Release of version 4.2.7

Closes #297.

.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

LICENSE

@@ -1,6 +1,6 @@
 The MIT License (MIT)
 
-Copyright (c) 2016-2018 Alexander Graf and André Koch-Kramer.
+Copyright (c) 2016-2019 Alexander Graf and André Koch-Kramer.
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

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/_templates/layout.html

@@ -51,6 +51,9 @@
         <li class="nav-item">
           <a target="_blank" class="nav-link" href="https://github.com/instaloader/instaloader">GitHub</a>
         </li>
+        <li class="nav-item d-sm-none d-lg-block">
+          <a target="_blank" class="nav-link" href="https://saythanks.io/to/aandergr">Say Thanks!</a>
+        </li>
       </ul>
       <form class="form-inline" action="search.html" method="get">
         <div class="input-group my-2 my-sm-0 ml-2">

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:
 
@@ -198,6 +201,8 @@ Exceptions
 
 .. autoexception:: BadCredentialsException
 
+.. autoexception:: PostChangedException
+
 .. autoexception:: TooManyRequestsException
 
 ``InstaloaderContext`` (Low-level functions)

docs/conf.py

@@ -86,7 +86,7 @@ author = 'Alexander Graf and Andre Koch-Kramer'
 #
 # This is also used if you do content translation via gettext catalogs.
 # Usually you set "language" from the command line for these cases.
-language = None
+language = "en"
 
 # There are two options for replacing |today|: either, you set today to some
 # non-false value, then it is used:

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__ = '4.2.1'
+__version__ = '4.2.7'
 
 
 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/__main__.py

@@ -331,7 +331,6 @@ def main():
     g_how.add_argument('--user-agent',
                        help='User Agent to use for HTTP requests. Defaults to \'{}\'.'.format(default_user_agent()))
     g_how.add_argument('-S', '--no-sleep', action='store_true', help=SUPPRESS)
-    g_how.add_argument('--graphql-rate-limit', type=int, help=SUPPRESS)
     g_how.add_argument('--max-connection-attempts', metavar='N', type=int, default=3,
                        help='Maximum number of connection attempts until a request is aborted. Defaults to 3. If a '
                             'connection fails, it can be manually skipped by hitting CTRL+C. Set this to 0 to retry '
@@ -393,7 +392,6 @@ def main():
                              compress_json=not args.no_compress_json,
                              post_metadata_txt_pattern=post_metadata_txt_pattern,
                              storyitem_metadata_txt_pattern=storyitem_metadata_txt_pattern,
-                             graphql_rate_limit=args.graphql_rate_limit,
                              max_connection_attempts=args.max_connection_attempts,
                              commit_mode=args.commit_mode)
         _main(loader,

instaloader/exceptions.py

@@ -22,6 +22,10 @@ class ProfileNotExistsException(InstaloaderException):
 
 
 class ProfileHasNoPicsException(InstaloaderException):
+    """
+    .. deprecated:: 4.2.2
+       Not raised anymore.
+    """
     pass
 
 
@@ -53,5 +57,10 @@ class ConnectionException(InstaloaderException):
     pass
 
 
+class PostChangedException(InstaloaderException):
+    """.. versionadded:: 4.2.2"""
+    pass
+
+
 class TooManyRequestsException(ConnectionException):
     pass

