chore(example): media download

.gitignore

@@ -1,167 +1,10 @@
 .DS_Store
 .ruff_cache/
+.coverage
 accounts/
 results-raw/
 results-parsed/
 accounts.db*
-
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
+data/
+data_media/
 dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
-target/
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#pdm.lock
-#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
-#   in version control.
-#   https://pdm.fming.dev/#use-with-ide
-.pdm.toml
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
-
-# Environments
-.env
-.venv
-env/
-venv/
-ENV/
-env.bak/
-venv.bak/
-
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
-
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/

examples/download_media.py

@@ -0,0 +1,43 @@
+import asyncio
+import os
+
+import httpx
+
+from twscrape import API
+
+
+async def download_file(client: httpx.AsyncClient, url: str, outdir: str):
+    filename = url.split("/")[-1].split("?")[0]
+    outpath = os.path.join(outdir, filename)
+
+    async with client.stream("GET", url) as resp:
+        with open(outpath, "wb") as f:
+            async for chunk in resp.aiter_bytes():
+                f.write(chunk)
+
+
+async def load_user_media(api: API, user_id: int, outdir: str):
+    os.makedirs(outdir, exist_ok=True)
+    all_photos = []
+    all_videos = []
+
+    async for doc in api.user_media(user_id):
+        all_photos.extend([x.url for x in doc.media.photos])
+        for video in doc.media.videos:
+            variant = sorted(video.variants, key=lambda x: x.bitrate)[-1]
+            all_videos.append(variant.url)
+
+    async with httpx.AsyncClient() as client:
+        await asyncio.gather(
+            *[download_file(client, url, outdir) for url in all_photos],
+            *[download_file(client, url, outdir) for url in all_videos],
+        )
+
+
+async def main():
+    api = API()
+    await load_user_media(api, 2244994945, "data_media")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

twscrape/api.py

@@ -94,7 +94,7 @@ class API:
 
         return rep if is_res else None, new_total, is_cur and not is_lim
 
-    def _get_cursor(self, obj: dict, cursor_type="Bottom"):
+    def _get_cursor(self, obj: dict, cursor_type="Bottom") -> str | None:
         if cur := find_obj(obj, lambda x: x.get("cursorType") == cursor_type):
             return cur.get("value")
         return None