Release of Version 4.2.6

Closes #293.

.pylintrc

@@ -0,0 +1,584 @@
+[MASTER]
+
+# A comma-separated list of package or module names from where C extensions may
+# be loaded. Extensions are loading into the active Python interpreter and may
+# run arbitrary code.
+extension-pkg-whitelist=
+
+# Add files or directories to the blacklist. They should be base names, not
+# paths.
+ignore=CVS
+
+# Add files or directories matching the regex patterns to the blacklist. The
+# regex matches against base names, not paths.
+ignore-patterns=
+
+# Python code to execute, usually for sys.path manipulation such as
+# pygtk.require().
+#init-hook=
+
+# Use multiple processes to speed up Pylint. Specifying 0 will auto-detect the
+# number of processors available to use.
+jobs=0
+
+# Control the amount of potential inferred values when inferring a single
+# object. This can help the performance when dealing with large functions or
+# complex, nested conditions.
+limit-inference-results=100
+
+# List of plugins (as comma separated values of python modules names) to load,
+# usually to register additional checkers.
+load-plugins=
+
+# Pickle collected data for later comparisons.
+persistent=yes
+
+# Specify a configuration file.
+#rcfile=
+
+# When enabled, pylint would attempt to guess common misconfiguration and emit
+# user-friendly hints instead of false-positive error messages.
+suggestion-mode=yes
+
+# Allow loading of arbitrary C extensions. Extensions are imported into the
+# active Python interpreter and may run arbitrary code.
+unsafe-load-any-extension=no
+
+
+[MESSAGES CONTROL]
+
+# Only show warnings with the listed confidence levels. Leave empty to show
+# all. Valid levels: HIGH, INFERENCE, INFERENCE_FAILURE, UNDEFINED.
+confidence=
+
+# Disable the message, report, category or checker with the given id(s). You
+# can either give multiple identifiers separated by comma (,) or put this
+# option multiple times (only on the command line, not in the configuration
+# file where it should appear only once). You can also use "--disable=all" to
+# disable everything first and then reenable specific checks. For example, if
+# you want to run only the similarities checker, you can use "--disable=all
+# --enable=similarities". If you want to run only the classes checker, but have
+# no Warning level messages displayed, use "--disable=all --enable=classes
+# --disable=W".
+disable=invalid-name,
+        missing-docstring,
+        too-many-lines,
+        print-statement,
+        parameter-unpacking,
+        unpacking-in-except,
+        old-raise-syntax,
+        backtick,
+        long-suffix,
+        old-ne-operator,
+        old-octal-literal,
+        import-star-module-level,
+        non-ascii-bytes-literal,
+        raw-checker-failed,
+        bad-inline-option,
+        locally-disabled,
+        file-ignored,
+        suppressed-message,
+        useless-suppression,
+        deprecated-pragma,
+        use-symbolic-message-instead,
+        too-many-instance-attributes,
+        too-many-public-methods,
+        too-many-branches,
+        too-many-arguments,
+        too-many-locals,
+        too-many-statements,
+        no-else-return,
+        no-else-raise,
+        unnecessary-pass,
+        wildcard-import,
+        unused-wildcard-import,
+        apply-builtin,
+        basestring-builtin,
+        buffer-builtin,
+        cmp-builtin,
+        coerce-builtin,
+        execfile-builtin,
+        file-builtin,
+        long-builtin,
+        raw_input-builtin,
+        reduce-builtin,
+        standarderror-builtin,
+        unicode-builtin,
+        xrange-builtin,
+        coerce-method,
+        delslice-method,
+        getslice-method,
+        setslice-method,
+        no-absolute-import,
+        old-division,
+        dict-iter-method,
+        dict-view-method,
+        next-method-called,
+        metaclass-assignment,
+        indexing-exception,
+        raising-string,
+        reload-builtin,
+        oct-method,
+        hex-method,
+        nonzero-method,
+        cmp-method,
+        input-builtin,
+        round-builtin,
+        intern-builtin,
+        unichr-builtin,
+        map-builtin-not-iterating,
+        zip-builtin-not-iterating,
+        range-builtin-not-iterating,
+        filter-builtin-not-iterating,
+        using-cmp-argument,
+        eq-without-hash,
+        div-method,
+        idiv-method,
+        rdiv-method,
+        exception-message-attribute,
+        invalid-str-codec,
+        sys-max-int,
+        bad-python3-import,
+        deprecated-string-function,
+        deprecated-str-translate-call,
+        deprecated-itertools-function,
+        deprecated-types-field,
+        next-method-defined,
+        dict-items-not-iterating,
+        dict-keys-not-iterating,
+        dict-values-not-iterating,
+        deprecated-operator-function,
+        deprecated-urllib-function,
+        xreadlines-attribute,
+        deprecated-sys-function,
+        exception-escape,
+        comprehension-escape
+
+# Enable the message, report, category or checker with the given id(s). You can
+# either give multiple identifier separated by comma (,) or put this option
+# multiple time (only on the command line, not in the configuration file where
+# it should appear only once). See also the "--disable" option for examples.
+enable=c-extension-no-member
+
+
+[REPORTS]
+
+# Python expression which should return a note less than 10 (10 is the highest
+# note). You have access to the variables errors warning, statement which
+# respectively contain the number of errors / warnings messages and the total
+# number of statements analyzed. This is used by the global evaluation report
+# (RP0004).
+evaluation=10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10)
+
+# Template used to display messages. This is a python new-style format string
+# used to format the message information. See doc for all details.
+#msg-template=
+
+# Set the output format. Available formats are text, parseable, colorized, json
+# and msvs (visual studio). You can also give a reporter class, e.g.
+# mypackage.mymodule.MyReporterClass.
+output-format=text
+
+# Tells whether to display a full report or only the messages.
+reports=no
+
+# Activate the evaluation score.
+score=yes
+
+
+[REFACTORING]
+
+# Maximum number of nested blocks for function / method body
+max-nested-blocks=5
+
+# Complete name of functions that never returns. When checking for
+# inconsistent-return-statements if a never returning function is called then
+# it will be considered as an explicit return statement and no message will be
+# printed.
+never-returning-functions=sys.exit
+
+
+[VARIABLES]
+
+# List of additional names supposed to be defined in builtins. Remember that
+# you should avoid defining new builtins when possible.
+additional-builtins=
+
+# Tells whether unused global variables should be treated as a violation.
+allow-global-unused-variables=yes
+
+# List of strings which can identify a callback function by name. A callback
+# name must start or end with one of those strings.
+callbacks=cb_,
+          _cb
+
+# A regular expression matching the name of dummy variables (i.e. expected to
+# not be used).
+dummy-variables-rgx=_+$|(_[a-zA-Z0-9_]*[a-zA-Z0-9]+?$)|dummy|^ignored_|^unused_
+
+# Argument names that match this expression will be ignored. Default to name
+# with leading underscore.
+ignored-argument-names=_.*|^ignored_|^unused_
+
+# Tells whether we should check for unused import in __init__ files.
+init-import=no
+
+# List of qualified module names which can have objects that can redefine
+# builtins.
+redefining-builtins-modules=six.moves,past.builtins,future.builtins,builtins,io
+
+
+[TYPECHECK]
+
+# List of decorators that produce context managers, such as
+# contextlib.contextmanager. Add to this list to register other decorators that
+# produce valid context managers.
+contextmanager-decorators=contextlib.contextmanager
+
+# List of members which are set dynamically and missed by pylint inference
+# system, and so shouldn't trigger E1101 when accessed. Python regular
+# expressions are accepted.
+generated-members=
+
+# Tells whether missing members accessed in mixin class should be ignored. A
+# mixin class is detected if its name ends with "mixin" (case insensitive).
+ignore-mixin-members=yes
+
+# Tells whether to warn about missing members when the owner of the attribute
+# is inferred to be None.
+ignore-none=yes
+
+# This flag controls whether pylint should warn about no-member and similar
+# checks whenever an opaque object is returned when inferring. The inference
+# can return multiple potential results while evaluating a Python object, but
+# some branches might not be evaluated, which results in partial inference. In
+# that case, it might be useful to still emit no-member and other checks for
+# the rest of the inferred objects.
+ignore-on-opaque-inference=yes
+
+# List of class names for which member attributes should not be checked (useful
+# for classes with dynamically set attributes). This supports the use of
+# qualified names.
+ignored-classes=optparse.Values,thread._local,_thread._local
+
+# List of module names for which member attributes should not be checked
