instagram-archiver 0.0.5__tar.gz

instagram-archiver-0.0.5/PKG-INFO

@@ -0,0 +1,29 @@
+Metadata-Version: 2.1
+Name: instagram-archiver
+Version: 0.0.5
+Summary: Archive Instagram content.
+Home-page: https://github.com/Tatsh/instgram-archiver
+Author: Andrew Udvare
+Author-email: audvare@gmail.com
+License: MIT
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Provides-Extra: dev
+
+# Instagram Archiver
+
+Tool to download data from an Instagram profile you have access to. It downloads the images, videos, and related metadata (stored as JSON files).
+
+## Installation
+
+```shell
+pip install instagram-archiver
+```
+
+## Usage
+
+```shell
+ia USERNAME
+```
+
+If you like to see output, pass `--debug`.

instagram-archiver-0.0.5/README.md

@@ -0,0 +1,17 @@
+# Instagram Archiver
+
+Tool to download data from an Instagram profile you have access to. It downloads the images, videos, and related metadata (stored as JSON files).
+
+## Installation
+
+```shell
+pip install instagram-archiver
+```
+
+## Usage
+
+```shell
+ia USERNAME
+```
+
+If you like to see output, pass `--debug`.

instagram-archiver-0.0.5/instagram_archiver/__init__.py

@@ -0,0 +1,3 @@
+from .main import main
+
+__all__ = ('main',)

instagram-archiver-0.0.5/instagram_archiver/constants.py

@@ -0,0 +1,33 @@
+from typing import Final, Mapping
+
+__all__ = ('SHARED_HEADERS', 'USER_AGENT')
+
+USER_AGENT: Final[str] = ('Mozilla/5.0 (X11; Linux x86_64) '
+                          'AppleWebKit/537.36 (KHTML, like Gecko) '
+                          'Chrome/112.0.0.0 Safari/537.36')
+SHARED_HEADERS: Final[Mapping[str, str]] = {
+    'accept':
+    ('text/html,application/xhtml+xml,application/xml;q=0.9,image/jxl,'
+     'image/avif,image/webp,image/apng,*/*;q=0.8,'
+     'application/signed-exchange;v=b3;q=0.9'),
+    'accept-language':
+    'en,en-GB;q=0.9,en-US;q=0.8',
+    'authority':
+    'www.instagram.com',
+    'cache-control':
+    'no-cache',
+    'dnt':
+    '1',
+    'pragma':
+    'no-cache',
+    'referer':
+    'https://www.instagram.com',
+    'upgrade-insecure-requests':
+    '1',
+    'user-agent':
+    USER_AGENT,
+    'viewport-width':
+    '2560',
+    'x-ig-app-id':
+    '936619743392459'
+}

instagram-archiver-0.0.5/instagram_archiver/ig_typing.py

@@ -0,0 +1,26 @@
+from typing import Any, Sequence, TypedDict
+
+
+class MediaInfoItemVideoVersion(TypedDict):
+    height: int
+    url: str
+    width: int
+
+
+class MediaInfoItemImageVersions2Candidate(TypedDict):
+    height: int
+    url: str
+    width: int
+
+
+class MediaInfoItemImageVersions2(TypedDict):
+    candidates: Sequence[MediaInfoItemImageVersions2Candidate]
+
+
+class MediaInfoItem(TypedDict):
+    image_versions2: MediaInfoItemImageVersions2
+    taken_at: int
+    user: Any
+    video_dash_manifest: str
+    video_duration: float
+    video_versions: Sequence[MediaInfoItemVideoVersion]

instagram-archiver-0.0.5/instagram_archiver/main.py

@@ -0,0 +1,175 @@
+from os import chdir, makedirs
+from os.path import isfile
+from pathlib import Path
+from typing import Any
+import json
+import re
+import sys
+
+from loguru import logger
+from requests.adapters import HTTPAdapter
+from urllib3.util.retry import Retry
+from yt_dlp.cookies import extract_cookies_from_browser
+import click
+import requests
+import yt_dlp
+
+from .constants import SHARED_HEADERS
+from .utils import (YoutubeDLLogger, get_extension, setup_logging,
+                    write_if_new)
+
+
+def highlights_tray(session: requests.Session, user_id: int | str) -> Any:
+    with session.get(f'https://i.instagram.com/api/v1/highlights/{user_id}/'
+                     'highlights_tray/') as r:
+        r.raise_for_status()
+        return r.json()
+
+
+@click.command()
+@click.option('-o',
+              '--output-dir',
+              default=None,
+              help='Output directory',
+              type=click.Path(exists=True))
+@click.option('-b',
+              '--browser',
+              default='chrome',
+              help='Browser to read cookies from')
+@click.option('-p', '--profile', default='Default', help='Browser profile')
+@click.option('-d', '--debug', is_flag=True, help='Enable debug output')
+@click.argument('username')
+def main(output_dir: Path | str | None,
+         browser: str,
+         profile: str,
+         username: str,
+         debug: bool = False) -> None:
+    setup_logging(debug)
+    if output_dir is None:
+        output_dir = Path('.', username)
+        makedirs(output_dir, exist_ok=True)
+    chdir(output_dir)
+    with requests.Session() as session:
+        session.mount(
+            'https://',
+            HTTPAdapter(max_retries=Retry(backoff_factor=2.5,
+                                          status_forcelist=(
+                                              429,
+                                              500,
+                                              502,
+                                              503,
+                                              504,
+                                          ))))
+        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://www.instagram.com')
+        r.raise_for_status()
+        r = session.get(f'https://www.instagram.com/{username}/')
+        r.raise_for_status()
+        m = re.search(r'"config":{"csrf_token":"([^"]+)"', r.text)
+        assert m is not None
+        session.headers.update({'x-csrftoken': m.group(1)})
+        r = session.get(
+            'https://i.instagram.com/api/v1/users/web_profile_info/',
+            params={'username': username})
+        r.raise_for_status()
+        with open('web_profile_info.json', 'wb') as f:
+            f.write(r.content)
+        user_info = r.json()['data']['user']
+        r = session.get(user_info['profile_pic_url_hd'])
+        r.raise_for_status()
+        with open('profile_pic.jpg', 'wb') as f:
+            f.write(r.content)
+        video_urls = []
+
+        # for item in highlights_tray(session, user_info['id'])['tray']:
+        #     video_urls.append('https://www.instagram.com/stories/highlights/'
+        #                       f'{item["id"].split(":")[-1]}/')
+        # sys.argv = [sys.argv[0]]
+        # ydl_opts = yt_dlp.parse_options()[-1]
+        # with yt_dlp.YoutubeDL({
+        #         **ydl_opts,
+        #         **dict(http_headers=SHARED_HEADERS,
+        #                logger=YoutubeDLLogger(),
+        #                verbose=debug)
+        # }) as ydl:
+        #     for url in video_urls:
+        #         ydl.extract_info(url)
+
+        def save_stuff(edges: Any) -> None:
+            nonlocal video_urls
+            for edge in edges:
+                shortcode = edge['node']['shortcode']
+                if edge['node']['__typename'] == 'GraphVideo':
+                    video_urls.append(
+                        f'https://www.instagram.com/p/{shortcode}')
+                elif edge['node']['__typename'] == 'GraphImage':
+                    r = session.head(edge['node']['display_url'])
+                    r.raise_for_status()
+                    ext = get_extension(r.headers['content-type'])
+                    name = f'{edge["node"]["id"]}.{ext}'
+                    if not isfile(name):
+                        r = session.get(edge['node']['display_url'])
+                        r.raise_for_status()
+                        write_if_new(name, r.content, 'wb')
+                    write_if_new(f'{edge["node"]["id"]}.json',
+                                 json.dumps(edge['node']))
+                elif edge['node']['__typename'] == 'GraphSidecar':
+                    r = session.get('https://i.instagram.com/api/v1/media/'
+                                    f'{edge["node"]["id"]}/info/')
+                    item = r.json()['items'][0]
+                    r.raise_for_status()
+                    write_if_new(f'{edge["node"]["id"]}.json',
+                                 json.dumps(item))
+                    for item in item['carousel_media']:
+                        best = sorted(item['image_versions2']['candidates'],
+                                      key=lambda x: x['width'] * x['height'],
+                                      reverse=True)[0]
+                        r = session.head(best['url'])
+                        r.raise_for_status()
+                        ext = get_extension(r.headers['content-type'])
+                        name = f'{item["id"]}.{ext}'
+                        if not isfile(name):
+                            r = session.get(best['url'])
+                            r.raise_for_status()
+                            write_if_new(name, r.content, 'wb')
+
+        save_stuff(user_info['edge_owner_to_timeline_media']['edges'])
+        page_info = user_info['edge_owner_to_timeline_media']['page_info']
+        while page_info['has_next_page']:
+            params = dict(query_hash='69cba40317214236af40e7efa697781d',
+                          variables=json.dumps(
+                              dict(id=user_info['id'],
+                                   first=12,
+                                   after=page_info['end_cursor'])))
+            r = session.get('https://www.instagram.com/graphql/query/',
+                            params=params)
+            r.raise_for_status()
+            media = r.json()['data']['user']['edge_owner_to_timeline_media']
+            page_info = media['page_info']
+            save_stuff(media['edges'])
+        sys.argv = [sys.argv[0]]
+        ydl_opts = yt_dlp.parse_options()[-1]
+        if len(video_urls) > 0:
+            with yt_dlp.YoutubeDL({
+                    **ydl_opts,
+                    **dict(http_headers=SHARED_HEADERS,
+                           logger=YoutubeDLLogger(),
+                           verbose=debug)
+            }) as ydl:
+                failed_urls = []
+                for url in video_urls:
+                    if (not ydl.in_download_archive(
+                            dict(id=url.split('/')[-1],
+                                 extractor_key='instagram'))
+                            and not ydl.extract_info(url, ie_key='Instagram')):
+                        failed_urls.append(url)
+                if len(failed_urls) > 0:
+                    logger.error('Some video URIs failed. Check failed.txt.')
+                    with open('failed.txt', 'w') as f:
+                        for url in failed_urls:
+                            f.write(f'{url}\n')

