and modify AUR repo
 git clone --depth 1 ssh://aur@aur.archlinux.org/instaloader.git

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==2020.11.15",
+commands = ["pip install pipenv==2023.2.4",
             f"pipenv --python {sys.version_info.major}.{sys.version_info.minor} sync --dev",
             "pipenv run pyinstaller --log-level=DEBUG instaloader.spec"]
 

docs/cli-options.rst

@@ -239,6 +239,13 @@ How to Download
 
    .. versionadded:: 4.8
 
+.. option:: --sanitize-paths
+
+   Force sanitization of paths so that the resulting file and directory names
+   are valid on both Windows and Unix.
+
+   .. versionadded:: 4.9
+
 .. option:: --resume-prefix prefix
 
    For many targets, Instaloader is capable of resuming a previously-aborted
@@ -251,7 +258,8 @@ How to Download
     - Profile posts,
     - Profile IGTV posts (:option:`--igtv`),
     - Profile tagged posts (:option:`--tagged`),
-    - Saved posts (``:saved``).
+    - Saved posts (``:saved``),
+    - Hashtags.
 
    This feature is enabled by default for targets where it is supported;
    :option:`--resume-prefix` only changes the name of the iterator files.
@@ -273,7 +281,7 @@ How to Download
 .. option:: --user-agent USER_AGENT
 
    User Agent to use for HTTP requests. Per default, Instaloader pretends being
-   Chrome/89 on Linux.
+   Chrome/92 on Linux.
 
 .. option:: --max-connection-attempts N
 
@@ -321,12 +329,13 @@ Miscellaneous Options
    Read arguments from file `args.txt`, a shortcut to provide arguments from
    file rather than command-line. This provides a convenient way to hide login
    info from CLI, and can also be used to simplify management of long arguments.
+   You can provide more than one file at once, e.g.: ``+args1.txt +args2.txt``.
 
    .. note::
 
       Text file should separate arguments with line breaks.
 
-   args.txt example::
+   `args.txt` example::
 
       --login=MYUSERNAME
       --password=MYPASSWORD

docs/conf.py

@@ -48,7 +48,7 @@ autodoc_default_flags = ['show-inheritance', 'members', 'undoc-members']
 autodoc_member_order = 'bysource'
 
 intersphinx_mapping = {'python': ('https://docs.python.org/3', None),
-                       'requests': ('https://requests.kennethreitz.org/en/master/', None)}
+                       'requests': ('https://requests.readthedocs.io/en/latest/', None)}
 
 nitpick_ignore = [('py:class', 'typing.Tuple')]
 

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/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``
 """""""""""""""""""""""

instaloader/__init__.py

@@ -1,7 +1,7 @@
 """Download pictures (or videos) along with their captions and other metadata from Instagram."""
 
 
-__version__ = '4.8.2'
+__version__ = '4.10'
 
 
 try:

instaloader/__main__.py

@@ -45,7 +45,6 @@ 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":
@@ -383,6 +382,9 @@ def main():
     g_how.add_argument('--resume-prefix', metavar='PREFIX',
                        help='Prefix for filenames that are used to save the information to resume an interrupted '
                             'download.')
+    g_how.add_argument('--sanitize-paths', action='store_true',
+                       help='Sanitize paths so that the resulting file and directory names are valid on both '
+                            'Windows and Unix.')
     g_how.add_argument('--no-resume', action='store_true',
                        help='Do not resume a previously-aborted download iteration, and do not save such information '
                             'when interrupted.')
@@ -463,7 +465,8 @@ def main():
                              slide=args.slide,
                              fatal_status_codes=args.abort_on,
                              iphone_support=not args.no_iphone,
-                             title_pattern=args.title_pattern)
+                             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,

instaloader/instaloader.py

@@ -22,6 +22,7 @@ from .exceptions import *
 from .instaloadercontext import InstaloaderContext, RateController
 from .lateststamps import LatestStamps
 from .nodeiterator import NodeIterator, resumable_iteration
+from .sectioniterator import SectionIterator
 from .structures import (Hashtag, Highlight, JsonExportable, Post, PostLocation, Profile, Story, StoryItem,
                          load_structure_from_file, save_structure_to_file, PostSidecarNode, TitlePic)
 
@@ -136,20 +137,38 @@ class _ArbitraryItemFormatter(string.Formatter):
 
 
 class _PostPathFormatter(_ArbitraryItemFormatter):
+    RESERVED: set = {'CON', 'PRN', 'AUX', 'NUL',
+                     'COM1', 'COM2', 'COM3', 'COM4', 'COM5', 'COM6', 'COM7', 'COM8', 'COM9',
+                     'LPT1', 'LPT2', 'LPT3', 'LPT4', 'LPT5', 'LPT6', 'LPT7', 'LPT8', 'LPT9'}
+
+    def __init__(self, item: Any, force_windows_path: bool = False):
+        super().__init__(item)
+        self.force_windows_path = force_windows_path
+
     def get_value(self, key, args, kwargs):
         ret = super().get_value(key, args, kwargs)
         if not isinstance(ret, str):
             return ret
-        return self.sanitize_path(ret)
+        return self.sanitize_path(ret, self.force_windows_path)
 
     @staticmethod
-    def sanitize_path(ret: str) -> str:
+    def sanitize_path(ret: str, force_windows_path: bool = False) -> str:
         """Replaces '/' with similar looking Division Slash and some other illegal filename characters on Windows."""
         ret = ret.replace('/', '\u2215')
-        if platform.system() == 'Windows':
+
+        if ret.startswith('.'):
+            ret = ret.replace('.', '\u2024', 1)
+
+        if force_windows_path or platform.system() == 'Windows':
             ret = ret.replace(':', '\uff1a').replace('<', '\ufe64').replace('>', '\ufe65').replace('\"', '\uff02')
             ret = ret.replace('\\', '\ufe68').replace('|', '\uff5c').replace('?', '\ufe16').replace('*', '\uff0a')
             ret = ret.replace('\n', ' ').replace('\r', ' ')
+            root, ext = os.path.splitext(ret)
+            if root.upper() in _PostPathFormatter.RESERVED:
+                root += '_'
+            if ext == '.':
+                ext = '\u2024'
+            ret = root + ext
         return ret
 
 
@@ -182,6 +201,7 @@ class Instaloader:
     :param slide: :option:`--slide`
     :param fatal_status_codes: :option:`--abort-on`
     :param iphone_support: not :option:`--no-iphone`
+    :param sanitize_paths: :option:`--sanitize-paths`
 