+# (useful for modules/projects where namespaces are manipulated during runtime
+# and thus existing member attributes cannot be deduced by static analysis. It
+# supports qualified module names, as well as Unix pattern matching.
+ignored-modules=
+
+# Show a hint with possible names when a member name was not found. The aspect
+# of finding the hint is based on edit distance.
+missing-member-hint=yes
+
+# The minimum edit distance a name should have in order to be considered a
+# similar match for a missing member name.
+missing-member-hint-distance=1
+
+# The total number of similar names that should be taken in consideration when
+# showing a hint for a missing member.
+missing-member-max-choices=1
+
+
+[STRING]
+
+# This flag controls whether the implicit-str-concat-in-sequence should
+# generate a warning on implicit string concatenation in sequences defined over
+# several lines.
+check-str-concat-over-line-jumps=no
+
+
+[SPELLING]
+
+# Limits count of emitted suggestions for spelling mistakes.
+max-spelling-suggestions=4
+
+# Spelling dictionary name. Available dictionaries: none. To make it working
+# install python-enchant package..
+spelling-dict=
+
+# List of comma separated words that should not be checked.
+spelling-ignore-words=
+
+# A path to a file that contains private dictionary; one word per line.
+spelling-private-dict-file=
+
+# Tells whether to store unknown words to indicated private dictionary in
+# --spelling-private-dict-file option instead of raising a message.
+spelling-store-unknown-words=no
+
+
+[SIMILARITIES]
+
+# Ignore comments when computing similarities.
+ignore-comments=yes
+
+# Ignore docstrings when computing similarities.
+ignore-docstrings=yes
+
+# Ignore imports when computing similarities.
+ignore-imports=no
+
+# Minimum lines number of a similarity.
+min-similarity-lines=4
+
+
+[MISCELLANEOUS]
+
+# List of note tags to take in consideration, separated by a comma.
+notes=FIXME,
+      XXX,
+      TODO
+
+
+[LOGGING]
+
+# Format style used to check logging format string. `old` means using %
+# formatting, while `new` is for `{}` formatting.
+logging-format-style=old
+
+# Logging modules to check that the string format arguments are in logging
+# function parameter format.
+logging-modules=logging
+
+
+[FORMAT]
+
+# Expected format of line ending, e.g. empty (any line ending), LF or CRLF.
+expected-line-ending-format=
+
+# Regexp for a line that is allowed to be longer than the limit.
+ignore-long-lines=^\s*(# )?<?https?://\S+>?$
+
+# Number of spaces of indent required inside a hanging or continued line.
+indent-after-paren=4
+
+# String used as indentation unit. This is usually "    " (4 spaces) or "\t" (1
+# tab).
+indent-string='    '
+
+# Maximum number of characters on a single line.
+max-line-length=120
+
+# Maximum number of lines in a module.
+max-module-lines=1000
+
+# List of optional constructs for which whitespace checking is disabled. `dict-
+# separator` is used to allow tabulation in dicts, etc.: {1  : 1,\n222: 2}.
+# `trailing-comma` allows a space between comma and closing bracket: (a, ).
+# `empty-line` allows space-only lines.
+no-space-check=trailing-comma,
+               dict-separator
+
+# Allow the body of a class to be on the same line as the declaration if body
+# contains single statement.
+single-line-class-stmt=no
+
+# Allow the body of an if to be on the same line as the test if there is no
+# else.
+single-line-if-stmt=no
+
+
+[BASIC]
+
+# Naming style matching correct argument names.
+argument-naming-style=snake_case
+
+# Regular expression matching correct argument names. Overrides argument-
+# naming-style.
+#argument-rgx=
+
+# Naming style matching correct attribute names.
+attr-naming-style=snake_case
+
+# Regular expression matching correct attribute names. Overrides attr-naming-
+# style.
+#attr-rgx=
+
+# Bad variable names which should always be refused, separated by a comma.
+bad-names=foo,
+          bar,
+          baz,
+          toto,
+          tutu,
+          tata
+
+# Naming style matching correct class attribute names.
+class-attribute-naming-style=any
+
+# Regular expression matching correct class attribute names. Overrides class-
+# attribute-naming-style.
+#class-attribute-rgx=
+
+# Naming style matching correct class names.
+class-naming-style=PascalCase
+
+# Regular expression matching correct class names. Overrides class-naming-
+# style.
+#class-rgx=
+
+# Naming style matching correct constant names.
+const-naming-style=UPPER_CASE
+
+# Regular expression matching correct constant names. Overrides const-naming-
+# style.
+#const-rgx=
+
+# Minimum line length for functions/classes that require docstrings, shorter
+# ones are exempt.
+docstring-min-length=-1
+
+# Naming style matching correct function names.
+function-naming-style=snake_case
+
+# Regular expression matching correct function names. Overrides function-
+# naming-style.
+#function-rgx=
+
+# Good variable names which should always be accepted, separated by a comma.
+good-names=i,
+           j,
+           k,
+           ex,
+           Run,
+           _
+
+# Include a hint for the correct naming format with invalid-name.
+include-naming-hint=no
+
+# Naming style matching correct inline iteration names.
+inlinevar-naming-style=any
+
+# Regular expression matching correct inline iteration names. Overrides
+# inlinevar-naming-style.
+#inlinevar-rgx=
+
+# Naming style matching correct method names.
+method-naming-style=snake_case
+
+# Regular expression matching correct method names. Overrides method-naming-
+# style.
+#method-rgx=
+
+# Naming style matching correct module names.
+module-naming-style=snake_case
+
+# Regular expression matching correct module names. Overrides module-naming-
+# style.
+#module-rgx=
+
+# Colon-delimited sets of names that determine each other's naming style when
+# the name regexes allow several styles.
+name-group=
+
+# Regular expression which should only match function or class names that do
+# not require a docstring.
+no-docstring-rgx=^_
+
+# List of decorators that produce properties, such as abc.abstractproperty. Add
+# to this list to register other decorators that produce valid properties.
+# These decorators are taken in consideration only for invalid-name.
+property-classes=abc.abstractproperty
+
+# Naming style matching correct variable names.
+variable-naming-style=snake_case
+
+# Regular expression matching correct variable names. Overrides variable-
+# naming-style.
+#variable-rgx=
+
+
+[IMPORTS]
+
+# Allow wildcard imports from modules that define __all__.
+allow-wildcard-with-all=no
+
+# Analyse import fallback blocks. This can be used to support both Python 2 and
+# 3 compatible code, which means that the block might have code that exists
+# only in one or another interpreter, leading to false positives when analysed.
+analyse-fallback-blocks=no
+
+# Deprecated modules which should not be used, separated by a comma.
+deprecated-modules=optparse,tkinter.tix
+
+# Create a graph of external dependencies in the given file (report RP0402 must
+# not be disabled).
+ext-import-graph=
+
+# Create a graph of every (i.e. internal and external) dependencies in the
+# given file (report RP0402 must not be disabled).
+import-graph=
+
+# Create a graph of internal dependencies in the given file (report RP0402 must
+# not be disabled).
+int-import-graph=
+
+# Force import order to recognize a module as part of the standard
+# compatibility libraries.
+known-standard-library=
+
+# Force import order to recognize a module as part of a third party library.
+known-third-party=enchant
+
+
+[DESIGN]
+
+# Maximum number of arguments for function / method.
+max-args=5
+
+# Maximum number of attributes for a class (see R0902).
+max-attributes=7
+
+# Maximum number of boolean expressions in an if statement.
+max-bool-expr=5
+
+# Maximum number of branch for function / method body.
+max-branches=12
+
+# Maximum number of locals for function / method body.
+max-locals=15
+
+# Maximum number of parents for a class (see R0901).
+max-parents=7
+
+# Maximum number of public methods for a class (see R0904).
+max-public-methods=20
+
+# Maximum number of return / yield for function / method body.
+max-returns=6
+
+# Maximum number of statements in function / method body.
+max-statements=50
+
+# Minimum number of public methods for a class (see R0903).
+min-public-methods=2
+
+
+[CLASSES]
+
+# List of method names used to declare (i.e. assign) instance attributes.
+defining-attr-methods=__init__,
+                      __new__,
+                      setUp
+
+# List of member names, which should be excluded from the protected access
+# warning.
+exclude-protected=_asdict,
+                  _fields,
+                  _replace,
+                  _source,
+                  _make
+
+# List of valid names for the first argument in a class method.
+valid-classmethod-first-arg=cls
+
+# List of valid names for the first argument in a metaclass class method.
+valid-metaclass-classmethod-first-arg=cls
+
+
+[EXCEPTIONS]
+
+# Exceptions that will emit a warning when being caught. Defaults to
+# "BaseException, Exception".
+overgeneral-exceptions=BaseException,
+                       Exception

.travis.yml

@@ -1,15 +1,18 @@
+dist: xenial
 language: python
 python:
  - "3.5"
- - "3.5-dev"
  - "3.6"
- - "3.6-dev"
+ - "3.7"
 install:
- - pip install pylint requests
+ - pip install pylint~=2.3.1 requests mypy
  - pip install -r docs/requirements.txt
 script:
- - python3 -m pylint -r n -d bad-whitespace,missing-docstring,too-many-arguments,locally-disabled,line-too-long,too-many-public-methods,too-many-lines,too-many-instance-attributes,too-many-locals,too-many-branches,too-many-statements,inconsistent-return-statements,invalid-name,wildcard-import,unused-wildcard-import,no-else-return,cyclic-import,unnecessary-pass instaloader
+ - python3 -m pylint instaloader
+ - python3 -m mypy -m instaloader
  - make -C docs html SPHINXOPTS="-W -n"
+addons:
+  ssh_known_hosts: aur.archlinux.org
 deploy:
   - provider: pypi
     user: aandergr
@@ -27,3 +30,8 @@ deploy:
     on:
       branch: master
       python: 3.6
+  - provider: script
+    script: deploy/arch/deploy.sh $TRAVIS_TAG
+    on:
+      tags: true
+      python: 3.6

README.rst

@@ -1,5 +1,41 @@
 .. image:: https://raw.githubusercontent.com/instaloader/instaloader/master/docs/logo_heading.png
 
+.. badges-start
+
+|travis| |pypi| |pyversion| |license| |aur| |contributors| |downloads| |saythanks|
+
+.. |travis| image:: https://img.shields.io/travis/instaloader/instaloader/master.svg
+   :alt: Travis-CI Build Status
+   :target: https://travis-ci.org/instaloader/instaloader
+
+.. |pypi| image:: https://img.shields.io/pypi/v/instaloader.svg
+   :alt: Instaloader PyPI Project Page
+   :target: https://pypi.org/project/instaloader/
+
+.. |license| image:: https://img.shields.io/github/license/instaloader/instaloader.svg
+   :alt: MIT License
+   :target: https://github.com/instaloader/instaloader/blob/master/LICENSE
+
+.. |pyversion| image:: https://img.shields.io/pypi/pyversions/instaloader.svg
+   :alt: Supported Python Versions
+
+.. |contributors| image:: https://img.shields.io/github/contributors/instaloader/instaloader.svg
+   :alt: Contributor Count
+   :target: https://github.com/instaloader/instaloader/graphs/contributors
+
+.. |saythanks| image:: https://img.shields.io/badge/Say%20Thanks-!-ff7efd.svg
+   :alt: Say Thanks!
+   :target: https://saythanks.io/to/aandergr
+
+.. |aur| image:: https://img.shields.io/aur/version/instaloader.svg
+   :alt: Arch User Repository Package
+   :target: https://aur.archlinux.org/packages/instaloader/
+
+.. |downloads| image:: https://img.shields.io/pypi/dm/instaloader.svg
+   :alt: PyPI Download Count
+
+.. badges-end
+
 ::
 
     $ pip3 install instaloader

deploy/arch/.SRCINFO.template

@@ -0,0 +1,15 @@
+pkgbase = instaloader
+	pkgdesc = Command line tool to download pictures, videos and metadata from Instagram
+	pkgver = {{version}}
+	pkgrel = 1
+	url = https://instaloader.github.io/
+	arch = any
+	license = MIT
+	makedepends = python-setuptools
+	depends = python>=3.5
+	depends = python-requests>=2.4
+	options = !emptydirs
+	source = instaloader-{{version}}.tar.gz::https://codeload.github.com/instaloader/instaloader/tar.gz/v{{version}}
+	sha512sums = {{hash}}
+
+pkgname = instaloader

deploy/arch/PKGBUILD.template

@@ -0,0 +1,27 @@
+# Maintainer: André Koch-Kramer <koch-kramer@web.de>
+
+pkgname=instaloader
+pkgver={{version}}
+pkgrel=1
+pkgdesc="Command line tool to download pictures, videos and metadata from Instagram"
+arch=('any')
+url="https://instaloader.github.io/"
+license=('MIT')
+groups=()
+depends=('python>=3.5' 'python-requests>=2.4')
+makedepends=('python-setuptools')
+options=('!emptydirs')
+source=($pkgname-$pkgver.tar.gz::https://codeload.github.com/instaloader/instaloader/tar.gz/v$pkgver)
+sha512sums=('{{hash}}')
+
+build() {
+	cd "$srcdir/$pkgname-$pkgver"
+	python setup.py clean --all
+	python setup.py build
+}
+
+package() {
+	cd "$srcdir/$pkgname-$pkgver"
+	install -Dm644 LICENSE "$pkgdir"/usr/share/licenses/$pkgname/LICENSE
+	python setup.py install --root "$pkgdir/" --skip-build
+}

deploy/arch/deploy.sh

@@ -0,0 +1,30 @@
+#!/usr/bin/env bash
+
+VERSION=${1:1}
+
+# do not deploy pre-releases
+echo $VERSION | grep -qe "[abc]" && exit 0
+
+cd $(dirname $0)
+
+# decrypt and add ssh key
+openssl aes-256-cbc -K $encrypted_354637631c28_key -iv $encrypted_354637631c28_iv -in id_rsa_AUR.enc -out /tmp/AUR_openssh -d
+eval "$(ssh-agent -s)"
+chmod 600 /tmp/AUR_openssh
+ssh-add /tmp/AUR_openssh
+
+# clone and modify AUR repo
+git clone --depth 1 ssh://aur@aur.archlinux.org/instaloader.git
+
+curl -sSfOJ https://codeload.github.com/instaloader/instaloader/tar.gz/$1
+HASH=$(sha512sum instaloader-$VERSION.tar.gz | cut -f1 -d " ")
+sed -e "s/{{version}}/$VERSION/g" -e "s/{{hash}}/$HASH/g" PKGBUILD.template > instaloader/PKGBUILD
+sed -e "s/{{version}}/$VERSION/g" -e "s/{{hash}}/$HASH/g" .SRCINFO.template > instaloader/.SRCINFO
+
+# commit and push changes
+cd instaloader
+git config user.email "koch-kramer@web.de"
+git config user.name "André Koch-Kramer"
+git add .
+git commit -m "Release of version $VERSION"
+git push

docs/as-module.rst

@@ -123,6 +123,9 @@ Additionally, the following trivial structures are defined:
 .. autoclass:: PostComment
    :no-show-inheritance:
 
+.. autoclass:: PostCommentAnswer
+   :no-show-inheritance:
+
 .. autoclass:: PostLocation
    :no-show-inheritance:
 

docs/index.rst

@@ -15,6 +15,10 @@ Instaloader
 **Instaloader** is a tool to download pictures (or videos) along with
 their captions and other metadata from Instagram.
 
+.. include:: ../README.rst
+   :start-after: badges-start
+   :end-before: badges-end
+
 With `Python <https://www.python.org/>`__ installed, do::
 
     $ pip3 install instaloader

instaloader/__init__.py

@@ -1,12 +1,12 @@
 """Download pictures (or videos) along with their captions and other metadata from Instagram."""
 
 
-__version__ = '4.2.3'
+__version__ = '4.2.6'
 
 
 try:
     # pylint:disable=wrong-import-position
-    import win_unicode_console
+    import win_unicode_console  # type: ignore
 except ImportError:
     pass
 else:
@@ -15,5 +15,5 @@ else:
 from .exceptions import *
 from .instaloader import Instaloader
 from .instaloadercontext import InstaloaderContext
-from .structures import (Highlight, Post, PostSidecarNode, PostComment, PostLocation, Profile, Story, StoryItem,
-                         load_structure_from_file, save_structure_to_file)
+from .structures import (Highlight, Post, PostSidecarNode, PostComment, PostCommentAnswer, PostLocation, Profile, Story,
+                         StoryItem, load_structure_from_file, save_structure_to_file)

instaloader/instaloader.py

@@ -13,14 +13,16 @@ from datetime import datetime, timezone
 from functools import wraps
 from hashlib import md5
 from io import BytesIO
+from pathlib import Path
 from typing import Any, Callable, Iterator, List, Optional, Set, Union
 
 import requests
-import urllib3
+import urllib3  # type: ignore
 
 from .exceptions import *
 from .instaloadercontext import InstaloaderContext
-from .structures import Highlight, JsonExportable, Post, PostLocation, Profile, Story, StoryItem, save_structure_to_file, load_structure_from_file
+from .structures import (Highlight, JsonExportable, Post, PostLocation, Profile, Story, StoryItem,
+                         save_structure_to_file, load_structure_from_file)
 
 
 def get_default_session_filename(username: str) -> str:
@@ -45,8 +47,8 @@ def _requires_login(func: Callable) -> Callable:
         if not instaloader.context.is_logged_in:
             raise LoginRequiredException("--login=USERNAME required.")
         return func(instaloader, *args, **kwargs)
-    # pylint:disable=no-member
-    call.__doc__ += ":raises LoginRequiredException: If called without being logged in.\n"
+    docstring_text = ":raises LoginRequiredException: If called without being logged in.\n"
+    call.__doc__ = call.__doc__ + docstring_text if call.__doc__ is not None else docstring_text
     return call
 
