major: Revamp repo and pip package structure

The structure of the respository was quite legacy. Here it is updated to a
more modern pip package that should be easier to maintain.

Most of the changes are cosmetic, the functionality didn't change. Still, the
API is now slightly different as the GoogleDriveDownloader class has been
replaced by a simple function. Since the logic is stateless, there was no
reason to have this class around.

The only package dependency, i.e. requests, has been added to the toml config
so that it will be finally handled via pip at installation time (see:
#29).

The examples in the README have been updated as the previous links were not
working anymore.

Author: ndrplz

.gitignore

@@ -0,0 +1,4 @@
+.idea/
+data/
+dist/
+venv/

README.md

@@ -2,23 +2,25 @@
 Minimal class to download shared files from Google Drive.
 
 ### How to install:
-Installing is as simple as
+
+This package is on [PyPI](https://pypi.org/project/googledrivedownloader/). Installing is as simple as
 
 ```
 pip install googledrivedownloader
 ```
 
 ### Hello World
-You will need to obtain the sharable link from Google Drive:
 
 ```python
-from google_drive_downloader import GoogleDriveDownloader as gdd
+from googledrivedownloader import download_file_from_google_drive
 
-gdd.download_file_from_google_drive(file_id='1iytA1n2z4go3uVCwE__vIKouTKyIDjEq',
-                                    dest_path='./data/mnist.zip',
-                                    unzip=True)
+# Single image file
+download_file_from_google_drive(file_id='1H1ett7yg-TdtTt6mj2jwmeGZaC8iY1CH',
+                                dest_path='data/crossing.jpg')
+# Zip archive
+download_file_from_google_drive(file_id='13nD8T7_Q9fkQzq9bXF2oasuIZWao8uio',
+                                dest_path='data/docs.zip', unzip=True)
 ```
-This will download a `mnist.zip` file into a `data` folder and unzip it.
 
 
 ### Tips

google_drive_downloader/__init__.py

@@ -0,0 +1,23 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "googledrivedownloader"
+version = "1.0.0"
+dependencies = [
+  "requests",
+]
+authors = [
+  { name = "Davide Abati and Andrea Palazzi"},
+]
+maintainers = [
+  {name = "Andrea Palazzi", email = "[email protected]"}
+]
+description = "Minimal class to download shared files from Google Drive."
+readme = "README.md"
+requires-python = ">=3.8"
+
+[project.urls]
+Homepage = "https://github.com/ndrplz/google-drive-downloader"
+Issues = "https://github.com/ndrplz/google-drive-downloader/issues"

google_drive_downloader/google_drive_downloader.py

@@ -0,0 +1,3 @@
+from .download import download_file_from_google_drive
+
+__all__ = ['download_file_from_google_drive']

pyproject.toml

@@ -0,0 +1,99 @@
+import warnings
+import zipfile
+from os import makedirs
+from os.path import dirname
+from os.path import exists
+from sys import stdout
+
+from requests import Session
+
+CHUNK_SIZE = 32768
+DOWNLOAD_URL = 'https://docs.google.com/uc?export=download'
+
+
+# From https://stackoverflow.com/questions/1094841/reusable-library-to-get-human-readable-version-of-file-size
+def _sizeof_fmt(num, suffix='B'):
+    for unit in ['', 'Ki', 'Mi', 'Gi', 'Ti', 'Pi', 'Ei', 'Zi']:
+        if abs(num) < 1024.0:
+            return '{:.1f} {}{}'.format(num, unit, suffix)
+        num /= 1024.0
+    return '{:.1f} {}{}'.format(num, 'Yi', suffix)
+
+
+def _get_confirm_token(response):
+    for key, value in response.cookies.items():
+        if key.startswith('download_warning'):
+            return value
+    return None
+
+
+def _save_response_content(response, destination, showsize, current_size):
+    with open(destination, 'wb') as f:
+        for chunk in response.iter_content(CHUNK_SIZE):
+            if chunk:  # filter out keep-alive new chunks
+                f.write(chunk)
+                if showsize:
+                    print('\r' + _sizeof_fmt(current_size[0]), end=' ')
+                    stdout.flush()
+                    current_size[0] += CHUNK_SIZE
+
+
+def download_file_from_google_drive(file_id, dest_path, overwrite=False, unzip=False, showsize=False):
+    """
+    Downloads a shared file from Google Drive into a given folder.
+    Optionally unzips it.
+
+    Parameters
+    ----------
+    file_id: str
+        the file identifier.
+        You can obtain it from the sharable link.
+    dest_path: str
+        the destination where to save the downloaded file.
+        Must be a path (for example: './downloaded_file.txt')
+    overwrite: bool
+        optional, if True forces re-download and overwrite.
+    unzip: bool
+        optional, if True unzips a file.
+        If the file is not a zip file, ignores it.
+    showsize: bool
+        optional, if True print the current download size.
+    Returns
+    -------
+    None
+    """
+
+    destination_directory = dirname(dest_path)
+    if destination_directory and not exists(destination_directory):
+        makedirs(destination_directory)
+
+    if not exists(dest_path) or overwrite:
+
+        session = Session()
+
+        print('Downloading {} into {}... '.format(file_id, dest_path), end='')
+        stdout.flush()
+
+        response = session.get(DOWNLOAD_URL, params={'id': file_id}, stream=True)
+
+        token = _get_confirm_token(response)
+        if token:
+            params = {'id': file_id, 'confirm': token}
+            response = session.get(DOWNLOAD_URL, params=params, stream=True)
+
+        if showsize:
+            print()  # Skip to the next line
+
+        current_download_size = [0]
+        _save_response_content(response, dest_path, showsize, current_download_size)
+        print('Done.')
+
+        if unzip:
+            try:
+                print('Unzipping...', end='')
+                stdout.flush()
+                with zipfile.ZipFile(dest_path, 'r') as z:
+                    z.extractall(destination_directory)
+                print('Done.')
+            except zipfile.BadZipfile:
+                warnings.warn('Ignoring `unzip` since "{}" does not look like a valid zip file'.format(file_id))