Release of version 4.2.10

Closes #380.
Closes #394.

Co-Authored-By: Dāvis <davispuh@users.noreply.github.com>
Co-Authored-By: Alexander Graf <mail@agraf.me>
Co-Authored-By: Thammus <koch-kramer@web.de>

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,6 +1,7 @@
 ---
-name: Bug report
-about: Create a report to help us improve
+name: 🐛 Bug report
+about: Create a report to help us improve 🤕
+labels: bug
 
 ---
 
@@ -22,3 +23,5 @@ If applicable, add error messages and tracebacks to help explain your problem.
 
 **Additional context**
 Add any other context about the problem here.
+
+(please also see https://instaloader.github.io/contributing.html for how to report a bug)

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,6 +1,7 @@
 ---
-name: Feature request
-about: Suggest an idea for this project
+name: 🚀 Feature Suggestion
+about: Suggest an idea for this project 💡
+labels: "feature suggestion"
 
 ---
 
@@ -13,5 +14,11 @@ A clear and concise description of what you want to happen.
 **Describe alternatives you've considered**
 A clear and concise description of any alternative solutions or features you've considered.
 
+**If the feature request is accepted, would you be willing to submit a PR?**
+
+Yes / No _(Help can be provided if you need assistance submitting a PR)_
+
 **Additional context**
 Add any other context about the feature request here.
+
+(please also see https://instaloader.github.io/contributing.html for how to suggest a feature)

.github/ISSUE_TEMPLATE/question.md

@@ -0,0 +1,8 @@
+---
+name: ❓ Question
+about: If you have a question about how to use Instaloader that's not well covered by our documentation
+labels: question
+
+---
+
+Your question here...

.github/workflows/stale.yml

@@ -0,0 +1,24 @@
+name: Mark stale issues and pull requests
+
+on:
+  schedule:
+  - cron: "15 16 * * *"
+
+jobs:
+  stale:
+
+    runs-on: ubuntu-latest
+    
+    steps:
+    - uses: actions/stale@v1
+      with:
+        repo-token: ${{ secrets.GITHUB_TOKEN }}
+        stale-issue-message: 'There has been no activity on this issue for an extended period of time. This issue will be closed after further 14 days of inactivity.'
+        stale-pr-message: 'There has been no activity on this Pull Request for an extended period of time. This Pull Request will be closed after further 14 days of inactivity.'
+        stale-issue-label: 'stale'
+        stale-pr-label: 'stale'
+        exempt-issue-label: 'leave open'
+        exempt-pr-label: 'leave open'
+        days-before-stale: 90
+        days-before-close: 14
+        operations-per-run: 7

.gitignore

@@ -1 +1,2 @@
 __pycache__/
+.mypy_cache/

.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 +1,17 @@
+dist: xenial
 language: python
 python:
  - "3.5"
- - "3.5-dev"
  - "3.6"
- - "3.6-dev"
+ - "3.7"
 install:
- - pip install pylint requests
- - pip install -r docs/requirements.txt
+ - pipenv sync --dev
 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
+ - pylint instaloader
+ - mypy -m instaloader
  - make -C docs html SPHINXOPTS="-W -n"
+addons:
+  ssh_known_hosts: aur.archlinux.org
 deploy:
   - provider: pypi
     user: aandergr
@@ -27,3 +29,8 @@ deploy:
     on:
       branch: master
       python: 3.6
+  - provider: script
+    script: deploy/arch/deploy.sh $TRAVIS_TAG
+    on:
+      tags: true
+      python: 3.6

Pipfile

@@ -0,0 +1,12 @@
+[[source]]
+name = "pypi"
+url = "https://pypi.org/simple"
+verify_ssl = true
+
+[dev-packages]
+pylint = "*"
+mypy = "*"
+sphinx = "*"
+
+[packages]
+requests = "*"