instaloader/instaloader.py

@@ -13,11 +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  # 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:
@@ -42,8 +47,39 @@ 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
+
+
+def _retry_on_connection_error(func: Callable) -> Callable:
+    """Decorator to retry the function max_connection_attemps number of times.
+
+    Herewith-decorated functions need an ``_attempt`` keyword argument.
+
+    This is to decorate functions that do network requests that may fail. Note that
+    :meth:`.get_json`, :meth:`.get_iphone_json`, :meth:`.graphql_query` and :meth:`.graphql_node_list` already have
+    their own logic for retrying, hence functions that only use these for network access must not be decorated with this
+    decorator."""
+    @wraps(func)
+    def call(instaloader, *args, **kwargs):
+        try:
+            return func(instaloader, *args, **kwargs)
+        except (urllib3.exceptions.HTTPError, requests.exceptions.RequestException, ConnectionException) as err:
+            error_string = "{}({}): {}".format(func.__name__, ', '.join([repr(arg) for arg in args]), err)
+            if (kwargs.get('_attempt') or 1) == instaloader.context.max_connection_attempts:
+                raise ConnectionException(error_string) from None
+            instaloader.context.error(error_string + " [retrying; skip with ^C]", repeat_at_end=False)
+            try:
+                if kwargs.get('_attempt'):
+                    kwargs['_attempt'] += 1
+                else:
+                    kwargs['_attempt'] = 2
+                instaloader.context.do_sleep()
+                return call(instaloader, *args, **kwargs)
+            except KeyboardInterrupt:
+                instaloader.context.error("[skipped by user]", repeat_at_end=False)
+                raise ConnectionException(error_string) from None
     return call
 
 
@@ -74,7 +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
 
 
@@ -118,11 +164,10 @@ class Instaloader:
                  compress_json: bool = True,
                  post_metadata_txt_pattern: str = None,
                  storyitem_metadata_txt_pattern: str = None,
-                 graphql_rate_limit: Optional[int] = None,
                  max_connection_attempts: int = 3,
                  commit_mode: bool = False):
 
-        self.context = InstaloaderContext(sleep, quiet, user_agent, graphql_rate_limit, max_connection_attempts)
+        self.context = InstaloaderContext(sleep, quiet, user_agent, max_connection_attempts)
 
         # configuration parameters
         self.dirname_pattern = dirname_pattern or "{target}"
@@ -143,7 +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):
@@ -156,13 +201,10 @@ class Instaloader:
                                  save_metadata=self.save_metadata, compress_json=self.compress_json,
                                  post_metadata_txt_pattern=self.post_metadata_txt_pattern,
                                  storyitem_metadata_txt_pattern=self.storyitem_metadata_txt_pattern,
-                                 graphql_rate_limit=self.context.graphql_count_per_slidingwindow,
                                  max_connection_attempts=self.context.max_connection_attempts)
-        new_loader.context.query_timestamps = self.context.query_timestamps
         yield new_loader
         self.context.error_log.extend(new_loader.context.error_log)
         new_loader.context.error_log = []  # avoid double-printing of errors
-        self.context.query_timestamps = new_loader.context.query_timestamps
         new_loader.close()
 
     def close(self):
@@ -175,7 +217,9 @@ class Instaloader:
     def __exit__(self, *args):
         self.close()
 
-    def download_pic(self, filename: str, url: str, mtime: datetime, filename_suffix: Optional[str] = None) -> bool:
+    @_retry_on_connection_error
+    def download_pic(self, filename: str, url: str, mtime: datetime,
+                     filename_suffix: Optional[str] = None, _attempt: int = 1) -> bool:
         """Downloads and saves picture with given url under given directory with given timestamp.
         Returns true, if file was actually downloaded, i.e. updated."""
         urlmatch = re.search('\\.[a-z0-9]*\\?', url)
@@ -208,11 +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:
@@ -221,18 +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:
@@ -243,11 +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:
@@ -271,7 +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:
@@ -285,19 +343,20 @@ class Instaloader:
         os.utime(filename, (datetime.now().timestamp(), mtime.timestamp()))
         self.context.log('geo', end=' ', flush=True)
 
-    def download_profilepic(self, profile: Profile) -> None:
+    @_retry_on_connection_error
+    def download_profilepic(self, profile: Profile, _attempt: int = 1) -> None:
         """Downloads and saves profile pic."""
 
         def _epoch_to_string(epoch: datetime) -> str:
             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'
@@ -311,7 +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)
@@ -326,6 +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):
@@ -359,7 +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:
@@ -372,13 +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.
 
@@ -456,6 +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]
@@ -504,7 +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`
@@ -581,10 +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
 
@@ -654,6 +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
@@ -731,7 +796,7 @@ class Instaloader:
                     for node in self.context.graphql_node_list("df0dcc250c2b18d9fd27c5581ef33c7c",
                                                                {}, 'https://www.instagram.com/explore/',
                                                                lambda d: d['data']['user']['edge_web_discover_media'],
-                                                               data['rhx_gis']))
+                                                               data.get('rhx_gis')))
 
     def get_hashtag_posts(self, hashtag: str) -> Iterator[Post]:
         """Get Posts associated with a #hashtag."""
@@ -786,8 +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():
@@ -796,7 +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
 
@@ -889,15 +952,22 @@ 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
+                if profile_pic:
+                    with self.context.error_catcher('Download profile picture of {}'.format(profile_name)):
+                        self.download_profilepic(profile)
+
                 # Save metadata as JSON if desired.
                 if self.save_metadata:
                     json_filename = '{0}/{1}_{2}'.format(self.dirname_pattern.format(profile=profile_name,
@@ -905,11 +975,6 @@ class Instaloader:
                                                          profile_name, profile.userid)
                     self.save_metadata_json(json_filename, profile)
 
-                # Download profile picture
-                if profile_pic:
-                    with self.context.error_catcher('Download profile picture of {}'.format(profile_name)):
-                        self.download_profilepic(profile)
-
                 # Catch some errors
                 if profile.is_private and (tagged or highlights or posts):
                     if not self.context.is_logged_in:
@@ -939,8 +1004,22 @@ class Instaloader:
                             self.context.log('<skipped>')
                             continue
                         with self.context.error_catcher("Download {} of {}".format(post, profile_name)):
-                            downloaded = self.download_post(post, target=profile_name)
-                            if fast_update and not downloaded:
+                            # The PostChangedException gets raised if the Post's id/shortcode changed while obtaining
+                            # additional metadata. This is most likely the case if a HTTP redirect takes place while
+                            # resolving the shortcode URL.
+                            # The `post_changed` variable keeps the fast-update functionality alive: A Post which is
+                            # obained after a redirect has probably already been downloaded as a previous Post of the
+                            # same Profile.
+                            # Observed in issue #225: https://github.com/instaloader/instaloader/issues/225
+                            post_changed = False
+                            while True:
+                                try:
+                                    downloaded = self.download_post(post, target=profile_name)
+                                    break
+                                except PostChangedException:
+                                    post_changed = True
+                                    continue
+                            if fast_update and not downloaded and not post_changed:
                                 break
 
         if stories and profiles:

instaloader/instaloadercontext.py

@@ -10,11 +10,10 @@ 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
-import urllib3
 
 from .exceptions import *
 
@@ -23,7 +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
 
 
@@ -48,7 +47,7 @@ class InstaloaderContext:
     """
 
     def __init__(self, sleep: bool = True, quiet: bool = False, user_agent: Optional[str] = None,
-                 graphql_count_per_slidingwindow: Optional[int] = None, max_connection_attempts: int = 3):
+                 max_connection_attempts: int = 3):
 
         self.user_agent = user_agent if user_agent is not None else default_user_agent()
         self._session = self.get_anonymous_session()
@@ -57,21 +56,21 @@ class InstaloaderContext:
         self.quiet = quiet
         self.max_connection_attempts = max_connection_attempts
         self._graphql_page_length = 50
-        self.graphql_count_per_slidingwindow = graphql_count_per_slidingwindow or 200
         self._root_rhx_gis = None
         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.query_timestamps = list()
+        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):
@@ -182,7 +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
@@ -195,7 +195,7 @@ class InstaloaderContext:
         csrf_token = session.cookies.get_dict()['csrftoken']
         session.headers.update({'X-CSRFToken': csrf_token})
         # Not using self.get_json() here, because we need to access csrftoken cookie
-        self._sleep()
+        self.do_sleep()
         login = session.post('https://www.instagram.com/accounts/login/ajax/',
                              data={'password': passwd, 'username': user}, allow_redirects=True)
         try:
@@ -261,11 +261,77 @@ class InstaloaderContext:
         self.username = user
         self.two_factor_auth_pending = None
 
