Release of version 4.15.1

Use doc_id 26347858941511777 (search query) in from_username() to get user_id
Use doc_id 25980296051578533 (PolarisProfilePageContentQuery) in _obtain_metadata()
Add _normalize_profile_data() to map new API fields to legacy format

.github/workflows/documentation.yml

@@ -14,7 +14,7 @@ jobs:
       - name: "Setup Python"
         uses: actions/setup-python@v5
         with:
-          python-version: 3.12
+          python-version: 3.14
           cache: 'pipenv'
       - name: "Install Dependencies"
         run: |

.github/workflows/lint.yml

@@ -9,7 +9,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13", "3.14"]
     steps:
       - name: Checkout Instaloader Repository
         uses: actions/checkout@v4
@@ -23,6 +23,7 @@ jobs:
           python -m pip install pipenv==2025.0.4
           pipenv --python `python --version | grep -Eo '3\.[0-9]+'` sync --dev
       - name: PyLint
+        if: matrix.python-version != '3.9'
         run: pipenv --python `python --version | grep -Eo '3\.[0-9]+'` run pylint instaloader
       - name: MyPy
         run: pipenv --python `python --version | grep -Eo '3\.[0-9]+'` run mypy -m instaloader

.github/workflows/packages.yml

@@ -15,7 +15,7 @@ jobs:
       - name: "Setup Python"
         uses: actions/setup-python@v5
         with:
-          python-version: 3.12
+          python-version: 3.14
       - name: "Get the tagged version"
         id: get_version
         env:

.github/workflows/windows_exe.yml

@@ -12,7 +12,7 @@ jobs:
       - name: Setup Python
         uses: actions/setup-python@v5
         with:
-          python-version: "3.13"
+          python-version: "3.14"
           cache: 'pipenv'
           architecture: x64
       - name: Get the tagged version

docs/cli-options.rst

@@ -312,7 +312,7 @@ How to Download
 .. option:: --user-agent USER_AGENT
 
    User Agent to use for HTTP requests. Per default, Instaloader pretends being
-   Chrome/138 on Linux.
+   Chrome/142 on Linux.
 
 .. option:: --max-connection-attempts N
 

docs/codesnippets/113_only_one_per_user.py

@@ -2,7 +2,7 @@ import instaloader
 
 L = instaloader.Instaloader()
 
-posts = instaloader.Hashtag.from_name(L.context, 'urbanphotography').get_posts()
+posts = instaloader.Hashtag.from_name(L.context, 'urbanphotography').get_posts_resumable()
 
 users = set()
 

docs/codesnippets/666_historical_hashtag_data.py

@@ -3,7 +3,7 @@ import instaloader
 
 L = instaloader.Instaloader()
 
-posts = instaloader.Hashtag.from_name(L.context, "urbanphotography").get_posts()
+posts = instaloader.Hashtag.from_name(L.context, "urbanphotography").get_posts_resumable()
 
 SINCE = datetime(2020, 5, 10)  # further from today, inclusive
 UNTIL = datetime(2020, 5, 11)  # closer to today, not inclusive

instaloader/__init__.py

@@ -1,7 +1,7 @@
 """Download pictures (or videos) along with their captions and other metadata from Instagram."""
 
 
-__version__ = '4.15a1'
+__version__ = '4.15.1'
 
 
 try:

instaloader/instaloadercontext.py

@@ -32,7 +32,7 @@ def copy_session(session: requests.Session, request_timeout: Optional[float] = N
 
 def default_user_agent() -> str:
     return ('Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 '
-            '(KHTML, like Gecko) Chrome/138.0.0.0 Safari/537.36')
+            '(KHTML, like Gecko) Chrome/142.0.0.0 Safari/537.36')
 
 
 def default_iphone_headers() -> Dict[str, Any]:
@@ -395,7 +395,10 @@ class InstaloaderContext:
         :param session: Session to use, or None to use self.session
         :param use_post: Use POST instead of GET to make the request
         :return: Decoded response dictionary
-        :raises QueryReturnedBadRequestException: When the server responds with a 400.
+        :raises AbortDownloadException: When the server responds with
+            'feedback_required'/'checkpoint_required'/'challenge_required'
+        :raises QueryReturnedBadRequestException: When the server responds with a 400 (and not
+            'feedback_required'/'checkpoint_required'/'challenge_required').
         :raises QueryReturnedNotFoundException: When the server responds with a 404.
         :raises ConnectionException: When query repeatedly failed.
 
