Release of Version 4.9.4

We are proud to announce @socialmethod as our new sponsor.

.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==2022.1.8
+          pipenv sync --dev
+      - name: "Build Documentation"
+        run: pipenv 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

@@ -8,24 +8,19 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10"]
+        python-version: ["3.6", "3.7", "3.8", "3.9", "3.10"]
     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==2021.5.29
+          python -m pip install pipenv==2022.1.8
           pipenv sync --dev
       - name: PyLint
         run: pipenv run pylint instaloader
       - name: MyPy
         run: pipenv 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

README.rst

@@ -127,6 +127,9 @@ Supporters
 
 .. current-sponsors-start
 
+| Instaloader is proudly sponsored by
+|  `@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/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==2021.5.29",
+commands = ["pip install pipenv==2022.1.8",
             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.
@@ -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')]
 

instaloader/__init__.py

@@ -1,7 +1,7 @@
 """Download pictures (or videos) along with their captions and other metadata from Instagram."""
 
 
-__version__ = '4.9b2'
+__version__ = '4.9.4'
 
 
 try:

instaloader/__main__.py

@@ -383,6 +383,9 @@ 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 +466,8 @@ 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

@@ -137,24 +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 ret.startswith('.'):
             ret = ret.replace('.', '\u2024', 1)
 
-        if platform.system() == 'Windows':
+        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
 
 
@@ -187,6 +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
 
@@ -216,7 +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,
@@ -233,6 +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
@@ -296,7 +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
@@ -317,15 +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
-        if os.path.isfile(filename):
+        urlmatch = re.search('\\.[a-z0-9]*\\?', url)
+        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
 
@@ -450,9 +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 BytesIO(bcaption) as bio:
-                shutil.copyfileobj(cast(IO, bio), text_file)
+        with open(filename, 'w', encoding='UTF-8') as fio:
+            fio.write(caption)
         os.utime(filename, (datetime.now().timestamp(), mtime.timestamp()))
 
     def save_location(self, filename: str, location: PostLocation, mtime: datetime) -> None:
@@ -506,9 +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)
-        filename_template = os.path.join(dirname,
-                                         _PostPathFormatter(pic_data).format(self.title_pattern, target=target))
+        dirname = _PostPathFormatter(pic_data, self.sanitize_paths).format(self.dirname_pattern, target=target)
+        filename_template = os.path.join(
+                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
@@ -534,7 +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
@@ -633,7 +661,7 @@ 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:
         """
@@ -665,7 +693,7 @@ 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)
 
@@ -846,17 +874,22 @@ 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:
@@ -914,8 +947,9 @@ class Instaloader:
             name = user_highlight.owner_username
             highlight_target = (filename_target
                                 if filename_target
-                                else (Path(_PostPathFormatter.sanitize_path(name)) /
-                                      _PostPathFormatter.sanitize_path(user_highlight.title)))  # type: Union[str, Path]
+                                else (Path(_PostPathFormatter.sanitize_path(name, self.sanitize_paths)) /
+                                      _PostPathFormatter.sanitize_path(user_highlight.title,
+                                                                       self.sanitize_paths)))  # type: Union[str, Path]
             self.context.log("Retrieving highlights \"{}\" from profile {}".format(user_highlight.title, name))
             self.download_highlight_cover(user_highlight, highlight_target)
             totalcount = user_highlight.itemcount
@@ -965,7 +999,7 @@ 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(
@@ -980,7 +1014,10 @@ 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,
@@ -1012,7 +1049,7 @@ 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
@@ -1146,8 +1183,8 @@ class Instaloader:
         """Get Posts associated with a #hashtag.
 
         .. deprecated:: 4.4
-           Use :meth:`Hashtag.get_posts`."""
-        return Hashtag.from_name(self.context, hashtag).get_posts()
+           Use :meth:`Hashtag.get_posts_resumable`."""
+        return Hashtag.from_name(self.context, hashtag).get_posts_resumable()
 
     def download_hashtag(self, hashtag: Union[Hashtag, str],
                          max_count: Optional[int] = None,
@@ -1183,7 +1220,7 @@ 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,
@@ -1209,8 +1246,8 @@ class Instaloader:
         tagged_posts = profile.get_tagged_posts()
         self.posts_download_loop(tagged_posts,
                                  target if target
-                                 else (Path(_PostPathFormatter.sanitize_path(profile.username)) /
-                                       _PostPathFormatter.sanitize_path(':tagged')),
+                                 else (Path(_PostPathFormatter.sanitize_path(profile.username, self.sanitize_paths)) /
+                                       _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)
@@ -1304,6 +1341,10 @@ 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