-    def _sleep(self):
+    def do_sleep(self):
         """Sleep a short time if self.sleep is set. Called before each request to instagram.com."""
         if self.sleep:
             time.sleep(min(random.expovariate(0.7), 5.0))
 
+    def _dump_query_timestamps(self, current_time: float):
+        """Output the number of GraphQL queries grouped by their query_hash within the last time."""
+        windows = [10, 11, 15, 20, 30, 60]
+        print("GraphQL requests:", file=sys.stderr)
+        for query_hash, times in self._graphql_query_timestamps.items():
+            print("  {}".format(query_hash), file=sys.stderr)
+            for window in windows:
+                reqs_in_sliding_window = sum(t > current_time - window * 60 for t in times)
+                print("    last {} minutes: {} requests".format(window, reqs_in_sliding_window), file=sys.stderr)
+
+    def _graphql_request_count_per_sliding_window(self, query_hash: str) -> int:
+        """Return how many GraphQL requests can be done within the sliding window."""
+        if self.is_logged_in:
+            max_reqs = {'1cb6ec562846122743b61e492c85999f': 20, '33ba35852cb50da46f5b5e889df7d159': 20}
+        else:
+            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) -> float:
+        """Calculate time needed to wait before GraphQL query can be executed."""
+        sliding_window = 660
+        if query_hash not in self._graphql_query_timestamps:
+            self._graphql_query_timestamps[query_hash] = []
+        self._graphql_query_timestamps[query_hash] = list(filter(lambda t: t > current_time - 60 * 60,
+                                                                 self._graphql_query_timestamps[query_hash]))
+        reqs_in_sliding_window = list(filter(lambda t: t > current_time - sliding_window,
+                                             self._graphql_query_timestamps[query_hash]))
+        count_per_sliding_window = self._graphql_request_count_per_sliding_window(query_hash)
+        if len(reqs_in_sliding_window) < count_per_sliding_window and not untracked_queries:
+            return max(0, self._graphql_earliest_next_request_time - current_time)
+        next_request_time = min(reqs_in_sliding_window) + sliding_window + 6
+        if untracked_queries:
+            self._graphql_earliest_next_request_time = next_request_time
+        return round(max(next_request_time, self._graphql_earliest_next_request_time) - current_time)
+
+    def _ratecontrol_graphql_query(self, query_hash: str, untracked_queries: bool = False):
+        """Called before a GraphQL query is made in order to stay within Instagram's rate limits.
+
+        :param query_hash: The query_hash parameter of the query.
+        :param untracked_queries: True, if 429 has been returned to apply 429 logic.
+        """
+        if not untracked_queries:
+            waittime = self._graphql_query_waittime(query_hash, time.monotonic(), untracked_queries)
+            assert waittime >= 0
+            if waittime > 10:
+                self.log('\nToo many queries in the last time. Need to wait {} seconds, until {:%H:%M}.'
+                         .format(waittime, datetime.now() + timedelta(seconds=waittime)))
+            time.sleep(waittime)
+            if query_hash not in self._graphql_query_timestamps:
+                self._graphql_query_timestamps[query_hash] = [time.monotonic()]
+            else:
+                self._graphql_query_timestamps[query_hash].append(time.monotonic())
+        else:
+            text_for_429 = ("HTTP error code 429 was returned because too many queries occured in the last time. "
+                            "Please do not use Instagram in your browser or run multiple instances of Instaloader "
+                            "in parallel.")
+            print(textwrap.fill(text_for_429), file=sys.stderr)
+            current_time = time.monotonic()
+            waittime = self._graphql_query_waittime(query_hash, current_time, untracked_queries)
+            assert waittime >= 0
+            if waittime > 10:
+                self.log('The request will be retried in {} seconds, at {:%H:%M}.'
+                         .format(waittime, datetime.now() + timedelta(seconds=waittime)))
+            self._dump_query_timestamps(current_time)
+            time.sleep(waittime)
+
     def get_json(self, path: str, params: Dict[str, Any], host: str = 'www.instagram.com',
                  session: Optional[requests.Session] = None, _attempt=1) -> Dict[str, Any]:
         """JSON request to Instagram.
@@ -279,32 +345,12 @@ class InstaloaderContext:
         :raises QueryReturnedNotFoundException: When the server responds with a 404.
         :raises ConnectionException: When query repeatedly failed.
         """
-        def graphql_query_waittime(untracked_queries: bool = False) -> int:
-            sliding_window = 660
-            if not self.query_timestamps:
-                return sliding_window if untracked_queries else 0
-            current_time = time.monotonic()
-            self.query_timestamps = list(filter(lambda t: t > current_time - sliding_window, self.query_timestamps))
-            if len(self.query_timestamps) < self.graphql_count_per_slidingwindow and not untracked_queries:
-                return 0
-            return round(min(self.query_timestamps) + sliding_window - current_time) + 6
         is_graphql_query = 'query_hash' in params and 'graphql/query' in path
-        # some queries are not rate limited if invoked anonymously:
-        query_not_limited = is_graphql_query and not self.is_logged_in \
-                            and params['query_hash'] in ['9ca88e465c3f866a76f7adee3871bdd8']
-        if is_graphql_query and not query_not_limited:
-            waittime = graphql_query_waittime()
-            if waittime > 0:
-                self.log('\nToo many queries in the last time. Need to wait {} seconds, until {:%H:%M}.'
-                         .format(waittime, datetime.now() + timedelta(seconds=waittime)))
-                time.sleep(waittime)
-            if self.query_timestamps is not None:
-                self.query_timestamps.append(time.monotonic())
-            else:
-                self.query_timestamps = [time.monotonic()]
         sess = session if session else self._session
         try:
-            self._sleep()
+            self.do_sleep()
+            if is_graphql_query:
+                self._ratecontrol_graphql_query(params['query_hash'])
             resp = sess.get('https://{0}/{1}'.format(host, path), params=params, allow_redirects=False)
             while resp.is_redirect:
                 redirect_url = resp.headers['location']
@@ -342,20 +388,9 @@ class InstaloaderContext:
             if _attempt == self.max_connection_attempts:
                 raise ConnectionException(error_string) from err
             self.error(error_string + " [retrying; skip with ^C]", repeat_at_end=False)
-            text_for_429 = ("HTTP error code 429 was returned because too many queries occured in the last time. "
-                            "Please do not use Instagram in your browser or run multiple instances of Instaloader "
-                            "in parallel.")
             try:
                 if isinstance(err, TooManyRequestsException):
-                    print(textwrap.fill(text_for_429), file=sys.stderr)
-                    if is_graphql_query:
-                        print("Made {} GraphQL requests.".format(len(self.query_timestamps)), file=sys.stderr)
-                        waittime = graphql_query_waittime(untracked_queries=True)
-                        if waittime > 0:
-                            self.log('The request will be retried in {} seconds, at {:%H:%M}.'
-                                     .format(waittime, datetime.now() + timedelta(seconds=waittime)))
-                            time.sleep(waittime)
-                self._sleep()
+                    self._ratecontrol_graphql_query(params['query_hash'], untracked_queries=True)
                 return self.get_json(path=path, params=params, host=host, session=sess, _attempt=_attempt + 1)
             except KeyboardInterrupt:
                 self.error("[skipped by user]", repeat_at_end=False)
@@ -440,15 +475,17 @@ class InstaloaderContext:
         :raises ConnectionException: When query repeatedly failed.
 
         .. versionadded:: 4.2.1"""
-        tempsession = copy_session(self._session)
-        tempsession.headers['User-Agent'] = 'Instagram 10.3.2 (iPhone7,2; iPhone OS 9_3_3; en_US; en-US; ' \
-                                            'scale=2.00; 750x1334) AppleWebKit/420+'
-        for header in ['Host', 'Origin', 'X-Instagram-AJAX', 'X-Requested-With']:
-            tempsession.headers.pop(header, None)
-        return self.get_json(path, params, 'i.instagram.com', tempsession)
+        with copy_session(self._session) as tempsession:
+            tempsession.headers['User-Agent'] = 'Instagram 10.3.2 (iPhone7,2; iPhone OS 9_3_3; en_US; en-US; ' \
+                                                'scale=2.00; 750x1334) AppleWebKit/420+'
+            for header in ['Host', 'Origin', 'X-Instagram-AJAX', 'X-Requested-With']:
+                tempsession.headers.pop(header, None)
+            return self.get_json(path, params, 'i.instagram.com', tempsession)
 
     def write_raw(self, resp: Union[bytes, requests.Response], filename: str) -> None:
-        """Write raw response data into a file."""
+        """Write raw response data into a file.
+
+        .. versionadded:: 4.2.1"""
         self.log(filename, end=' ', flush=True)
         with open(filename, 'wb') as file:
             if isinstance(resp, requests.Response):
@@ -461,32 +498,22 @@ class InstaloaderContext:
 
         :raises QueryReturnedNotFoundException: When the server responds with a 404.
         :raises QueryReturnedForbiddenException: When the server responds with a 403.
-        :raises ConnectionException: When download repeatedly failed."""
-        try:
-            with self.get_anonymous_session() as anonymous_session:
-                resp = anonymous_session.get(url, stream=True)
-            if resp.status_code == 200:
-                resp.raw.decode_content = True
-                return resp
-            else:
-                if resp.status_code == 403:
-                    # suspected invalid URL signature
-                    raise QueryReturnedForbiddenException("403 when accessing {}.".format(url))
-                if resp.status_code == 404:
-                    # 404 not worth retrying.
-                    raise QueryReturnedNotFoundException("404 when accessing {}.".format(url))
-                raise ConnectionException("HTTP error code {}.".format(resp.status_code))
-        except (urllib3.exceptions.HTTPError, requests.exceptions.RequestException, ConnectionException) as err:
-            error_string = "URL {}: {}".format(url, err)
-            if _attempt == self.max_connection_attempts:
-                raise ConnectionException(error_string) from err
-            self.error(error_string + " [retrying; skip with ^C]", repeat_at_end=False)
-            try:
-                self._sleep()
-                return self.get_raw(url, _attempt + 1)
-            except KeyboardInterrupt:
-                self.error("[skipped by user]", repeat_at_end=False)
-                raise ConnectionException(error_string) from err
+        :raises ConnectionException: When download failed.
+
+        .. versionadded:: 4.2.1"""
+        with self.get_anonymous_session() as anonymous_session:
+            resp = anonymous_session.get(url, stream=True)
+        if resp.status_code == 200:
+            resp.raw.decode_content = True
+            return resp
+        else:
+            if resp.status_code == 403:
+                # suspected invalid URL signature
+                raise QueryReturnedForbiddenException("403 when accessing {}.".format(url))
+            if resp.status_code == 404:
+                # 404 not worth retrying.
+                raise QueryReturnedNotFoundException("404 when accessing {}.".format(url))
+            raise ConnectionException("HTTP error code {}.".format(resp.status_code))
 
     def get_and_write_raw(self, url: str, filename: str) -> None:
         """Downloads and writes anonymously-requested raw data into a file.
@@ -503,6 +530,6 @@ class InstaloaderContext:
             # At the moment, rhx_gis seems to be required for anonymous requests only. By returning None when logged
             # in, we can save the root_rhx_gis lookup query.
             return None
-        if not self._root_rhx_gis:
-            self._root_rhx_gis = self.get_json('', {})['rhx_gis']
-        return self._root_rhx_gis
+        if self._root_rhx_gis is None:
+            self._root_rhx_gis = self.get_json('', {}).get('rhx_gis', '')
+        return self._root_rhx_gis or None