     .. attribute:: context
 
@@ -201,8 +221,8 @@ class Instaloader:
                  download_comments: bool = False,
                  save_metadata: bool = True,
                  compress_json: bool = True,
-                 post_metadata_txt_pattern: str = None,
+                 post_metadata_txt_pattern: Optional[str] = None,
-                 storyitem_metadata_txt_pattern: 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,
@@ -211,7 +231,8 @@ class Instaloader:
                  slide: Optional[str] = None,
                  fatal_status_codes: Optional[List[int]] = None,
                  iphone_support: bool = True,
-                 title_pattern: Optional[str] = None):
+                 title_pattern: Optional[str] = None,
+                 sanitize_paths: bool = False):
 
         self.context = InstaloaderContext(sleep, quiet, user_agent, max_connection_attempts,
                                           request_timeout, rate_controller, fatal_status_codes,
@@ -228,6 +249,7 @@ class Instaloader:
                 self.title_pattern = '{date_utc}_UTC_{typename}'
             else:
                 self.title_pattern = '{target}_{date_utc}_UTC_{typename}'
+        self.sanitize_paths = sanitize_paths
         self.download_pictures = download_pictures
         self.download_videos = download_videos
         self.download_video_thumbnails = download_video_thumbnails
@@ -291,7 +313,8 @@ class Instaloader:
             check_resume_bbd=self.check_resume_bbd,
             slide=self.slide,
             fatal_status_codes=self.context.fatal_status_codes,
-            iphone_support=self.context.iphone_support)
+            iphone_support=self.context.iphone_support,
+            sanitize_paths=self.sanitize_paths)
         yield new_loader
         self.context.error_log.extend(new_loader.context.error_log)
         new_loader.context.error_log = []  # avoid double-printing of errors
@@ -312,15 +335,25 @@ class Instaloader:
                      filename_suffix: Optional[str] = None, _attempt: int = 1) -> bool:
         """Downloads and saves picture with given url under given directory with given timestamp.
         Returns true, if file was actually downloaded, i.e. updated."""
-        urlmatch = re.search('\\.[a-z0-9]*\\?', url)
-        file_extension = url[-3:] if urlmatch is None else urlmatch.group(0)[1:-1]
         if filename_suffix is not None:
             filename += '_' + filename_suffix
-        filename += '.' + file_extension
+        urlmatch = re.search('\\.[a-z0-9]*\\?', url)
-        if os.path.isfile(filename):
+        file_extension = url[-3:] if urlmatch is None else urlmatch.group(0)[1:-1]
+        nominal_filename = filename + '.' + file_extension
+        if os.path.isfile(nominal_filename):
+            self.context.log(nominal_filename + ' exists', end=' ', flush=True)
+            return False
+        resp = self.context.get_raw(url)
+        if 'Content-Type' in resp.headers and resp.headers['Content-Type']:
+            header_extension = '.' + resp.headers['Content-Type'].split(';')[0].split('/')[-1]
+            header_extension = header_extension.lower().replace('jpeg', 'jpg')
+            filename += header_extension
+        else:
+            filename = nominal_filename
+        if filename != nominal_filename and os.path.isfile(filename):
             self.context.log(filename + ' exists', end=' ', flush=True)
             return False
-        self.context.get_and_write_raw(url, filename)
+        self.context.write_raw(resp, filename)
         os.utime(filename, (datetime.now().timestamp(), mtime.timestamp()))
         return True
 
@@ -414,7 +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)
@@ -445,9 +478,8 @@ class Instaloader:
             self.context.log(pcaption, end=' ', flush=True)
         except UnicodeEncodeError:
             self.context.log('txt', end=' ', flush=True)
-        with open(filename, 'wb') as text_file:
+        with open(filename, 'w', encoding='UTF-8') as fio:
-            with BytesIO(bcaption) as bio:
+            fio.write(caption)
-                shutil.copyfileobj(cast(IO, bio), text_file)
         os.utime(filename, (datetime.now().timestamp(), mtime.timestamp()))
 
     def save_location(self, filename: str, location: PostLocation, mtime: datetime) -> None:
@@ -492,7 +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)
@@ -501,9 +533,10 @@ class Instaloader:
             pic_bytes = http_response.content
         ig_filename = url.split('/')[-1].split('?')[0]
         pic_data = TitlePic(owner_profile, target, name_suffix, ig_filename, date_object)
-        dirname = _PostPathFormatter(pic_data).format(self.dirname_pattern, target=target)
+        dirname = _PostPathFormatter(pic_data, self.sanitize_paths).format(self.dirname_pattern, target=target)
-        filename_template = os.path.join(dirname,
+        filename_template = os.path.join(
-                                         _PostPathFormatter(pic_data).format(self.title_pattern, target=target))
+                dirname,
+                _PostPathFormatter(pic_data, self.sanitize_paths).format(self.title_pattern, target=target))
         filename = self.__prepare_filename(filename_template, lambda: url) + ".jpg"
         content_length = http_response.headers.get('Content-Length', None)
         if os.path.isfile(filename) and (not self.context.is_logged_in or
@@ -529,7 +562,7 @@ class Instaloader:
         if latest_stamps is None:
             self.download_profilepic(profile)
             return
-        profile_pic_basename = profile.profile_pic_url.split('/')[-1].split('?')[0]
+        profile_pic_basename = profile.profile_pic_url_no_iphone.split('/')[-1].split('?')[0]
         saved_basename = latest_stamps.get_profile_pic(profile.username)
         if saved_basename == profile_pic_basename:
             return
@@ -552,6 +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.
@@ -628,7 +678,7 @@ class Instaloader:
         """Format filename of a :class:`Post` or :class:`StoryItem` according to ``filename-pattern`` parameter.
 
         .. versionadded:: 4.1"""
-        return _PostPathFormatter(item).format(self.filename_pattern, target=target)
+        return _PostPathFormatter(item, self.sanitize_paths).format(self.filename_pattern, target=target)
 
     def download_post(self, post: Post, target: Union[str, Path]) -> bool:
         """
@@ -660,7 +710,7 @@ class Instaloader:
                         return False
             return True
 
-        dirname = _PostPathFormatter(post).format(self.dirname_pattern, target=target)
+        dirname = _PostPathFormatter(post, self.sanitize_paths).format(self.dirname_pattern, target=target)
         filename_template = os.path.join(dirname, self.format_filename(post, target=target))
         filename = self.__prepare_filename(filename_template, lambda: post.url)
 
