instagram-archiver 0.2.1__py3-none-any.whl → 0.3.1__py3-none-any.whl

instagram_archiver/typing.py

@@ -0,0 +1,172 @@
+"""Typing helpers."""
+# ruff: noqa: D101
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Literal, NotRequired, TypedDict
+
+if TYPE_CHECKING:
+    from collections.abc import Sequence
+
+__all__ = ('BrowserName', 'CarouselMedia', 'Comments', 'Edge', 'HasID', 'HighlightsTray',
+           'MediaInfo', 'MediaInfoItem', 'MediaInfoItemImageVersions2Candidate', 'UserInfo',
+           'WebProfileInfo', 'WebProfileInfoData', 'XDTAPIV1FeedUserTimelineGraphQLConnection',
+           'XDTAPIV1FeedUserTimelineGraphQLConnectionContainer', 'XDTMediaDict')
+
+
+class MediaInfoItemVideoVersion(TypedDict):
+    height: int
+    url: str
+    width: int
+
+
+class MediaInfoItemImageVersions2Candidate(TypedDict):
+    height: int
+    """Height of the image."""
+    url: str
+    """URL of the image."""
+    width: int
+    """Width of the image."""
+
+
+class HighlightItem(TypedDict):
+    id: str
+    """Identifier."""
+
+
+class HighlightsTray(TypedDict):
+    tray: Sequence[HighlightItem]
+    """Highlights tray items."""
+
+
+class PageInfo(TypedDict):
+    end_cursor: str
+    """End cursor for pagination."""
+    has_next_page: bool
+    """Whether there are more pages."""
+
+
+class EdgeOwnerToTimelineMedia(TypedDict):
+    edges: Sequence[Edge]
+    page_info: PageInfo
+    """Pagination information."""
+
+
+class UserInfo(TypedDict):
+    """User information."""
+    edge_owner_to_timeline_media: EdgeOwnerToTimelineMedia
+    """Timeline media edge."""
+    id: str
+    """User ID."""
+    profile_pic_url_hd: str
+    """Profile picture URL."""
+
+
+class MediaInfoItemImageVersions2(TypedDict):
+    candidates: Sequence[MediaInfoItemImageVersions2Candidate]
+    """Image versions."""
+
+
+class CarouselMedia(TypedDict):
+    image_versions2: MediaInfoItemImageVersions2
+    """Image versions."""
+    id: str
+    """Identifier."""
+
+
+class HasID(TypedDict):
+    """Dictionary with an ``id`` field."""
+    id: str
+    """Identifier."""
+
+
+class MediaInfoItem(TypedDict):
+    """Media information item."""
+    carousel_media: NotRequired[Sequence[CarouselMedia] | None]
+    """Carousel media items."""
+    image_versions2: MediaInfoItemImageVersions2
+    """Image versions."""
+    id: str
+    """Identifier."""
+    taken_at: int
+    """Timestamp when the media was taken"""
+    user: HasID
+    """User who posted the media."""
+    video_dash_manifest: NotRequired[str | None]
+    """URL of the video dash manifest."""
+    video_duration: float
+    """Duration of the video in seconds."""
+    video_versions: Sequence[MediaInfoItemVideoVersion]
+    """Video versions."""
+
+
+class Comments(TypedDict):
+    """Comments container."""
+    can_view_more_preview_comments: bool
+    """Whether more preview comments can be viewed."""
+    comments: Sequence[HasID]
+    """List of comments."""
+    next_min_id: str
+    """Next minimum ID for pagination."""
+
+
+class MediaInfo(TypedDict):
+    """Media information."""
+    items: Sequence[MediaInfoItem]
+    """List of media items."""
+
+
+class Owner(TypedDict):
+    id: str
+    """Owner ID."""
+    username: str
+    """Owner username."""
+
+
+class XDTMediaDict(TypedDict):
+    __typename: Literal['XDTMediaDict']
+    """Type name."""
+    code: str
+    """Short code."""
+    id: str
+    """Media ID."""
+    owner: Owner
+    """Owner information."""
+    pk: str
+    """Primary key. Also carousel ID."""
+    video_dash_manifest: NotRequired[str | None]
+    """Video dash manifest URL, if available."""
+
+
+class Edge(TypedDict):
+    """Edge of a graph."""
+    node: XDTMediaDict
+    """Node at this edge."""
+
+
+class XDTAPIV1FeedUserTimelineGraphQLConnection(TypedDict):
+    edges: Sequence[Edge]
+    """Edges of the graph."""
+    page_info: PageInfo
+    """Pagination information."""
+
+
+class XDTAPIV1FeedUserTimelineGraphQLConnectionContainer(TypedDict):
+    """Container for :py:class:`XDTAPIV1FeedUserTimelineGraphQLConnection`."""
+    xdt_api__v1__feed__user_timeline_graphql_connection: XDTAPIV1FeedUserTimelineGraphQLConnection
+    """User timeline data."""
+
+
+class WebProfileInfoData(TypedDict):
+    user: UserInfo
+    """User information."""
+
+
+class WebProfileInfo(TypedDict):
+    """Profile information container."""
+    data: WebProfileInfoData
+    """Profile data."""
+
+
+BrowserName = Literal['brave', 'chrome', 'chromium', 'edge', 'firefox', 'opera', 'safari',
+                      'vivaldi']
+"""Possible browser choices to get cookies from."""

instagram_archiver/utils.py

@@ -1,60 +1,112 @@
-from contextlib import contextmanager
-from os import chdir as os_chdir, getcwd
-from os.path import isfile
+"""Utility functions."""
+from __future__ import annotations
+
 from pathlib import Path
-from types import FrameType
-from typing import Generic, Iterator, Literal, TypeVar
+from typing import TYPE_CHECKING, Any, Literal, Protocol, TypeVar, override
 import json
 import logging
-import sys
+import logging.config
 
-from loguru import logger
 import click
 
-__all__ = ('UnknownMimetypeError', 'YoutubeDLLogger', 'chdir', 'get_extension',
-           'json_dumps_formatted', 'setup_logging', 'write_if_new')
+if TYPE_CHECKING:
+    from .typing import Edge
+
+__all__ = ('JSONFormattedString', 'UnknownMimetypeError', 'get_extension', 'json_dumps_formatted',
+           'setup_logging', 'write_if_new')
 
 T = TypeVar('T')
 
 
-class JSONFormattedString(Generic[T]):  # pylint: disable=too-few-public-methods
-    def __init__(self, formatted: str, original: T) -> None:
+def setup_logging(*,
+                  debug: bool = False,
+                  force_color: bool = False,
+                  no_color: bool = False) -> None:  # pragma: no cover
+    """Set up logging configuration."""
+    logging.config.dictConfig({
+        'version': 1,
+        'disable_existing_loggers': True,
+        'root': {
+            'handlers': ('console',),
+            'level': 'DEBUG' if debug else 'INFO',
+        },
+        'formatters': {
+            'default': {
+                '()': 'colorlog.ColoredFormatter',
+                'force_color': force_color,
+                'format':
+                    '%(log_color)s%(levelname)-8s%(reset)s | %(light_green)s%(name)s%(reset)s:'
+                    '%(light_red)s%(funcName)s%(reset)s:%(blue)s%(lineno)d%(reset)s - %(message)s',
+                'no_color': no_color,
+            },
+            'simple': {
+                'format': '%(message)s',
+            },
+        },
+        'handlers': {
+            'console': {
+                'class': 'colorlog.StreamHandler',
+                'formatter': 'default' if debug else 'simple',
+            },
+        },
+        'loggers': {
+            'instagram_archiver': {
+                'handlers': ('console',),
+                'propagate': False,
+            },
+            'urllib3': {
+                'handlers': ('console',),
+                'propagate': False,
+            }
+        },
+    })
+
+
+class JSONFormattedString:
+    """Contains a formatted version of the JSON str and the original value."""
+    def __init__(self, formatted: str, original: Any) -> None:
         self.formatted = formatted
+        """Formatted JSON string."""
         self.original_value = original
+        """Original value."""
 