@@ -447,6 +450,15 @@ class InstaloaderContext:
                 response_headers.clear()
                 response_headers.update(resp.headers)
             if resp.status_code == 400:
+                with suppress(json.decoder.JSONDecodeError):
+                    if resp.json().get("message") in [
+                        "feedback_required",
+                        "checkpoint_required",
+                        "challenge_required",
+                    ]:
+                        # Raise AbortDownloadException in case of substantial Instagram
+                        # requirements to stop producing more requests
+                        raise AbortDownloadException(self._response_error(resp))
                 raise QueryReturnedBadRequestException(self._response_error(resp))
             if resp.status_code == 404:
                 raise QueryReturnedNotFoundException(self._response_error(resp))

instaloader/nodeiterator.py

@@ -7,7 +7,7 @@ from datetime import datetime, timedelta
 from lzma import LZMAError
 from typing import Any, Callable, Dict, Iterable, Iterator, NamedTuple, Optional, Tuple, TypeVar
 
-from .exceptions import AbortDownloadException, InvalidArgumentException
+from .exceptions import InvalidArgumentException
 from .instaloadercontext import InstaloaderContext
 
 class FrozenNodeIterator(NamedTuple):
@@ -318,7 +318,7 @@ def resumable_iteration(context: InstaloaderContext,
             context.error("Warning: Not resuming from {}: {}".format(resume_file_path, exc))
     try:
         yield is_resuming, start_index
-    except (KeyboardInterrupt, AbortDownloadException):
+    except (Exception, KeyboardInterrupt):
         if os.path.dirname(resume_file_path):
             os.makedirs(os.path.dirname(resume_file_path), exist_ok=True)
         save(iterator.freeze(), resume_file_path)

instaloader/structures.py

@@ -602,6 +602,15 @@ class Post:
             return self._field('video_view_count')
         return None
 
+    @property
+    def video_play_count(self) -> Optional[int]:
+        """Play count of the video, or None.
+
+        .. versionadded:: 4.14.3"""
+        if self.is_video:
+            return self._field('video_play_count')
+        return None
+
     @property
     def video_duration(self) -> Optional[float]:
         """Duration of the video in seconds, or None.
@@ -880,7 +889,8 @@ class Profile:
     Also, this class implements == and is hashable.
     """
     def __init__(self, context: InstaloaderContext, node: Dict[str, Any]):
-        assert 'username' in node
+        assert "username" in node
+        assert "id" in node or "pk" in node
         self._context = context
         self._has_public_story: Optional[bool] = None
         self._node = node
@@ -900,10 +910,13 @@ class Profile:
         :param username: Username
         :raises: :class:`ProfileNotExistsException`
         """
-        # pylint:disable=protected-access
-        profile = cls(context, {'username': username.lower()})
-        profile._obtain_metadata()  # to raise ProfileNotExistsException now in case username is invalid
-        return profile
+        data = context.doc_id_graphql_query("26347858941511777", {"hasQuery": True, "query": username})["data"]
+        if data:
+            for user in data["xdt_api__v1__fbsearch__non_profiled_serp"]["users"]:
+                if user["username"].lower() == username.lower():
+                    return cls(context, user)
+
+        raise ProfileNotExistsException("Profile {} does not exist.".format(username))
 
     @classmethod
     def from_id(cls, context: InstaloaderContext, profile_id: int):
@@ -970,11 +983,21 @@ class Profile:
     def _obtain_metadata(self):
         try:
             if not self._has_full_metadata:
-                metadata = self._context.get_iphone_json(f'api/v1/users/web_profile_info/?username={self.username}',
-                                                         params={})
-                if metadata['data']['user'] is None:
+                user_id = self._node.get('id') or self._node.get('pk')
+                variables = {
+                    "id": str(user_id),
+                    "render_surface": "PROFILE",
+                    "__relay_internal__pv__PolarisCannesGuardianExperienceEnabledrelayprovider": True,
+                    "__relay_internal__pv__PolarisCASB976ProfileEnabledrelayprovider": False,
+                    "__relay_internal__pv__PolarisRepostsConsumptionEnabledrelayprovider": False,
+                }
+                data = self._context.doc_id_graphql_query('25980296051578533', variables)
+                if data is None:
+                    raise QueryReturnedNotFoundException('GraphQL query returned None')
+                user_data = data.get('data', {}).get('user')
+                if user_data is None:
                     raise ProfileNotExistsException('Profile {} does not exist.'.format(self.username))
-                self._node = metadata['data']['user']
+                self._node = self._normalize_profile_data(user_data)
                 self._has_full_metadata = True
         except (QueryReturnedNotFoundException, KeyError) as err:
             top_search_results = TopSearchResults(self._context, self.username)
@@ -989,6 +1012,44 @@ class Profile:
                                                         ', '.join(similar_profiles[0:5]))) from err
             raise ProfileNotExistsException('Profile {} does not exist.'.format(self.username)) from err
 