@@ -679,7 +729,7 @@ 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):
@@ -811,7 +861,7 @@ class Instaloader:
                 last_scraped = latest_stamps.get_last_story_timestamp(name)
                 scraped_timestamp = datetime.now().astimezone()
             for item in user_story.get_items():
-                if latest_stamps is not None and item.date_utc.replace(tzinfo=timezone.utc) <= last_scraped:
+                if latest_stamps is not None and item.date_local <= last_scraped:
                     break
                 if storyitem_filter is not None and not storyitem_filter(item):
                     self.context.log("<{} skipped>".format(item), flush=True)
@@ -841,17 +891,22 @@ class Instaloader:
                 return True
 
         date_local = item.date_local
-        dirname = _PostPathFormatter(item).format(self.dirname_pattern, target=target)
+        dirname = _PostPathFormatter(item, self.sanitize_paths).format(self.dirname_pattern, target=target)
         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:
@@ -907,10 +962,11 @@ 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)) /
+                                else (Path(_PostPathFormatter.sanitize_path(name, self.sanitize_paths)) /
-                                      _PostPathFormatter.sanitize_path(user_highlight.title)))  # type: Union[str, Path]
+                                      _PostPathFormatter.sanitize_path(user_highlight.title,
+                                                                       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
@@ -960,7 +1016,7 @@ class Instaloader:
                            else total_count)
         sanitized_target = target
         if isinstance(target, str):
-            sanitized_target = _PostPathFormatter.sanitize_path(target)
+            sanitized_target = _PostPathFormatter.sanitize_path(target, self.sanitize_paths)
         if takewhile is None:
             takewhile = lambda _: True
         with resumable_iteration(
@@ -975,7 +1031,10 @@ class Instaloader:
                 enabled=self.resume_prefix is not None
         ) as (is_resuming, start_index):
             for number, post in enumerate(posts, start=start_index + 1):
-                if (max_count is not None and number > max_count) or not takewhile(post):
+                should_stop = not takewhile(post)
+                if should_stop and post.is_pinned:
+                    continue
+                if (max_count is not None and number > max_count) or should_stop:
                     break
                 if displayed_count is not None:
                     self.context.log("[{0:{w}d}/{1:{w}d}] ".format(number, displayed_count,
@@ -1007,7 +1066,7 @@ class Instaloader:
                         except PostChangedException:
                             post_changed = True
                             continue
-                    if fast_update and not downloaded and not post_changed:
+                    if fast_update and not downloaded and not post_changed and not post.is_pinned:
                         # disengage fast_update for first post when resuming
                         if not is_resuming or number > 0:
                             break
@@ -1038,7 +1097,7 @@ 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.
@@ -1059,7 +1118,7 @@ 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.
 
@@ -1087,18 +1146,12 @@ class Instaloader:
         .. versionchanged:: 4.2.9
            Require being logged in (as required by Instagram)
         """
-        has_next_page = True
+        yield from SectionIterator(
-        end_cursor = None
+            self.context,
-        while has_next_page:
+            lambda d: d["native_location_data"]["recent"],
-            if end_cursor:
+            lambda m: Post.from_iphone_struct(self.context, m),
-                params = {'__a': 1, 'max_id': end_cursor}
+            f"explore/locations/{location}/",
-            else:
+        )
-                params = {'__a': 1}
-            location_data = self.context.get_json('explore/locations/{0}/'.format(location),
-                                                  params)['graphql']['location']['edge_location_to_media']
-            yield from (Post(self.context, edge['node']) for edge in location_data['edges'])
-            has_next_page = location_data['page_info']['has_next_page']
-            end_cursor = location_data['page_info']['end_cursor']
 
     @_requires_login
     def download_location(self, location: str,
@@ -1147,8 +1200,8 @@ class Instaloader:
         """Get Posts associated with a #hashtag.
 
         .. deprecated:: 4.4
-           Use :meth:`Hashtag.get_posts`."""
+           Use :meth:`Hashtag.get_posts_resumable`."""
-        return Hashtag.from_name(self.context, hashtag).get_posts()
+        return Hashtag.from_name(self.context, hashtag).get_posts_resumable()
 
     def download_hashtag(self, hashtag: Union[Hashtag, str],
                          max_count: Optional[int] = None,
@@ -1184,7 +1237,7 @@ class Instaloader:
                 self.download_hashtag_profilepic(hashtag)
         if posts:
             self.context.log("Retrieving pictures with hashtag #{}...".format(hashtag.name))
-            self.posts_download_loop(hashtag.get_all_posts(), target, fast_update, post_filter,
+            self.posts_download_loop(hashtag.get_posts_resumable(), target, fast_update, post_filter,
                                      max_count=max_count)
         if self.save_metadata:
             json_filename = '{0}/{1}'.format(self.dirname_pattern.format(profile=target,
@@ -1206,15 +1259,15 @@ class Instaloader:
         posts_takewhile: Optional[Callable[[Post], bool]] = None
         if latest_stamps is not None:
             last_scraped = latest_stamps.get_last_tagged_timestamp(profile.username)
-            posts_takewhile = lambda p: p.date_utc.replace(tzinfo=timezone.utc) > last_scraped
+            posts_takewhile = lambda p: p.date_local > last_scraped
         tagged_posts = profile.get_tagged_posts()
         self.posts_download_loop(tagged_posts,
                                  target if target
-                                 else (Path(_PostPathFormatter.sanitize_path(profile.username)) /
+                                 else (Path(_PostPathFormatter.sanitize_path(profile.username, self.sanitize_paths)) /
-                                       _PostPathFormatter.sanitize_path(':tagged')),
+                                       _PostPathFormatter.sanitize_path(':tagged', self.sanitize_paths)),
                                  fast_update, post_filter, takewhile=posts_takewhile)
         if latest_stamps is not None and tagged_posts.first_item is not None:
-            latest_stamps.set_last_tagged_timestamp(profile.username, tagged_posts.first_item.date_local.astimezone())
+            latest_stamps.set_last_tagged_timestamp(profile.username, tagged_posts.first_item.date_local)
 
     def download_igtv(self, profile: Profile, fast_update: bool = False,
                       post_filter: Optional[Callable[[Post], bool]] = None,
@@ -1229,12 +1282,12 @@ class Instaloader:
         posts_takewhile: Optional[Callable[[Post], bool]] = None
         if latest_stamps is not None:
             last_scraped = latest_stamps.get_last_igtv_timestamp(profile.username)
-            posts_takewhile = lambda p: p.date_utc.replace(tzinfo=timezone.utc) > last_scraped
+            posts_takewhile = lambda p: p.date_local > last_scraped
         igtv_posts = profile.get_igtv_posts()
         self.posts_download_loop(igtv_posts, profile.username, fast_update, post_filter,
                                  total_count=profile.igtvcount, owner_profile=profile, takewhile=posts_takewhile)
         if latest_stamps is not None and igtv_posts.first_item is not None:
-            latest_stamps.set_last_igtv_timestamp(profile.username, igtv_posts.first_item.date_local.astimezone())
+            latest_stamps.set_last_igtv_timestamp(profile.username, igtv_posts.first_item.date_local)
 
     def _get_id_filename(self, profile_name: str) -> str:
         if ((format_string_contains_key(self.dirname_pattern, 'profile') or
@@ -1305,6 +1358,10 @@ class Instaloader:
                                                                                                   profile_id))
                 profile_from_id = Profile.from_id(self.context, profile_id)
                 newname = profile_from_id.username
+                if profile_name == newname:
+                    self.context.error(
+                        f"Warning: Profile {profile_name} could not be retrieved by its name, but by its ID.")
+                    return profile_from_id
                 self.context.error("Profile {0} has changed its name to {1}.".format(profile_name, newname))
                 if latest_stamps is None:
                     if ((format_string_contains_key(self.dirname_pattern, 'profile') or
@@ -1427,14 +1484,14 @@ class Instaloader:
                     if latest_stamps is not None:
                         # pylint:disable=cell-var-from-loop
                         last_scraped = latest_stamps.get_last_post_timestamp(profile_name)
-                        posts_takewhile = lambda p: p.date_utc.replace(tzinfo=timezone.utc) > last_scraped
+                        posts_takewhile = lambda p: p.date_local > last_scraped
                     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)
                     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.astimezone())
+                                                              posts_to_download.first_item.date_local)
 