+    @override
     def __str__(self) -> str:
         return self.formatted
 
 
-def json_dumps_formatted(obj: T) -> JSONFormattedString[T]:
-    """Returns a special object with the formatted version of the JSON str and the original."""
-    return JSONFormattedString(json.dumps(obj, sort_keys=True, indent=2), obj)
+def json_dumps_formatted(obj: Any) -> JSONFormattedString:
+    """
+    Return a special object with the formatted version of the JSON str and the original.
 
-
-@contextmanager
-def chdir(path: str | Path) -> Iterator[None]:
-    """Context-managing ``chdir``. Changes to old path on exit."""
-    old_path = getcwd()
-    os_chdir(path)
-    try:
-        yield
-    finally:
-        chdir(old_path)
+    Parameters
+    ----------
+    obj : Any
+        The object to be formatted.
+    """
+    return JSONFormattedString(json.dumps(obj, sort_keys=True, indent=2), obj)
 
 
 def write_if_new(target: Path | str, content: str | bytes, mode: str = 'w') -> None:
     """Write a file only if it will be a new file."""
-    if not isfile(target):
+    if not Path(target).is_file():
         with click.open_file(str(target), mode) as f:
             f.write(content)
 
 
 class UnknownMimetypeError(Exception):
-    """Raised when an unknown mimetype is encountered in ``get_extension()``."""
+    """Raised when an unknown mimetype is encountered in :py:func:`~get_extension`."""
 
 
 def get_extension(mimetype: str) -> Literal['png', 'jpg']:
-    """Gets the appropriate three-letter extension for a mimetype."""
+    """
+    Get the appropriate three-letter extension for a mimetype.
+
+    Raises
+    ------
+    UnknownMimetypeError
+        If the mimetype is not recognised.
+    """
     if mimetype == 'image/jpeg':
         return 'jpg'
     if mimetype == 'image/png':
@@ -62,55 +114,21 @@ def get_extension(mimetype: str) -> Literal['png', 'jpg']:
     raise UnknownMimetypeError(mimetype)
 
 
-class InterceptHandler(logging.Handler):  # pragma: no cover
-    """Intercept handler taken from Loguru's documentation."""
-    def emit(self, record: logging.LogRecord) -> None:
-        level: str | int
-        # Get corresponding Loguru level if it exists
-        try:
-            level = logger.level(record.levelname).name
-        except ValueError:
-            level = record.levelno
-        # Find caller from where originated the logged message
-        frame: FrameType | None = logging.currentframe()
-        depth = 2
-        while frame and frame.f_code.co_filename == logging.__file__:
-            frame = frame.f_back
-            depth += 1
-        logger.opt(depth=depth, exception=record.exc_info).log(level, record.getMessage())
-
-
-def setup_log_intercept_handler() -> None:  # pragma: no cover
-    """Sets up Loguru to intercept records from the logging module."""
-    logging.basicConfig(handlers=(InterceptHandler(),), level=0)
-
-
-def setup_logging(debug: bool | None = False) -> None:
-    """Shared function to enable logging."""
-    if debug:  # pragma: no cover
-        setup_log_intercept_handler()
-        logger.enable('')
-    else:
-        logger.configure(handlers=(dict(
-            format='<level>{message}</level>',
-            level='INFO',
-            sink=sys.stderr,
-        ),))
-
-
-class YoutubeDLLogger:
-    """Basic logger front-end to loguru for use with ``YoutubeDL``."""
-    def debug(self, message: str) -> None:
-        if message.startswith('[debug] '):
-            logger.debug(message)
-        else:
-            logger.info(message)
-
-    def info(self, message: str) -> None:
-        pass
-
-    def warning(self, message: str) -> None:
-        logger.warning(message)
-
-    def error(self, message: str) -> None:
-        logger.error(message)
+if TYPE_CHECKING:
+
+    class InstagramClientInterface(Protocol):
+        should_save_comments: bool
+
+        def save_comments(self, edge: Edge) -> None:
+            ...
+else:
+    InstagramClientInterface = object
+
+
+class SaveCommentsCheckDisabledMixin(InstagramClientInterface):
+    """Mixin to control saving comments."""
+    @override
+    def save_comments(self, edge: Edge) -> None:
+        if not self.should_save_comments:
+            return
+        super().save_comments(edge)  # type: ignore[safe-super]