+    def _normalize_profile_data(self, user_data: Dict[str, Any]) -> Dict[str, Any]:
+        """Normalize PolarisProfilePageContentQuery response to match legacy format."""
+        normalized = user_data.copy()
+        if 'id' not in normalized and 'pk' in normalized:
+            normalized['id'] = normalized['pk']
+        if 'edge_owner_to_timeline_media' not in normalized and 'media_count' in normalized:
+            normalized['edge_owner_to_timeline_media'] = {'count': normalized['media_count']}
+        if 'edge_felix_video_timeline' not in normalized:
+            normalized['edge_felix_video_timeline'] = {'count': 0}
+        if 'edge_followed_by' not in normalized and 'follower_count' in normalized:
+            normalized['edge_followed_by'] = {'count': normalized['follower_count']}
+        if 'edge_follow' not in normalized and 'following_count' in normalized:
+            normalized['edge_follow'] = {'count': normalized['following_count']}
+        if 'is_business_account' not in normalized and 'is_business' in normalized:
+            normalized['is_business_account'] = normalized['is_business']
+        if 'business_category_name' not in normalized and 'category' in normalized:
+            normalized['business_category_name'] = normalized['category']
+        friendship = normalized.get('friendship_status', {}) or {}
+        if 'followed_by_viewer' not in normalized:
+            normalized['followed_by_viewer'] = friendship.get('following', False)
+        if 'follows_viewer' not in normalized:
+            normalized['follows_viewer'] = friendship.get('followed_by', False)
+        if 'blocked_by_viewer' not in normalized:
+            normalized['blocked_by_viewer'] = friendship.get('blocking', False)
+        if 'has_blocked_viewer' not in normalized:
+            normalized['has_blocked_viewer'] = False
+        if 'has_requested_viewer' not in normalized:
+            normalized['has_requested_viewer'] = friendship.get('incoming_request', False)
+        if 'requested_by_viewer' not in normalized:
+            normalized['requested_by_viewer'] = friendship.get('outgoing_request', False)
+        if 'profile_pic_url_hd' not in normalized:
+            hd_info = normalized.get('hd_profile_pic_url_info')
+            if hd_info and 'url' in hd_info:
+                normalized['profile_pic_url_hd'] = hd_info['url']
+            elif 'profile_pic_url' in normalized:
+                normalized['profile_pic_url_hd'] = normalized['profile_pic_url']
+        return normalized
+
     def _metadata(self, *keys) -> Any:
         try:
             d = self._node
@@ -1197,18 +1258,33 @@ class Profile:
 
         :rtype: NodeIterator[Post]"""
         self._obtain_metadata()
+        logged_in = self._context.is_logged_in
         return NodeIterator(
-            context = self._context,
-            edge_extractor = lambda d: d['data']['xdt_api__v1__feed__user_timeline_graphql_connection'],
-            node_wrapper = lambda n: Post.from_iphone_struct(self._context, n),
-            query_variables = {'data': {
-                'count': 12, 'include_relationship_info': True,
-                'latest_besties_reel_media': True, 'latest_reel_media': True},
-             'username': self.username},
-            query_referer = 'https://www.instagram.com/{0}/'.format(self.username),
-            is_first = Profile._make_is_newest_checker(),
-            doc_id = '7898261790222653',
-            query_hash = None,
+            context=self._context,
+            edge_extractor=(
+                (lambda d: d["data"]["xdt_api__v1__feed__user_timeline_graphql_connection"])
+                if logged_in
+                else (lambda d: d["data"]["user"]["edge_owner_to_timeline_media"])
+            ),
+            node_wrapper=(
+                (lambda n: Post.from_iphone_struct(self._context, n))
+                if logged_in
+                else (lambda n: Post(self._context, n, self))
+            ),
+            query_variables={
+                "data": {
+                    "count": 12,
+                    "include_relationship_info": True,
+                    "latest_besties_reel_media": True,
+                    "latest_reel_media": True,
+                },
+                **({"username": self.username} if logged_in else {"id": self.userid}),
+            },
+            query_referer="https://www.instagram.com/{0}/".format(self.username),
+            is_first=Profile._make_is_newest_checker(),
+            doc_id="7898261790222653" if logged_in else "7950326061742207",
+            query_hash=None,
+            first_data=(None if logged_in else self._metadata("edge_owner_to_timeline_media")),
         )
 
     def get_saved_posts(self) -> NodeIterator[Post]:

setup.py

@@ -63,6 +63,7 @@ setup(
         'Programming Language :: Python :: 3.11',
         'Programming Language :: Python :: 3.12',
         'Programming Language :: Python :: 3.13',
+        'Programming Language :: Python :: 3.14',
         'Programming Language :: Python :: 3 :: Only',
         'Topic :: Internet',
         'Topic :: Multimedia :: Graphics'