 
@@ -108,7 +110,17 @@ class _PostPathFormatter(_ArbitraryItemFormatter):
         ret = super().vformat(format_string, args, kwargs)
         if platform.system() == 'Windows':
             ret = ret.replace(':', '\ua789').replace('<', '\ufe64').replace('>', '\ufe65').replace('\"', '\uff02')
-            ret = ret.replace('\\', '\uff3c').replace('|', '\uff5c').replace('?', '\ufe16').replace('*', '\uff0a')
+            ret = ret.replace('\\', '\ufe68').replace('|', '\uff5c').replace('?', '\ufe16').replace('*', '\uff0a')
+        return ret
+
+    def get_value(self, key, args, kwargs):
+        """Replaces '/' with similar looking Division Slash and on windows newline with space"""
+        ret = super().get_value(key, args, kwargs)
+        if not isinstance(ret, str):
+            return ret
+        ret = ret.replace('/', '\u2215')
+        if platform.system() == 'Windows':
+            ret = ret.replace('\n', ' ')
         return ret
 
 
@@ -176,7 +188,7 @@ class Instaloader:
             raise InvalidArgumentException("Commit mode requires JSON metadata to be saved.")
 
         # Used to keep state in commit mode
-        self._committed = None
+        self._committed = None  # type: Optional[bool]
 
     @contextmanager
     def anonymous_copy(self):
@@ -240,11 +252,33 @@ class Instaloader:
             self.context.log('json', end=' ', flush=True)
 
     def update_comments(self, filename: str, post: Post) -> None:
-        def _postcomment_asdict(comment):
+        def _postcommentanswer_asdict(comment):
             return {'id': comment.id,
                     'created_at': int(comment.created_at_utc.replace(tzinfo=timezone.utc).timestamp()),
                     'text': comment.text,
                     'owner': comment.owner._asdict()}
+
+        def _postcomment_asdict(comment):
+            return {**_postcommentanswer_asdict(comment),
+                    'answers': sorted([_postcommentanswer_asdict(answer) for answer in comment.answers],
+                                      key=lambda t: int(t['id']),
+                                      reverse=True)}
+
+        def get_unique_comments(comments, combine_answers=False):
+            if not comments:
+                return list()
+            comments_list = sorted(sorted(list(comments), key=lambda t: int(t['id'])),
+                                   key=lambda t: int(t['created_at']), reverse=True)
+            unique_comments_list = [comments_list[0]]
+            for x, y in zip(comments_list[:-1], comments_list[1:]):
+                if x['id'] != y['id']:
+                    unique_comments_list.append(y)
+                elif combine_answers:
+                    combined_answers = unique_comments_list[-1].get('answers') or list()
+                    if 'answers' in y:
+                        combined_answers.extend(y['answers'])
+                    unique_comments_list[-1]['answers'] = get_unique_comments(combined_answers)
+            return unique_comments_list
         filename += '_comments.json'
         try:
             with open(filename) as fp:
@@ -253,18 +287,10 @@ class Instaloader:
             comments = list()
         comments.extend(_postcomment_asdict(comment) for comment in post.get_comments())
         if comments:
-            comments_list = sorted(sorted(list(comments), key=lambda t: int(t['id'])),
-                                   key=lambda t: int(t['created_at']), reverse=True)
-            unique_comments_list = [comments_list[0]]
-            #for comment in comments_list:
-            #    if unique_comments_list[-1]['id'] != comment['id']:
-            #        unique_comments_list.append(comment)
-            #file.write(json.dumps(unique_comments_list, indent=4))
-            for x, y in zip(comments_list[:-1], comments_list[1:]):
-                if x['id'] != y['id']:
-                    unique_comments_list.append(y)
+            comments = get_unique_comments(comments, combine_answers=True)
+            answer_ids = set(int(answer['id']) for comment in comments for answer in comment.get('answers', []))
             with open(filename, 'w') as file:
-                file.write(json.dumps(unique_comments_list, indent=4))
+                file.write(json.dumps(list(filter(lambda t: int(t['id']) not in answer_ids, comments)), indent=4))
             self.context.log('comments', end=' ', flush=True)
 
     def save_caption(self, filename: str, mtime: datetime, caption: str) -> None:
@@ -275,11 +301,11 @@ class Instaloader:
         filename += '.txt'
         caption += '\n'
         pcaption = _elliptify(caption)
-        caption = caption.encode("UTF-8")
+        bcaption = caption.encode("UTF-8")
         with suppress(FileNotFoundError):
             with open(filename, 'rb') as file:
                 file_caption = file.read()
-            if file_caption.replace(b'\r\n', b'\n') == caption.replace(b'\r\n', b'\n'):
+            if file_caption.replace(b'\r\n', b'\n') == bcaption.replace(b'\r\n', b'\n'):
                 try:
                     self.context.log(pcaption + ' unchanged', end=' ', flush=True)
                 except UnicodeEncodeError:
@@ -303,7 +329,7 @@ class Instaloader:
         except UnicodeEncodeError:
             self.context.log('txt', end=' ', flush=True)
         with open(filename, 'wb') as text_file:
-            shutil.copyfileobj(BytesIO(caption), text_file)
+            shutil.copyfileobj(BytesIO(bcaption), text_file)
         os.utime(filename, (datetime.now().timestamp(), mtime.timestamp()))
 
     def save_location(self, filename: str, location: PostLocation, mtime: datetime) -> None:
@@ -325,12 +351,12 @@ class Instaloader:
             return epoch.strftime('%Y-%m-%d_%H-%M-%S_UTC')
 
         profile_pic_response = self.context.get_raw(profile.profile_pic_url)
+        date_object = None  # type: Optional[datetime]
         if 'Last-Modified' in profile_pic_response.headers:
             date_object = datetime.strptime(profile_pic_response.headers["Last-Modified"], '%a, %d %b %Y %H:%M:%S GMT')
             profile_pic_bytes = None
             profile_pic_identifier = _epoch_to_string(date_object)
         else:
-            date_object = None
             profile_pic_bytes = profile_pic_response.content
             profile_pic_identifier = md5(profile_pic_bytes).hexdigest()[:16]
         profile_pic_extension = 'jpg'
@@ -344,7 +370,8 @@ class Instaloader:
                                                             profile_pic_identifier, profile_pic_extension)
         content_length = profile_pic_response.headers.get('Content-Length', None)
         if os.path.isfile(filename) and (not self.context.is_logged_in or
-                                         content_length is not None and os.path.getsize(filename) >= int(content_length)):
+                                         (content_length is not None and
+                                          os.path.getsize(filename) >= int(content_length))):
             self.context.log(filename + ' already exists')
             return None
         self.context.write_raw(profile_pic_bytes if profile_pic_bytes else profile_pic_response, filename)
@@ -359,6 +386,7 @@ class Instaloader:
         :param filename: Filename, or None to use default filename.
         """
         if filename is None:
+            assert self.context.username is not None
             filename = get_default_session_filename(self.context.username)
         dirname = os.path.dirname(filename)
         if dirname != '' and not os.path.exists(dirname):
@@ -392,7 +420,8 @@ class Instaloader:
         :raises InvalidArgumentException: If the provided username does not exist.
         :raises BadCredentialsException: If the provided password is wrong.
         :raises ConnectionException: If connection to Instagram failed.
-        :raises TwoFactorAuthRequiredException: First step of 2FA login done, now call :meth:`Instaloader.two_factor_login`."""
+        :raises TwoFactorAuthRequiredException: First step of 2FA login done, now call
+           :meth:`Instaloader.two_factor_login`."""
         self.context.login(user, passwd)
 
