From 270178d0278fe2d1ceddf98186feb744fe174489 Mon Sep 17 00:00:00 2001
From: Jeff Moe <moe@spacecruft.org>
Date: Fri, 10 Jun 2022 21:17:08 -0600
Subject: [PATCH] Add script to download Internet Archive torrents

---
 README.md       |  8 ++++++++
 wut-ia-torrents | 24 ++++++++++++++++++++++++
 2 files changed, 32 insertions(+)
 create mode 100755 wut-ia-torrents

diff --git a/README.md b/README.md
index 4da0803..5187cd1 100644
--- a/README.md
+++ b/README.md
@@ -88,6 +88,7 @@ The following scripts are in the repo.
 * `wut-files` --- Tells you about what files you have in `downloads/` and `data/`.
 * `wut-files-data` --- Tells you about what files you have in `data/`.
 * `wut-ia` --- Download SatNOGS data from the Internet Archive at `archive.org`.
+* `wut-ia-torrents` --- Download SatNOGS torrents from the Internet Archive at `archive.org`.
 * `wut-img-ck.py` --- Validate image files are not corrupt with PIL.
 * `wut-ml` --- Main machine learning Python script using Tensorflow and Keras.
 * `wut-ml-auto` --- Machine learning Python script using Tensorflow and Keras, auto.
@@ -249,6 +250,13 @@ Get an account at archive.org, then run this to set up your account locally:
 ia configure
 ```
 
+To download all the SatNOGS collections `.torrent` files from the
+Internet Archive, run:
+
+```
+wut-ia-torrents
+```
+
 
 # Caveats
 This is the first artificial intelligence script I've done,
diff --git a/wut-ia-torrents b/wut-ia-torrents
new file mode 100755
index 0000000..9cf61c2
--- /dev/null
+++ b/wut-ia-torrents
@@ -0,0 +1,24 @@
+#!/usr/bin/env python3
+#
+# wut-ia-torrents --- Download SatNOGS torrents from the Internet Archive.
+#
+# https://archive.org/details/satnogs
+
+from internetarchive import get_item
+from internetarchive import get_session
+from internetarchive import download
+from internetarchive import search_items
+
+# Download dir
+obs_dl='/srv/dl'
+
+s = get_session()
+s.mount_http_adapter()
+search_results = s.search_items('satnogs-observations')
+for i in search_items('identifier:satnogs-observations-*'):
+    obs_id=(i['identifier'])
+    print('Collection', obs_id)
+    download(obs_id, verbose=True, glob_pattern='*.torrent',
+    checksum=True, destdir=obs_dl,
+    retries=4, ignore_errors=True)
+