Third Beta Release for Version 4.9

.github/workflows/documentation.yml

@@ -0,0 +1,31 @@
+name: "Documentation"
+
+on: [push, pull_request]
+
+jobs:
+  docs:
+    name: "Documentation"
+    runs-on: ubuntu-latest
+    steps:
+      - name: "Checkout Instaloader Repository"
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0  # needed for building docs
+      - name: "Setup Python"
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.8
+      - name: "Install Dependencies"
+        run: |
+          python -m pip install pipenv==2022.1.8
+          pipenv sync --dev
+      - name: "Build Documentation"
+        run: pipenv run make -C docs html SPHINXOPTS="-W -n"
+      - name: "Deploy Documentation"
+        if: github.event_name == 'push' && github.ref == 'refs/heads/master'
+        uses: JamesIves/github-pages-deploy-action@v4.2.5
+        with:
+          branch: master
+          repository-name: instaloader/instaloader.github.io
+          folder: docs/_build/html
+          token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/lint.yml

@@ -8,24 +8,19 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10"]
+        python-version: ["3.6", "3.7", "3.8", "3.9", "3.10"]
     steps:
       - name: Checkout Instaloader Repository
         uses: actions/checkout@v2
-        with:
-          fetch-depth: 0  # needed for building docs
       - name: Setup Python
         uses: actions/setup-python@v2
         with:
           python-version: ${{ matrix.python-version }}
       - name: Install Dependencies
         run: |
-          python -m pip install pipenv==2021.5.29
+          python -m pip install pipenv==2022.1.8
           pipenv sync --dev
       - name: PyLint
         run: pipenv run pylint instaloader
       - name: MyPy
         run: pipenv run mypy -m instaloader
-      - name: Build Documentation
-        if: matrix.python-version == '3.8'
-        run: pipenv run make -C docs html SPHINXOPTS="-W -n"

.github/workflows/packages.yml

@@ -0,0 +1,40 @@
+name: "Publish Packages"
+
+on:
+  push:
+    tags:
+      - v*
+
+jobs:
+  publish:
+    name: "Publish Package"
+    runs-on: ubuntu-latest
+    steps:
+      - name: "Checkout Repository"
+        uses: actions/checkout@v2
+      - name: "Setup Python"
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.8
+      - name: "Get the tagged version"
+        id: get_version
+        env:
+          GITHUB_REF: ${{ github.ref }}
+        run: echo ::set-output name=VERSION::${GITHUB_REF/refs\/tags\/v/}
+        shell: bash
+      - name: "Install Dependencies"
+        run: |
+          python -m pip install pipenv==2022.1.8
+          pipenv sync --dev
+      - name: "Generate Python Package"
+        run: python setup.py sdist
+      - name: "Publish Distribution to PyPI"
+        uses: pypa/gh-action-pypi-publish@master
+        with:
+          password: ${{ secrets.PYPI_PASSWORD }}
+      - name: "Publish Distribution to AUR"
+        run: deploy/arch/deploy.sh $VERSION_TAG
+        env:
+          VERSION_TAG: v${{ steps.get_version.outputs.VERSION }}
+          AUR_KEY: ${{ secrets.AUR_KEY }}
+          AUR_IV: ${{ secrets.AUR_IV }}

.travis.yml

@@ -1,35 +0,0 @@
-dist: xenial
-language: python
-python:
- - "3.6"
- - "3.7"
-install:
- - pipenv sync --dev
-script:
- - pylint instaloader
- - mypy -m instaloader
- - make -C docs html SPHINXOPTS="-W -n"
-addons:
-  ssh_known_hosts: aur.archlinux.org
-deploy:
-  - provider: pypi
-    user: aandergr
-    on:
-      tags: true
-      python: 3.6
-    password:
-      secure: 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
-  - provider: pages
-    skip-cleanup: true
-    github-token: $GITHUB_TOKEN
-    local-dir: docs/_build/html
-    repo: instaloader/instaloader.github.io
-    target-branch: master
-    on:
-      branch: master
-      python: 3.6
-  - provider: script
-    script: deploy/arch/deploy.sh $TRAVIS_TAG
-    on:
-      tags: true
-      python: 3.6

deploy/arch/deploy.sh

@@ -3,15 +3,16 @@
 VERSION=${1:1}
 
 # do not deploy pre-releases
-echo $VERSION | grep -qe "[abc]" && exit 0
+#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
+openssl aes-256-cbc -K $AUR_KEY -iv $AUR_IV -in id_rsa_AUR.enc -out /tmp/AUR_openssh -d
 eval "$(ssh-agent -s)"
 chmod 600 /tmp/AUR_openssh
 ssh-add /tmp/AUR_openssh
+ssh-keyscan -t rsa aur.archlinux.org >> ~/.ssh/known_hosts
 
 # clone and modify AUR repo
 git clone --depth 1 ssh://aur@aur.archlinux.org/instaloader.git

deploy/windows/create_exe.py

@@ -44,7 +44,7 @@ with open('__main__.py', 'w+') as f:
     f.writelines(lines)
 
 # install dependencies and invoke PyInstaller
-commands = ["pip install pipenv==2021.5.29",
+commands = ["pip install pipenv==2022.1.8",
             f"pipenv --python {sys.version_info.major}.{sys.version_info.minor} sync --dev",
             "pipenv run pyinstaller --log-level=DEBUG instaloader.spec"]
 

docs/cli-options.rst

@@ -239,6 +239,13 @@ How to Download
 
    .. versionadded:: 4.8
 
+.. option:: --sanitize-paths
+
+   Force sanitization of paths so that the resulting file and directory names
+   are valid on both Windows and Unix.
+
+   .. versionadded:: 4.9
+
 .. option:: --resume-prefix prefix
 
    For many targets, Instaloader is capable of resuming a previously-aborted

instaloader/__init__.py

@@ -1,7 +1,7 @@
 """Download pictures (or videos) along with their captions and other metadata from Instagram."""
 
 
-__version__ = '4.9b2'
+__version__ = '4.9b3'
 
 
 try:

instaloader/__main__.py

@@ -383,6 +383,9 @@ def main():
     g_how.add_argument('--resume-prefix', metavar='PREFIX',
                        help='Prefix for filenames that are used to save the information to resume an interrupted '
                             'download.')
+    g_how.add_argument('--sanitize-paths', action='store_true',
+                       help='Sanitize paths so that the resulting file and directory names are valid on both '
+                            'Windows and Unix.')
     g_how.add_argument('--no-resume', action='store_true',
                        help='Do not resume a previously-aborted download iteration, and do not save such information '
                             'when interrupted.')
@@ -463,7 +466,8 @@ def main():
                              slide=args.slide,
                              fatal_status_codes=args.abort_on,
                              iphone_support=not args.no_iphone,
-                             title_pattern=args.title_pattern)
+                             title_pattern=args.title_pattern,
+                             sanitize_paths=args.sanitize_paths)
         _main(loader,
               args.profile,
               username=args.login.lower() if args.login is not None else None,

instaloader/instaloader.py

@@ -137,24 +137,38 @@ class _ArbitraryItemFormatter(string.Formatter):
 
 
 class _PostPathFormatter(_ArbitraryItemFormatter):
+    RESERVED: set = {'CON', 'PRN', 'AUX', 'NUL',
+                     'COM1', 'COM2', 'COM3', 'COM4', 'COM5', 'COM6', 'COM7', 'COM8', 'COM9',
+                     'LPT1', 'LPT2', 'LPT3', 'LPT4', 'LPT5', 'LPT6', 'LPT7', 'LPT8', 'LPT9'}
+
+    def __init__(self, item: Any, force_windows_path: bool = False):
+        super().__init__(item)
+        self.force_windows_path = force_windows_path
+
     def get_value(self, key, args, kwargs):
         ret = super().get_value(key, args, kwargs)
         if not isinstance(ret, str):
             return ret
-        return self.sanitize_path(ret)
+        return self.sanitize_path(ret, self.force_windows_path)
 
     @staticmethod
-    def sanitize_path(ret: str) -> str:
+    def sanitize_path(ret: str, force_windows_path: bool = False) -> str:
         """Replaces '/' with similar looking Division Slash and some other illegal filename characters on Windows."""
         ret = ret.replace('/', '\u2215')
 
         if ret.startswith('.'):
             ret = ret.replace('.', '\u2024', 1)
 
-        if platform.system() == 'Windows':
+        if force_windows_path or platform.system() == 'Windows':
             ret = ret.replace(':', '\uff1a').replace('<', '\ufe64').replace('>', '\ufe65').replace('\"', '\uff02')
             ret = ret.replace('\\', '\ufe68').replace('|', '\uff5c').replace('?', '\ufe16').replace('*', '\uff0a')
             ret = ret.replace('\n', ' ').replace('\r', ' ')
+            root, ext = os.path.splitext(ret)
+            if root.upper() in _PostPathFormatter.RESERVED:
+                root += '_'
+            if ext == '.':
+                ext = '\u2024'
+            ret = root + ext
         return ret
 
 
@@ -187,6 +201,7 @@ class Instaloader:
     :param slide: :option:`--slide`
     :param fatal_status_codes: :option:`--abort-on`
     :param iphone_support: not :option:`--no-iphone`
+    :param sanitize_paths: :option:`--sanitize-paths`
 
     .. attribute:: context
 
@@ -216,7 +231,8 @@ class Instaloader:
                  slide: Optional[str] = None,
                  fatal_status_codes: Optional[List[int]] = None,
                  iphone_support: bool = True,
-                 title_pattern: Optional[str] = None):
+                 title_pattern: Optional[str] = None,
+                 sanitize_paths: bool = False):
 
         self.context = InstaloaderContext(sleep, quiet, user_agent, max_connection_attempts,
                                           request_timeout, rate_controller, fatal_status_codes,
@@ -233,6 +249,7 @@ class Instaloader:
                 self.title_pattern = '{date_utc}_UTC_{typename}'
             else:
                 self.title_pattern = '{target}_{date_utc}_UTC_{typename}'
+        self.sanitize_paths = sanitize_paths
         self.download_pictures = download_pictures
         self.download_videos = download_videos
         self.download_video_thumbnails = download_video_thumbnails
@@ -296,7 +313,8 @@ class Instaloader:
             check_resume_bbd=self.check_resume_bbd,
             slide=self.slide,
             fatal_status_codes=self.context.fatal_status_codes,
-            iphone_support=self.context.iphone_support)
+            iphone_support=self.context.iphone_support,
+            sanitize_paths=self.sanitize_paths)
         yield new_loader
         self.context.error_log.extend(new_loader.context.error_log)
         new_loader.context.error_log = []  # avoid double-printing of errors
@@ -317,15 +335,25 @@ class Instaloader:
                      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)
-        file_extension = url[-3:] if urlmatch is None else urlmatch.group(0)[1:-1]
         if filename_suffix is not None:
             filename += '_' + filename_suffix
-        filename += '.' + file_extension
-        if os.path.isfile(filename):
+        urlmatch = re.search('\\.[a-z0-9]*\\?', url)
+        file_extension = url[-3:] if urlmatch is None else urlmatch.group(0)[1:-1]
+        nominal_filename = filename + '.' + file_extension
+        if os.path.isfile(nominal_filename):
+            self.context.log(nominal_filename + ' exists', end=' ', flush=True)
+            return False
+        resp = self.context.get_raw(url)
+        if 'Content-Type' in resp.headers and resp.headers['Content-Type']:
+            header_extension = '.' + resp.headers['Content-Type'].split(';')[0].split('/')[-1]
+            header_extension = header_extension.lower().replace('jpeg', 'jpg')
+            filename += header_extension
+        else:
+            filename = nominal_filename
+        if filename != nominal_filename and os.path.isfile(filename):
             self.context.log(filename + ' exists', end=' ', flush=True)
             return False
-        self.context.get_and_write_raw(url, filename)
+        self.context.write_raw(resp, filename)
         os.utime(filename, (datetime.now().timestamp(), mtime.timestamp()))
         return True
 
@@ -506,9 +534,10 @@ class Instaloader:
             pic_bytes = http_response.content
         ig_filename = url.split('/')[-1].split('?')[0]
         pic_data = TitlePic(owner_profile, target, name_suffix, ig_filename, date_object)
-        dirname = _PostPathFormatter(pic_data).format(self.dirname_pattern, target=target)
-        filename_template = os.path.join(dirname,
-                                         _PostPathFormatter(pic_data).format(self.title_pattern, target=target))
+        dirname = _PostPathFormatter(pic_data, self.sanitize_paths).format(self.dirname_pattern, target=target)
+        filename_template = os.path.join(
+                dirname,
+                _PostPathFormatter(pic_data, self.sanitize_paths).format(self.title_pattern, target=target))
         filename = self.__prepare_filename(filename_template, lambda: url) + ".jpg"
         content_length = http_response.headers.get('Content-Length', None)
         if os.path.isfile(filename) and (not self.context.is_logged_in or
@@ -633,7 +662,7 @@ class Instaloader:
         """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)
+        return _PostPathFormatter(item, self.sanitize_paths).format(self.filename_pattern, target=target)
 
     def download_post(self, post: Post, target: Union[str, Path]) -> bool:
         """
@@ -665,7 +694,7 @@ class Instaloader:
                         return False
             return True
 