     def two_factor_login(self, two_factor_code) -> None:
@@ -405,13 +434,13 @@ class Instaloader:
         .. versionadded:: 4.2"""
         self.context.two_factor_login(two_factor_code)
 
-    def format_filename(self, item: Union[Post, StoryItem], target: Optional[str] = None):
+    def format_filename(self, item: Union[Post, StoryItem], target: Optional[Union[str, Path]] = None):
         """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)
 
-    def download_post(self, post: Post, target: str) -> bool:
+    def download_post(self, post: Post, target: Union[str, Path]) -> bool:
         """
         Download everything associated with one instagram post node, i.e. picture, caption and video.
 
@@ -489,6 +518,7 @@ class Instaloader:
             userids = list(edge["node"]["id"] for edge in data["feed_reels_tray"]["edge_reels_tray_to_reel"]["edges"])
 
         def _userid_chunks():
+            assert userids is not None
             userids_per_query = 100
             for i in range(0, len(userids), userids_per_query):
                 yield userids[i:i + userids_per_query]
@@ -537,7 +567,7 @@ class Instaloader:
                     if fast_update and not downloaded:
                         break
 
-    def download_storyitem(self, item: StoryItem, target: str) -> bool:
+    def download_storyitem(self, item: StoryItem, target: Union[str, Path]) -> bool:
         """Download one user story.
 
         :param item: Story item, as in story['items'] for story in :meth:`get_stories`
@@ -614,10 +644,11 @@ class Instaloader:
                     continue
                 self.context.log("[%3i/%3i] " % (count, totalcount), end="", flush=True)
                 count += 1
-                with self.context.error_catcher('Download highlights \"{}\" from user {}'.format(user_highlight.title, name)):
+                with self.context.error_catcher('Download highlights \"{}\" from user {}'.format(user_highlight.title,
+                                                                                                 name)):
                     downloaded = self.download_storyitem(item, filename_target
                                                          if filename_target
-                                                         else '{}/{}'.format(name, user_highlight.title))
+                                                         else Path(name) / Path(user_highlight.title))
                     if fast_update and not downloaded:
                         break
 
@@ -687,6 +718,7 @@ class Instaloader:
         """
         self.context.log("Retrieving saved posts...")
         count = 1
+        assert self.context.username is not None
         for post in Profile.from_username(self.context, self.context.username).get_saved_posts():
             if max_count is not None and count > max_count:
                 break
@@ -819,8 +851,6 @@ class Instaloader:
         """Download all posts where a profile is tagged.
 
         .. versionadded:: 4.1"""
-        if target is None:
-            target = profile.username + '/:tagged'
         self.context.log("Retrieving tagged posts for profile {}.".format(profile.username))
         count = 1
         for post in profile.get_tagged_posts():
@@ -829,7 +859,7 @@ class Instaloader:
             if post_filter is not None and not post_filter(post):
                 self.context.log('<{} skipped>'.format(post))
             with self.context.error_catcher('Download tagged {}'.format(profile.username)):
-                downloaded = self.download_post(post, target)
+                downloaded = self.download_post(post, target if target else Path(profile.username) / Path(':tagged'))
                 if fast_update and not downloaded:
                     break
 
@@ -922,13 +952,15 @@ class Instaloader:
 
         .. versionadded:: 4.1"""
 
+        @contextmanager
         def _error_raiser(_str):
             yield
 
+        # error_handler type is Callable[[Optional[str]], ContextManager[None]] (not supported with Python 3.5)
         error_handler = _error_raiser if raise_errors else self.context.error_catcher
 
         for profile in profiles:
-            with error_handler(profile.username):
+            with error_handler(profile.username):  # type: ignore
                 profile_name = profile.username
 
                 # Download profile picture

instaloader/instaloadercontext.py

@@ -10,7 +10,7 @@ import time
 import urllib.parse
 from contextlib import contextmanager
 from datetime import datetime, timedelta
-from typing import Any, Callable, Dict, Iterator, Optional, Union
+from typing import Any, Callable, Dict, Iterator, List, Optional, Union
 
 import requests
 import requests.utils
@@ -22,7 +22,7 @@ def copy_session(session: requests.Session) -> requests.Session:
     """Duplicates a requests.Session."""
     new = requests.Session()
     new.cookies = requests.utils.cookiejar_from_dict(requests.utils.dict_from_cookiejar(session.cookies))
-    new.headers = session.headers.copy()
+    new.headers = session.headers.copy() # type: ignore
     return new
 
 
@@ -60,17 +60,17 @@ class InstaloaderContext:
         self.two_factor_auth_pending = None
 
         # error log, filled with error() and printed at the end of Instaloader.main()
-        self.error_log = []
+        self.error_log = []                      # type: List[str]
 
         # For the adaption of sleep intervals (rate control)
-        self._graphql_query_timestamps = dict()
-        self._graphql_earliest_next_request_time = 0
+        self._graphql_query_timestamps = dict()  # type: Dict[str, List[float]]
+        self._graphql_earliest_next_request_time = 0.0
 
         # Can be set to True for testing, disables supression of InstaloaderContext._error_catcher
         self.raise_all_errors = False
 
         # Cache profile from id (mapping from id to Profile)
-        self.profile_id_cache = dict()
+        self.profile_id_cache = dict()           # type: Dict[int, Any]
 
     @contextmanager
     def anonymous_copy(self):
@@ -181,7 +181,8 @@ class InstaloaderContext:
         :raises InvalidArgumentException: If the provided username does not exist.
         :raises BadCredentialsException: If the provided password is wrong.
         :raises ConnectionException: If connection to Instagram failed.
-        :raises TwoFactorAuthRequiredException: First step of 2FA login done, now call :meth:`Instaloader.two_factor_login`."""
+        :raises TwoFactorAuthRequiredException: First step of 2FA login done, now call
+           :meth:`Instaloader.two_factor_login`."""
         import http.client
         # pylint:disable=protected-access
         http.client._MAXHEADERS = 200
@@ -283,7 +284,7 @@ class InstaloaderContext:
             max_reqs = {'1cb6ec562846122743b61e492c85999f': 200, '33ba35852cb50da46f5b5e889df7d159': 200}
         return max_reqs.get(query_hash) or min(max_reqs.values())
 