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):
@@ -127,15 +132,19 @@ class Post:
         if not self._full_metadata_dict:
             pic_json = self._context.get_json("p/{0}/".format(self.shortcode), params={})
             self._full_metadata_dict = pic_json['entry_data']['PostPage'][0]['graphql']['shortcode_media']
-            self._rhx_gis_str = pic_json['rhx_gis']
+            self._rhx_gis_str = pic_json.get('rhx_gis')
+            if self.shortcode != self._full_metadata_dict['shortcode']:
+                self._node.update(self._full_metadata_dict)
+                raise PostChangedException
 
     @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:
+    def _rhx_gis(self) -> Optional[str]:
         self._obtain_metadata()
         return self._rhx_gis_str
 
@@ -180,12 +189,16 @@ 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:
@@ -223,6 +236,7 @@ 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]:
@@ -244,6 +258,16 @@ 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."""
@@ -263,6 +287,25 @@ 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]:
@@ -280,34 +323,72 @@ 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."""
@@ -370,8 +451,9 @@ 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._has_full_metadata = False
         self._rhx_gis = None
         self._iphone_struct_ = None
         if 'iphone_struct' in node:
@@ -396,28 +478,27 @@ class Profile:
     @classmethod
     def from_id(cls, context: InstaloaderContext, profile_id: int):
         """Create a Profile instance from a given userid. If possible, use :meth:`Profile.from_username`
-        or constructor directly rather than this method, since it does many requests.
+        or constructor directly rather than this method, since it requires more requests.
 
         :param context: :attr:`Instaloader.context`
         :param profile_id: userid
-        :raises: :class:`ProfileNotExistsException`, :class:`ProfileHasNoPicsException`
+        :raises: :class:`ProfileNotExistsException`
         """
         if profile_id in context.profile_id_cache:
             return context.profile_id_cache[profile_id]
-        data = context.graphql_query("472f257a40c653c64c666ce877d59d2b",
-                                     {'id': str(profile_id), 'first': 1},
+        data = context.graphql_query('7c16654f22c819fb63d1183034a5162f',
+                                     {'user_id': str(profile_id),
+                                      'include_chaining': False,
+                                      'include_reel': True,
+                                      'include_suggested_users': False,
+                                      'include_logged_out_extras': False,
+                                      'include_highlight_reels': False},
                                      rhx_gis=context.root_rhx_gis)['data']['user']
         if data:
-            data = data["edge_owner_to_timeline_media"]
+            profile = cls(context, data['reel']['owner'])
         else:
             raise ProfileNotExistsException("No profile found, the user may have blocked you (ID: " +
                                             str(profile_id) + ").")
-        if not data['edges']:
-            if data['count'] == 0:
-                raise ProfileHasNoPicsException("Profile with ID {0}: no pics found.".format(str(profile_id)))
-            else:
-                raise LoginRequiredException("Login required to determine username (ID: " + str(profile_id) + ").")
-        profile = Post(context, data['edges'][0]['node']).owner_profile
         context.profile_id_cache[profile_id] = profile
         return profile
 
@@ -433,10 +514,11 @@ class Profile:
 
     def _obtain_metadata(self):
         try:
-            if not self._rhx_gis:
+            if not self._has_full_metadata:
                 metadata = self._context.get_json('{}/'.format(self.username), params={})
                 self._node = metadata['entry_data']['ProfilePage'][0]['graphql']['user']
-                self._rhx_gis = metadata['rhx_gis']
+                self._has_full_metadata = True
+                self._rhx_gis = metadata.get('rhx_gis')
         except (QueryReturnedNotFoundException, KeyError) as err:
             raise ProfileNotExistsException('Profile {} does not exist.'.format(self.username)) from err
 