-        dirname = _PostPathFormatter(post).format(self.dirname_pattern, target=target)
+        dirname = _PostPathFormatter(post, self.sanitize_paths).format(self.dirname_pattern, target=target)
         filename_template = os.path.join(dirname, self.format_filename(post, target=target))
         filename = self.__prepare_filename(filename_template, lambda: post.url)
 
@@ -846,7 +875,7 @@ class Instaloader:
                 return True
 
         date_local = item.date_local
-        dirname = _PostPathFormatter(item).format(self.dirname_pattern, target=target)
+        dirname = _PostPathFormatter(item, self.sanitize_paths).format(self.dirname_pattern, target=target)
         filename_template = os.path.join(dirname, self.format_filename(item, target=target))
         filename = self.__prepare_filename(filename_template, lambda: item.url)
         downloaded = False
@@ -914,8 +943,9 @@ class Instaloader:
             name = user_highlight.owner_username
             highlight_target = (filename_target
                                 if filename_target
-                                else (Path(_PostPathFormatter.sanitize_path(name)) /
-                                      _PostPathFormatter.sanitize_path(user_highlight.title)))  # type: Union[str, Path]
+                                else (Path(_PostPathFormatter.sanitize_path(name, self.sanitize_paths)) /
+                                      _PostPathFormatter.sanitize_path(user_highlight.title,
+                                                                       self.sanitize_paths)))  # type: Union[str, Path]
             self.context.log("Retrieving highlights \"{}\" from profile {}".format(user_highlight.title, name))
             self.download_highlight_cover(user_highlight, highlight_target)
             totalcount = user_highlight.itemcount
@@ -965,7 +995,7 @@ class Instaloader:
                            else total_count)
         sanitized_target = target
         if isinstance(target, str):
-            sanitized_target = _PostPathFormatter.sanitize_path(target)
+            sanitized_target = _PostPathFormatter.sanitize_path(target, self.sanitize_paths)
         if takewhile is None:
             takewhile = lambda _: True
         with resumable_iteration(
@@ -1209,8 +1239,8 @@ class Instaloader:
         tagged_posts = profile.get_tagged_posts()
         self.posts_download_loop(tagged_posts,
                                  target if target
-                                 else (Path(_PostPathFormatter.sanitize_path(profile.username)) /
-                                       _PostPathFormatter.sanitize_path(':tagged')),
+                                 else (Path(_PostPathFormatter.sanitize_path(profile.username, self.sanitize_paths)) /
+                                       _PostPathFormatter.sanitize_path(':tagged', self.sanitize_paths)),
                                  fast_update, post_filter, takewhile=posts_takewhile)
         if latest_stamps is not None and tagged_posts.first_item is not None:
             latest_stamps.set_last_tagged_timestamp(profile.username, tagged_posts.first_item.date_local)

instaloader/structures.py

@@ -8,6 +8,7 @@ from datetime import datetime
 from itertools import islice
 from pathlib import Path
 from typing import Any, Dict, Iterable, Iterator, List, Optional, Tuple, Union
+from unicodedata import normalize
 
 from . import __version__
 from .exceptions import *
@@ -365,9 +366,9 @@ class Post:
     def caption(self) -> Optional[str]:
         """Caption."""
         if "edge_media_to_caption" in self._node and self._node["edge_media_to_caption"]["edges"]:
-            return self._node["edge_media_to_caption"]["edges"][0]["node"]["text"]
+            return normalize("NFC", self._node["edge_media_to_caption"]["edges"][0]["node"]["text"])
         elif "caption" in self._node:
-            return self._node["caption"]
+            return normalize("NFC", self._node["caption"])
         return None
 
     @property
@@ -389,7 +390,7 @@ class Post:
         # support Unicode and a word/beginning of string delimiter at the beginning to ensure
         # that no email addresses join the list of mentions.
         # http://blog.jstassen.com/2016/03/code-regex-for-instagram-username-and-hashtags/
-        mention_regex = re.compile(r"(?:^|\W|_)(?:@)(\w(?:(?:\w|(?:\.(?!\.))){0,28}(?:\w))?)")
+        mention_regex = re.compile(r"(?:^|\W|_)(?:@)(\w(?:(?:\w|(?:\.(?!\.))){0,28}(?:\w))?)", re.ASCII)
         return re.findall(mention_regex, self.caption.lower())
 
     @property