instaloader/nodeiterator.py

@@ -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
@@ -91,6 +92,7 @@ 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]
@@ -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:
-                self._first_node = node
+            if self._is_first is not None:
+                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']:
             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
 

instaloader/structures.py

@@ -7,7 +7,8 @@ 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, Optional, Tuple, Union
+from unicodedata import normalize
 
 from . import __version__
 from .exceptions import *
@@ -292,7 +293,7 @@ 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
@@ -356,18 +357,23 @@ 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(
-                                err, self))
+                            self._context.error(f"Unable to fetch high quality image version of {self}: {err}")
                     yield PostSidecarNode(is_video=is_video, display_url=display_url,
                                           video_url=node['video_url'] if is_video else None)
 
     @property
     def caption(self) -> Optional[str]:
         """Caption."""
+        def _normalize(string: Optional[str]) -> Optional[str]:
+            if string is not None:
+                return normalize("NFC", string)
+            else:
+                return None
+
         if "edge_media_to_caption" in self._node and self._node["edge_media_to_caption"]["edges"]:
-            return self._node["edge_media_to_caption"]["edges"][0]["node"]["text"]
+            return _normalize(self._node["edge_media_to_caption"]["edges"][0]["node"]["text"])
         elif "caption" in self._node:
-            return self._node["caption"]
+            return _normalize(self._node["caption"])
         return None
 
     @property
@@ -389,7 +395,7 @@ class Post:
         # 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))?)")
+        mention_regex = re.compile(r"(?:^|\W|_)(?:@)(\w(?:(?:\w|(?:\.(?!\.))){0,28}(?:\w))?)", re.ASCII)
         return re.findall(mention_regex, self.caption.lower())
 
     @property
@@ -637,6 +643,13 @@ class Post:
                                       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:
     """
@@ -757,13 +770,19 @@ class Profile:
     def _obtain_metadata(self):
         try:
             if not self._has_full_metadata:
-                metadata = self._context.get_json('{}/feed/'.format(self.username), params={})
-                self._node = metadata['entry_data']['ProfilePage'][0]['graphql']['user']
+                metadata = self._context.get_iphone_json(f'api/v1/users/web_profile_info/?username={self.username}',
+                                                         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',
@@ -933,11 +952,18 @@ 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
 
@@ -957,6 +983,7 @@ 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]:
@@ -990,6 +1017,7 @@ 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]:
@@ -1007,8 +1035,13 @@ 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_followers(self) -> NodeIterator['Profile']:
         """
         Retrieve list of followers of given profile.
@@ -1114,6 +1147,21 @@ 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:
@@ -1121,8 +1169,14 @@ 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={})
-            self._iphone_struct_ = data['items'][0]
+            data = self._context.get_iphone_json(
+                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
@@ -1179,13 +1233,14 @@ 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
@@ -1260,6 +1315,7 @@ class Story:
         self._node = node
         self._unique_id = None      # type: Optional[str]
         self._owner_profile = None  # type: Optional[Profile]
+        self._iphone_struct_ = None  # type: Optional[Dict[str, Any]]
 
     def __repr__(self):
         return '<Story by {} changed {:%Y-%m-%d_%H-%M-%S_UTC}>'.format(self.owner_username, self.latest_media_utc)
@@ -1330,9 +1386,23 @@ 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):
@@ -1362,6 +1432,7 @@ class Highlight(Story):
         super().__init__(context, node)
         self._owner_profile = owner
         self._items = None  # type: Optional[List[Dict[str, Any]]]
+        self._iphone_struct_ = None  # type: Optional[Dict[str, Any]]
 
     def __repr__(self):
         return '<Highlight by {}: {}>'.format(self.owner_username, self.title)
@@ -1400,6 +1471,13 @@ 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."""
@@ -1410,8 +1488,15 @@ 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:
@@ -1552,7 +1637,10 @@ class Hashtag:
             return self._metadata("media_count")
 
     def get_posts(self) -> Iterator[Post]:
-        """Yields the recent posts associated with this hashtag."""
+        """Yields the recent posts associated with this hashtag.
+
+        .. deprecated:: 4.9
+           Use :meth:`Hashtag.get_posts_resumable` as this method may return incorrect results (:issue:`1457`)"""
         try:
             self._metadata("edge_hashtag_to_media", "edges")
             self._metadata("edge_hashtag_to_media", "page_info")
@@ -1574,7 +1662,7 @@ class Hashtag:
     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(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: