Merge branch 'master' into upcoming/v4.8

instaloader/__init__.py

@@ -1,7 +1,7 @@
 """Download pictures (or videos) along with their captions and other metadata from Instagram."""
 
 
-__version__ = '4.7.1'
+__version__ = '4.7.3'
 
 
 try:

instaloader/__main__.py

@@ -113,7 +113,8 @@ def _main(instaloader: Instaloader, targetlist: List[str],
                             code = input("Enter 2FA verification code: ")
                             instaloader.two_factor_login(code)
                             break
-                        except BadCredentialsException:
+                        except BadCredentialsException as err:
+                            print(err, file=sys.stderr)
                             pass
             else:
                 instaloader.interactive_login(username)
@@ -346,7 +347,7 @@ def main():
 
     g_cond.add_argument('-c', '--count',
                         help='Do not attempt to download more than COUNT posts. '
-                             'Applies only to #hashtag and :feed.')
+                             'Applies to #hashtag, %%location_id, :feed, and :saved.')
 
     g_login = parser.add_argument_group('Login (Download Private Profiles)',
                                         'Instaloader can login to Instagram. This allows downloading private profiles. '

instaloader/instaloader.py

@@ -1534,5 +1534,6 @@ class Instaloader:
                     code = input("Enter 2FA verification code: ")
                     self.two_factor_login(code)
                     break
-                except BadCredentialsException:
+                except BadCredentialsException as err:
+                    print(err, file=sys.stderr)
                     pass

instaloader/instaloadercontext.py

@@ -212,8 +212,8 @@ 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
-        session.get('https://www.instagram.com/web/__mid/')
-        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()
@@ -285,9 +285,9 @@ class InstaloaderContext:
         resp_json = login.json()
         if resp_json['status'] != 'ok':
             if 'message' in resp_json:
-                raise BadCredentialsException("Login error: {}".format(resp_json['message']))
+                raise BadCredentialsException("2FA error: {}".format(resp_json['message']))
             else:
-                raise BadCredentialsException("Login error: \"{}\" status.".format(resp_json['status']))
+                raise BadCredentialsException("2FA error: \"{}\" status.".format(resp_json['status']))
         session.headers.update({'X-CSRFToken': login.cookies['csrftoken']})
         self._session = session
         self.username = user

instaloader/structures.py

@@ -342,9 +342,11 @@ class Post:
         """List of all lowercased profiles that are mentioned in the Post's caption, without preceeding @."""
         if not self.caption:
             return []
-        # This regular expression is from jStassen, adjusted to use Python's \w to support Unicode
+        # This regular expression is modified from jStassen, adjusted to use Python's \w to
+        # 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|(?:\.(?!\.))){0,28}(?:\w))?)")
+        mention_regex = re.compile(r"(?:^|\W|_)(?:@)(\w(?:(?:\w|(?:\.(?!\.))){0,28}(?:\w))?)")
         return re.findall(mention_regex, self.caption.lower())
 
     @property
@@ -796,14 +798,13 @@ class Profile:
     def has_public_story(self) -> bool:
         if not self._has_public_story:
             self._obtain_metadata()
-            # query not rate limited if invoked anonymously:
-            with self._context.anonymous_copy() as anonymous_context:
-                data = anonymous_context.graphql_query('9ca88e465c3f866a76f7adee3871bdd8',
-                                                       {'user_id': self.userid, 'include_chaining': False,
-                                                        'include_reel': False, 'include_suggested_users': False,
-                                                        'include_logged_out_extras': True,
-                                                        'include_highlight_reels': False},
-                                                       'https://www.instagram.com/{}/'.format(self.username))
+            # query rate might be limited:
+            data = self._context.graphql_query('9ca88e465c3f866a76f7adee3871bdd8',
+                                               {'user_id': self.userid, 'include_chaining': False,
+                                                'include_reel': False, 'include_suggested_users': False,
+                                                'include_logged_out_extras': True,
+                                                'include_highlight_reels': False},
+                                               'https://www.instagram.com/{}/'.format(self.username))
             self._has_public_story = data['data']['user']['has_public_story']
         assert self._has_public_story is not None
         return self._has_public_story