         if stories and profiles:
             with self.context.error_catcher("Download stories"):

instaloader/instaloadercontext.py

@@ -9,6 +9,7 @@ import sys
 import textwrap
 import time
 import urllib.parse
+import uuid
 from contextlib import contextmanager
 from datetime import datetime, timedelta
 from functools import partial
@@ -24,16 +25,44 @@ 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/89.0.4389.90 Safari/537.36'
+           '(KHTML, like Gecko) Chrome/92.0.4515.131 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 +90,7 @@ 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 +98,10 @@ 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 +112,26 @@ 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:
@@ -170,22 +207,30 @@ class InstaloaderContext:
         session.request = partial(session.request, timeout=self.request_timeout) # type: ignore
         return session
 
-    def save_session_to_file(self, sessionfile):
+    def save_session(self):
-        """Not meant to be used directly, use :meth:`Instaloader.save_session_to_file`."""
+        """Not meant to be used directly, use :meth:`Instaloader.save_session`."""
-        pickle.dump(requests.utils.dict_from_cookiejar(self._session.cookies), sessionfile)
+        return requests.utils.dict_from_cookiejar(self._session.cookies)
 
-    def load_session_from_file(self, username, sessionfile):
+    def load_session(self, username, sessiondata):
-        """Not meant to be used directly, use :meth:`Instaloader.load_session_from_file`."""
+        """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", {})
@@ -208,6 +253,8 @@ class InstaloaderContext:
                                 'ig_vw': '1920', 'ig_cb': '1', 'csrftoken': '',
                                 's_network': '', 'ds_user_id': ''})
         session.headers.update(self._default_http_header())
+        # Getting mid cookie value
+        session.get("https://i.instagram.com/api/v1/web/login_page/")
         # 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
@@ -262,9 +309,11 @@ class InstaloaderContext:
                 # username is invalid.
                 raise InvalidArgumentException('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']})
+        if 'csrftoken' in login.cookies:
+            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.
@@ -278,8 +327,15 @@ class InstaloaderContext:
             raise InvalidArgumentException("No two-factor authentication pending.")
         (session, user, two_factor_id) = self.two_factor_auth_pending
 
-        login = session.post('https://www.instagram.com/accounts/login/ajax/two_factor/',
+        login = session.post('https://www.instagram.com/api/v1/web/accounts/login/ajax/two_factor/',
-                             data={'username': user, 'verificationCode': two_factor_code, 'identifier': two_factor_id},
+                             data={
+                                 'identifier': two_factor_id,
+                                 'queryParams': '{"next":"/"}',
+                                 'trust_signal': 'true',
+                                 'username': user,
+                                 'verification_method': '1',
+                                 'verificationCode': two_factor_code,
+                             },
                              allow_redirects=True)
         resp_json = login.json()
         if resp_json['status'] != 'ok':
@@ -287,7 +343,8 @@ class InstaloaderContext:
                 raise BadCredentialsException("2FA error: {}".format(resp_json['message']))
             else:
                 raise BadCredentialsException("2FA error: \"{}\" status.".format(resp_json['status']))
-        session.headers.update({'X-CSRFToken': login.cookies['csrftoken']})
+        if 'csrftoken' in login.cookies:
+            session.headers.update({'X-CSRFToken': login.cookies['csrftoken']})
         self._session = session
         self.username = user
         self.two_factor_auth_pending = None
@@ -298,7 +355,8 @@ class InstaloaderContext:
             time.sleep(min(random.expovariate(0.6), 15.0))
 
     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/
@@ -325,22 +383,29 @@ 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(
+                body = ""
-                    host, path, resp.status_code, resp.reason, redirect
+                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 AbortDownloadException("Redirected to login page. You've been logged out, please wait " +
-                    raise TooManyRequestsException("Redirected to login")
+                                                 "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")
             if resp.status_code == 404:
@@ -351,20 +416,13 @@ class InstaloaderContext:
                 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)
+                # Extract JSON from HTML response
+                match = re.search('(?<={"raw":").*?(?<!\\\\)(?=")', resp.text)
                 if match is None:
-                    raise QueryReturnedNotFoundException("Could not find \"window._sharedData\" in html response.")
+                    raise QueryReturnedNotFoundException("Could not find JSON data in html response.")
-                resp_json = json.loads(match.group(1))
+                # Unescape escaped JSON string
-                entry_data = resp_json.get('entry_data')
+                unescaped_string = match.group(0).encode("utf-8").decode("unicode_escape")
-                post_or_profile_page = list(entry_data.values())[0] if entry_data is not None else None
+                resp_json = json.loads(unescaped_string)
-                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
             else:
                 resp_json = resp.json()
@@ -391,7 +449,8 @@ 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 +540,57 @@ 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; ' \
+            # Set headers to simulate an API request from iPad
-                                                'scale=2.00; 1656x3584; 190542906)'
+            tempsession.headers['ig-intended-user-id'] = str(self.user_id)
-            for header in ['Host', 'Origin', 'X-Instagram-AJAX', 'X-Requested-With']:
+            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.
@@ -581,7 +686,7 @@ 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 +694,6 @@ 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 +717,6 @@ 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',
+class FrozenNodeIterator(NamedTuple):
-                                [('query_hash', str),
+    query_hash: str
-                                 ('query_variables', Dict),
+    query_variables: Dict
-                                 ('query_referer', Optional[str]),
+    query_referer: Optional[str]
-                                 ('context_username', Optional[str]),
+    context_username: Optional[str]
-                                 ('total_index', int),
+    total_index: int
-                                 ('best_before', Optional[float]),
+    best_before: Optional[float]
-                                 ('remaining_data', Optional[Dict]),
+    remaining_data: Optional[Dict]
-                                 ('first_node', 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."""
@@ -76,7 +76,8 @@ class NodeIterator(Iterator[T]):
                  node_wrapper: Callable[[Dict], T],
                  query_variables: Optional[Dict[str, Any]] = None,
                  query_referer: Optional[str] = None,
-                 first_data: Optional[Dict[str, Any]] = None):
+                 first_data: Optional[Dict[str, Any]] = None,
+                 is_first: Optional[Callable[[T, Optional[T]], bool]] = None):
         self._context = context
         self._query_hash = query_hash
         self._edge_extractor = edge_extractor
@@ -91,9 +92,10 @@ class NodeIterator(Iterator[T]):
         else:
             self._data = self._query()
         self._first_node: Optional[Dict] = None
+        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:
@@ -128,12 +130,16 @@ class NodeIterator(Iterator[T]):
                 self._page_index, self._total_index = page_index, total_index
                 raise
             item = self._node_wrapper(node)
-            if self._first_node is None:
+            if self._is_first is not None:
-                self._first_node = node
+                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']:
+            if self._data['edges'] != query_response['edges'] and len(query_response['edges']) > 0:
                 page_index, data = self._page_index, self._data
                 try:
                     self._page_index = 0
@@ -168,7 +174,13 @@ class NodeIterator(Iterator[T]):
         """
         If this iterator has produced any items, returns the first item produced.
 
