commit 6ad826f3ee32aa8c7c2834a759cdf516d046e20c
Author: retoor <retoor@molodetz.nl>
Date:   Wed Feb 12 14:40:14 2025 +0100

    Initial commit.

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..08a196e
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,4 @@
+downie*
+__pycache__/
+www*
+.venv
diff --git a/Makefile b/Makefile
new file mode 100644
index 0000000..8d5fa6b
--- /dev/null
+++ b/Makefile
@@ -0,0 +1,18 @@
+PYTHON=.venv/bin/python 
+PIP=.venv/bin/pip 
+DOWNIE=.venv/bin/downie 
+
+
+install:
+	sudo apt install python3 python3-venv python3-pip -y
+	python3 -m venv .venv
+	${PIP} install -e . 
+	@ln -s ${DOWNIE} downie || true
+	@echo "Installed downie. Use by executing ./downie [your url to downie]"
+
+build:
+	${PIP} install build 
+	${PYTHON} -m build .
+
+example:
+	${DOWNIE} https://www.molodetz.nl
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..bc0814f
--- /dev/null
+++ b/README.md
@@ -0,0 +1,65 @@
+# Downie
+
+**Downie** is a full **site downloader**. I tried several downloaders and they all were not capable to download big sites like **molodetz.nl** (containing **300.000+** links / resources). See **features** to see what makes this site downloader **better than most competition**.
+
+If you encounter a site that can't be downloaded using this downloader, contact me @ *retoor@molodetz.nl*. Also, creating a bug ticket is possible after logging in. **I respond to both methods within 24h**.
+
+## Features
+ - Fast as light **async** fetching of your pages allowing concurrency.
+ - Limit fetching only to given domain. **Remote URLs are not followed**. Also redirects to remote URLs (yes, that can be an issue) are not followed.
+ - Discriminates between file and folder for urls by adding `.html` to pages not having an extension. So `/pony` becomes /pony.html so that `/pony/photos.html` is possible.
+ - **Absolute URLs will be converted to relative URLs** so that the site becomes **portable** and **will work isolated** on your webserver.
+ - **Progress is saved.** You do not have to start over completely after exiting the application. It will just continue.
+ - Caching of already visited urls.
+
+## Using Downie
+After following the **installation instructions**, use `downie https://target-site.com` if **globally installed**. If not globally installed, execute `./downie https://target-site.com` from the current directory.
+
+## Installation
+
+### Debian (for development)
+Only **requirement** is `make`. Install by executing `sudo apt install make -y` in the terminal.
+Installation of all required Python dependencies are done by executing `make install`.
+This will **install system packages** using `apt`:
+ - `python`
+ - `python3-venv`
+ - `python3-pip`
+ *There is a big chance you already have them.*
+ After that:
+ 1. A Python environment will be created named `.venv`. *You can ignore this folder.*
+ 2. Required Python libraries will be installed. *(aiohttp, aiofiles, beautifullsoup4, app (molodetz)).*
+ 3. Downie will be installed. *(For the devs: in edit mode with -e!).*
+ 4. A executable file named `downie` will be placed in the current directory. This is the main application.
+**Tip:** make downie globally accessable by copying `downie` to `/usr/local/bin`.
+
+### Other operating systems; Windows / Mac; not for development.
+You have to figure out how to install python3, python3-venv and python3-pip on your OS. Make sure you have these on your system. Chance is big that you already got those.
+Run the following commands:
+```bash
+python3 -m venv .venv 
+source .venv/bin/activate 
+pip install git+https://retoor.molodetz.nl/retoor/downie.git
+cp .venv/bin/downie .
+```
+**Tip:** make downie globally accessable by copying `downie` to `/usr/local/bin`.
+
+## Default configuration / internals
+Not defined by CLI parameters, but configurable as Downie class constructor parameters:
+ - `concurrent_request_count` - Amount of concurrent requests. This defaults to 500. 
+ - `concurrent_write_count` - Amount of concurrent downloads of files. This defaults to 10.
+These values are based on my usage. There is a possibility that there are more optimial parameters.
+
+## Running a downloaded site:
+
+### Open site statically
+Just open a page (.html) from the site using your browser.
+
+### Serve the site
+Simple, run:
+```bash
+python3 -m http.server [port]
+```
+If you don't know what port to use, use `7331`. Your website is accessable on `https://localhost:7331` now.
+
+## Caution
+URLs of downloaded content can be modified to make the site portable. So it is possible that your downloaded site is literally the content online. It is optimized. A literal copy of the site could be unusable.
diff --git a/pyproject.toml b/pyproject.toml
new file mode 100644
index 0000000..95cfb9d
--- /dev/null
+++ b/pyproject.toml
@@ -0,0 +1,34 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "downie"
+version = "1.0.0"
+description = "A fast async download parser with concurrency control. Written for specific use case to crawl a certain site. Will only download urls under the base url. Remote links are not followed."
+readme = "README.md"
+requires-python = ">=3.7"
+dependencies = [
+    "aiohttp",
+    "beautifulsoup4",
+    "aiofiles",
+    "app @ git+https://retoor.molodetz.nl/retoor/app.git"
+]
+authors = [
+    { name = "retoor", email = "retoor@molodetz.nl" }
+]
+
+[project.scripts]
+downie = "downie.__main__:main"
+
+[project.optional-dependencies]
+autocomplete = [
+    "argcomplete>=1.12.3"
+]
+
+[tool.setuptools]
+package-dir = {"" = "src"}
+
+[tool.setuptools.packages.find]
+where = ["src"]
+