-    def _graphql_query_waittime(self, query_hash: str, current_time: float, untracked_queries: bool = False) -> int:
+    def _graphql_query_waittime(self, query_hash: str, current_time: float, untracked_queries: bool = False) -> float:
         """Calculate time needed to wait before GraphQL query can be executed."""
         sliding_window = 660
         if query_hash not in self._graphql_query_timestamps:

instaloader/structures.py

@@ -17,11 +17,16 @@ PostSidecarNode.is_video.__doc__ = "Whether this node is a video."
 PostSidecarNode.display_url.__doc__ = "URL of image or video thumbnail."
 PostSidecarNode.video_url.__doc__ = "URL of video or None."
 
-PostComment = namedtuple('PostComment', ['id', 'created_at_utc', 'text', 'owner'])
-PostComment.id.__doc__ = "ID number of comment."
-PostComment.created_at_utc.__doc__ = ":class:`~datetime.datetime` when comment was created (UTC)."
-PostComment.text.__doc__ = "Comment text."
-PostComment.owner.__doc__ = "Owner :class:`Profile` of the comment."
+PostCommentAnswer = namedtuple('PostCommentAnswer', ['id', 'created_at_utc', 'text', 'owner'])
+PostCommentAnswer.id.__doc__ = "ID number of comment."
+PostCommentAnswer.created_at_utc.__doc__ = ":class:`~datetime.datetime` when comment was created (UTC)."
+PostCommentAnswer.text.__doc__ = "Comment text."
+PostCommentAnswer.owner.__doc__ = "Owner :class:`Profile` of the comment."
+
+PostComment = namedtuple('PostComment', (*PostCommentAnswer._fields, 'answers')) # type: ignore
+for field in PostCommentAnswer._fields:
+    getattr(PostComment, field).__doc__ = getattr(PostCommentAnswer, field).__doc__
+PostComment.answers.__doc__ = r"Iterator which yields all :class:`PostCommentAnswer`\ s for the comment." # type: ignore
 
 PostLocation = namedtuple('PostLocation', ['id', 'name', 'slug', 'has_public_page', 'lat', 'lng'])
 PostLocation.id.__doc__ = "ID number of location."
@@ -62,9 +67,9 @@ class Post:
         self._context = context
         self._node = node
         self._owner_profile = owner_profile
-        self._full_metadata_dict = None
-        self._rhx_gis_str = None
-        self._location = None
+        self._full_metadata_dict = None  # type: Optional[Dict[str, Any]]
+        self._rhx_gis_str = None         # type: Optional[str]
+        self._location = None            # type: Optional[PostLocation]
 
     @classmethod
     def from_shortcode(cls, context: InstaloaderContext, shortcode: str):
@@ -135,11 +140,13 @@ class Post:
     @property
     def _full_metadata(self) -> Dict[str, Any]:
         self._obtain_metadata()
+        assert self._full_metadata_dict is not None
         return self._full_metadata_dict
 
     @property
     def _rhx_gis(self) -> str:
         self._obtain_metadata()
+        assert self._rhx_gis_str is not None
         return self._rhx_gis_str
 
     def _field(self, *keys) -> Any:
@@ -183,12 +190,16 @@ 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"])
+        return datetime.fromtimestamp(self._node["date"]
+                                      if "date" in self._node
+                                      else self._node["taken_at_timestamp"])
 
     @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._node["date"]
+                                         if "date" in self._node
+                                         else self._node["taken_at_timestamp"])
 
     @property
     def date(self) -> datetime:
@@ -226,6 +237,7 @@ class Post:
             return self._node["edge_media_to_caption"]["edges"][0]["node"]["text"]
         elif "caption" in self._node:
             return self._node["caption"]
+        return None
 
     @property
     def caption_hashtags(self) -> List[str]:
@@ -247,6 +259,16 @@ class Post:
         mention_regex = re.compile(r"(?:@)(\w(?:(?:\w|(?:\.(?!\.))){0,28}(?:\w))?)")
         return re.findall(mention_regex, self.caption.lower())
 
+    @property
+    def pcaption(self) -> str:
+        """Printable caption, useful as a format specifier for --filename-pattern.
+
+        .. versionadded:: 4.2.6"""
+        def _elliptify(caption):
+            pcaption = ' '.join([s.replace('/', '\u2215') for s in caption.splitlines() if s]).strip()
+            return (pcaption[:30] + u"\u2026") if len(pcaption) > 31 else pcaption
+        return _elliptify(self.caption) if self.caption else ''
+
     @property
     def tagged_users(self) -> List[str]:
         """List of all lowercased users that are tagged in the Post."""
@@ -266,6 +288,25 @@ class Post:
         """URL of the video, or None."""
         if self.is_video:
             return self._field('video_url')
+        return None
+
+    @property
+    def video_view_count(self) -> Optional[int]:
+        """View count of the video, or None.
+
+        .. versionadded:: 4.2.6"""
+        if self.is_video:
+            return self._field('video_view_count')
+        return None
+
+    @property
+    def video_duration(self) -> Optional[float]:
+        """Duration of the video in seconds, or None.
+
+        .. versionadded:: 4.2.6"""
+        if self.is_video:
+            return self._field('video_duration')
+        return None
 
     @property
     def viewer_has_liked(self) -> Optional[bool]:
@@ -283,34 +324,72 @@ class Post:
 
     @property
     def comments(self) -> int:
-        """Comment count"""
-        return self._field('edge_media_to_comment', 'count')
+        """Comment count including answers"""
+        try:
+            return self._field('edge_media_to_parent_comment', 'count')
+        except KeyError:
+            return self._field('edge_media_to_comment', 'count')
 
     def get_comments(self) -> Iterator[PostComment]:
-        """Iterate over all comments of the post.
+        r"""Iterate over all comments of the post.
 