instagram_archiver-0.3.1.dist-info/LICENSE.txt

@@ -0,0 +1,18 @@
+The MIT License (MIT)
+
+Copyright (c) 2025 instagram-archiver authors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and
+associated documentation files (the "Software"), to deal in the Software without restriction,
+including without limitation the rights to use, copy, modify, merge, publish, distribute,
+sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or
+substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT
+NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM,
+DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT
+OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

instagram_archiver-0.3.1.dist-info/METADATA

@@ -0,0 +1,119 @@
+Metadata-Version: 2.3
+Name: instagram-archiver
+Version: 0.3.1
+Summary: Save Instagram content you have access to.
+License: MIT
+Keywords: command line,instagram
+Author: Andrew Udvare
+Author-email: audvare@gmail.com
+Requires-Python: >=3.12,<3.14
+Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Typing :: Typed
+Requires-Dist: beautifulsoup4 (>=4.13.4,<5.0.0)
+Requires-Dist: click (>=8.2.0,<9.0.0)
+Requires-Dist: colorlog (>=6.9.0,<7.0.0)
+Requires-Dist: html5lib (>=1.1,<2.0)
+Requires-Dist: requests (>=2.32.3,<3.0.0)
+Requires-Dist: typing-extensions (>=4.13.1,<5.0.0)
+Requires-Dist: yt-dlp-utils (>=0,<1)
+Project-URL: Documentation, https://instagram-archiver.readthedocs.org
+Project-URL: Homepage, https://tatsh.github.io/instagram-archiver/
+Project-URL: Issues, https://github.com/Tatsh/instagram-archiver/issues
+Project-URL: Repository, https://github.com/Tatsh/instagram-archiver
+Description-Content-Type: text/markdown
+
+# instagram-archiver
+
+[![Python versions](https://img.shields.io/pypi/pyversions/instagram-archiver.svg?color=blue&logo=python&logoColor=white)](https://www.python.org/)
+[![PyPI - Version](https://img.shields.io/pypi/v/instagram-archiver)](https://pypi.org/project/instagram-archiver/)
+[![GitHub tag (with filter)](https://img.shields.io/github/v/tag/Tatsh/instagram-archiver)](https://github.com/Tatsh/instagram-archiver/tags)
+[![License](https://img.shields.io/github/license/Tatsh/instagram-archiver)](https://github.com/Tatsh/instagram-archiver/blob/master/LICENSE.txt)
+[![GitHub commits since latest release (by SemVer including pre-releases)](https://img.shields.io/github/commits-since/Tatsh/instagram-archiver/v0.3.1/master)](https://github.com/Tatsh/instagram-archiver/compare/v0.3.1...master)
+[![QA](https://github.com/Tatsh/instagram-archiver/actions/workflows/qa.yml/badge.svg)](https://github.com/Tatsh/instagram-archiver/actions/workflows/qa.yml)
+[![Tests](https://github.com/Tatsh/instagram-archiver/actions/workflows/tests.yml/badge.svg)](https://github.com/Tatsh/instagram-archiver/actions/workflows/tests.yml)
+[![Coverage Status](https://coveralls.io/repos/github/Tatsh/instagram-archiver/badge.svg?branch=master)](https://coveralls.io/github/Tatsh/instagram-archiver?branch=master)
+[![Documentation Status](https://readthedocs.org/projects/instagram-archiver/badge/?version=latest)](https://instagram-archiver.readthedocs.org/?badge=latest)