instagram-archiver-0.0.5/instagram_archiver/utils.py

@@ -0,0 +1,85 @@
+from os.path import isfile
+from pathlib import Path
+from types import FrameType
+from typing import (Literal, Optional, Union)
+import logging
+import sys
+
+from loguru import logger
+import click
+
+__all__ = ('UnknownMimetypeError', 'get_extension', 'write_if_new')
+
+
+def write_if_new(target: Union[Path, str],
+                 content: Union[str, bytes],
+                 mode: str = 'w') -> None:
+    if not isfile(target):
+        with click.open_file(str(target), mode) as f:
+            f.write(content)
+
+
+class UnknownMimetypeError(Exception):
+    pass
+
+
+def get_extension(mimetype: str) -> Literal['png', 'jpg']:
+    if mimetype == 'image/jpeg':
+        return 'jpg'
+    if mimetype == 'image/png':
+        return 'png'
+    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: Union[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: Optional[FrameType] = 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: Optional[bool] = 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:
+    def debug(self, message: str) -> None:
+        if message.startswith('[debug] '):
+            logger.debug(message)
+        else:
+            logger.info(message)
+
+    def info(self, _: str) -> None:
+        pass
+
+    def warning(self, message: str) -> None:
+        logger.warning(message)
+
+    def error(self, message: str) -> None:
+        logger.error(message)

instagram-archiver-0.0.5/instagram_archiver.egg-info/PKG-INFO

@@ -0,0 +1,29 @@
+Metadata-Version: 2.1
+Name: instagram-archiver
+Version: 0.0.5
+Summary: Archive Instagram content.
+Home-page: https://github.com/Tatsh/instgram-archiver
+Author: Andrew Udvare
+Author-email: audvare@gmail.com
+License: MIT
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+Provides-Extra: dev
+
+# Instagram Archiver
+
+Tool to download data from an Instagram profile you have access to. It downloads the images, videos, and related metadata (stored as JSON files).
+
+## Installation
+
+```shell
+pip install instagram-archiver
+```
+
+## Usage
+
+```shell
+ia USERNAME
+```
+
+If you like to see output, pass `--debug`.

instagram-archiver-0.0.5/instagram_archiver.egg-info/SOURCES.txt

@@ -0,0 +1,13 @@
+README.md
+setup.py
+instagram_archiver/__init__.py
+instagram_archiver/constants.py
+instagram_archiver/ig_typing.py
+instagram_archiver/main.py
+instagram_archiver/utils.py
+instagram_archiver.egg-info/PKG-INFO
+instagram_archiver.egg-info/SOURCES.txt
+instagram_archiver.egg-info/dependency_links.txt
+instagram_archiver.egg-info/entry_points.txt
+instagram_archiver.egg-info/requires.txt
+instagram_archiver.egg-info/top_level.txt

instagram-archiver-0.0.5/instagram_archiver.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

instagram-archiver-0.0.5/instagram_archiver.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+ia = instagram_archiver:main

instagram-archiver-0.0.5/instagram_archiver.egg-info/requires.txt

@@ -0,0 +1,12 @@
+click>=8.0.0
+loguru>=0.5.3
+requests
+yt-dlp>=2022.7.18
+
+[dev]
+mypy
+mypy-extensions
+pylint
+pylint-quotes
+rope
+types-requests>=2.25.9

instagram-archiver-0.0.5/instagram_archiver.egg-info/top_level.txt

@@ -0,0 +1 @@
+instagram_archiver

instagram-archiver-0.0.5/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

instagram-archiver-0.0.5/setup.py

@@ -0,0 +1,24 @@
+from setuptools import find_packages, setup
+
+with open('README.md') as f:
+    setup(author='Andrew Udvare',
+          author_email='audvare@gmail.com',
+          description='Archive Instagram content.',
+          entry_points={'console_scripts': ['ia = instagram_archiver:main']},
+          extras_require={
+              'dev': [
+                  'mypy', 'mypy-extensions', 'pylint', 'pylint-quotes', 'rope',
+                  'types-requests>=2.25.9'
+              ]
+          },
+          install_requires=[
+              'click>=8.0.0', 'loguru>=0.5.3', 'requests', 'yt-dlp>=2022.7.18'
+          ],
+          license='MIT',
+          long_description=f.read(),
+          long_description_content_type='text/markdown',
+          name='instagram-archiver',
+          packages=find_packages(),
+          python_requires='>=3.9',
+          url='https://github.com/Tatsh/instgram-archiver',
+          version='0.0.5')