         Each comment is represented by a PostComment namedtuple with fields text (string), created_at (datetime),
-        id (int) and owner (:class:`Profile`).
+        id (int), owner (:class:`Profile`) and answers (:class:`~typing.Iterator`\ [:class:`PostCommentAnswer`])
+        if available.
         """
+        def _postcommentanswer(node):
+            return PostCommentAnswer(id=int(node['id']),
+                                     created_at_utc=datetime.utcfromtimestamp(node['created_at']),
+                                     text=node['text'],
+                                     owner=Profile(self._context, node['owner']))
+
+        def _postcommentanswers(node):
+            if 'edge_threaded_comments' not in node:
+                return
+            answer_count = node['edge_threaded_comments']['count']
+            if answer_count == 0:
+                # Avoid doing additional requests if there are no comment answers
+                return
+            answer_edges = node['edge_threaded_comments']['edges']
+            if answer_count == len(answer_edges):
+                # If the answer's metadata already contains all comments, don't do GraphQL requests to obtain them
+                yield from (_postcommentanswer(comment['node']) for comment in answer_edges)
+                return
+            yield from (_postcommentanswer(answer_node) for answer_node in
+                        self._context.graphql_node_list("51fdd02b67508306ad4484ff574a0b62",
+                                                        {'comment_id': node['id']},
+                                                        'https://www.instagram.com/p/' + self.shortcode + '/',
+                                                        lambda d: d['data']['comment']['edge_threaded_comments']))
+
         def _postcomment(node):
-            return PostComment(id=int(node['id']),
-                               created_at_utc=datetime.utcfromtimestamp(node['created_at']),
-                               text=node['text'],
-                               owner=Profile(self._context, node['owner']))
+            return PostComment(*_postcommentanswer(node),
+                               answers=_postcommentanswers(node))
         if self.comments == 0:
             # Avoid doing additional requests if there are no comments
             return
-        comment_edges = self._field('edge_media_to_comment', 'edges')
-        if self.comments == len(comment_edges):
-            # If the Post's metadata already contains all comments, don't do GraphQL requests to obtain them
+        try:
+            comment_edges = self._field('edge_media_to_parent_comment', 'edges')
+            answers_count = sum([edge['node']['edge_threaded_comments']['count'] for edge in comment_edges])
+            threaded_comments_available = True
+        except KeyError:
+            comment_edges = self._field('edge_media_to_comment', 'edges')
+            answers_count = 0
+            threaded_comments_available = False
+
+        if self.comments == len(comment_edges) + answers_count:
+            # If the Post's metadata already contains all parent comments, don't do GraphQL requests to obtain them
             yield from (_postcomment(comment['node']) for comment in comment_edges)
             return
         yield from (_postcomment(node) for node in
-                    self._context.graphql_node_list("33ba35852cb50da46f5b5e889df7d159",
-                                                    {'shortcode': self.shortcode},
-                                                    'https://www.instagram.com/p/' + self.shortcode + '/',
-                                                    lambda d: d['data']['shortcode_media']['edge_media_to_comment'],
-                                                    self._rhx_gis))
+                    self._context.graphql_node_list(
+                        "97b41c52301f77ce508f55e66d17620e" if threaded_comments_available
+                        else "f0986789a5c5d17c2400faebf16efd0d",
+                        {'shortcode': self.shortcode},
+                        'https://www.instagram.com/p/' + self.shortcode + '/',
+                        lambda d:
+                        d['data']['shortcode_media'][
+                            'edge_media_to_parent_comment' if threaded_comments_available else 'edge_media_to_comment'],
+                        self._rhx_gis))
 
     def get_likes(self) -> Iterator['Profile']:
         """Iterate over all likes of the post. A :class:`Profile` instance of each likee is yielded."""
@@ -373,7 +452,7 @@ class Profile:
     def __init__(self, context: InstaloaderContext, node: Dict[str, Any]):
         assert 'username' in node
         self._context = context
-        self._has_public_story = None
+        self._has_public_story = None  # type: Optional[bool]
         self._node = node
         self._rhx_gis = None
         self._iphone_struct_ = None
@@ -553,6 +632,7 @@ class Profile:
                                                        'https://www.instagram.com/{}/'.format(self.username),
                                                        self._rhx_gis)
             self._has_public_story = data['data']['user']['has_public_story']
+        assert self._has_public_story is not None
         return self._has_public_story
 
     @property
@@ -719,6 +799,7 @@ class StoryItem:
         """:class:`Profile` instance of the story item's owner."""
         if not self._owner_profile:
             self._owner_profile = Profile.from_id(self._context, self._node['owner']['id'])
+        assert self._owner_profile is not None
         return self._owner_profile
 
     @property
@@ -781,6 +862,7 @@ class StoryItem:
         """URL of the video, or None."""
         if self.is_video:
             return self._node['video_resources'][-1]['src']
+        return None
 
 
 class Story:
@@ -807,8 +889,8 @@ class Story:
     def __init__(self, context: InstaloaderContext, node: Dict[str, Any]):
         self._context = context
         self._node = node
-        self._unique_id = None
-        self._owner_profile = None
+        self._unique_id = None      # type: Optional[str]
+        self._owner_profile = None  # type: Optional[Profile]
 
     def __repr__(self):
         return '<Story by {} changed {:%Y-%m-%d_%H-%M-%S_UTC}>'.format(self.owner_username, self.latest_media_utc)
@@ -822,7 +904,7 @@ class Story:
         return hash(self.unique_id)
 
     @property
-    def unique_id(self) -> str:
+    def unique_id(self) -> Union[str, int]:
         """
         This ID only equals amongst :class:`Story` instances which have the same owner and the same set of
         :class:`StoryItem`. For all other :class:`Story` instances this ID is different.
@@ -838,12 +920,14 @@ class Story:
         """Timestamp when the story has last been watched or None (local time zone)."""
         if self._node['seen']:
             return datetime.fromtimestamp(self._node['seen'])
+        return None
 
     @property
     def last_seen_utc(self) -> Optional[datetime]:
         """Timestamp when the story has last been watched or None (UTC)."""
         if self._node['seen']:
             return datetime.utcfromtimestamp(self._node['seen'])
+        return None
 
     @property
     def latest_media_local(self) -> datetime:
@@ -908,7 +992,7 @@ class Highlight(Story):
     def __init__(self, context: InstaloaderContext, node: Dict[str, Any], owner: Optional[Profile] = None):
         super().__init__(context, node)
         self._owner_profile = owner
-        self._items = None
+        self._items = None  # type: Optional[List[Dict[str, Any]]]
 
     def __repr__(self):
         return '<Highlight by {}: {}>'.format(self.owner_username, self.title)
@@ -951,11 +1035,13 @@ class Highlight(Story):
     def itemcount(self) -> int:
         """Count of items associated with the :class:`Highlight` instance."""
         self._fetch_items()
+        assert self._items is not None
         return len(self._items)
 
     def get_items(self) -> Iterator[StoryItem]:
         """Retrieve all associated highlight items."""
         self._fetch_items()
+        assert self._items is not None
         yield from (StoryItem(self._context, item, self.owner_profile) for item in self._items)