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

@@ -28,4 +28,4 @@ jobs:
           branch: master
           repository-name: instaloader/instaloader.github.io
           folder: docs/_build/html
-          token: ${{ secrets.GITHUB_TOKEN }}
+          token: ${{ secrets.PAGES_DEPLOYMENT_TOKEN }}

.github/workflows/packages.yml

@@ -22,10 +22,6 @@ jobs:
           GITHUB_REF: ${{ github.ref }}
         run: echo ::set-output name=VERSION::${GITHUB_REF/refs\/tags\/v/}
         shell: bash
-      - name: "Install Dependencies"
-        run: |
-          python -m pip install pipenv==2022.1.8
-          pipenv sync --dev
       - name: "Generate Python Package"
         run: python setup.py sdist
       - name: "Publish Distribution to PyPI"

deploy/arch/deploy.sh

@@ -3,7 +3,7 @@
 VERSION=${1:1}
 
 # do not deploy pre-releases
-#echo $VERSION | grep -qe "[abc]" && exit 0
+echo $VERSION | grep -qe "[abc]" && exit 0
 
 cd $(dirname $0)
 
@@ -12,6 +12,7 @@ openssl aes-256-cbc -K $AUR_KEY -iv $AUR_IV -in id_rsa_AUR.enc -out /tmp/AUR_ope
 eval "$(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

docs/cli-options.rst

@@ -258,7 +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.
@@ -328,12 +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__ = '4.9b3'
+__version__ = '4.9.2'
 
 
 try:

instaloader/instaloader.py

@@ -1010,7 +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,
@@ -1042,7 +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
@@ -1176,8 +1179,8 @@ class Instaloader:
         """Get Posts associated with a #hashtag.
 
         .. deprecated:: 4.4
-           Use :meth:`Hashtag.get_posts`."""
+           Use :meth:`Hashtag.get_posts_resumable`."""
-        return Hashtag.from_name(self.context, hashtag).get_posts()
+        return Hashtag.from_name(self.context, hashtag).get_posts_resumable()
 
     def download_hashtag(self, hashtag: Union[Hashtag, str],
                          max_count: Optional[int] = None,
@@ -1213,7 +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,
@@ -1334,6 +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

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]
@@ -128,12 +130,16 @@ class NodeIterator(Iterator[T]):
                 self._page_index, self._total_index = page_index, total_index
                 raise
             item = self._node_wrapper(node)
-            if self._first_node is None:
+            if self._is_first is not None:
-                self._first_node = node
+                if self._is_first(item):
+                    self._first_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 +7,7 @@ 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__
@@ -365,10 +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 normalize("NFC", 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 normalize("NFC", self._node["caption"])
+            return _normalize(self._node["caption"])
         return None
 
     @property
@@ -638,6 +644,13 @@ 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:
     """
@@ -758,13 +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={})
+                metadata = self._context.get_iphone_json(f'api/v1/users/web_profile_info/?username={self.username}',
-                self._node = metadata['entry_data']['ProfilePage'][0]['graphql']['user']
+                                                         params={})
+                if metadata['data']['user'] is None:
+                    raise ProfileNotExistsException('Profile {} does not exist.'.format(self.username))
+                self._node = metadata['data']['user']
                 self._has_full_metadata = True
         except (QueryReturnedNotFoundException, KeyError) as err:
             top_search_results = TopSearchResults(self._context, self.username)
             similar_profiles = [profile.username for profile in top_search_results.get_profiles()]
             if similar_profiles:
+                if self.username in similar_profiles:
+                    raise ProfileNotExistsException(
+                        f"Profile {self.username} seems to exist, but could not be loaded.") from err
                 raise ProfileNotExistsException('Profile {} does not exist.\nThe most similar profile{}: {}.'
                                                 .format(self.username,
                                                         's are' if len(similar_profiles) > 1 else ' is',
@@ -958,6 +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]:
@@ -991,6 +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]:
@@ -1008,8 +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.
@@ -1115,6 +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:
@@ -1180,7 +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('&')
@@ -1553,7 +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")
@@ -1575,7 +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: