Release of version 4.2.4

Freeze pylint version to 2.3.1.

.travis.yml

@@ -5,10 +5,10 @@ python:
  - "3.6"
  - "3.6-dev"
 install:
- - pip install pylint requests
+ - pip install pylint~=2.3.1 requests
  - pip install -r docs/requirements.txt
 script:
- - python3 -m pylint -r n -d bad-whitespace,missing-docstring,too-many-arguments,locally-disabled,line-too-long,too-many-public-methods,too-many-lines,too-many-instance-attributes,too-many-locals,too-many-branches,too-many-statements,inconsistent-return-statements,invalid-name,wildcard-import,unused-wildcard-import,no-else-return,cyclic-import,unnecessary-pass instaloader
+ - python3 -m pylint -r n -d bad-whitespace,missing-docstring,too-many-arguments,locally-disabled,line-too-long,no-else-raise,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
  - make -C docs html SPHINXOPTS="-W -n"
 deploy:
   - provider: pypi

LICENSE

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

docs/_static/instaloader.css

@@ -0,0 +1,75 @@
+@import url(bootstrap-4.1.3.min.css);
+a {
+  color: #008d06; }
+  a:hover, a.current, a.active {
+    color: #f48400; }
+  a.current, a.active {
+    font-weight: 500; }
+
+.doc-sidebar a:hover, .modal-body a:hover {
+  text-decoration: none; }
+
+code {
+  color: #212529; }
+
+.highlight {
+  border-radius: 0.3em; }
+  .highlight pre {
+    padding: 0.7em;
+    color: #fff; }
+  .highlight .c1 {
+    color: #008d06; }
+  .highlight .k, .highlight .kn, .highlight .ow {
+    color: #f48400;
+    font-weight: bold; }
+  .highlight .nb {
+    color: #f48400; }
+  .highlight .s1, .highlight .s2, .highlight .mi {
+    color: #ff7efd; }
+
+.doc-content {
+  padding-top: 0.5em;
+  top: 3.5625em;
+  position: fixed;
+  bottom: 0;
+  overflow-y: auto; }
+
+.doc-sidebar {
+  position: fixed;
+  padding-top: 0.5em;
+  top: 3.5625em;
+  bottom: 0;
+  right: 0;
+  overflow-y: auto; }
+  .doc-sidebar ul {
+    list-style-type: none;
+    padding-left: 1em; }
+    .doc-sidebar ul.current {
+      padding-left: 0; }
+  .doc-sidebar li {
+    padding-top: 0.2em;
+    padding-bottom: 0.2em; }
+
+.admonition {
+  border-radius: 0.3em;
+  border: 1px solid #ccc;
+  background-color: #f8f9fa; }
+  .admonition .admonition-title {
+    color: #ff7efd; }
+
+.topic {
+  border-radius: 0.3em;
+  background-color: #f8f9fa; }
+
+.nav-link {
+  padding-top: 0;
+  padding-bottom: 0; }
+
+.btn-success {
+  background-color: #008d06;
+  border-color: #008d06; }
+  .btn-success:hover {
+    background-color: #f48400;
+    border-color: #f48400; }
+
+/*# sourceMappingURL=instaloader.css.map */

docs/_static/instaloader.js

@@ -0,0 +1,22 @@
+$(function () {
+    $('[data-toggle="tooltip"]').tooltip();
+
+    $('.doc-sidebar > ul > li.current').attr("id", "localtoc");
+    $('#localtoc ul').addClass("nav flex-column");
+    $('#localtoc ul li').addClass("nav-item");
+    $('#localtoc ul li a').addClass("nav-link");
+    $('.doc-content').scrollspy({target: '#localtoc'});
+
+    const top_href = '#' + $('.section:first').attr("id");
+    $('#localtoc > a.current').attr("href", top_href);
+
+    $('#navbarToc a').on("click", function () {
+        const href = $(this).attr("href");
+        if (href === '#') {
+            window.location.href = top_href;
+        } else {
+            window.location.href = href;
+        }
+        $('#navbarToc').modal('hide');
+    });
+});

docs/_static/instaloader.scss

@@ -0,0 +1,117 @@
+@import 'bootstrap-4.1.3.min.css';
+
+$color_instaloader_main: #008d06;
+$color_instaloader_accent: #f48400;
+$color_instaloader_hyper: #ff7efd;
+$color_normal_text: #212529;
+$color_light_bg: #f8f9fa;
+
+a {
+  color: $color_instaloader_main;
+
+  &:hover, &.current, &.active {
+    color: $color_instaloader_accent;
+  }
+
+  &.current, &.active {
+    font-weight: 500;
+  }
+}
+
+.doc-sidebar, .modal-body {
+  a:hover {
+    text-decoration: none
+  }
+}
+
+code {
+  color: $color_normal_text;
+}
+
+.highlight {
+  border-radius: 0.3em;
+
+  pre {
+    padding: 0.7em;
+    color: #fff;
+  }
+
+  .c1 {
+    color: $color_instaloader_main
+  }
+
+  .k, .kn, .ow {
+    color: $color_instaloader_accent;
+    font-weight: bold
+  }
+
+  .nb {
+    color: $color_instaloader_accent
+  }
+
+  .s1, .s2, .mi {
+    color: $color_instaloader_hyper
+  }
+}
+
+.doc-content {
+  padding-top: 0.5em;
+  top: 3.5625em;
+  position: fixed;
+  bottom: 0;
+  overflow-y: auto;
+}
+
+.doc-sidebar {
+  position: fixed;
+  padding-top: 0.5em;
+  top: 3.5625em;
+  bottom: 0;
+  right: 0;
+  overflow-y: auto;
+
+  ul {
+    list-style-type: none;
+    padding-left: 1em;
+
+    &.current {
+      padding-left: 0;
+    }
+  }
+
+  li {
+    padding-top: 0.2em;
+    padding-bottom: 0.2em;
+
+  }
+}
+
+.admonition {
+  border-radius: 0.3em;
+  border: 1px solid #ccc;
+  background-color: $color_light_bg;
+
+  .admonition-title {
+    color: $color_instaloader_hyper;
+  }
+}
+
+.topic {
+  border-radius: 0.3em;
+  background-color: $color_light_bg;
+}
+
+.nav-link {
+  padding-top: 0;
+  padding-bottom: 0;
+}
+
+.btn-success {
+  background-color: $color_instaloader_main;
+  border-color: $color_instaloader_main;
+
+  &:hover {
+    background-color: $color_instaloader_accent;
+    border-color: $color_instaloader_accent;
+  }
+}

docs/_static/style.css

@@ -1,28 +0,0 @@
-code {
-    color: #222;
-    background-color: #f5f5f5;
-}
-
-dd {
-    padding-left: 8px;
-}
-
-dl.option dd {
-    padding-left: 12px;
-}
-
-a {
-    color: #008d06;
-}
-
-a:hover {
-    color: #f48400;
-}
-
-body {
-    font-size: 16px;
-}
-
-.versionmodified {
-    font-size: 14px;
-}

docs/_templates/globaltoc.html

@@ -1,14 +0,0 @@
-<li class="dropdown globaltoc-container">
-  <a role="button"
-     id="dLabelGlobalToc"
-     data-toggle="dropdown"
-     data-target="#"
-     href="{{ pathto(master_doc) }}">{{ theme_navbar_site_name }} <b class="caret"></b></a>
-  <ul class="dropdown-menu globaltoc"
-      role="menu"
-      aria-labelledby="dLabelGlobalToc">
-    {{ toctree(maxdepth=theme_globaltoc_depth|toint, collapse=False, includehidden=theme_globaltoc_includehidden|tobool) }}
-    <li role="separator" class="divider"></li>
-    <li class="toctree-l1"><a class="reference internal" href="genindex.html">Index</a></li>
-  </ul>
-</li>

docs/_templates/layout.html

@@ -1,18 +1,118 @@
 {% extends "!layout.html" %}
+
+{% set html5_doctype = True %}
+
+{% set script_files = script_files + ['_static/bootstrap-4.1.3.bundle.min.js', '_static/instaloader.js'] %}
+
 {% block htmltitle %}
   {% if pagename == "index" %}
-  <title>{{ title|striptags|e }}</title>
+    <title>{{ title|striptags|e }}</title>
   {% else %}
-  <title>{{ title|striptags|e }}{{ titlesuffix }}</title>
+    <title>{{ title|striptags|e }}{{ titlesuffix }}</title>
   {% endif %}
 {% endblock %}
+
 {% block extrahead %}
-{{ super() }}
-  <meta name="google-site-verification" content="FNUsDdkOJM9obm9QEdrNBVd9AtAzHzA-aaSMCUrS6C8" />
+  {{ super() }}
+  <meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
+  <meta name="google-site-verification" content="FNUsDdkOJM9obm9QEdrNBVd9AtAzHzA-aaSMCUrS6C8"/>
   {% if pagename == "index" %}
-  <link rel="canonical" href="https://instaloader.github.io/" />
+    <link rel="canonical" href="https://instaloader.github.io/"/>
   {% else %}
-  <link rel="canonical" href="https://instaloader.github.io/{{ pagename }}.html" />
+    <link rel="canonical" href="https://instaloader.github.io/{{ pagename }}.html"/>
   {% endif %}
-  <script async defer src="https://buttons.github.io/buttons.js"></script>
 {% endblock %}
+
+{% block header %}
+  <nav class="navbar navbar-expand-sm navbar-light bg-light fixed-top border-bottom">
+    <a class="navbar-brand" href="{{ pathto(master_doc) }}">
+      <img src="{{ pathto('_static/' + logo, 1) }}" width="30" height="30" class="d-inline-block align-top" alt="logo">
+      Instaloader
+    </a>
+    <ul class="navbar-nav mr-auto">
+      <li class="nav-item ml-0 ml-sm-2 ml-md-0">
+        <a target="_blank" class="nav-link"
+           href="https://github.com/instaloader/instaloader/releases/tag/v{{ current_release }}"
+           title="Released on {{ current_release_date }}" data-toggle="tooltip">v<b>{{ current_release }}</b></a>
+      </li>
+    </ul>
+    <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbarLinks"
+            aria-controls="navbarLinks" aria-expanded="false" aria-label="Toggle navigation">
+      <span class="navbar-toggler-icon"></span>
+    </button>
+    <div class="collapse navbar-collapse" id="navbarLinks">
+      <ul class="navbar-nav ml-auto">
+        <li class="nav-item">
+          <a target="_blank" class="nav-link" href="https://github.com/instaloader/instaloader/issues">Issues</a>
+        </li>
+        <li class="nav-item">
+          <a target="_blank" class="nav-link" href="https://github.com/instaloader/instaloader/releases">Releases</a>
+        </li>
+        <li class="nav-item">
+          <a target="_blank" class="nav-link" href="https://github.com/instaloader/instaloader">GitHub</a>
+        </li>
+        <li class="nav-item d-sm-none d-lg-block">
+          <a target="_blank" class="nav-link" href="https://saythanks.io/to/aandergr">Say Thanks!</a>
+        </li>
+      </ul>
+      <form class="form-inline" action="search.html" method="get">
+        <div class="input-group my-2 my-sm-0 ml-2">
+          <input class="form-control" type="search" placeholder="Search" aria-label="Search" name="q">
+          <div class="input-group-append">
+            <button class="btn btn-success btn-small" type="submit">Go</button>
+          </div>
+        </div>
+      </form>
+    </div>
+    {% if pagename != "index" %}
+      <button type="button" class="btn btn-success d-md-none btn-small ml-2" data-toggle="modal"
+              data-target="#navbarToc">
+        TOC
+      </button>
+    {% endif %}
+  </nav>
+  {% if pagename != "index" %}
+    <div class="modal fade" id="navbarToc" tabindex="-1" role="dialog"
+         aria-hidden="true" aria-labelledby="navbarTocTitle">
+      <div class="modal-dialog modal-dialog-centered" role="document">
+        <div class="modal-content">
+          <div class="modal-header">
+            <h5 class="modal-title" id="navbarTocTitle">Contents</h5>
+            <button type="button" class="close" data-dismiss="modal" aria-label="Close">
+              <span aria-hidden="true">&times;</span>
+            </button>
+          </div>
+          <div class="modal-body">
+            {{ toctree(maxdepth=-1) }}
+          </div>
+        </div>
+      </div>
+    </div>
+  {% endif %}
+{% endblock %}
+
+{% block relbar1 %}{% endblock %}
+{% block relbar2 %}{% endblock %}
+{% block footer %}{% endblock %}
+{% block content %}
+  <div class="container-fluid row">
+    <div class="col-12 {% if pagename != "index" %}col-md-9 col-xl-10{% endif %} doc-content">
+      {% block body %}{% endblock %}
+    </div>
+    {% if pagename != "index" %}
+      <div class="d-none col-md-3 col-xl-2 bg-light doc-sidebar d-md-flex flex-column border-left">
+
+        <h3>{{ _('Table of Contents') }}</h3>
+        {{ toctree(maxdepth=-1) }}
+
+        <div class="d-flex justify-content-between small mt-auto mb-2">
+          <a class="reference internal{% if pagename == "genindex" %} current{% endif %}" href="genindex.html">Index</a>
+          {% if pagename != "genindex" and pagename != "search" %}
+            <a class="reference external"
+               href="https://github.com/instaloader/instaloader/edit/master/docs/{{ pagename }}.rst">Edit this page</a>
+          {% endif %}
+        </div>
+      </div>
+    {% endif %}
+  </div>
+{% endblock %}

docs/_templates/navbar.html

@@ -1,60 +0,0 @@
-  <div id="navbar" class="{{ theme_navbar_class }} navbar-default {% if theme_navbar_fixed_top|tobool -%} navbar-fixed-top{%- endif -%}">
-    <div class="container">
-      <div class="navbar-header">
-        <!-- .btn-navbar is used as the toggle for collapsed navbar content -->
-        <button type="button" class="navbar-toggle" data-toggle="collapse" data-target=".nav-collapse">
-          <span class="icon-bar"></span>
-          <span class="icon-bar"></span>
-          <span class="icon-bar"></span>
-        </button>
-        <a class="navbar-brand" href="{{ pathto(master_doc) }}">
-          {%- block sidebarlogo %}
-            {%- if logo %}<span><img src="{{ pathto('_static/' + logo, 1) }}"></span>{%- endif %}
-          {%- endblock %}
-          {% if theme_navbar_title -%}{{ theme_navbar_title|e }}{%- else -%}{{ project|e }}{%- endif -%}
-        </a>
-        <span class="navbar-text navbar-version pull-left">
-          <a href="https://github.com/instaloader/instaloader/releases/tag/v{{current_release}}" title="Released on {{current_release_date}}">v<b>{{current_release}}</b></a>
-        </span>
-      </div>
-
-        <div class="collapse navbar-collapse nav-collapse">
-          <ul class="nav navbar-nav">
-            {% if theme_navbar_links %}
-              {%- for link in theme_navbar_links %}
-                <li><a href="{{ pathto(*link[1:]) }}">{{ link[0] }}</a></li>
-              {%- endfor %}
-            {% endif %}
-            {% block navbartoc %}
-              {% include "globaltoc.html" %}
-              {% if theme_navbar_pagenav and pagename not in ("index", "genindex", "installation") %}
-                {% include "navbartoc.html" %}
-              {% endif %}
-            {% endblock %}
-            {% if theme_navbar_sidebarrel %}
-              {% block sidebarrel %}
-                {% include "relations.html" %}
-              {% endblock %}
-            {% endif %}
-            </ul>
-            <ul class="nav navbar-nav navbar-right">
-              <li class="dropdown">
-                <a role="button" id="dLabelUsefulLinks" data-toggle="dropdown" data-target="#" href="#">
-                  Useful Links
-                  <b class="caret"></b>
-                </a>
-                <ul class="dropdown-menu" role="menu" aria-labelledby="dLabelUsefulLinks">
-                  <li><a href="https://github.com/instaloader/instaloader/issues">Issue Tracker</a></li>
-                  <li><a href="https://github.com/instaloader/instaloader/releases">Version History</a></li>
-                  <li><a href="https://pypi.org/project/instaloader/">Instaloader on PyPI</a></li>
-                  <li><a href="https://github.com/instaloader/instaloader">Instaloader on GitHub</a></li>
-                  <li role="separator" class="divider"></li>
-                  <li style="padding-left: 20px;"><a class="github-button" href="https://github.com/instaloader/instaloader" data-icon="octicon-star" data-size="large" data-show-count="true" aria-label="Star Instaloader on GitHub">Star</a></li>
-                  <li role="separator" class="divider"></li>
-                  <li><a href="https://www.paypal.me/aandergr"><b>Donate (via Paypal)</b></a></li>
-                </ul>
-              </li>
-            </ul>
-        </div>
-    </div>
-  </div>

docs/_templates/search.html

@@ -0,0 +1,28 @@
+{% extends "!search.html" %}
+
+{% block body %}
+  <div id="fallback" class="admonition warning">
+    <script type="text/javascript">$('#fallback').hide();</script>
+    <p>
+      {% trans %}Please activate JavaScript to enable the search
+        functionality.{% endtrans %}
+    </p>
+  </div>
+  {% if search_performed %}
+    <h1>{{ _('Search Results') }}</h1>
+    {% if not search_results %}
+      <p>{{ _('Your search did not match any documents. Please make sure that all words are spelled correctly and that you\'ve selected enough categories.') }}</p>
+    {% endif %}
+  {% endif %}
+  <div id="search-results">
+    {% if search_results %}
+      <ul>
+        {% for href, caption, context in search_results %}
+          <li><a href="{{ pathto(item.href) }}">{{ caption }}</a>
+            <div class="context">{{ context|e }}</div>
+          </li>
+        {% endfor %}
+      </ul>
+    {% endif %}
+  </div>
+{% endblock %}

docs/as-module.rst

@@ -123,6 +123,9 @@ Additionally, the following trivial structures are defined:
 .. autoclass:: PostComment
    :no-show-inheritance:
 
+.. autoclass:: PostCommentAnswer
+   :no-show-inheritance:
+
 .. autoclass:: PostLocation
    :no-show-inheritance:
 
@@ -198,6 +201,8 @@ Exceptions
 
 .. autoexception:: BadCredentialsException
 
+.. autoexception:: PostChangedException
+
 .. autoexception:: TooManyRequestsException
 
 ``InstaloaderContext`` (Low-level functions)

docs/cli-options.rst

@@ -249,18 +249,20 @@ Miscellaneous Options
 
 .. option:: +args.txt
 
-   Read arguments from file `args.txt`, a shortcut to provide argument from
-   file rather than command-line. This provide a convient way to hide login
-   info from CLI. and also can use for simplify managment of long arguments.
+   Read arguments from file `args.txt`, a shortcut to provide arguments from
+   file rather than command-line. This provides a convenient way to hide login
+   info from CLI, and can also be used to simplify managment of long arguments.
 
    .. note::
 
-      text file should separate arg with line break.
+      Text file should separate arguments with line breaks.
 
       args.txt example::
 
-         --login MYUSENAME
-         --password MYPASSWORD
+         --login=MYUSERNAME
+         --password=MYPASSWORD
          --fast-update
+         profile1
+         profile2
 
    .. versionadded:: 4.1

docs/codesnippets.rst

@@ -82,6 +82,15 @@ See also :class:`Post`, :meth:`Instaloader.download_post`,
 
 Discussed in :issue:`113`.
 
+Top X Posts of User
+-------------------
+
+With Instaloader, it is easy to download the few most-liked pictres of a user.
+
+.. literalinclude:: codesnippets/194_top_x_of_user.py
+
+Discussed in :issue:`194`.
+
 Upgrade Images by Local Copies
 ------------------------------
 

docs/codesnippets/194_top_x_of_user.py

@@ -0,0 +1,15 @@
+from itertools import islice
+from math import ceil
+
+from instaloader import Instaloader, Profile
+
+PROFILE = ...        # profile to download from
+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)
+
+for post in islice(posts_sorted_by_likes, ceil(profile.mediacount * X_percentage / 100)):
+    L.download_post(post, PROFILE)

docs/codesnippets/92_import_firefox_session.py

@@ -0,0 +1,23 @@
+from glob import glob
+from os.path import expanduser
+from sqlite3 import connect
+
+from instaloader import ConnectionException, Instaloader
+
+# FIREFOXCOOKIEFILE = "/home/alex/.mozilla/firefox/l96w6b90.default/cookies.sqlite"
+FIREFOXCOOKIEFILE = glob(expanduser("~/.mozilla/firefox/*.default/cookies.sqlite"))[0]
+
+instaloader = Instaloader(max_connection_attempts=1)
+instaloader.context._session.cookies.update(connect(FIREFOXCOOKIEFILE)
+                                            .execute("SELECT name, value FROM moz_cookies "
+                                                     "WHERE baseDomain='instagram.com'"))
+
+try:
+    username = instaloader.test_login()
+    if not username:
+        raise ConnectionException()
+except ConnectionException:
+    raise SystemExit("Cookie import failed. Are you logged in successfully in Firefox?")
+
+instaloader.context.username = username
+instaloader.save_session_to_file()

docs/conf.py

@@ -22,8 +22,6 @@ import subprocess
 import sys
 import typing
 
-import sphinx_bootstrap_theme
-
 sys.path.insert(0, os.path.abspath('..'))
 
 import docs.sphinx_autodoc_typehints as sphinx_autodoc_typehints
@@ -88,7 +86,7 @@ author = 'Alexander Graf and Andre Koch-Kramer'
 #
 # This is also used if you do content translation via gettext catalogs.
 # Usually you set "language" from the command line for these cases.
-language = None
+language = "en"
 
 # There are two options for replacing |today|: either, you set today to some
 # non-false value, then it is used:
@@ -124,7 +122,7 @@ add_module_names = False
 # show_authors = False
 
 # The name of the Pygments (syntax highlighting) style to use.
-pygments_style = 'sphinx'
+pygments_style = 'fruity'
 
 # A list of ignored prefixes for module index sorting.
 # modindex_common_prefix = []
@@ -141,20 +139,7 @@ todo_include_todos = False
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = 'bootstrap'
-html_theme_path = sphinx_bootstrap_theme.get_html_theme_path()
-
-# Theme options are theme-specific and customize the look and feel of a theme
-# further.  For a list of options available for each theme, see the
-# documentation.
-#
-html_theme_options = {
-    'navbar_site_name': 'Site Contents',
-    'navbar_pagenav_name': 'Page Contents',
-    'navbar_pagenav': True,
-    'navbar_sidebarrel': True,
-    'nosidebar': True,
-     }
+html_theme = 'basic'
 
 # Add any paths that contain custom themes here, relative to this directory.
 # html_theme_path = []
@@ -376,6 +361,6 @@ html_context = {'current_release': current_release, 'current_release_date': curr
 
 def setup(app):
     typing.TYPE_CHECKING = True
-    app.add_stylesheet("style.css")
+    app.add_stylesheet("instaloader.css")
     app.connect('autodoc-process-signature', sphinx_autodoc_typehints.process_signature)
     app.connect('autodoc-process-docstring', sphinx_autodoc_typehints.process_docstring)

docs/contributing.rst

@@ -17,12 +17,14 @@ 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
-**3 days** after being reported. When reporting a problem, please keep the
+**4 days** after being reported. 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``.
 
+- Check whether there is a valid solution in our :ref:`troubleshooting` section.
+
 - Briefly **check whether the bug has already been reported**. If you find an
   issue reporting the same bug you encountered, comment there rather than
   opening a new issue. However, if unsure, please create a new issue.

docs/index.rst

@@ -60,6 +60,7 @@ Instaloader Documentation
    cli-options
    as-module
    codesnippets
+   troubleshooting
    contributing
 
 Useful Links

docs/requirements.txt

@@ -1,3 +1,2 @@
 requests
 sphinx!=1.7.7
-sphinx-bootstrap-theme

docs/troubleshooting.rst

@@ -0,0 +1,60 @@
+.. _troubleshooting:
+
+Troubleshooting
+===============
+
+.. highlight:: python
+
+429 - Too Many Requests
+-----------------------
+
+Instaloader has a logic to keep track of its requests to Instagram and to obey
+their rate limits. Since they are nowhere documented, we try them out
+experimentally. We have a daily cron job running to confirm that Instaloader
+still stays within the rate limits. Nevertheless, the rate control logic assumes
+that
+
+- at one time, Instaloader is the only application that consumes requests. I.e.
+  neither the Instagram browser interface, nor a mobile app, nor another
+  Instaloader instance is running in parallel,
+
+- no requests had been consumed when Instaloader starts.
+
+The latter one implies that restarting or reinstantiating Instaloader often
+within short time is prone to cause a 429. When a request is denied with a 429,
+Instaloader retries the request as soon as the temporary ban is assumed to be
+expired. In case the retry continuously fails for some reason, which should not
+happen in normal conditions, consider adjusting the
+:option:`--max-connection-attempts` option.
+
+**"Too many queries in the last time"** is not an error. It is a notice that the
+rate limit has almost been reached, according to Instaloader's own rate
+accounting mechanism. We regularly adjust this mechanism to match Instagram's
+current rate limiting.
+
+Login error
+-----------
+
+Instaloader's login *should* work fine, both with and without
+Two-Factor-Authentication. It also supports handling the *checkpoint challenge*,
+issued when Instagram suspects authentication activity on your account, by
+pointing the user to an URL to be opened in a browser.
+
+Nevertheless, in :issue:`92` users report problems with logging in. To still use
+Instaloader's logged-in functionality, you may use the following script to
+workaround login problems by importing the session cookies from Firefox and
+bypassing Instaloader's login.
+
+.. literalinclude:: codesnippets/92_import_firefox_session.py
+
+To use this,
+
+#. login to Instagram in Firefox, 
+
+#. execute the snippet,
+
+#. then, ``instaloader -l USERNAME`` should work fine.
+
+If you do not use your default firefox profile, or your operating system has the
+paths differently set up, you may have to alter the ``FIREFOXCOOKIEFILE``
+variable first.

instaloader/__init__.py

@@ -1,7 +1,7 @@
 """Download pictures (or videos) along with their captions and other metadata from Instagram."""
 
 
-__version__ = '4.2rc2'
+__version__ = '4.2.4'
 
 
 try:
@@ -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,
+from .structures import (Highlight, Post, PostSidecarNode, PostComment, PostCommentAnswer, PostLocation, Profile, Story, StoryItem,
                          load_structure_from_file, save_structure_to_file)

instaloader/__main__.py

@@ -179,6 +179,8 @@ def _main(instaloader: Instaloader, targetlist: List[str],
         if len(profiles) > 1:
             instaloader.context.log("Downloading {} profiles: {}".format(len(profiles),
                                                                          ' '.join([p.username for p in profiles])))
+        if profiles and download_profile_pic and not instaloader.context.is_logged_in:
+            instaloader.context.error("Warning: Use --login to download HD version of profile pictures.")
         instaloader.download_profiles(profiles,
                                       download_profile_pic, download_posts, download_tagged, download_highlights,
                                       download_stories, fast_update, post_filter, storyitem_filter)
@@ -329,7 +331,6 @@ def main():
     g_how.add_argument('--user-agent',
                        help='User Agent to use for HTTP requests. Defaults to \'{}\'.'.format(default_user_agent()))
     g_how.add_argument('-S', '--no-sleep', action='store_true', help=SUPPRESS)
-    g_how.add_argument('--graphql-rate-limit', type=int, help=SUPPRESS)
     g_how.add_argument('--max-connection-attempts', metavar='N', type=int, default=3,
                        help='Maximum number of connection attempts until a request is aborted. Defaults to 3. If a '
                             'connection fails, it can be manually skipped by hitting CTRL+C. Set this to 0 to retry '
@@ -391,7 +392,6 @@ def main():
                              compress_json=not args.no_compress_json,
                              post_metadata_txt_pattern=post_metadata_txt_pattern,
                              storyitem_metadata_txt_pattern=storyitem_metadata_txt_pattern,
-                             graphql_rate_limit=args.graphql_rate_limit,
                              max_connection_attempts=args.max_connection_attempts,
                              commit_mode=args.commit_mode)
         _main(loader,

instaloader/exceptions.py

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

instaloader/instaloader.py

@@ -11,9 +11,13 @@ import tempfile
 from contextlib import contextmanager, suppress
 from datetime import datetime, timezone
 from functools import wraps
+from hashlib import md5
 from io import BytesIO
 from typing import Any, Callable, Iterator, List, Optional, Set, Union
 
+import requests
+import urllib3
+
 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
@@ -46,6 +50,37 @@ def _requires_login(func: Callable) -> Callable:
     return call
 
 
+def _retry_on_connection_error(func: Callable) -> Callable:
+    """Decorator to retry the function max_connection_attemps number of times.
+
+    Herewith-decorated functions need an ``_attempt`` keyword argument.
+
+    This is to decorate functions that do network requests that may fail. Note that
+    :meth:`.get_json`, :meth:`.get_iphone_json`, :meth:`.graphql_query` and :meth:`.graphql_node_list` already have
+    their own logic for retrying, hence functions that only use these for network access must not be decorated with this
+    decorator."""
+    @wraps(func)
+    def call(instaloader, *args, **kwargs):
+        try:
+            return func(instaloader, *args, **kwargs)
+        except (urllib3.exceptions.HTTPError, requests.exceptions.RequestException, ConnectionException) as err:
+            error_string = "{}({}): {}".format(func.__name__, ', '.join([repr(arg) for arg in args]), err)
+            if (kwargs.get('_attempt') or 1) == instaloader.context.max_connection_attempts:
+                raise ConnectionException(error_string) from None
+            instaloader.context.error(error_string + " [retrying; skip with ^C]", repeat_at_end=False)
+            try:
+                if kwargs.get('_attempt'):
+                    kwargs['_attempt'] += 1
+                else:
+                    kwargs['_attempt'] = 2
+                instaloader.context.do_sleep()
+                return call(instaloader, *args, **kwargs)
+            except KeyboardInterrupt:
+                instaloader.context.error("[skipped by user]", repeat_at_end=False)
+                raise ConnectionException(error_string) from None
+    return call
+
+
 class _ArbitraryItemFormatter(string.Formatter):
     def __init__(self, item: Any):
         self._item = item
@@ -117,11 +152,10 @@ 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}"
@@ -155,13 +189,10 @@ 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):
@@ -174,7 +205,9 @@ class Instaloader:
     def __exit__(self, *args):
         self.close()
 
-    def download_pic(self, filename: str, url: str, mtime: datetime, filename_suffix: Optional[str] = None) -> bool:
+    @_retry_on_connection_error
+    def download_pic(self, filename: str, url: str, mtime: datetime,
+                     filename_suffix: Optional[str] = None, _attempt: int = 1) -> bool:
         """Downloads and saves picture with given url under given directory with given timestamp.
         Returns true, if file was actually downloaded, i.e. updated."""
         urlmatch = re.search('\\.[a-z0-9]*\\?', url)
@@ -207,11 +240,33 @@ class Instaloader:
             self.context.log('json', end=' ', flush=True)
 
     def update_comments(self, filename: str, post: Post) -> None:
-        def _postcomment_asdict(comment):
+        def _postcommentanswer_asdict(comment):
             return {'id': comment.id,
                     'created_at': int(comment.created_at_utc.replace(tzinfo=timezone.utc).timestamp()),
                     'text': comment.text,
                     'owner': comment.owner._asdict()}
+
+        def _postcomment_asdict(comment):
+            return {**_postcommentanswer_asdict(comment),
+                    'answers': sorted([_postcommentanswer_asdict(answer) for answer in comment.answers],
+                                      key=lambda t: int(t['id']),
+                                      reverse=True)}
+
+        def get_unique_comments(comments, combine_answers=False):
+            if not comments:
+                return list()
+            comments_list = sorted(sorted(list(comments), key=lambda t: int(t['id'])),
+                                   key=lambda t: int(t['created_at']), reverse=True)
+            unique_comments_list = [comments_list[0]]
+            for x, y in zip(comments_list[:-1], comments_list[1:]):
+                if x['id'] != y['id']:
+                    unique_comments_list.append(y)
+                elif combine_answers:
+                    combined_answers = unique_comments_list[-1].get('answers') or list()
+                    if 'answers' in y:
+                        combined_answers.extend(y['answers'])
+                    unique_comments_list[-1]['answers'] = get_unique_comments(combined_answers)
+            return unique_comments_list
         filename += '_comments.json'
         try:
             with open(filename) as fp:
@@ -220,18 +275,10 @@ 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:
@@ -254,8 +301,7 @@ class Instaloader:
                 return None
             else:
                 def get_filename(index):
-                    return filename if index == 0 else (filename[:-4] + '_old_' +
-                                                        (str(0) if index < 10 else str()) + str(index) + filename[-4:])
+                    return filename if index == 0 else '{0}_old_{2:02}{1}'.format(*os.path.splitext(filename), index)
 
                 i = 0
                 while os.path.isfile(get_filename(i)):
@@ -285,30 +331,39 @@ class Instaloader:
         os.utime(filename, (datetime.now().timestamp(), mtime.timestamp()))
         self.context.log('geo', end=' ', flush=True)
 
-    def download_profilepic(self, profile: Profile) -> None:
+    @_retry_on_connection_error
+    def download_profilepic(self, profile: Profile, _attempt: int = 1) -> None:
         """Downloads and saves profile pic."""
 
         def _epoch_to_string(epoch: datetime) -> str:
-            return epoch.strftime('%Y-%m-%d_%H-%M-%S')
+            return epoch.strftime('%Y-%m-%d_%H-%M-%S_UTC')
 
-        profile_pic_url = profile.profile_pic_url
-        with self.context.get_anonymous_session() as anonymous_session:
-            date_object = datetime.strptime(anonymous_session.head(profile_pic_url).headers["Last-Modified"],
-                                            '%a, %d %b %Y %H:%M:%S GMT')
+        profile_pic_response = self.context.get_raw(profile.profile_pic_url)
+        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'
         if ((format_string_contains_key(self.dirname_pattern, 'profile') or
              format_string_contains_key(self.dirname_pattern, 'target'))):
-            filename = '{0}/{1}_UTC_profile_pic.{2}'.format(self.dirname_pattern.format(profile=profile.username.lower(),
-                                                                                        target=profile.username.lower()),
-                                                            _epoch_to_string(date_object), profile_pic_extension)
+            filename = '{0}/{1}_profile_pic.{2}'.format(self.dirname_pattern.format(profile=profile.username.lower(),
+                                                                                    target=profile.username.lower()),
+                                                        profile_pic_identifier, profile_pic_extension)
         else:
-            filename = '{0}/{1}_{2}_UTC_profile_pic.{3}'.format(self.dirname_pattern.format(), profile.username.lower(),
-                                                                _epoch_to_string(date_object), profile_pic_extension)
-        if os.path.isfile(filename):
+            filename = '{0}/{1}_{2}_profile_pic.{3}'.format(self.dirname_pattern.format(), profile.username.lower(),
+                                                            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)):
             self.context.log(filename + ' already exists')
             return None
-        self.context.get_and_write_raw(profile_pic_url, filename)
-        os.utime(filename, (datetime.now().timestamp(), date_object.timestamp()))
+        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()))
         self.context.log('')  # log output of _get_and_write_raw() does not produce \n
 
     @_requires_login
@@ -890,6 +945,11 @@ class Instaloader:
             with error_handler(profile.username):
                 profile_name = profile.username
 
+                # Download profile picture
+                if profile_pic:
+                    with self.context.error_catcher('Download profile picture of {}'.format(profile_name)):
+                        self.download_profilepic(profile)
+
                 # Save metadata as JSON if desired.
                 if self.save_metadata:
                     json_filename = '{0}/{1}_{2}'.format(self.dirname_pattern.format(profile=profile_name,
@@ -897,11 +957,6 @@ class Instaloader:
                                                          profile_name, profile.userid)
                     self.save_metadata_json(json_filename, profile)
 
-                # Download profile picture
-                if profile_pic:
-                    with self.context.error_catcher('Download profile picture of {}'.format(profile_name)):
-                        self.download_profilepic(profile)
-
                 # Catch some errors
                 if profile.is_private and (tagged or highlights or posts):
                     if not self.context.is_logged_in:
@@ -931,8 +986,22 @@ class Instaloader:
                             self.context.log('<skipped>')
                             continue
                         with self.context.error_catcher("Download {} of {}".format(post, profile_name)):
-                            downloaded = self.download_post(post, target=profile_name)
-                            if fast_update and not downloaded:
+                            # The PostChangedException gets raised if the Post's id/shortcode changed while obtaining
+                            # additional metadata. This is most likely the case if a HTTP redirect takes place while
+                            # resolving the shortcode URL.
+                            # The `post_changed` variable keeps the fast-update functionality alive: A Post which is
+                            # obained after a redirect has probably already been downloaded as a previous Post of the
+                            # same Profile.
+                            # Observed in issue #225: https://github.com/instaloader/instaloader/issues/225
+                            post_changed = False
+                            while True:
+                                try:
+                                    downloaded = self.download_post(post, target=profile_name)
+                                    break
+                                except PostChangedException:
+                                    post_changed = True
+                                    continue
+                            if fast_update and not downloaded and not post_changed:
                                 break
 
         if stories and profiles:

instaloader/instaloadercontext.py

@@ -10,11 +10,10 @@ import time
 import urllib.parse
 from contextlib import contextmanager
 from datetime import datetime, timedelta
-from typing import Any, Callable, Dict, Iterator, Optional
+from typing import Any, Callable, Dict, Iterator, Optional, Union
 
 import requests
 import requests.utils
-import urllib3
 
 from .exceptions import *
 
@@ -48,7 +47,7 @@ class InstaloaderContext:
     """
 
     def __init__(self, sleep: bool = True, quiet: bool = False, user_agent: Optional[str] = None,
-                 graphql_count_per_slidingwindow: Optional[int] = None, max_connection_attempts: int = 3):
+                 max_connection_attempts: int = 3):
 
         self.user_agent = user_agent if user_agent is not None else default_user_agent()
         self._session = self.get_anonymous_session()
@@ -57,7 +56,6 @@ 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
 
@@ -65,7 +63,8 @@ class InstaloaderContext:
         self.error_log = []
 
         # For the adaption of sleep intervals (rate control)
-        self.query_timestamps = list()
+        self._graphql_query_timestamps = dict()
+        self._graphql_earliest_next_request_time = 0
 
         # Can be set to True for testing, disables supression of InstaloaderContext._error_catcher
         self.raise_all_errors = False
@@ -195,10 +194,13 @@ class InstaloaderContext:
         csrf_token = session.cookies.get_dict()['csrftoken']
         session.headers.update({'X-CSRFToken': csrf_token})
         # Not using self.get_json() here, because we need to access csrftoken cookie
-        self._sleep()
+        self.do_sleep()
         login = session.post('https://www.instagram.com/accounts/login/ajax/',
                              data={'password': passwd, 'username': user}, allow_redirects=True)
-        resp_json = login.json()
+        try:
+            resp_json = login.json()
+        except json.decoder.JSONDecodeError:
+            raise ConnectionException("Login error: JSON decode fail, {} - {}.".format(login.status_code, login.reason))
         if resp_json.get('two_factor_required'):
             two_factor_session = copy_session(session)
             two_factor_session.headers.update({'X-CSRFToken': csrf_token})
@@ -207,6 +209,10 @@ class InstaloaderContext:
                                             user,
                                             resp_json['two_factor_info']['two_factor_identifier'])
             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{}, "
+                                      "follow the instructions, then retry.".format(resp_json.get('checkpoint_url')))
         if resp_json['status'] != 'ok':
             if 'message' in resp_json:
                 raise ConnectionException("Login error: \"{}\" status, message \"{}\".".format(resp_json['status'],
@@ -254,11 +260,77 @@ class InstaloaderContext:
         self.username = user
         self.two_factor_auth_pending = None
 
-    def _sleep(self):
+    def do_sleep(self):
         """Sleep a short time if self.sleep is set. Called before each request to instagram.com."""
         if self.sleep:
             time.sleep(min(random.expovariate(0.7), 5.0))
 
+    def _dump_query_timestamps(self, current_time: float):
+        """Output the number of GraphQL queries grouped by their query_hash within the last time."""
+        windows = [10, 11, 15, 20, 30, 60]
+        print("GraphQL requests:", file=sys.stderr)
+        for query_hash, times in self._graphql_query_timestamps.items():
+            print("  {}".format(query_hash), file=sys.stderr)
+            for window in windows:
+                reqs_in_sliding_window = sum(t > current_time - window * 60 for t in times)
+                print("    last {} minutes: {} requests".format(window, reqs_in_sliding_window), file=sys.stderr)
+
+    def _graphql_request_count_per_sliding_window(self, query_hash: str) -> int:
+        """Return how many GraphQL requests can be done within the sliding window."""
+        if self.is_logged_in:
+            max_reqs = {'1cb6ec562846122743b61e492c85999f': 20, '33ba35852cb50da46f5b5e889df7d159': 20}
+        else:
+            max_reqs = {'1cb6ec562846122743b61e492c85999f': 200, '33ba35852cb50da46f5b5e889df7d159': 200}
+        return max_reqs.get(query_hash) or min(max_reqs.values())
+
+    def _graphql_query_waittime(self, query_hash: str, current_time: float, untracked_queries: bool = False) -> int:
+        """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.
@@ -272,32 +344,12 @@ class InstaloaderContext:
         :raises QueryReturnedNotFoundException: When the server responds with a 404.
         :raises ConnectionException: When query repeatedly failed.
         """
-        def graphql_query_waittime(untracked_queries: bool = False) -> int:
-            sliding_window = 660
-            if not self.query_timestamps:
-                return sliding_window if untracked_queries else 0
-            current_time = time.monotonic()
-            self.query_timestamps = list(filter(lambda t: t > current_time - sliding_window, self.query_timestamps))
-            if len(self.query_timestamps) < self.graphql_count_per_slidingwindow and not untracked_queries:
-                return 0
-            return round(min(self.query_timestamps) + sliding_window - current_time) + 6
         is_graphql_query = 'query_hash' in params and 'graphql/query' in path
-        # some queries are not rate limited if invoked anonymously:
-        query_not_limited = is_graphql_query and not self.is_logged_in \
-                            and params['query_hash'] in ['9ca88e465c3f866a76f7adee3871bdd8']
-        if is_graphql_query and not query_not_limited:
-            waittime = graphql_query_waittime()
-            if waittime > 0:
-                self.log('\nToo many queries in the last time. Need to wait {} seconds, until {:%H:%M}.'
-                         .format(waittime, datetime.now() + timedelta(seconds=waittime)))
-                time.sleep(waittime)
-            if self.query_timestamps is not None:
-                self.query_timestamps.append(time.monotonic())
-            else:
-                self.query_timestamps = [time.monotonic()]
         sess = session if session else self._session
         try:
-            self._sleep()
+            self.do_sleep()
+            if is_graphql_query:
+                self._ratecontrol_graphql_query(params['query_hash'])
             resp = sess.get('https://{0}/{1}'.format(host, path), params=params, allow_redirects=False)
             while resp.is_redirect:
                 redirect_url = resp.headers['location']
@@ -335,20 +387,9 @@ class InstaloaderContext:
             if _attempt == self.max_connection_attempts:
                 raise ConnectionException(error_string) from err
             self.error(error_string + " [retrying; skip with ^C]", repeat_at_end=False)
-            text_for_429 = ("HTTP error code 429 was returned because too many queries occured in the last time. "
-                            "Please do not use Instagram in your browser or run multiple instances of Instaloader "
-                            "in parallel.")
             try:
                 if isinstance(err, TooManyRequestsException):
-                    print(textwrap.fill(text_for_429), file=sys.stderr)
-                    if is_graphql_query:
-                        print("Made {} GraphQL requests.".format(len(self.query_timestamps)), file=sys.stderr)
-                        waittime = graphql_query_waittime(untracked_queries=True)
-                        if waittime > 0:
-                            self.log('The request will be retried in {} seconds, at {:%H:%M}.'
-                                     .format(waittime, datetime.now() + timedelta(seconds=waittime)))
-                            time.sleep(waittime)
-                self._sleep()
+                    self._ratecontrol_graphql_query(params['query_hash'], untracked_queries=True)
                 return self.get_json(path=path, params=params, host=host, session=sess, _attempt=_attempt + 1)
             except KeyboardInterrupt:
                 self.error("[skipped by user]", repeat_at_end=False)
@@ -422,39 +463,64 @@ class InstaloaderContext:
             data = _query()
             yield from (edge['node'] for edge in data['edges'])
 
-    def get_and_write_raw(self, url: str, filename: str, _attempt=1) -> None:
-        """Downloads raw data.
+    def get_iphone_json(self, path: str, params: Dict[str, Any]) -> Dict[str, Any]:
+        """JSON request to ``i.instagram.com``.
+
+        :param path: URL, relative to ``i.instagram.com/``
+        :param params: GET parameters
+        :return: Decoded response dictionary
+        :raises QueryReturnedBadRequestException: When the server responds with a 400.
+        :raises QueryReturnedNotFoundException: When the server responds with a 404.
+        :raises ConnectionException: When query repeatedly failed.
+
+        .. versionadded:: 4.2.1"""
+        with copy_session(self._session) as tempsession:
+            tempsession.headers['User-Agent'] = 'Instagram 10.3.2 (iPhone7,2; iPhone OS 9_3_3; en_US; en-US; ' \
+                                                'scale=2.00; 750x1334) AppleWebKit/420+'
+            for header in ['Host', 'Origin', 'X-Instagram-AJAX', 'X-Requested-With']:
+                tempsession.headers.pop(header, None)
+            return self.get_json(path, params, 'i.instagram.com', tempsession)
+
+    def write_raw(self, resp: Union[bytes, requests.Response], filename: str) -> None:
+        """Write raw response data into a file.
+
+        .. versionadded:: 4.2.1"""
+        self.log(filename, end=' ', flush=True)
+        with open(filename, 'wb') as file:
+            if isinstance(resp, requests.Response):
+                shutil.copyfileobj(resp.raw, file)
+            else:
+                file.write(resp)
+
+    def get_raw(self, url: str, _attempt=1) -> requests.Response:
+        """Downloads a file anonymously.
+
+        :raises QueryReturnedNotFoundException: When the server responds with a 404.
+        :raises QueryReturnedForbiddenException: When the server responds with a 403.
+        :raises ConnectionException: When download failed.
+
+        .. versionadded:: 4.2.1"""
+        with self.get_anonymous_session() as anonymous_session:
+            resp = anonymous_session.get(url, stream=True)
+        if resp.status_code == 200:
+            resp.raw.decode_content = True
+            return resp
+        else:
+            if resp.status_code == 403:
+                # suspected invalid URL signature
+                raise QueryReturnedForbiddenException("403 when accessing {}.".format(url))
+            if resp.status_code == 404:
+                # 404 not worth retrying.
+                raise QueryReturnedNotFoundException("404 when accessing {}.".format(url))
+            raise ConnectionException("HTTP error code {}.".format(resp.status_code))
+
+    def get_and_write_raw(self, url: str, filename: str) -> None:
+        """Downloads and writes anonymously-requested raw data into a file.
 
         :raises QueryReturnedNotFoundException: When the server responds with a 404.
         :raises QueryReturnedForbiddenException: When the server responds with a 403.
         :raises ConnectionException: When download repeatedly failed."""
-        try:
-            with self.get_anonymous_session() as anonymous_session:
-                resp = anonymous_session.get(url, stream=True)
-            if resp.status_code == 200:
-                self.log(filename, end=' ', flush=True)
-                with open(filename, 'wb') as file:
-                    resp.raw.decode_content = True
-                    shutil.copyfileobj(resp.raw, file)
-            else:
-                if resp.status_code == 403:
-                    # suspected invalid URL signature
-                    raise QueryReturnedForbiddenException("403 when accessing {}.".format(url))
-                if resp.status_code == 404:
-                    # 404 not worth retrying.
-                    raise QueryReturnedNotFoundException("404 when accessing {}.".format(url))
-                raise ConnectionException("HTTP error code {}.".format(resp.status_code))
-        except (urllib3.exceptions.HTTPError, requests.exceptions.RequestException, ConnectionException) as err:
-            error_string = "URL {}: {}".format(url, err)
-            if _attempt == self.max_connection_attempts:
-                raise ConnectionException(error_string) from err
-            self.error(error_string + " [retrying; skip with ^C]", repeat_at_end=False)
-            try:
-                self._sleep()
-                self.get_and_write_raw(url, filename, _attempt + 1)
-            except KeyboardInterrupt:
-                self.error("[skipped by user]", repeat_at_end=False)
-                raise ConnectionException(error_string) from err
+        self.write_raw(self.get_raw(url), filename)
 
     @property
     def root_rhx_gis(self) -> Optional[str]:

instaloader/structures.py

@@ -17,11 +17,16 @@ PostSidecarNode.is_video.__doc__ = "Whether this node is a video."
 PostSidecarNode.display_url.__doc__ = "URL of image or video thumbnail."
 PostSidecarNode.video_url.__doc__ = "URL of video or None."
 
-PostComment = namedtuple('PostComment', ['id', 'created_at_utc', 'text', 'owner'])
-PostComment.id.__doc__ = "ID number of comment."
-PostComment.created_at_utc.__doc__ = ":class:`~datetime.datetime` when comment was created (UTC)."
-PostComment.text.__doc__ = "Comment text."
-PostComment.owner.__doc__ = "Owner :class:`Profile` of the comment."
+PostCommentAnswer = namedtuple('PostCommentAnswer', ['id', 'created_at_utc', 'text', 'owner'])
+PostCommentAnswer.id.__doc__ = "ID number of comment."
+PostCommentAnswer.created_at_utc.__doc__ = ":class:`~datetime.datetime` when comment was created (UTC)."
+PostCommentAnswer.text.__doc__ = "Comment text."
+PostCommentAnswer.owner.__doc__ = "Owner :class:`Profile` of the comment."
+
+PostComment = namedtuple('PostComment', (*PostCommentAnswer._fields, 'answers'))
+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."
 
 PostLocation = namedtuple('PostLocation', ['id', 'name', 'slug', 'has_public_page', 'lat', 'lng'])
 PostLocation.id.__doc__ = "ID number of location."
@@ -128,6 +133,9 @@ class Post:
             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']
+            if self.shortcode != self._full_metadata_dict['shortcode']:
+                self._node.update(self._full_metadata_dict)
+                raise PostChangedException
 
     @property
     def _full_metadata(self) -> Dict[str, Any]:
@@ -280,34 +288,72 @@ class Post:
 
     @property
     def comments(self) -> int:
-        """Comment count"""
-        return self._field('edge_media_to_comment', 'count')
+        """Comment count including answers"""
+        try:
+            return self._field('edge_media_to_parent_comment', 'count')
+        except KeyError:
+            return self._field('edge_media_to_comment', 'count')
 
     def get_comments(self) -> Iterator[PostComment]:
-        """Iterate over all comments of the post.
+        r"""Iterate over all comments of the post.
 
         Each comment is represented by a PostComment namedtuple with fields text (string), created_at (datetime),
-        id (int) and owner (:class:`Profile`).
+        id (int), owner (:class:`Profile`) and answers (:class:`~typing.Iterator`\ [:class:`PostCommentAnswer`])
+        if available.
         """
+        def _postcommentanswer(node):
+            return PostCommentAnswer(id=int(node['id']),
+                                     created_at_utc=datetime.utcfromtimestamp(node['created_at']),
+                                     text=node['text'],
+                                     owner=Profile(self._context, node['owner']))
+
+        def _postcommentanswers(node):
+            if 'edge_threaded_comments' not in node:
+                return
+            answer_count = node['edge_threaded_comments']['count']
+            if answer_count == 0:
+                # Avoid doing additional requests if there are no comment answers
+                return
+            answer_edges = node['edge_threaded_comments']['edges']
+            if answer_count == len(answer_edges):
+                # If the answer's metadata already contains all comments, don't do GraphQL requests to obtain them
+                yield from (_postcommentanswer(comment['node']) for comment in answer_edges)
+                return
+            yield from (_postcommentanswer(answer_node) for answer_node in
+                        self._context.graphql_node_list("51fdd02b67508306ad4484ff574a0b62",
+                                                        {'comment_id': node['id']},
+                                                        'https://www.instagram.com/p/' + self.shortcode + '/',
+                                                        lambda d: d['data']['comment']['edge_threaded_comments']))
+
         def _postcomment(node):
-            return PostComment(id=int(node['id']),
-                               created_at_utc=datetime.utcfromtimestamp(node['created_at']),
-                               text=node['text'],
-                               owner=Profile(self._context, node['owner']))
+            return PostComment(*_postcommentanswer(node),
+                               answers=_postcommentanswers(node))
         if self.comments == 0:
             # Avoid doing additional requests if there are no comments
             return
-        comment_edges = self._field('edge_media_to_comment', 'edges')
-        if self.comments == len(comment_edges):
-            # If the Post's metadata already contains all comments, don't do GraphQL requests to obtain them
+        try:
+            comment_edges = self._field('edge_media_to_parent_comment', 'edges')
+            answers_count = sum([edge['node']['edge_threaded_comments']['count'] for edge in comment_edges])
+            threaded_comments_available = True
+        except KeyError:
+            comment_edges = self._field('edge_media_to_comment', 'edges')
+            answers_count = 0
+            threaded_comments_available = False
+
+        if self.comments == len(comment_edges) + answers_count:
+            # If the Post's metadata already contains all parent comments, don't do GraphQL requests to obtain them
             yield from (_postcomment(comment['node']) for comment in comment_edges)
             return
         yield from (_postcomment(node) for node in
-                    self._context.graphql_node_list("33ba35852cb50da46f5b5e889df7d159",
-                                                    {'shortcode': self.shortcode},
-                                                    'https://www.instagram.com/p/' + self.shortcode + '/',
-                                                    lambda d: d['data']['shortcode_media']['edge_media_to_comment'],
-                                                    self._rhx_gis))
+                    self._context.graphql_node_list(
+                        "97b41c52301f77ce508f55e66d17620e" if threaded_comments_available
+                        else "f0986789a5c5d17c2400faebf16efd0d",
+                        {'shortcode': self.shortcode},
+                        'https://www.instagram.com/p/' + self.shortcode + '/',
+                        lambda d:
+                        d['data']['shortcode_media'][
+                            'edge_media_to_parent_comment' if threaded_comments_available else 'edge_media_to_comment'],
+                        self._rhx_gis))
 
     def get_likes(self) -> Iterator['Profile']:
         """Iterate over all likes of the post. A :class:`Profile` instance of each likee is yielded."""
@@ -373,6 +419,10 @@ class Profile:
         self._has_public_story = None
         self._node = node
         self._rhx_gis = None
+        self._iphone_struct_ = None
+        if 'iphone_struct' in node:
+            # if loaded from JSON with load_structure_from_file()
+            self._iphone_struct_ = node['iphone_struct']
 
     @classmethod
     def from_username(cls, context: InstaloaderContext, username: str):
@@ -392,28 +442,27 @@ class Profile:
     @classmethod
     def from_id(cls, context: InstaloaderContext, profile_id: int):
         """Create a Profile instance from a given userid. If possible, use :meth:`Profile.from_username`
-        or constructor directly rather than this method, since it does many requests.
+        or constructor directly rather than this method, since it requires more requests.
 
         :param context: :attr:`Instaloader.context`
         :param profile_id: userid
-        :raises: :class:`ProfileNotExistsException`, :class:`ProfileHasNoPicsException`
+        :raises: :class:`ProfileNotExistsException`
         """
         if profile_id in context.profile_id_cache:
             return context.profile_id_cache[profile_id]
-        data = context.graphql_query("472f257a40c653c64c666ce877d59d2b",
-                                     {'id': str(profile_id), 'first': 1},
+        data = context.graphql_query('7c16654f22c819fb63d1183034a5162f',
+                                     {'user_id': str(profile_id),
+                                      'include_chaining': False,
+                                      'include_reel': True,
+                                      'include_suggested_users': False,
+                                      'include_logged_out_extras': False,
+                                      'include_highlight_reels': False},
                                      rhx_gis=context.root_rhx_gis)['data']['user']
         if data:
-            data = data["edge_owner_to_timeline_media"]
+            profile = cls(context, data['reel']['owner'])
         else:
             raise ProfileNotExistsException("No profile found, the user may have blocked you (ID: " +
                                             str(profile_id) + ").")
-        if not data['edges']:
-            if data['count'] == 0:
-                raise ProfileHasNoPicsException("Profile with ID {0}: no pics found.".format(str(profile_id)))
-            else:
-                raise LoginRequiredException("Login required to determine username (ID: " + str(profile_id) + ").")
-        profile = Post(context, data['edges'][0]['node']).owner_profile
         context.profile_id_cache[profile_id] = profile
         return profile
 
@@ -423,6 +472,8 @@ class Profile:
         json_node.pop('edge_media_collections', None)
         json_node.pop('edge_owner_to_timeline_media', None)
         json_node.pop('edge_saved_media', None)
+        if self._iphone_struct_:
+            json_node['iphone_struct'] = self._iphone_struct_
         return json_node
 
     def _obtain_metadata(self):
@@ -447,6 +498,15 @@ class Profile:
                 d = d[key]
             return d
 
+    @property
+    def _iphone_struct(self) -> Dict[str, Any]:
+        if not self._context.is_logged_in:
+            raise LoginRequiredException("--login required to access iPhone profile info endpoint.")
+        if not self._iphone_struct_:
+            data = self._context.get_iphone_json(path='api/v1/users/{}/info/'.format(self.userid), params={})
+            self._iphone_struct_ = data['user']
+        return self._iphone_struct_
+
     @property
     def userid(self) -> int:
         """User ID"""
@@ -563,10 +623,20 @@ class Profile:
 
     @property
     def profile_pic_url(self) -> str:
-        """Return URL of profile picture
+        """Return URL of profile picture. If logged in, the HD version is returned, otherwise a lower-quality version.
 
-        .. versionadded:: 4.0.3"""
-        return self._metadata("profile_pic_url_hd")
+        .. versionadded:: 4.0.3
+
+        .. versionchanged:: 4.2.1
+           Require being logged in for HD version (as required by Instagram)."""
+        if self._context.is_logged_in:
+            try:
+                return self._iphone_struct['hd_profile_pic_url_info']['url']
+            except (InstaloaderException, KeyError) as err:
+                self._context.error('{} Unable to fetch high quality profile pic.'.format(err))
+                return self._metadata("profile_pic_url_hd")
+        else:
+            return self._metadata("profile_pic_url_hd")
 
     def get_profile_pic_url(self) -> str:
         """.. deprecated:: 4.0.3

test/instaloader_unittests.py

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