.github/workflows/lint.yml

@@ -9,7 +9,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["3.8", "3.9", "3.10"]
+        python-version: ["3.8", "3.9", "3.10", "3.11"]
     steps:
       - name: Checkout Instaloader Repository
         uses: actions/checkout@v2

README.rst

@@ -124,7 +124,6 @@ Supporters
 .. current-sponsors-start
 
 | Instaloader is proudly sponsored by
-|  `@rocketapi-io <https://github.com/rocketapi-io>`__
 |  `@socialmethod <https://github.com/socialmethod>`__
 
 See `Alex' GitHub Sponsors <https://github.com/sponsors/aandergr>`__ page for

instaloader/__init__.py

@@ -1,7 +1,7 @@
 """Download pictures (or videos) along with their captions and other metadata from Instagram."""
 
 
-__version__ = '4.10.2'
+__version__ = '4.10b1'
 
 
 try:

instaloader/instaloadercontext.py

@@ -3,6 +3,7 @@ import json
 import os
 import pickle
 import random
+import re
 import shutil
 import sys
 import textwrap
@@ -255,23 +256,18 @@ class InstaloaderContext:
         # Override default timeout behavior.
         # Need to silence mypy bug for this. See: https://github.com/python/mypy/issues/2427
         session.request = partial(session.request, timeout=self.request_timeout) # type: ignore
-
-        # Make a request to Instagram's root URL, which will set the session's csrftoken cookie
-        # Not using self.get_json() here, because we need to access the cookie
-        session.get('https://www.instagram.com/')
-        # Add session's csrftoken cookie to session headers
-        csrf_token = session.cookies.get_dict()['csrftoken']
+        csrf_json = self.get_json('accounts/login/', {}, session=session)
+        csrf_token = csrf_json['config']['csrf_token']
         session.headers.update({'X-CSRFToken': csrf_token})
-
+        # Not using self.get_json() here, because we need to access csrftoken cookie
         self.do_sleep()
         # Workaround credits to pgrimaud.
         # See: https://github.com/pgrimaud/instagram-user-feed/commit/96ad4cf54d1ad331b337f325c73e664999a6d066
         enc_password = '#PWD_INSTAGRAM_BROWSER:0:{}:{}'.format(int(datetime.now().timestamp()), passwd)
-        login = session.post('https://www.instagram.com/api/v1/web/accounts/login/ajax/',
+        login = session.post('https://www.instagram.com/accounts/login/ajax/',
                              data={'enc_password': enc_password, 'username': user}, allow_redirects=True)
         try:
             resp_json = login.json()
-
         except json.decoder.JSONDecodeError as err:
             raise ConnectionException(
                 "Login error: JSON decode fail, {} - {}.".format(login.status_code, login.reason)
@@ -407,6 +403,23 @@ class InstaloaderContext:
                 raise TooManyRequestsException("429 Too Many Requests")
             if resp.status_code != 200:
                 raise ConnectionException("HTTP error code {}.".format(resp.status_code))
+            is_html_query = not is_graphql_query and not "__a" in params and host == "www.instagram.com"
+            if is_html_query:
+                match = re.search(r'window\._sharedData = (.*);</script>', resp.text)
+                if match is None:
+                    raise QueryReturnedNotFoundException("Could not find \"window._sharedData\" in html response.")
+                resp_json = json.loads(match.group(1))
+                entry_data = resp_json.get('entry_data')
+                post_or_profile_page = list(entry_data.values())[0] if entry_data is not None else None
+                if post_or_profile_page is None:
+                    raise ConnectionException("\"window._sharedData\" does not contain required keys.")
+                # If GraphQL data is missing in `window._sharedData`, search for it in `__additionalDataLoaded`.
+                if 'graphql' not in post_or_profile_page[0]:
+                    match = re.search(r'window\.__additionalDataLoaded\(.*?({.*"graphql":.*})\);</script>',
+                                      resp.text)
+                    if match is not None:
+                        post_or_profile_page[0]['graphql'] = json.loads(match.group(1))['graphql']
+                return resp_json
             else:
                 resp_json = resp.json()
             if 'status' in resp_json and resp_json['status'] != "ok":

instaloader/lateststamps.py

@@ -27,8 +27,7 @@ class LatestStamps:
         self.data.read(latest_stamps_file)
 
     def _save(self):
-        if dn := dirname(self.file):
-            makedirs(dn, exist_ok=True)
+        makedirs(dirname(self.file), exist_ok=True)
         with open(self.file, 'w') as f:
             self.data.write(f)
 

instaloader/nodeiterator.py

@@ -289,7 +289,7 @@ def resumable_iteration(context: InstaloaderContext,
             is_resuming = True
             start_index = iterator.total_index
             context.log("Resuming from {}.".format(resume_file_path))
-        except (InvalidArgumentException, LZMAError, json.decoder.JSONDecodeError, EOFError) as exc:
+        except (InvalidArgumentException, LZMAError, json.decoder.JSONDecodeError) as exc:
             context.error("Warning: Not resuming from {}: {}".format(resume_file_path, exc))
     try:
         yield is_resuming, start_index

instaloader/structures.py

@@ -1097,27 +1097,6 @@ class Profile:
     def _make_is_newest_checker() -> Callable[[Post, Optional[Post]], bool]:
         return lambda post, first: first is None or post.date_local > first.date_local
 
-    def get_followed_hashtags(self) -> NodeIterator['Hashtag']:
-        """
-        Retrieve list of hashtags followed by given profile.
-        To use this, one needs to be logged in and private profiles has to be followed.
-
-        :rtype: NodeIterator[Hashtag]
-
-        .. versionadded:: 4.10
-        """
-        if not self._context.is_logged_in:
-            raise LoginRequiredException("--login required to get a profile's followers.")
-        self._obtain_metadata()
-        return NodeIterator(
-            self._context,
-            'e6306cc3dbe69d6a82ef8b5f8654c50b',
-            lambda d: d["data"]["user"]["edge_following_hashtag"],
-            lambda n: Hashtag(self._context, n),
-            {'id': str(self.userid)},
-            'https://www.instagram.com/{0}/'.format(self.username),
-        )
-
     def get_followers(self) -> NodeIterator['Profile']:
         """
         Retrieve list of followers of given profile.