+[![mypy](https://www.mypy-lang.org/static/mypy_badge.svg)](http://mypy-lang.org/)
+[![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
+[![pydocstyle](https://img.shields.io/badge/pydocstyle-enabled-AD4CD3)](http://www.pydocstyle.org/en/stable/)
+[![pytest](https://img.shields.io/badge/pytest-zz?logo=Pytest&labelColor=black&color=black)](https://docs.pytest.org/en/stable/)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
+[![Downloads](https://static.pepy.tech/badge/instagram-archiver/month)](https://pepy.tech/project/instagram-archiver)
+[![Stargazers](https://img.shields.io/github/stars/Tatsh/instagram-archiver?logo=github&style=flat)](https://github.com/Tatsh/instagram-archiver/stargazers)
+
+[![@Tatsh](https://img.shields.io/badge/dynamic/json?url=https%3A%2F%2Fpublic.api.bsky.app%2Fxrpc%2Fapp.bsky.actor.getProfile%2F%3Factor%3Ddid%3Aplc%3Auq42idtvuccnmtl57nsucz72%26query%3D%24.followersCount%26style%3Dsocial%26logo%3Dbluesky%26label%3DFollow%2520%40Tatsh&query=%24.followersCount&style=social&logo=bluesky&label=Follow%20%40Tatsh)](https://bsky.app/profile/Tatsh.bsky.social)
+[![Mastodon Follow](https://img.shields.io/mastodon/follow/109370961877277568?domain=hostux.social&style=social)](https://hostux.social/@Tatsh)
+
+Save Instagram content you have access to.
+
+## Installation
+
+### Poetry
+
+```shell
+poetry add instagram-archiver
+```
+
+### Pip
+
+```shell
+pip install instagram-archiver
+```
+
+## Usage
+
+```plain
+Usage: instagram-archiver [OPTIONS] USERNAME
+
+  Archive a profile's posts.
+
+Options:
+  -o, --output-dir DIRECTORY      Output directory.
+  -b, --browser [brave|chrome|chromium|edge|opera|vivaldi|firefox|safari]
+                                  Browser to read cookies from.
+  -p, --profile TEXT              Browser profile.
+  -d, --debug                     Enable debug output.
+  --no-log                        Ignore log (re-fetch everything).
+  -C, --include-comments          Also download all comments (extends download
+                                  time significantly).
+  -h, --help                      Show this message and exit.
+```
+
+Typical use:
+
+```shell
+instagram-archiver -o ~/instagram-backups/username username
+```
+
+### `instagram-save-saved`
+
+This tool saves your saved posts (at `www.instagram.com/username/saved/all-posts`).
+
+```plain
+Usage: instagram-save-saved [OPTIONS]
+
+  Archive your saved posts.
+
+Options:
+  -o, --output-dir DIRECTORY      Output directory.
+  -b, --browser [brave|chrome|chromium|edge|opera|vivaldi|firefox|safari]
+                                  Browser to read cookies from.
+  -p, --profile TEXT              Browser profile.
+  -d, --debug                     Enable debug output.
+  -C, --include-comments          Also download all comments (extends download
+                                  time significantly).
+  -u, --unsave                    Unsave posts after successful archive.
+  -h, --help                      Show this message and exit.
+```
+
+## Notes
+
+The default output path is the username under the current working directory.
+
+Videos are saved using yt-dlp and its respective configuration.
+

instagram_archiver-0.3.1.dist-info/RECORD

@@ -0,0 +1,15 @@
+instagram_archiver/__init__.py,sha256=FtYFsiDxC03kcF2BoC_fCDdSIV_Q81cMBQIeYhA9hwk,270
+instagram_archiver/__main__.py,sha256=oQ6s6zvZTBiEOgt-qep3bDY9ayxSanQr7KHzr6ENK0o,115
+instagram_archiver/client.py,sha256=xde2O-ADvyFw5q7bZxbX9R2ae02ToJUElw-IKSbQhss,11091
+instagram_archiver/constants.py,sha256=NJ8QlQZviY3dwwrIONThK_G9VcvAzOQM6Yg-hSyaj9A,1459
+instagram_archiver/main.py,sha256=5blHCN2PSNGdTlIvXPyWr5vbgM6fW1Wn9nbzJUtBS2Y,4173
+instagram_archiver/profile_scraper.py,sha256=BGnJZD3rF2e4aHpqSvG7UBoAiDjTyrpcYKSzsDgHO3M,7988
+instagram_archiver/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+instagram_archiver/saved_scraper.py,sha256=PyrRCQ00x65nyiIUvmMw5-paJ6_aVrl5xmcTrHi5tHo,2769
+instagram_archiver/typing.py,sha256=svEWoYwGXhkbdISw1r6tuOzo_5TwrhQTn3q0VxzBIlY,4359
+instagram_archiver/utils.py,sha256=l6f0W_brZhVPOjlKwoFYYum7ICyHJXpboTU7ANIQSPI,3842
+instagram_archiver-0.3.1.dist-info/LICENSE.txt,sha256=cDLmbhzFwEUz5FL_OnA6Jp9zdz80330J6YyEq-00yNQ,1093
+instagram_archiver-0.3.1.dist-info/METADATA,sha256=qoIzF1FkbuqwVB9npS6JE7xS5o-fVdVSf9k4XqvDISs,5925
+instagram_archiver-0.3.1.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+instagram_archiver-0.3.1.dist-info/entry_points.txt,sha256=kNXd0Sy6896DEBRcx2mVYiaE-OR9-XR56MpWuaNa49g,128
+instagram_archiver-0.3.1.dist-info/RECORD,,

{instagram_archiver-0.2.1.dist-info → instagram_archiver-0.3.1.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.5.2
+Generator: poetry-core 2.1.3
 Root-Is-Purelib: true
 Tag: py3-none-any

instagram_archiver-0.3.1.dist-info/entry_points.txt

@@ -0,0 +1,4 @@
+[console_scripts]
+instagram-archiver=instagram_archiver.main:main
+instagram-save-saved=instagram_archiver.main:save_saved_main
+

instagram_archiver/find_query_hashes.py

@@ -1,31 +0,0 @@
-from typing import Iterator, cast
-import re
-
-from bs4 import BeautifulSoup
-from yt_dlp.cookies import extract_cookies_from_browser
-import requests
-
-from .constants import SHARED_HEADERS
-from .ig_typing import BrowserName
-
-__all__ = ('find_query_hashes',)
-
-
-def find_query_hashes(browser: BrowserName = 'chrome', profile: str = 'Default') -> Iterator[str]:
-    """Gets the current query hashes in Instagram's JavaScript files."""
-    with requests.Session() as session:
-        session.headers.update({
-            **SHARED_HEADERS,
-            **dict(cookie='; '.join(f'{cookie.name}={cookie.value}' \
-                for cookie in extract_cookies_from_browser(browser, profile)
-                    if 'instagram.com' in cookie.domain))
-        })
-        r = session.get('https://instagram.com')
-        r.raise_for_status()
-        soup = BeautifulSoup(r.content, 'html5lib')
-        for script in soup.select('script'):
-            if script.has_attr('type') or not script.has_attr('src'):
-                continue
-            r = session.get(cast(str, script['src']))
-            r.raise_for_status()
-            yield from re.findall(r'[a-z]="([a-f0-9]{32})"', r.content.decode())