Pipfile.lock

@@ -0,0 +1,360 @@
+{
+    "_meta": {
+        "hash": {
+            "sha256": "dfbaa1642735b07bdcc118cb0c9328817b1d558af626b696593db099df863b39"
+        },
+        "pipfile-spec": 6,
+        "requires": {},
+        "sources": [
+            {
+                "name": "pypi",
+                "url": "https://pypi.org/simple",
+                "verify_ssl": true
+            }
+        ]
+    },
+    "default": {
+        "certifi": {
+            "hashes": [
+                "sha256:59b7658e26ca9c7339e00f8f4636cdfe59d34fa37b9b04f6f9e9926b3cece1a5",
+                "sha256:b26104d6835d1f5e49452a26eb2ff87fe7090b89dfcaee5ea2212697e1e1d7ae"
+            ],
+            "version": "==2019.3.9"
+        },
+        "chardet": {
+            "hashes": [
+                "sha256:84ab92ed1c4d4f16916e05906b6b75a6c0fb5db821cc65e70cbd64a3e2a5eaae",
+                "sha256:fc323ffcaeaed0e0a02bf4d117757b98aed530d9ed4531e3e15460124c106691"
+            ],
+            "version": "==3.0.4"
+        },
+        "idna": {
+            "hashes": [
+                "sha256:c357b3f628cf53ae2c4c05627ecc484553142ca23264e593d327bcde5e9c3407",
+                "sha256:ea8b7f6188e6fa117537c3df7da9fc686d485087abf6ac197f9c46432f7e4a3c"
+            ],
+            "version": "==2.8"
+        },
+        "requests": {
+            "hashes": [
+                "sha256:11e007a8a2aa0323f5a921e9e6a2d7e4e67d9877e85773fba9ba6419025cbeb4",
+                "sha256:9cf5292fcd0f598c671cfc1e0d7d1a7f13bb8085e9a590f48c010551dc6c4b31"
+            ],
+            "index": "pypi",
+            "version": "==2.22.0"
+        },
+        "urllib3": {
+            "hashes": [
+                "sha256:b246607a25ac80bedac05c6f282e3cdaf3afb65420fd024ac94435cabe6e18d1",
+                "sha256:dbe59173209418ae49d485b87d1681aefa36252ee85884c31346debd19463232"
+            ],
+            "version": "==1.25.3"
+        }
+    },
+    "develop": {
+        "alabaster": {
+            "hashes": [
+                "sha256:446438bdcca0e05bd45ea2de1668c1d9b032e1a9154c2c259092d77031ddd359",
+                "sha256:a661d72d58e6ea8a57f7a86e37d86716863ee5e92788398526d58b26a4e4dc02"
+            ],
+            "version": "==0.7.12"
+        },
+        "astroid": {
+            "hashes": [
+                "sha256:6560e1e1749f68c64a4b5dee4e091fce798d2f0d84ebe638cf0e0585a343acf4",
+                "sha256:b65db1bbaac9f9f4d190199bb8680af6f6f84fd3769a5ea883df8a91fe68b4c4"
+            ],
+            "version": "==2.2.5"
+        },
+        "babel": {
+            "hashes": [
+                "sha256:af92e6106cb7c55286b25b38ad7695f8b4efb36a90ba483d7f7a6628c46158ab",
+                "sha256:e86135ae101e31e2c8ec20a4e0c5220f4eed12487d5cf3f78be7e98d3a57fc28"
+            ],
+            "version": "==2.7.0"
+        },
+        "certifi": {
+            "hashes": [
+                "sha256:59b7658e26ca9c7339e00f8f4636cdfe59d34fa37b9b04f6f9e9926b3cece1a5",
+                "sha256:b26104d6835d1f5e49452a26eb2ff87fe7090b89dfcaee5ea2212697e1e1d7ae"
+            ],
+            "version": "==2019.3.9"
+        },
+        "chardet": {
+            "hashes": [
+                "sha256:84ab92ed1c4d4f16916e05906b6b75a6c0fb5db821cc65e70cbd64a3e2a5eaae",
+                "sha256:fc323ffcaeaed0e0a02bf4d117757b98aed530d9ed4531e3e15460124c106691"
+            ],
+            "version": "==3.0.4"
+        },
+        "docutils": {
+            "hashes": [
+                "sha256:02aec4bd92ab067f6ff27a38a38a41173bf01bed8f89157768c1573f53e474a6",
+                "sha256:51e64ef2ebfb29cae1faa133b3710143496eca21c530f3f71424d77687764274",
+                "sha256:7a4bd47eaf6596e1295ecb11361139febe29b084a87bf005bf899f9a42edc3c6"
+            ],
+            "version": "==0.14"
+        },
+        "idna": {
+            "hashes": [
+                "sha256:c357b3f628cf53ae2c4c05627ecc484553142ca23264e593d327bcde5e9c3407",
+                "sha256:ea8b7f6188e6fa117537c3df7da9fc686d485087abf6ac197f9c46432f7e4a3c"
+            ],
+            "version": "==2.8"
+        },
+        "imagesize": {
+            "hashes": [
+                "sha256:3f349de3eb99145973fefb7dbe38554414e5c30abd0c8e4b970a7c9d09f3a1d8",
+                "sha256:f3832918bc3c66617f92e35f5d70729187676313caa60c187eb0f28b8fe5e3b5"
+            ],
+            "version": "==1.1.0"
+        },
+        "isort": {
+            "hashes": [
+                "sha256:c40744b6bc5162bbb39c1257fe298b7a393861d50978b565f3ccd9cb9de0182a",
+                "sha256:f57abacd059dc3bd666258d1efb0377510a89777fda3e3274e3c01f7c03ae22d"
+            ],
+            "version": "==4.3.20"
+        },
+        "jinja2": {
+            "hashes": [
+                "sha256:065c4f02ebe7f7cf559e49ee5a95fb800a9e4528727aec6f24402a5374c65013",
+                "sha256:14dd6caf1527abb21f08f86c784eac40853ba93edb79552aa1e4b8aef1b61c7b"
+            ],
+            "version": "==2.10.1"
+        },
+        "lazy-object-proxy": {
+            "hashes": [
+                "sha256:159a745e61422217881c4de71f9eafd9d703b93af95618635849fe469a283661",
+                "sha256:23f63c0821cc96a23332e45dfaa83266feff8adc72b9bcaef86c202af765244f",
+                "sha256:3b11be575475db2e8a6e11215f5aa95b9ec14de658628776e10d96fa0b4dac13",
+                "sha256:3f447aff8bc61ca8b42b73304f6a44fa0d915487de144652816f950a3f1ab821",
+                "sha256:4ba73f6089cd9b9478bc0a4fa807b47dbdb8fad1d8f31a0f0a5dbf26a4527a71",
+                "sha256:4f53eadd9932055eac465bd3ca1bd610e4d7141e1278012bd1f28646aebc1d0e",
+                "sha256:64483bd7154580158ea90de5b8e5e6fc29a16a9b4db24f10193f0c1ae3f9d1ea",
+                "sha256:6f72d42b0d04bfee2397aa1862262654b56922c20a9bb66bb76b6f0e5e4f9229",
+                "sha256:7c7f1ec07b227bdc561299fa2328e85000f90179a2f44ea30579d38e037cb3d4",
+                "sha256:7c8b1ba1e15c10b13cad4171cfa77f5bb5ec2580abc5a353907780805ebe158e",
+                "sha256:8559b94b823f85342e10d3d9ca4ba5478168e1ac5658a8a2f18c991ba9c52c20",
+                "sha256:a262c7dfb046f00e12a2bdd1bafaed2408114a89ac414b0af8755c696eb3fc16",
+                "sha256:acce4e3267610c4fdb6632b3886fe3f2f7dd641158a843cf6b6a68e4ce81477b",
+                "sha256:be089bb6b83fac7f29d357b2dc4cf2b8eb8d98fe9d9ff89f9ea6012970a853c7",
+                "sha256:bfab710d859c779f273cc48fb86af38d6e9210f38287df0069a63e40b45a2f5c",
+                "sha256:c10d29019927301d524a22ced72706380de7cfc50f767217485a912b4c8bd82a",
+                "sha256:dd6e2b598849b3d7aee2295ac765a578879830fb8966f70be8cd472e6069932e",
+                "sha256:e408f1eacc0a68fed0c08da45f31d0ebb38079f043328dce69ff133b95c29dc1"
+            ],
+            "version": "==1.4.1"
+        },
+        "markupsafe": {
+            "hashes": [
+                "sha256:00bc623926325b26bb9605ae9eae8a215691f33cae5df11ca5424f06f2d1f473",
+                "sha256:09027a7803a62ca78792ad89403b1b7a73a01c8cb65909cd876f7fcebd79b161",
+                "sha256:09c4b7f37d6c648cb13f9230d847adf22f8171b1ccc4d5682398e77f40309235",
+                "sha256:1027c282dad077d0bae18be6794e6b6b8c91d58ed8a8d89a89d59693b9131db5",
+                "sha256:24982cc2533820871eba85ba648cd53d8623687ff11cbb805be4ff7b4c971aff",
+                "sha256:29872e92839765e546828bb7754a68c418d927cd064fd4708fab9fe9c8bb116b",
+                "sha256:43a55c2930bbc139570ac2452adf3d70cdbb3cfe5912c71cdce1c2c6bbd9c5d1",
+                "sha256:46c99d2de99945ec5cb54f23c8cd5689f6d7177305ebff350a58ce5f8de1669e",
+                "sha256:500d4957e52ddc3351cabf489e79c91c17f6e0899158447047588650b5e69183",
+                "sha256:535f6fc4d397c1563d08b88e485c3496cf5784e927af890fb3c3aac7f933ec66",
+                "sha256:62fe6c95e3ec8a7fad637b7f3d372c15ec1caa01ab47926cfdf7a75b40e0eac1",
+                "sha256:6dd73240d2af64df90aa7c4e7481e23825ea70af4b4922f8ede5b9e35f78a3b1",
+                "sha256:717ba8fe3ae9cc0006d7c451f0bb265ee07739daf76355d06366154ee68d221e",
+                "sha256:79855e1c5b8da654cf486b830bd42c06e8780cea587384cf6545b7d9ac013a0b",
+                "sha256:7c1699dfe0cf8ff607dbdcc1e9b9af1755371f92a68f706051cc8c37d447c905",
+                "sha256:88e5fcfb52ee7b911e8bb6d6aa2fd21fbecc674eadd44118a9cc3863f938e735",
+                "sha256:8defac2f2ccd6805ebf65f5eeb132adcf2ab57aa11fdf4c0dd5169a004710e7d",
+                "sha256:98c7086708b163d425c67c7a91bad6e466bb99d797aa64f965e9d25c12111a5e",
+                "sha256:9add70b36c5666a2ed02b43b335fe19002ee5235efd4b8a89bfcf9005bebac0d",
+                "sha256:9bf40443012702a1d2070043cb6291650a0841ece432556f784f004937f0f32c",
+                "sha256:ade5e387d2ad0d7ebf59146cc00c8044acbd863725f887353a10df825fc8ae21",
+                "sha256:b00c1de48212e4cc9603895652c5c410df699856a2853135b3967591e4beebc2",
+                "sha256:b1282f8c00509d99fef04d8ba936b156d419be841854fe901d8ae224c59f0be5",
+                "sha256:b2051432115498d3562c084a49bba65d97cf251f5a331c64a12ee7e04dacc51b",
+                "sha256:ba59edeaa2fc6114428f1637ffff42da1e311e29382d81b339c1817d37ec93c6",
+                "sha256:c8716a48d94b06bb3b2524c2b77e055fb313aeb4ea620c8dd03a105574ba704f",
+                "sha256:cd5df75523866410809ca100dc9681e301e3c27567cf498077e8551b6d20e42f",
+                "sha256:e249096428b3ae81b08327a63a485ad0878de3fb939049038579ac0ef61e17e7"
+            ],
+            "version": "==1.1.1"
+        },
+        "mccabe": {
+            "hashes": [
+                "sha256:ab8a6258860da4b6677da4bd2fe5dc2c659cff31b3ee4f7f5d64e79735b80d42",
+                "sha256:dd8d182285a0fe56bace7f45b5e7d1a6ebcbf524e8f3bd87eb0f125271b8831f"
+            ],
+            "version": "==0.6.1"
+        },
+        "mypy": {
+            "hashes": [
+                "sha256:2afe51527b1f6cdc4a5f34fc90473109b22bf7f21086ba3e9451857cf11489e6",
+                "sha256:56a16df3e0abb145d8accd5dbb70eba6c4bd26e2f89042b491faa78c9635d1e2",
+                "sha256:5764f10d27b2e93c84f70af5778941b8f4aa1379b2430f85c827e0f5464e8714",
+                "sha256:5bbc86374f04a3aa817622f98e40375ccb28c4836f36b66706cf3c6ccce86eda",
+                "sha256:6a9343089f6377e71e20ca734cd8e7ac25d36478a9df580efabfe9059819bf82",
+                "sha256:6c9851bc4a23dc1d854d3f5dfd5f20a016f8da86bcdbb42687879bb5f86434b0",
+                "sha256:b8e85956af3fcf043d6f87c91cbe8705073fc67029ba6e22d3468bfee42c4823",
+                "sha256:b9a0af8fae490306bc112229000aa0c2ccc837b49d29a5c42e088c132a2334dd",
+                "sha256:bbf643528e2a55df2c1587008d6e3bda5c0445f1240dfa85129af22ae16d7a9a",
+                "sha256:c46ab3438bd21511db0f2c612d89d8344154c0c9494afc7fbc932de514cf8d15",
+                "sha256:f7a83d6bd805855ef83ec605eb01ab4fa42bcef254b13631e451cbb44914a9b0"
+            ],
+            "index": "pypi",
+            "version": "==0.701"
+        },
+        "mypy-extensions": {
+            "hashes": [
+                "sha256:37e0e956f41369209a3d5f34580150bcacfabaa57b33a15c0b25f4b5725e0812",
+                "sha256:b16cabe759f55e3409a7d231ebd2841378fb0c27a5d1994719e340e4f429ac3e"
+            ],
+            "version": "==0.4.1"
+        },
+        "packaging": {
+            "hashes": [
+                "sha256:0c98a5d0be38ed775798ece1b9727178c4469d9c3b4ada66e8e6b7849f8732af",
+                "sha256:9e1cbf8c12b1f1ce0bb5344b8d7ecf66a6f8a6e91bcb0c84593ed6d3ab5c4ab3"
+            ],
+            "version": "==19.0"
+        },
+        "pygments": {
+            "hashes": [
+                "sha256:36586500a94cd97f8c2c19d251cdb78868d1a822e0e491bfc1d811766aedb772",
+                "sha256:b437bc0d04dc36f1f5b3592985b3e0a3d0af46b7c39199231706d19a4ee63344"
+            ],
+            "version": "==2.4.1"
+        },
+        "pylint": {
+            "hashes": [
+                "sha256:5d77031694a5fb97ea95e828c8d10fc770a1df6eb3906067aaed42201a8a6a09",
+                "sha256:723e3db49555abaf9bf79dc474c6b9e2935ad82230b10c1138a71ea41ac0fff1"
+            ],
+            "index": "pypi",
+            "version": "==2.3.1"
+        },
+        "pyparsing": {
+            "hashes": [
+                "sha256:1873c03321fc118f4e9746baf201ff990ceb915f433f23b395f5580d1840cb2a",
+                "sha256:9b6323ef4ab914af344ba97510e966d64ba91055d6b9afa6b30799340e89cc03"
+            ],
+            "version": "==2.4.0"
+        },
+        "pytz": {
+            "hashes": [
+                "sha256:303879e36b721603cc54604edcac9d20401bdbe31e1e4fdee5b9f98d5d31dfda",
+                "sha256:d747dd3d23d77ef44c6a3526e274af6efeb0a6f1afd5a69ba4d5be4098c8e141"
+            ],
+            "version": "==2019.1"
+        },
+        "requests": {
+            "hashes": [
+                "sha256:11e007a8a2aa0323f5a921e9e6a2d7e4e67d9877e85773fba9ba6419025cbeb4",
+                "sha256:9cf5292fcd0f598c671cfc1e0d7d1a7f13bb8085e9a590f48c010551dc6c4b31"
+            ],
+            "index": "pypi",
+            "version": "==2.22.0"
+        },
+        "six": {
+            "hashes": [
+                "sha256:3350809f0555b11f552448330d0b52d5f24c91a322ea4a15ef22629740f3761c",
+                "sha256:d16a0141ec1a18405cd4ce8b4613101da75da0e9a7aec5bdd4fa804d0e0eba73"
+            ],
+            "version": "==1.12.0"
+        },
+        "snowballstemmer": {
+            "hashes": [
+                "sha256:919f26a68b2c17a7634da993d91339e288964f93c274f1343e3bbbe2096e1128",
+                "sha256:9f3bcd3c401c3e862ec0ebe6d2c069ebc012ce142cce209c098ccb5b09136e89"
+            ],
+            "version": "==1.2.1"
+        },
+        "sphinx": {
+            "hashes": [
+                "sha256:423280646fb37944dd3c85c58fb92a20d745793a9f6c511f59da82fa97cd404b",
+                "sha256:de930f42600a4fef993587633984cc5027dedba2464bcf00ddace26b40f8d9ce"
+            ],
+            "index": "pypi",
+            "version": "==2.0.1"
+        },
+        "sphinxcontrib-applehelp": {
+            "hashes": [
+                "sha256:edaa0ab2b2bc74403149cb0209d6775c96de797dfd5b5e2a71981309efab3897",
+                "sha256:fb8dee85af95e5c30c91f10e7eb3c8967308518e0f7488a2828ef7bc191d0d5d"
+            ],
+            "version": "==1.0.1"
+        },
+        "sphinxcontrib-devhelp": {
+            "hashes": [
+                "sha256:6c64b077937330a9128a4da74586e8c2130262f014689b4b89e2d08ee7294a34",
+                "sha256:9512ecb00a2b0821a146736b39f7aeb90759834b07e81e8cc23a9c70bacb9981"
+            ],
+            "version": "==1.0.1"
+        },
+        "sphinxcontrib-htmlhelp": {
+            "hashes": [
+                "sha256:4670f99f8951bd78cd4ad2ab962f798f5618b17675c35c5ac3b2132a14ea8422",
+                "sha256:d4fd39a65a625c9df86d7fa8a2d9f3cd8299a3a4b15db63b50aac9e161d8eff7"
+            ],
+            "version": "==1.0.2"
+        },
+        "sphinxcontrib-jsmath": {
+            "hashes": [
+                "sha256:2ec2eaebfb78f3f2078e73666b1415417a116cc848b72e5172e596c871103178",
+                "sha256:a9925e4a4587247ed2191a22df5f6970656cb8ca2bd6284309578f2153e0c4b8"
+            ],
+            "version": "==1.0.1"
+        },
+        "sphinxcontrib-qthelp": {
+            "hashes": [
+                "sha256:513049b93031beb1f57d4daea74068a4feb77aa5630f856fcff2e50de14e9a20",
+                "sha256:79465ce11ae5694ff165becda529a600c754f4bc459778778c7017374d4d406f"
+            ],
+            "version": "==1.0.2"
+        },
+        "sphinxcontrib-serializinghtml": {
+            "hashes": [
+                "sha256:c0efb33f8052c04fd7a26c0a07f1678e8512e0faec19f4aa8f2473a8b81d5227",
+                "sha256:db6615af393650bf1151a6cd39120c29abaf93cc60db8c48eb2dddbfdc3a9768"
+            ],
+            "version": "==1.1.3"
+        },
+        "typed-ast": {
+            "hashes": [
+                "sha256:132eae51d6ef3ff4a8c47c393a4ef5ebf0d1aecc96880eb5d6c8ceab7017cc9b",
+                "sha256:18141c1484ab8784006c839be8b985cfc82a2e9725837b0ecfa0203f71c4e39d",
+                "sha256:2baf617f5bbbfe73fd8846463f5aeafc912b5ee247f410700245d68525ec584a",
+                "sha256:3d90063f2cbbe39177e9b4d888e45777012652d6110156845b828908c51ae462",
+                "sha256:4304b2218b842d610aa1a1d87e1dc9559597969acc62ce717ee4dfeaa44d7eee",
+                "sha256:4983ede548ffc3541bae49a82675996497348e55bafd1554dc4e4a5d6eda541a",
+                "sha256:5315f4509c1476718a4825f45a203b82d7fdf2a6f5f0c8f166435975b1c9f7d4",
+                "sha256:6cdfb1b49d5345f7c2b90d638822d16ba62dc82f7616e9b4caa10b72f3f16649",
+                "sha256:7b325f12635598c604690efd7a0197d0b94b7d7778498e76e0710cd582fd1c7a",
+                "sha256:8d3b0e3b8626615826f9a626548057c5275a9733512b137984a68ba1598d3d2f",
+                "sha256:8f8631160c79f53081bd23446525db0bc4c5616f78d04021e6e434b286493fd7",
+                "sha256:912de10965f3dc89da23936f1cc4ed60764f712e5fa603a09dd904f88c996760",
+                "sha256:b010c07b975fe853c65d7bbe9d4ac62f1c69086750a574f6292597763781ba18",
+                "sha256:c908c10505904c48081a5415a1e295d8403e353e0c14c42b6d67f8f97fae6616",
+                "sha256:c94dd3807c0c0610f7c76f078119f4ea48235a953512752b9175f9f98f5ae2bd",
+                "sha256:ce65dee7594a84c466e79d7fb7d3303e7295d16a83c22c7c4037071b059e2c21",
+                "sha256:eaa9cfcb221a8a4c2889be6f93da141ac777eb8819f077e1d09fb12d00a09a93",
+                "sha256:f3376bc31bad66d46d44b4e6522c5c21976bf9bca4ef5987bb2bf727f4506cbb",
+                "sha256:f9202fa138544e13a4ec1a6792c35834250a85958fde1251b6a22e07d1260ae7"
+            ],
+            "markers": "implementation_name == 'cpython'",
+            "version": "==1.3.5"
+        },
+        "urllib3": {
+            "hashes": [
+                "sha256:b246607a25ac80bedac05c6f282e3cdaf3afb65420fd024ac94435cabe6e18d1",
+                "sha256:dbe59173209418ae49d485b87d1681aefa36252ee85884c31346debd19463232"
+            ],
+            "version": "==1.25.3"
+        },
+        "wrapt": {
+            "hashes": [
+                "sha256:4aea003270831cceb8a90ff27c4031da6ead7ec1886023b80ce0dfe0adf61533"
+            ],
+            "version": "==1.11.1"
+        }
+    }
+}

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/basic-usage.rst

@@ -89,6 +89,7 @@ Instaloader supports the following targets:
    Posts tagged with a given location; the location ID is the numerical ID
    Instagram labels a location with (e.g.
    \https://www.instagram.com/explore/locations/**362629379**/plymouth-naval-memorial/).
+   Requires :option:`--login`.
 
    .. versionadded:: 4.2
 
@@ -122,7 +123,7 @@ downloads the pictures and videos and their captions. You can specify
 
 - :option:`--geotags`
    **download geotags** of each post and save them as
-   Google Maps link,
+   Google Maps link (requires :option:`--login`),
 
 For a reference of all supported command line options, see
 :ref:`command-line-options`.

docs/cli-options.rst

@@ -61,8 +61,7 @@ What to Download of each Post
 
    **Download geotags** when available. Geotags are stored as a text file with
    the location's name and a Google Maps link. This requires an additional
-   request to the Instagram server for each picture, which is why it is disabled
-   by default.
+   request to the Instagram server for each picture. Requires :option:`--login`.
 
 .. option:: --comments, -C
 

docs/codesnippets/113_only_one_per_user.py

@@ -2,13 +2,13 @@ import instaloader
 
 L = instaloader.Instaloader()
 
-posts = L.get_hashtag_posts('milfgarden')
+posts = L.get_hashtag_posts('urbanphotography')
 
 users = set()
 
 for post in posts:
     if not post.owner_profile in users:
-        L.download_post(post, '#milfgarden')
+        L.download_post(post, '#urbanphotography')
         users.add(post.owner_profile)
     else:
         print("{} from {} skipped.".format(post, post.owner_profile))

docs/codesnippets/121_since_until.py

@@ -5,7 +5,7 @@ import instaloader
 
 L = instaloader.Instaloader()
 
-posts = L.get_hashtag_posts('milfgarden')
+posts = L.get_hashtag_posts('urbanphotography')
 # or
 # posts = instaloader.Profile.from_username(L.context, PROFILE).get_posts()
 
@@ -14,4 +14,4 @@ UNTIL = datetime(2015, 3, 1)
 
 for post in takewhile(lambda p: p.date > UNTIL, dropwhile(lambda p: p.date > SINCE, posts)):
     print(post.date)
-    L.download_post(post, '#milfgarden')
+    L.download_post(post, '#urbanphotography')

docs/codesnippets/194_top_x_of_user.py

@@ -9,7 +9,9 @@ X_percentage = 10    # percentage of posts that should be downloaded
 L = Instaloader()
 
 profile = Profile.from_username(L.context, PROFILE)
-posts_sorted_by_likes = sorted(profile.get_posts(), key = lambda p: p.likes + p.comments)
+posts_sorted_by_likes = sorted(profile.get_posts(),
+                               key=lambda p: p.likes + p.comments,
+                               reverse=True)
 
 for post in islice(posts_sorted_by_likes, ceil(profile.mediacount * X_percentage / 100)):
     L.download_post(post, PROFILE)

docs/conf.py

@@ -47,7 +47,7 @@ autodoc_default_flags = ['show-inheritance', 'members', 'undoc-members']
 autodoc_member_order = 'bysource'
 
 intersphinx_mapping = {'python': ('https://docs.python.org/3', None),
-                       'requests': ('http://docs.python-requests.org/en/master', None)}
+                       'requests': ('https://requests.kennethreitz.org/en/master/', None)}
 
 extlinks = {'issue': ('https://github.com/instaloader/instaloader/issues/%s', 'issue #')}
 

docs/contributing.rst

@@ -15,10 +15,8 @@ Reporting Bugs
 --------------
 
 If you encounter a bug, do not hesitate to report it in our
-`Issue Tracker <https://github.com/instaloader/instaloader/issues>`__. Since
-Instaloader is actively developed, the majority of bugs is fixed within only
-**4 days** after being reported. When reporting a problem, please keep the
-following in mind:
+`Issue Tracker <https://github.com/instaloader/instaloader/issues>`__. When
+reporting a problem, please keep the following in mind:
 
 - Ensure you **use the latest version** of Instaloader. The currently-installed
   version can be found out with ``instaloader --version``.
@@ -66,6 +64,16 @@ few things to consider:
 Suggesting Features
 -------------------
 
+.. goal-start
+
+Instaloader's goal is to mimick the browser's behavior to access the data that
+is available through the Instagram web interface, pack this data into complete
+and easily-(re)usable python objects, and provide a user interface for the most
+common downloading and metadata collection tasks, without changing any of the
+online data.
+
+.. goal-end
+
 If you have an idea of how Instaloader should be enhanced, but do not want to
 implement the feature yourself, feel free to open a ticket in our 
 `Issue Tracker <https://github.com/instaloader/instaloader/issues>`__.
@@ -82,6 +90,9 @@ Please consider the following:
   invoke the new function? Which problem would it solve? If new information is
   obtained, how would it be further processed?
 
+- If not obvious, briefly motivate how your suggested feature **conforms with
+  Instaloader's project goal**.
+
 - **Be patient**. Naturally, bugs and pull requests have a higher priority than
   feature suggestions. Keep in mind that this is a free software project, and
   unfortunately we only have limited time to work on it.

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__ = '4.2.2'
+__version__ = '4.2.10'
 
 
 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

@@ -98,6 +98,9 @@ def _main(instaloader: Instaloader, targetlist: List[str],
             else:
                 instaloader.interactive_login(username)
         instaloader.context.log("Logged in as %s." % username)
+    # since 4.2.9 login is required for geotags
+    if instaloader.download_geotags and not instaloader.context.is_logged_in:
+        instaloader.context.error("Warning: Use --login to download geotags of posts.")
     # Try block for KeyboardInterrupt (save session on ^C)
     profiles = set()
     anonymous_retry_profiles = set()
@@ -223,7 +226,8 @@ def main():
                            help="Download all followees of profile. Requires --login. "
                                 "Consider using :feed rather than @yourself.")
     g_targets.add_argument('_hashtag', nargs='*', metavar='"#hashtag"', help="Download #hashtag.")
-    g_targets.add_argument('_location', nargs='*', metavar='%location_id', help="Download %%location_id.")
+    g_targets.add_argument('_location', nargs='*', metavar='%location_id',
+                           help="Download %%location_id. Requires --login.")
     g_targets.add_argument('_feed', nargs='*', metavar=":feed",
                            help="Download pictures from your feed. Requires --login.")
     g_targets.add_argument('_stories', nargs='*', metavar=":stories",
@@ -258,7 +262,7 @@ def main():
                         help='Download geotags when available. Geotags are stored as a '
                              'text file with the location\'s name and a Google Maps link. '
                              'This requires an additional request to the Instagram '
-                             'server for each picture, which is why it is disabled by default.')
+                             'server for each picture. Requires --login.')
     g_post.add_argument('-C', '--comments', action='store_true',
                         help='Download and update comments for each post. '
                              'This requires an additional request to the Instagram '
@@ -331,7 +335,6 @@ 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 +396,6 @@ 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/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 +47,6 @@ 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"
     return call
 
 
@@ -108,7 +108,17 @@ 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
 
 
@@ -152,11 +162,10 @@ 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}"
@@ -177,7 +186,7 @@ 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):
@@ -190,13 +199,10 @@ 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):
@@ -238,17 +244,43 @@ class Instaloader:
             filename += '.json.xz'
         else:
             filename += '.json'
+        os.makedirs(os.path.dirname(filename), exist_ok=True)
         save_structure_to_file(structure, filename)
         if isinstance(structure, (Post, StoryItem)):
             # log 'json ' message when saving Post or StoryItem
             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()}
+                    'owner': comment.owner._asdict(),
+                    'likes_count': comment.likes_count}
+
+        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)
+                else:
+                    unique_comments_list[-1]['likes_count'] = y.get('likes_count')
+                    if 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:
@@ -257,18 +289,10 @@ 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:
@@ -279,11 +303,11 @@ 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:
@@ -307,7 +331,7 @@ 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:
@@ -329,12 +353,12 @@ 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'
@@ -348,9 +372,11 @@ 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
+        os.makedirs(os.path.dirname(filename), exist_ok=True)
         self.context.write_raw(profile_pic_bytes if profile_pic_bytes else profile_pic_response, filename)
         if date_object:
             os.utime(filename, (datetime.now().timestamp(), date_object.timestamp()))
@@ -361,8 +387,10 @@ class Instaloader:
         """Saves internally stored :class:`requests.Session` object.
 
         :param filename: Filename, or None to use default filename.
+        :raises LoginRequiredException: If called without being logged in.
         """
         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):
@@ -396,7 +424,8 @@ 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:
@@ -409,13 +438,13 @@ 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.
 
@@ -483,6 +512,7 @@ class Instaloader:
         To use this, one needs to be logged in
 
         :param userids: List of user IDs to be processed in terms of downloading their stories, or None.
+        :raises LoginRequiredException: If called without being logged in.
         """
 
         if not userids:
@@ -493,6 +523,7 @@ 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]
@@ -518,6 +549,7 @@ class Instaloader:
         :param filename_target: Replacement for {target} in dirname_pattern and filename_pattern
                or None if profile name should be used instead
         :param storyitem_filter: function(storyitem), which returns True if given StoryItem should be downloaded
+        :raises LoginRequiredException: If called without being logged in.
         """
 
         if not userids:
@@ -541,7 +573,7 @@ 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`
@@ -577,6 +609,7 @@ class Instaloader:
         .. versionadded:: 4.1
 
         :param user: ID or Profile of the user whose highlights should get fetched.
+        :raises LoginRequiredException: If called without being logged in.
         """
 
         userid = user if isinstance(user, int) else user.userid
@@ -606,6 +639,7 @@ class Instaloader:
         :param filename_target: Replacement for {target} in dirname_pattern and filename_pattern
                or None if profile name and the highlights' titles should be used instead
         :param storyitem_filter: function(storyitem), which returns True if given StoryItem should be downloaded
+        :raises LoginRequiredException: If called without being logged in.
         """
         for user_highlight in self.get_highlights(user):
             name = user_highlight.owner_username
@@ -618,10 +652,11 @@ 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
 
@@ -630,6 +665,7 @@ class Instaloader:
         """Get Posts of the user's feed.
 
         :return: Iterator over Posts of the user's feed.
+        :raises LoginRequiredException: If called without being logged in.
         """
 
         data = self.context.graphql_query("d6f4427fbe92d846298cf93df0b937d3", {})["data"]
@@ -663,6 +699,7 @@ class Instaloader:
         :param max_count: Maximum count of pictures to download
         :param fast_update: If true, abort when first already-downloaded picture is encountered
         :param post_filter: function(post), which returns True if given picture should be downloaded
+        :raises LoginRequiredException: If called without being logged in.
         """
         self.context.log("Retrieving pictures from your feed...")
         count = 1
@@ -688,9 +725,11 @@ class Instaloader:
         :param max_count: Maximum count of pictures to download
         :param fast_update: If true, abort when first already-downloaded picture is encountered
         :param post_filter: function(post), which returns True if given picture should be downloaded
+        :raises LoginRequiredException: If called without being logged in.
         """
         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
@@ -704,12 +743,17 @@ class Instaloader:
                 if fast_update and not downloaded:
                     break
 
+    @_requires_login
     def get_location_posts(self, location: str) -> Iterator[Post]:
         """Get Posts which are listed by Instagram for a given Location.
 
         :return:  Iterator over Posts of a location's posts
+        :raises LoginRequiredException: If called without being logged in.
 
         .. versionadded:: 4.2
+
+        .. versionchanged:: 4.2.9
+           Require being logged in (as required by Instagram)
         """
         has_next_page = True
         end_cursor = None
@@ -724,6 +768,7 @@ class Instaloader:
             has_next_page = location_data['page_info']['has_next_page']
             end_cursor = location_data['page_info']['end_cursor']
 
+    @_requires_login
     def download_location(self, location: str,
                           max_count: Optional[int] = None,
                           post_filter: Optional[Callable[[Post], bool]] = None,
@@ -739,8 +784,12 @@ class Instaloader:
         :param max_count: Maximum count of pictures to download
         :param post_filter: function(post), which returns True if given picture should be downloaded
         :param fast_update: If true, abort when first already-downloaded picture is encountered
+        :raises LoginRequiredException: If called without being logged in.
 
         .. versionadded:: 4.2
+
+        .. versionchanged:: 4.2.9
+           Require being logged in (as required by Instagram)
         """
         self.context.log("Retrieving pictures for location {}...".format(location))
         count = 1
@@ -762,13 +811,14 @@ class Instaloader:
         """Get Posts which are worthy of exploring suggested by Instagram.
 
         :return: Iterator over Posts of the user's suggested posts.
+        :raises LoginRequiredException: If called without being logged in.
         """
         data = self.context.get_json('explore/', {})
         yield from (Post(self.context, node)
                     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."""
@@ -823,8 +873,6 @@ 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():
@@ -833,7 +881,7 @@ 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
 
@@ -926,13 +974,15 @@ 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
 
 
@@ -47,7 +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()
@@ -56,21 +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):
@@ -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
@@ -211,7 +212,7 @@ class InstaloaderContext:
             raise TwoFactorAuthRequiredException("Login error: two-factor authentication required.")
         if resp_json.get('checkpoint_url'):
             raise ConnectionException("Login: Checkpoint required. Point your browser to "
-                                      "https://www.instagram.com{}, "
+                                      "https://www.instagram.com{} - "
                                       "follow the instructions, then retry.".format(resp_json.get('checkpoint_url')))
         if resp_json['status'] != 'ok':
             if 'message' in resp_json:
@@ -265,6 +266,72 @@ class InstaloaderContext:
         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, 'iphone': 100}
+        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.
@@ -278,36 +345,22 @@ 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()]
+        is_iphone_query = host == 'i.instagram.com'
         sess = session if session else self._session
         try:
             self.do_sleep()
+            if is_graphql_query:
+                self._ratecontrol_graphql_query(params['query_hash'])
+            if is_iphone_query:
+                self._ratecontrol_graphql_query('iphone')
             resp = sess.get('https://{0}/{1}'.format(host, path), params=params, allow_redirects=False)
             while resp.is_redirect:
                 redirect_url = resp.headers['location']
                 self.log('\nHTTP redirect from https://{0}/{1} to {2}'.format(host, path, redirect_url))
+                if redirect_url.startswith('https://www.instagram.com/accounts/login'):
+                    # alternate rate limit exceeded behavior
+                    raise TooManyRequestsException("429 Too Many Requests: redirected to login")
                 if redirect_url.startswith('https://{}/'.format(host)):
                     resp = sess.get(redirect_url if redirect_url.endswith('/') else redirect_url + '/',
                                     params=params, allow_redirects=False)
@@ -326,7 +379,18 @@ class InstaloaderContext:
                 match = re.search(r'window\._sharedData = (.*);</script>', resp.text)
                 if match is None:
                     raise ConnectionException("Could not find \"window._sharedData\" in html response.")
-                return json.loads(match.group(1))
+                resp_json = json.loads(match.group(1))
+                entry_data = resp_json.get('entry_data')
+                post_or_profile_page = list(entry_data.values())[0] if entry_data is not None else None
+                if post_or_profile_page is None:
+                    raise ConnectionException("\"window._sharedData\" does not contain required keys.")
+                # If GraphQL data is missing in `window._sharedData`, search for it in `__additionalDataLoaded`.
+                if 'graphql' not in post_or_profile_page[0]:
+                    match = re.search(r'window\.__additionalDataLoaded\([^{]+{"graphql":({.*})}\);</script>',
+                                      resp.text)
+                    if match is not None:
+                        post_or_profile_page[0]['graphql'] = json.loads(match.group(1))
+                return resp_json
             else:
                 resp_json = resp.json()
             if 'status' in resp_json and resp_json['status'] != "ok":
@@ -341,20 +405,11 @@ 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.do_sleep()
+                if is_graphql_query and isinstance(err, TooManyRequestsException):
+                    self._ratecontrol_graphql_query(params['query_hash'], untracked_queries=True)
+                if is_iphone_query and isinstance(err, TooManyRequestsException):
+                    self._ratecontrol_graphql_query('iphone', 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)
@@ -494,6 +549,6 @@ 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 +17,17 @@ 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', 'likes_count'])
+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."
+PostCommentAnswer.likes_count.__doc__ = "Number of likes on 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 +68,9 @@ 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):
@@ -127,7 +133,7 @@ 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
@@ -135,10 +141,11 @@ 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:
+    def _rhx_gis(self) -> Optional[str]:
         self._obtain_metadata()
         return self._rhx_gis_str
 
@@ -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 +324,73 @@ 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']),
+                                     likes_count=node['edge_liked_by']['count'])
+
+        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."""
@@ -330,10 +410,17 @@ class Post:
 
     @property
     def location(self) -> Optional[PostLocation]:
-        """If the Post has a location, returns PostLocation namedtuple with fields 'id', 'lat' and 'lng' and 'name'."""
+        """
+        If the Post has a location, returns PostLocation namedtuple with fields 'id', 'lat' and 'lng' and 'name'.
+
+        .. versionchanged:: 4.2.9
+           Require being logged in (as required by Instagram), return None if not logged-in.
+        """
         loc = self._field("location")
         if self._location or not loc:
             return self._location
+        if not self._context.is_logged_in:
+            return None
         location_id = int(loc['id'])
         if any(k not in loc for k in ('name', 'slug', 'has_public_page', 'lat', 'lng')):
             loc = self._context.get_json("explore/locations/{0}/".format(location_id),
@@ -373,8 +460,9 @@ 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:
@@ -435,10 +523,11 @@ 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
 
@@ -553,6 +642,7 @@ 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 +809,7 @@ 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 +872,7 @@ 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 +899,8 @@ 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 +914,7 @@ 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 +930,14 @@ 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 +1002,7 @@ 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 +1045,13 @@ 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)
 
 

setup.py

@@ -60,6 +60,7 @@ setup(
         'Programming Language :: Python :: 3.5',
         'Programming Language :: Python :: 3.6',
         'Programming Language :: Python :: 3.7',
+        'Programming Language :: Python :: 3.8',
         'Programming Language :: Python :: 3 :: Only',
         'Topic :: Internet',
         'Topic :: Multimedia :: Graphics'

test/instaloader_unittests.py

@@ -5,6 +5,7 @@ import shutil
 import tempfile
 import unittest
 from itertools import islice
+from typing import Dict, List
 
 import instaloader
 
@@ -22,7 +23,7 @@ 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()  # type: Dict[str, List[float]]
 
 
 class TestInstaloaderAnonymously(unittest.TestCase):
@@ -35,11 +36,13 @@ 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
+        # pylint:disable=protected-access
+        self.L.context._graphql_query_timestamps = instaloadercontext_query_timestamps.copy()
 
     def tearDown(self):
+        # pylint:disable=global-statement,protected-access
         global instaloadercontext_query_timestamps
-        instaloadercontext_query_timestamps = self.L.context.query_timestamps
+        instaloadercontext_query_timestamps = self.L.context._graphql_query_timestamps.copy()
         self.L.close()
         os.chdir('/')
         print("Removing {}".format(self.dir))
@@ -53,16 +56,17 @@ class TestInstaloaderAnonymously(unittest.TestCase):
                 self.assertTrue(post.date_utc < previous_post.date_utc)
             previous_post = post
 
-    @unittest.SkipTest
+    @unittest.skip('')
     def test_public_profile_download(self):
-        self.L.download_profile(PUBLIC_PROFILE, profile_pic=False, fast_update=True)
-        self.L.download_profile(PUBLIC_PROFILE, profile_pic=False, fast_update=True)
+        profiles = {self.L.check_profile_id(PUBLIC_PROFILE)}
+        self.L.download_profiles(profiles, profile_pic=False, fast_update=True, raise_errors=True)
+        self.L.download_profiles(profiles, profile_pic=False, fast_update=True, raise_errors=True)
 
     def test_public_profile_paging(self):
         self.post_paging_test(instaloader.Profile.from_username(self.L.context, PUBLIC_PROFILE).get_posts())
 
     def test_profile_pic_download(self):
-        self.L.download_profile(PUBLIC_PROFILE, profile_pic_only=True)
+        self.L.download_profiles({self.L.check_profile_id(PUBLIC_PROFILE)}, posts=False, raise_errors=True)
 
     def test_hashtag_download(self):
         self.L.download_hashtag(HASHTAG, NORMAL_MAX_COUNT)
@@ -73,15 +77,6 @@ class TestInstaloaderAnonymously(unittest.TestCase):
             if count == PAGING_MAX_COUNT:
                 break
 
-    def test_location_download(self):
-        self.L.download_location(LOCATION, NORMAL_MAX_COUNT)
-
-    def test_location_paging(self):
-        for count, post in enumerate(self.L.get_location_posts(LOCATION)):
-            print(post)
-            if count == PAGING_MAX_COUNT:
-                break
-
     def test_get_id_by_username(self):
         self.assertEqual(PUBLIC_PROFILE_ID,
                          instaloader.Profile.from_username(self.L.context, PUBLIC_PROFILE).userid)
@@ -116,13 +111,13 @@ class TestInstaloaderLoggedIn(TestInstaloaderAnonymously):
         super().setUp()
         self.L.load_session_from_file(OWN_USERNAME)
 
-    @unittest.SkipTest
+    @unittest.skip('')
     def test_stories_download(self):
         self.L.download_stories()
 
-    @unittest.SkipTest
+    @unittest.skip('')
     def test_private_profile_download(self):
-        self.L.download_profile(PRIVATE_PROFILE, download_stories=True)
+        self.L.download_profiles({self.L.check_profile_id(PRIVATE_PROFILE)}, stories=True, raise_errors=True)
 
     def test_stories_paging(self):
         for user_story in self.L.get_stories():
@@ -141,9 +136,6 @@ 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)
 
@@ -167,8 +159,8 @@ class TestInstaloaderLoggedIn(TestInstaloaderAnonymously):
 
     def test_followees_and_stories(self):
         profile = instaloader.Profile.from_username(self.L.context, OWN_USERNAME)
-        for f in islice(profile.get_followees(), PAGING_MAX_COUNT):
-            self.L.download_profile(f.username, profile_pic=False, download_stories_only=True)
+        followees = set(islice(profile.get_followees(), PAGING_MAX_COUNT))
+        self.L.download_profiles(followees, profile_pic=False, stories=True, posts=False, raise_errors=True)
 
     def test_get_followees(self):
         profile = instaloader.Profile.from_username(self.L.context, OWN_USERNAME)
@@ -192,6 +184,15 @@ class TestInstaloaderLoggedIn(TestInstaloaderAnonymously):
             if count == PAGING_MAX_COUNT:
                 break
 
+    def test_location_download(self):
+        self.L.download_location(LOCATION, NORMAL_MAX_COUNT)
+
+    def test_location_paging(self):
+        for count, post in enumerate(self.L.get_location_posts(LOCATION)):
+            print(post)
+            if count == PAGING_MAX_COUNT:
+                break
+
 
 if __name__ == '__main__':
     unittest.main()