@@ -551,6 +633,7 @@ 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
@@ -717,6 +800,7 @@ 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
@@ -779,6 +863,7 @@ class StoryItem:
         """URL of the video, or None."""
         if self.is_video:
             return self._node['video_resources'][-1]['src']
+        return None
 
 
 class Story:
@@ -805,8 +890,8 @@ 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)
@@ -820,7 +905,7 @@ 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.
@@ -836,12 +921,14 @@ 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:
@@ -906,7 +993,7 @@ 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)
@@ -949,11 +1036,13 @@ 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)
 
 

test/instaloader_unittests.py

@@ -17,9 +17,12 @@ OWN_USERNAME = "aandergr"
 NORMAL_MAX_COUNT = 2
 PAGING_MAX_COUNT = 15
 PRIVATE_PROFILE = "aandergr"
+PRIVATE_PROFILE_ID = 1706625676
+EMPTY_PROFILE = "not_public"
+EMPTY_PROFILE_ID = 1928659031
 
 # Preserve query timestamps (rate control) between tests to not get rate limited
-instaloadercontext_query_timestamps = list()
+instaloadercontext_query_timestamps = dict()
 
 
 class TestInstaloaderAnonymously(unittest.TestCase):
@@ -32,11 +35,11 @@ class TestInstaloaderAnonymously(unittest.TestCase):
                                          download_comments=True,
                                          save_metadata=True)
         self.L.context.raise_all_errors = True
-        self.L.context.query_timestamps = instaloadercontext_query_timestamps
+        self.L.context.query_timestamps = instaloadercontext_query_timestamps.copy()
 
     def tearDown(self):
         global instaloadercontext_query_timestamps
-        instaloadercontext_query_timestamps = self.L.context.query_timestamps
+        instaloadercontext_query_timestamps = self.L.context.query_timestamps.copy()
         self.L.close()
         os.chdir('/')
         print("Removing {}".format(self.dir))
@@ -83,10 +86,18 @@ class TestInstaloaderAnonymously(unittest.TestCase):
         self.assertEqual(PUBLIC_PROFILE_ID,
                          instaloader.Profile.from_username(self.L.context, PUBLIC_PROFILE).userid)
 
-    def test_get_username_by_id(self):
+    def test_get_username_by_id_private(self):
+        self.assertEqual(PRIVATE_PROFILE.lower(),
+                         instaloader.Profile.from_id(self.L.context, PRIVATE_PROFILE_ID).username)
+
+    def test_get_username_by_id_public(self):
         self.assertEqual(PUBLIC_PROFILE.lower(),
                          instaloader.Profile.from_id(self.L.context, PUBLIC_PROFILE_ID).username)
 
+    def test_get_username_by_id_empty(self):
+        self.assertEqual(EMPTY_PROFILE.lower(),
+                         instaloader.Profile.from_id(self.L.context, EMPTY_PROFILE_ID).username)
+
     def test_post_from_mediaid(self):
         for post in instaloader.Profile.from_username(self.L.context, PUBLIC_PROFILE).get_posts():
             post2 = instaloader.Post.from_mediaid(self.L.context, post.mediaid)
@@ -130,6 +141,9 @@ class TestInstaloaderLoggedIn(TestInstaloaderAnonymously):
     def test_private_profile_paging(self):
         self.post_paging_test(instaloader.Profile.from_username(self.L.context, PRIVATE_PROFILE).get_posts())
 
+    def test_profile_pic_download(self):
+        self.L.download_profile(PUBLIC_PROFILE, profile_pic_only=True)
+
     def test_feed_download(self):
         self.L.download_feed_posts(NORMAL_MAX_COUNT)
 
@@ -166,10 +180,6 @@ class TestInstaloaderLoggedIn(TestInstaloaderAnonymously):
         for f in profile.get_followers():
             print(f.username)
 
-    def test_get_username_by_id(self):
-        self.assertEqual(PUBLIC_PROFILE.lower(),
-                         instaloader.Profile.from_id(self.L.context, PUBLIC_PROFILE_ID).username)
-
     def test_get_likes(self):
         for post in instaloader.Profile.from_username(self.L.context, OWN_USERNAME).get_posts():
             for like in post.get_likes():