Release of Version 4.9.2

Instead of hard-coding a check for pinned items when storing the first
item, allows the creater of NodeIterator to specify how the comparison
should be made.

This also allows storing the newest post (whatever it's status is),
instead of simply storing the newst non-pinned post, which prevents
redownloads in case a user adds only a pinned post between runs.

.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 }}

.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

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__ = '4.9b1'
+__version__ = '4.9.2'
 
 
 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
 
@@ -458,9 +486,12 @@ class Instaloader:
     def save_location(self, filename: str, location: PostLocation, mtime: datetime) -> None:
         """Save post location name and Google Maps link."""
         filename += '_location.txt'
-        location_string = (location.name + "\n" +
-                           "https://maps.google.com/maps?q={0},{1}&ll={0},{1}\n".format(location.lat,
-                                                                                        location.lng))
+        if location.lat is not None and location.lng is not None:
+            location_string = (location.name + "\n" +
+                               "https://maps.google.com/maps?q={0},{1}&ll={0},{1}\n".format(location.lat,
+                                                                                            location.lng))
+        else:
+            location_string = location.name
         with open(filename, 'wb') as text_file:
             with BytesIO(location_string.encode()) as bio:
                 shutil.copyfileobj(cast(IO, bio), text_file)
@@ -503,9 +534,10 @@ 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
@@ -630,7 +662,7 @@ 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:
         """
@@ -662,7 +694,7 @@ 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)
 
@@ -813,7 +845,7 @@ 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)
@@ -843,7 +875,7 @@ 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
@@ -911,8 +943,9 @@ 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
@@ -962,7 +995,7 @@ 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(
@@ -977,7 +1010,10 @@ 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,
@@ -1009,7 +1045,7 @@ 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
@@ -1143,8 +1179,8 @@ 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,
@@ -1180,7 +1216,7 @@ 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,
@@ -1202,15 +1238,15 @@ 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)) /
-                                       _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.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,
@@ -1225,12 +1261,12 @@ 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
@@ -1301,6 +1337,10 @@ 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
@@ -1423,14 +1463,14 @@ 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/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], 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]
@@ -128,19 +130,24 @@ 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_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'])
-            page_index, data = self._page_index, self._data
-            try:
-                self._page_index = 0
-                self._data = query_response
-            except KeyboardInterrupt:
-                self._page_index, self._data = page_index, data
-                raise
-            return self.__next__()
+            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
+                    self._data = query_response
+                except KeyboardInterrupt:
+                    self._page_index, self._data = page_index, data
+                    raise
+                return self.__next__()
         raise StopIteration()
 
     @property
@@ -167,7 +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 *
@@ -38,8 +39,8 @@ PostLocation.id.__doc__ = "ID number of location."
 PostLocation.name.__doc__ = "Location name."
 PostLocation.slug.__doc__ = "URL friendly variant of location name."
 PostLocation.has_public_page.__doc__ = "Whether location has a public page."
-PostLocation.lat.__doc__ = "Latitude (:class:`float`)."
-PostLocation.lng.__doc__ = "Longitude (:class:`float`)."
+PostLocation.lat.__doc__ = "Latitude (:class:`float` or None)."
+PostLocation.lng.__doc__ = "Longitude (:class:`float` or None)."
 
 
 class Post:
@@ -262,17 +263,16 @@ class Post:
 
     @property
     def date_local(self) -> datetime:
-        """Timestamp when the post was created (local time zone)."""
-        return datetime.fromtimestamp(self._node["date"]
-                                      if "date" in self._node
-                                      else self._node["taken_at_timestamp"])
+        """Timestamp when the post was created (local time zone).
+
+        .. versionchanged:: 4.9
+           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"]
-                                         if "date" in self._node
-                                         else self._node["taken_at_timestamp"])
+        return datetime.utcfromtimestamp(self._get_timestamp_date_created())
 
     @property
     def date(self) -> datetime:
@@ -313,6 +313,12 @@ 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.
@@ -359,10 +365,16 @@ class Post:
     @property
     def caption(self) -> Optional[str]:
         """Caption."""
+        def _normalize(string: Optional[str]) -> Optional[str]:
+            if string is not None:
+                return normalize("NFC", string)
+            else:
+                return None
+
         if "edge_media_to_caption" in self._node and self._node["edge_media_to_caption"]["edges"]:
-            return 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
@@ -384,7 +396,7 @@ 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
@@ -629,9 +641,16 @@ class Post:
             loc.update(self._context.get_json("explore/locations/{0}/".format(location_id),
                                               params={'__a': 1})['native_location_data']['location_info'])
         self._location = PostLocation(location_id, loc['name'], loc['slug'], loc['has_public_page'],
-                                      loc['lat'], loc['lng'])
+                                      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:
     """
@@ -752,13 +771,19 @@ 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',
@@ -952,6 +977,7 @@ 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]:
@@ -985,6 +1011,7 @@ 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]:
@@ -1002,8 +1029,22 @@ 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], bool]:
+        newest_date: Optional[datetime] = None
+        def is_newest(p: Post) -> bool:
+            nonlocal newest_date
+            post_date = p.date_local
+            if newest_date is None or post_date > newest_date:
+                newest_date = post_date
+                return True
+            else:
+                return False
+        return is_newest
+
     def get_followers(self) -> NodeIterator['Profile']:
         """
         Retrieve list of followers of given profile.
@@ -1109,6 +1150,21 @@ 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:
@@ -1140,8 +1196,11 @@ class StoryItem:
 
     @property
     def date_local(self) -> datetime:
-        """Timestamp when the StoryItem was created (local time zone)."""
-        return datetime.fromtimestamp(self._node['taken_at_timestamp'])
+        """Timestamp when the StoryItem was created (local time zone).
+
+        .. versionchanged:: 4.9
+           Return timezone aware datetime object."""
+        return datetime.fromtimestamp(self._node['taken_at_timestamp']).astimezone()
 
     @property
     def date_utc(self) -> datetime:
@@ -1171,7 +1230,8 @@ 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('&')
@@ -1544,7 +1604,10 @@ 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")
@@ -1566,7 +1629,7 @@ 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:
@@ -1655,7 +1718,7 @@ class TopSearchResults:
             place = location.get('place', {})
             slug = place.get('slug')
             loc = place.get('location', {})
-            yield PostLocation(int(loc['pk']), loc['name'], slug, None, loc['lat'], loc['lng'])
+            yield PostLocation(int(loc['pk']), loc['name'], slug, None, loc.get('lat'), loc.get('lng'))
 
     def get_hashtag_strings(self) -> Iterator[str]:
         """