+        It is possible to override what is considered the first item (for example, to consider the
+        newest item in case items are not in strict chronological order) by passing a callback
+        function as the `is_first` parameter when creating the class.
+
         .. versionadded:: 4.8
+        .. versionchanged:: 4.9.2
+           What is considered the first item can be overridden.
         """
         return self._node_wrapper(self._first_node) if self._first_node is not None else None
 
@@ -277,7 +289,7 @@ 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

@@ -0,0 +1,46 @@
+from typing import Any, Callable, Dict, Iterator, Optional, TypeVar
+
+from .instaloadercontext import InstaloaderContext
+
+T = TypeVar('T')
+
+
+class SectionIterator(Iterator[T]):
+    """Iterator for the new 'sections'-style responses.
+
+    .. versionadded:: 4.9"""
+    def __init__(self,
+                 context: InstaloaderContext,
+                 sections_extractor: Callable[[Dict[str, Any]], Dict[str, Any]],
+                 media_wrapper: Callable[[Dict], T],
+                 query_path: str,
+                 first_data: Optional[Dict[str, Any]] = None):
+        self._context = context
+        self._sections_extractor = sections_extractor
+        self._media_wrapper = media_wrapper
+        self._query_path = query_path
+        self._data = first_data or self._query()
+        self._page_index = 0
+        self._section_index = 0
+
+    def __iter__(self):
+        return self
+
+    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, "__d": "dis", **pagination_variables})
+        )
+
+    def __next__(self) -> T:
+        if self._page_index < len(self._data['sections']):
+            media = self._data['sections'][self._page_index]['layout_content']['medias'][self._section_index]['media']
+            self._section_index += 1
+            if self._section_index >= len(self._data['sections'][self._page_index]['layout_content']['medias']):
+                self._section_index = 0
+                self._page_index += 1
+            return self._media_wrapper(media)
+        if self._data['more_available']:
+            self._page_index, self._section_index, self._data = 0, 0, self._query(self._data["next_max_id"])
+            return self.__next__()
+        raise StopIteration()

instaloader/structures.py

@@ -2,35 +2,70 @@ 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, 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__
 from .exceptions import *
 from .instaloadercontext import InstaloaderContext
 from .nodeiterator import FrozenNodeIterator, NodeIterator
+from .sectioniterator import SectionIterator
+
+
+class PostSidecarNode(NamedTuple):
+    """Item of a Sidecar Post."""
+    is_video: bool
+    display_url: str
+    video_url: str
+
 
-PostSidecarNode = namedtuple('PostSidecarNode', ['is_video', 'display_url', 'video_url'])
-PostSidecarNode.__doc__ = "Item of a Sidecar Post."
 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
+
+class PostComment(NamedTuple):
+    id: int
+    created_at_utc: datetime
+    text: str
+    owner: 'Profile'
+    likes_count: int
+    answers: Iterator[PostCommentAnswer]
+
+
 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
+PostComment.answers.__doc__ = r"Iterator which yields all :class:`PostCommentAnswer`\ s for the comment."
+
+
+class PostLocation(NamedTuple):
+    id: int
+    name: str
+    slug: str
+    has_public_page: Optional[bool]
+    lat: Optional[float]
+    lng: Optional[float]
+
 
-PostLocation = namedtuple('PostLocation', ['id', 'name', 'slug', 'has_public_page', 'lat', 'lng'])
 PostLocation.id.__doc__ = "ID number of location."
 PostLocation.name.__doc__ = "Location name."
 PostLocation.slug.__doc__ = "URL friendly variant of location name."
@@ -38,6 +73,22 @@ 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:
     """
@@ -69,8 +120,8 @@ class Post:
         self._context = context
         self._node = node
         self._owner_profile = owner_profile
-        self._full_metadata_dict = None  # type: Optional[Dict[str, Any]]
+        self._full_metadata_dict: Optional[Dict[str, Any]] = None
-        self._location = None            # type: Optional[PostLocation]
+        self._location: Optional[PostLocation] = None
         self._iphone_struct_ = None
         if 'iphone_struct' in node:
             # if loaded from JSON with load_structure_from_file()
@@ -89,6 +140,41 @@ class Post:
         """Create a post object from a given mediaid"""
         return cls.from_shortcode(context, Post.mediaid_to_shortcode(mediaid))
 
+    @classmethod
+    def from_iphone_struct(cls, context: InstaloaderContext, media: Dict[str, Any]):
+        """Create a post from a given iphone_struct.
+
+        .. versionadded:: 4.9"""
+        media_types = {
+            1: "GraphImage",
+            2: "GraphVideo",
+            8: "GraphSidecar",
+        }
+        fake_node = {
+            "shortcode": media["code"],
+            "id": media["pk"],
+            "__typename": media_types[media["media_type"]],
+            "is_video": media_types[media["media_type"]] == "GraphVideo",
+            "date": media["taken_at"],
+            "caption": media["caption"].get("text") if media.get("caption") is not None else None,
+            "title": media.get("title"),
+            "viewer_has_liked": media["has_liked"],
+            "edge_media_preview_like": {"count": media["like_count"]},
+            "iphone_struct": media,
+        }
+        with suppress(KeyError):
+            fake_node["display_url"] = media['image_versions2']['candidates'][0]['url']
+        with suppress(KeyError):
+            fake_node["video_url"] = media['video_versions'][-1]['url']
+            fake_node["video_duration"] = media["video_duration"]
+            fake_node["video_view_count"] = media["view_count"]
+        with suppress(KeyError):
+            fake_node["edge_sidecar_to_children"] = {"edges": [{"node": {
+                "display_url": node['image_versions2']['candidates'][0]['url'],
+                "is_video": media_types[node["media_type"]] == "GraphVideo",
+            }} for node in media["carousel_media"]]}
+        return cls(context, fake_node, Profile.from_iphone_struct(context, media["user"]) if "user" in media else None)
+
     @staticmethod
     def shortcode_to_mediaid(code: str) -> int:
         if len(code) > 11:
@@ -224,17 +310,16 @@ class Post:
 
     @property
     def date_local(self) -> datetime:
-        """Timestamp when the post was created (local time zone)."""
+        """Timestamp when the post was created (local time zone).
-        return datetime.fromtimestamp(self._node["date"]
+
-                                      if "date" in self._node
+        .. versionchanged:: 4.9
-                                      else self._node["taken_at_timestamp"])
+           Return timezone aware datetime object."""
+        return datetime.fromtimestamp(self._get_timestamp_date_created()).astimezone()
 
     @property
     def date_utc(self) -> datetime:
         """Timestamp when the post was created (UTC)."""
-        return datetime.utcfromtimestamp(self._node["date"]
+        return datetime.utcfromtimestamp(self._get_timestamp_date_created())
-                                         if "date" in self._node
-                                         else self._node["taken_at_timestamp"])
 
     @property
     def date(self) -> datetime:
@@ -255,7 +340,7 @@ class Post:
                 url = re.sub(r'([?&])se=\d+&?', r'\1', orig_url).rstrip('&')
                 return url
             except (InstaloaderException, KeyError, IndexError) as err:
-                self._context.error('{} Unable to fetch high quality image version of {}.'.format(err, self))
+                self._context.error(f"Unable to fetch high quality image version of {self}: {err}")
         return self._node["display_url"] if "display_url" in self._node else self._node["display_src"]
 
     @property
@@ -275,6 +360,12 @@ class Post:
             return len(edges)
         return 1
 
+    def _get_timestamp_date_created(self) -> float:
+        """Timestamp when the post was created"""
+        return (self._node["date"]
+                if "date" in self._node
+                else self._node["taken_at_timestamp"])
+
     def get_is_videos(self) -> List[bool]:
         """
         Return a list containing the ``is_video`` property for each media in the post.
@@ -313,8 +404,7 @@ class Post:
                             orig_url = carousel_media[idx]['image_versions2']['candidates'][0]['url']
                             display_url = re.sub(r'([?&])se=\d+&?', r'\1', orig_url).rstrip('&')
                         except (InstaloaderException, KeyError, IndexError) as err:
-                            self._context.error('{} Unable to fetch high quality image version of {}.'.format(
+                            self._context.error(f"Unable to fetch high quality image version of {self}: {err}")
-                                err, self))
                     yield PostSidecarNode(is_video=is_video, display_url=display_url,
                                           video_url=node['video_url'] if is_video else None)
 
@@ -322,9 +412,9 @@ class Post:
     def caption(self) -> Optional[str]:
         """Caption."""
         if "edge_media_to_caption" in self._node and self._node["edge_media_to_caption"]["edges"]:
-            return 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 self._node["caption"]
+            return _optional_normalize(self._node["caption"])
         return None
 
     @property
@@ -332,22 +422,14 @@ 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
+        return _hashtag_regex.findall(self.caption.lower())
-        # 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())
 
     @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
+        return _mention_regex.findall(self.caption.lower())
-        # 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))?)")
-        return re.findall(mention_regex, self.caption.lower())
 
     @property
     def pcaption(self) -> str:
@@ -356,9 +438,19 @@ 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
+    def accessibility_caption(self) -> Optional[str]:
+        """Accessibility caption of the post, if available.
+
+        .. versionadded:: 4.9"""
+        try:
+            return self._field("accessibility_caption")
+        except KeyError:
+            return None
+
     @property
     def tagged_users(self) -> List[str]:
         """List of all lowercased users that are tagged in the Post."""
@@ -456,7 +548,7 @@ class Post:
     def get_comments(self) -> Iterable[PostComment]:
         r"""Iterate over all comments of the post.
 
-        Each comment is represented by a PostComment namedtuple with fields text (string), created_at (datetime),
+        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.
 
@@ -499,7 +591,7 @@ class Post:
             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
@@ -566,7 +658,7 @@ 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.
@@ -579,11 +671,18 @@ 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.
+
+        .. versionadded: 4.9.2"""
+        return 'pinned_for_users' in self._node and bool(self._node['pinned_for_users'])
+
 
 class Profile:
     """
@@ -615,7 +714,7 @@ 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
@@ -665,6 +764,20 @@ class Profile:
         context.profile_id_cache[profile_id] = profile
         return profile
 
+    @classmethod
+    def from_iphone_struct(cls, context: InstaloaderContext, media: Dict[str, Any]):
+        """Create a profile from a given iphone_struct.
+
+        .. versionadded:: 4.9"""
+        return cls(context, {
+            "id": media["pk"],
+            "username": media["username"],
+            "is_private": media["is_private"],
+            "full_name": media["full_name"],
+            "profile_pic_url_hd": media["profile_pic_url"],
+            "iphone_struct": media,
+        })
+
     @classmethod
     def own_profile(cls, context: InstaloaderContext):
         """Return own profile if logged-in.
@@ -690,13 +803,19 @@ class Profile:
     def _obtain_metadata(self):
         try:
             if not self._has_full_metadata:
-                metadata = self._context.get_json('{}/feed/'.format(self.username), params={})
+                metadata = self._context.get_iphone_json(f'api/v1/users/web_profile_info/?username={self.username}',
-                self._node = metadata['entry_data']['ProfilePage'][0]['graphql']['user']
+                                                         params={})
+                if metadata['data']['user'] is None:
+                    raise ProfileNotExistsException('Profile {} does not exist.'.format(self.username))
+                self._node = metadata['data']['user']
                 self._has_full_metadata = True
         except (QueryReturnedNotFoundException, KeyError) as err:
             top_search_results = TopSearchResults(self._context, self.username)
             similar_profiles = [profile.username for profile in top_search_results.get_profiles()]
             if similar_profiles:
+                if self.username in similar_profiles:
+                    raise ProfileNotExistsException(
+                        f"Profile {self.username} seems to exist, but could not be loaded.") from err
                 raise ProfileNotExistsException('Profile {} does not exist.\nThe most similar profile{}: {}.'
                                                 .format(self.username,
                                                         's are' if len(similar_profiles) > 1 else ' is',
@@ -788,7 +907,29 @@ 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:
@@ -866,11 +1007,18 @@ class Profile:
             try:
                 return self._iphone_struct['hd_profile_pic_url_info']['url']
             except (InstaloaderException, KeyError) as err:
-                self._context.error('{} Unable to fetch high quality profile pic.'.format(err))
+                self._context.error(f"Unable to fetch high quality profile pic: {err}")
                 return self._metadata("profile_pic_url_hd")
         else:
             return self._metadata("profile_pic_url_hd")
 
+    @property
+    def profile_pic_url_no_iphone(self) -> str:
+        """Return URL of lower-quality profile picture.
+
+        .. versionadded:: 4.9.3"""
+        return self._metadata("profile_pic_url_hd")
+
     def get_profile_pic_url(self) -> str:
         """.. deprecated:: 4.0.3
 
@@ -890,6 +1038,7 @@ class Profile:
             {'id': self.userid},
             'https://www.instagram.com/{0}/'.format(self.username),
             self._metadata('edge_owner_to_timeline_media'),
+            Profile._make_is_newest_checker()
         )
 
     def get_saved_posts(self) -> NodeIterator[Post]:
@@ -923,6 +1072,7 @@ class Profile:
             lambda n: Post(self._context, n, self if int(n['owner']['id']) == self.userid else None),
             {'id': self.userid},
             'https://www.instagram.com/{0}/'.format(self.username),
+            is_first=Profile._make_is_newest_checker()
         )
 
     def get_igtv_posts(self) -> NodeIterator[Post]:
@@ -940,6 +1090,32 @@ class Profile:
             {'id': self.userid},
             'https://www.instagram.com/{0}/channel/'.format(self.username),
             self._metadata('edge_felix_video_timeline'),
+            Profile._make_is_newest_checker()
+        )
+
+    @staticmethod
+    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']:
@@ -1047,6 +1223,21 @@ class StoryItem:
     def __hash__(self) -> int:
         return hash(self.mediaid)
 
+    @classmethod
+    def from_mediaid(cls, context: InstaloaderContext, mediaid: int):
+        """Create a StoryItem object from a given mediaid.
+
+        .. versionadded:: 4.9
+        """
+        pic_json = context.graphql_query(
+            '2b0673e0dc4580674a88d426fe00ea90',
+            {'shortcode': Post.mediaid_to_shortcode(mediaid)}
+        )
+        shortcode_media = pic_json['data']['shortcode_media']
+        if shortcode_media is None:
+            raise BadResponseException("Fetching StoryItem metadata failed.")
+        return cls(context, shortcode_media)
+
     @property
     def _iphone_struct(self) -> Dict[str, Any]:
         if not self._context.iphone_support:
@@ -1054,8 +1245,14 @@ class StoryItem:
         if not self._context.is_logged_in:
             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={})
+            data = self._context.get_iphone_json(
-            self._iphone_struct_ = data['items'][0]
+                path='api/v1/feed/reels_media/?reel_ids={}'.format(self.owner_id), params={}
+            )
+            self._iphone_struct_ = {}
+            for item in data['reels'][str(self.owner_id)]['items']:
+                if item['pk'] == self.mediaid:
+                    self._iphone_struct_ = item
+                    break
         return self._iphone_struct_
 
     @property
@@ -1078,8 +1275,11 @@ class StoryItem:
 
     @property
     def date_local(self) -> datetime:
-        """Timestamp when the StoryItem was created (local time zone)."""
+        """Timestamp when the StoryItem was created (local time zone).
-        return datetime.fromtimestamp(self._node['taken_at_timestamp'])
+
+        .. versionchanged:: 4.9
+           Return timezone aware datetime object."""
+        return datetime.fromtimestamp(self._node['taken_at_timestamp']).astimezone()
 
     @property
     def date_utc(self) -> datetime:
@@ -1109,13 +1309,14 @@ class StoryItem:
     @property
     def url(self) -> str:
         """URL of the picture / video thumbnail of the StoryItem"""
-        if self.typename == "GraphStoryImage" and self._context.iphone_support and self._context.is_logged_in:
+        if self.typename in ["GraphStoryImage", "StoryImage"] and \
+                self._context.iphone_support and self._context.is_logged_in:
             try:
                 orig_url = self._iphone_struct['image_versions2']['candidates'][0]['url']
                 url = re.sub(r'([?&])se=\d+&?', r'\1', orig_url).rstrip('&')
                 return url
             except (InstaloaderException, KeyError, IndexError) as err:
-                self._context.error('{} Unable to fetch high quality image version of {}.'.format(err, self))
+                self._context.error(f"Unable to fetch high quality image version of {self}: {err}")
         return self._node['display_resources'][-1]['src']
 
     @property
@@ -1123,6 +1324,53 @@ 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."""
@@ -1188,8 +1436,9 @@ 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._unique_id: Optional[str] = None
-        self._owner_profile = None  # type: Optional[Profile]
+        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)
@@ -1260,9 +1509,23 @@ class Story:
         """The story owner's ID."""
         return self.owner_profile.userid
 
+    def _fetch_iphone_struct(self) -> None:
+        if self._context.iphone_support and self._context.is_logged_in and not self._iphone_struct_:
+            data = self._context.get_iphone_json(
+                path='api/v1/feed/reels_media/?reel_ids={}'.format(self.owner_id), params={}
+            )
+            self._iphone_struct_ = data['reels'][str(self.owner_id)]
+
     def get_items(self) -> Iterator[StoryItem]:
         """Retrieve all items from a story."""
-        yield from (StoryItem(self._context, item, self.owner_profile) for item in reversed(self._node['items']))
+        self._fetch_iphone_struct()
+        for item in reversed(self._node['items']):
+            if self._iphone_struct_ is not None:
+                for iphone_struct_item in self._iphone_struct_['items']:
+                    if iphone_struct_item['pk'] == int(item['id']):
+                        item['iphone_struct'] = iphone_struct_item
+                        break
+            yield StoryItem(self._context, item, self.owner_profile)
 
 
 class Highlight(Story):
@@ -1291,7 +1554,8 @@ 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._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)
@@ -1330,6 +1594,13 @@ class Highlight(Story):
                                                        "highlight_reel_ids": [str(self.unique_id)],
                                                        "precomposed_overlay": False})['data']['reels_media'][0]['items']
 
+    def _fetch_iphone_struct(self) -> None:
+        if self._context.iphone_support and self._context.is_logged_in and not self._iphone_struct_:
+            data = self._context.get_iphone_json(
+                path='api/v1/feed/reels_media/?reel_ids=highlight:{}'.format(self.unique_id), params={}
+            )
+            self._iphone_struct_ = data['reels']['highlight:{}'.format(self.unique_id)]
+
     @property
     def itemcount(self) -> int:
         """Count of items associated with the :class:`Highlight` instance."""
@@ -1340,8 +1611,15 @@ class Highlight(Story):
     def get_items(self) -> Iterator[StoryItem]:
         """Retrieve all associated highlight items."""
         self._fetch_items()
+        self._fetch_iphone_struct()
         assert self._items is not None
-        yield from (StoryItem(self._context, item, self.owner_profile) for item in self._items)
+        for item in self._items:
+            if self._iphone_struct_ is not None:
+                for iphone_struct_item in self._iphone_struct_['items']:
+                    if iphone_struct_item['pk'] == int(item['id']):
+                        item['iphone_struct'] = iphone_struct_item
+                        break
+            yield StoryItem(self._context, item, self.owner_profile)
 
 
 class Hashtag:
@@ -1359,6 +1637,9 @@ class Hashtag:
           L.download_post(post, target="#"+hashtag.name)
 
     Also, this class implements == and is hashable.
+
+    .. versionchanged:: 4.9
+       Removed ``get_related_tags()`` and ``is_top_media_only`` as these features were removed from Instagram.
     """
     def __init__(self, context: InstaloaderContext, node: Dict[str, Any]):
         assert "name" in node
@@ -1387,19 +1668,21 @@ class Hashtag:
         return self._node["name"].lower()
 
     def _query(self, params):
-        return self._context.get_json("explore/tags/{0}/".format(self.name),
+        json_response = self._context.get_json("explore/tags/{0}/".format(self.name), params)
-                                      params)["graphql"]["hashtag"]
+        return json_response["graphql"]["hashtag"] if "graphql" in json_response else json_response["data"]
 
     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):
         json_node = self._node.copy()
         # remove posts
         json_node.pop("edge_hashtag_to_top_posts", None)
+        json_node.pop("top", None)
         json_node.pop("edge_hashtag_to_media", None)
+        json_node.pop("recent", None)
         return json_node
 
     def __repr__(self):
@@ -1435,30 +1718,33 @@ class Hashtag:
         return self._metadata("profile_pic_url")
 
     @property
-    def description(self) -> str:
+    def description(self) -> Optional[str]:
         return self._metadata("description")
 
     @property
     def allow_following(self) -> bool:
-        return self._metadata("allow_following")
+        return bool(self._metadata("allow_following"))
 
     @property
     def is_following(self) -> bool:
-        return self._metadata("is_following")
+        try:
-
+            return self._metadata("is_following")
-    @property
+        except KeyError:
-    def is_top_media_only(self) -> bool:
+            return bool(self._metadata("following"))
-        return self._metadata("is_top_media_only")
-
-    def get_related_tags(self) -> Iterator["Hashtag"]:
-        """Yields similar hashtags."""
-        yield from (Hashtag(self._context, edge["node"])
-                    for edge in self._metadata("edge_hashtag_to_related_tags", "edges"))
 
     def get_top_posts(self) -> Iterator[Post]:
         """Yields the top posts of the hashtag."""
-        yield from (Post(self._context, edge["node"])
+        try:
-                    for edge in self._metadata("edge_hashtag_to_top_posts", "edges"))
+            yield from (Post(self._context, edge["node"])
+                        for edge in self._metadata("edge_hashtag_to_top_posts", "edges"))
+        except KeyError:
+            yield from SectionIterator(
+                self._context,
+                lambda d: d["data"]["top"],
+                lambda m: Post.from_iphone_struct(self._context, m),
+                f"explore/tags/{self.name}/",
+                self._metadata("top"),
+            )
 
     @property
     def mediacount(self) -> int:
@@ -1468,23 +1754,38 @@ class Hashtag:
         The number of posts with a certain hashtag may differ from the number of posts that can actually be accessed, as
         the hashtag count might include private posts
         """
-        return self._metadata("edge_hashtag_to_media", "count")
+        try:
+            return self._metadata("edge_hashtag_to_media", "count")
+        except KeyError:
+            return self._metadata("media_count")
 
     def get_posts(self) -> Iterator[Post]:
-        """Yields the posts associated with this hashtag."""
+        """Yields the recent posts associated with this hashtag.
-        self._metadata("edge_hashtag_to_media", "edges")
+
-        self._metadata("edge_hashtag_to_media", "page_info")
+        .. deprecated:: 4.9
-        conn = self._metadata("edge_hashtag_to_media")
+           Use :meth:`Hashtag.get_posts_resumable` as this method may return incorrect results (:issue:`1457`)"""
-        yield from (Post(self._context, edge["node"]) for edge in conn["edges"])
+        try:
-        while conn["page_info"]["has_next_page"]:
+            self._metadata("edge_hashtag_to_media", "edges")
-            data = self._query({'__a': 1, 'max_id': conn["page_info"]["end_cursor"]})
+            self._metadata("edge_hashtag_to_media", "page_info")
-            conn = data["edge_hashtag_to_media"]
+            conn = self._metadata("edge_hashtag_to_media")
             yield from (Post(self._context, edge["node"]) for edge in conn["edges"])
+            while conn["page_info"]["has_next_page"]:
+                data = self._query({'__a': 1, 'max_id': conn["page_info"]["end_cursor"]})
+                conn = data["edge_hashtag_to_media"]
+                yield from (Post(self._context, edge["node"]) for edge in conn["edges"])
+        except KeyError:
+            yield from SectionIterator(
+                self._context,
+                lambda d: d["data"]["recent"],
+                lambda m: Post.from_iphone_struct(self._context, m),
+                f"explore/tags/{self.name}/",
+                self._metadata("recent"),
+            )
 
     def get_all_posts(self) -> Iterator[Post]:
         """Yields all posts, i.e. all most recent posts and the top posts, in almost-chronological order."""
-        sorted_top_posts = iter(sorted(self.get_top_posts(), key=lambda p: p.date_utc, reverse=True))
+        sorted_top_posts = iter(sorted(islice(self.get_top_posts(), 9), key=lambda p: p.date_utc, reverse=True))
-        other_posts = self.get_posts()
+        other_posts = self.get_posts_resumable()
         next_top = next(sorted_top_posts, None)
         next_other = next(other_posts, None)
         while next_top is not None or next_other is not None:
@@ -1510,6 +1811,20 @@ class Hashtag:
                 yield next_other
                 next_other = next(other_posts, None)
 
+    def get_posts_resumable(self) -> NodeIterator[Post]:
+        """Get the recent posts of the hashtag in a resumable fashion.
+
+        :rtype: NodeIterator[Post]
+
+        .. versionadded:: 4.9"""
+        return NodeIterator(
+            self._context, "9b498c08113f1e09617a1703c22b2f32",
+            lambda d: d['data']['hashtag']['edge_hashtag_to_media'],
+            lambda n: Post(self._context, n),
+            {'tag_name': self.name},
+            f"https://www.instagram.com/explore/tags/{self.name}/"
+        )
+
 
 class TopSearchResults:
     """
@@ -1713,6 +2028,7 @@ def load_structure_from_file(context: InstaloaderContext, filename: str) -> Json
     if compressed:
         fp = lzma.open(filename, 'rt')
     else:
+        # pylint:disable=consider-using-with
         fp = open(filename, 'rt')
     json_structure = json.load(fp)
     fp.close()

setup.py

@@ -18,8 +18,8 @@ def get_version():
     raise SystemExit("Could not find version string.")
 
 
-if sys.version_info < (3, 6):
+if sys.version_info < (3, 8):
-    sys.exit('Instaloader requires Python >= 3.6.')
+    sys.exit('Instaloader requires Python >= 3.8.')
 
 requirements = ['requests>=2.4']
 
@@ -43,7 +43,7 @@ setup(
                 'from Instagram.',
     long_description=open(os.path.join(SRC, 'README.rst')).read(),
     install_requires=requirements,
-    python_requires='>=3.6',
+    python_requires='>=3.8',
     entry_points={'console_scripts': ['instaloader=instaloader.__main__:main']},
     zip_safe=False,
     keywords=keywords,
@@ -54,10 +54,10 @@ 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 :: 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):