From 9baa8d9a2ebeeddcb6f546df92261a00213db8c1 Mon Sep 17 00:00:00 2001
From: sevi-kun <dev@sevi-kun.me>
Date: Thu, 3 Aug 2023 22:45:20 +0200
Subject: [PATCH] Script + requirements

---
 main.py          | 55 ++++++++++++++++++++++++++++++++++++++++++++++++
 requirements.txt |  7 ++++++
 2 files changed, 62 insertions(+)
 create mode 100644 main.py
 create mode 100644 requirements.txt

diff --git a/main.py b/main.py
new file mode 100644
index 0000000..f129165
--- /dev/null
+++ b/main.py
@@ -0,0 +1,55 @@
+import sys
+import os
+import subprocess
+import re
+import scrapetube
+
+
+# cleanup
+
+for file in os.listdir('./out/'):
+    print('Cleanup ./out/' + file)
+    os.remove('./out/' + file)
+
+
+#scraping
+
+channel1_videos = scrapetube.get_channel("UCuefh-IW_h0HemxTUOA2PEA")
+channel2_videos = scrapetube.get_channel("UC-pBFf-6YwMt3P5Lx6FbJbQ")
+
+video_ids = [video.get('videoId') for video in channel1_videos] # online
+video_ids += [video.get('videoId') for video in channel2_videos] # online
+
+file_ids = [f.replace('_extra.png','') for f in os.listdir('/mnt/omv3/picture/YouTube Pics') if 'extra' in f] # already downloaded
+
+new_vids = ['https://youtu.be/' + str(id) for id in video_ids if id not in file_ids]
+
+
+# dl and processing
+
+os.chdir('./out/')
+
+for url in new_vids:
+    print('Downloading ' + url)
+    subprocess.call(["yt-dlp", "--write-thumbnail", "-f", "best", "--external-downloader", "ffmpeg", "--external-downloader-args", "ffmpeg_i:-ss 1 -t 11", url],
+        stdout=subprocess.DEVNULL,
+        stderr=subprocess.STDOUT)
+
+for dl in os.listdir('.'):
+    print('Processing ' + dl)
+    match = re.search(r"\[([A-Za-z0-9_-]+)\]", dl)
+    #match = re.search(r"\[.*\]", dl)
+    if '.webp' in dl:
+        os.rename(dl, match.group(1) + '_extra.webp')
+    if '.mp4' in dl:
+        subprocess.call(["ffmpeg", "-sseof", "-3", "-i", dl, "-update", "1", "-q:v", "1", dl.replace('.mp4','') + ".jpg"],
+            stdout=subprocess.DEVNULL,
+            stderr=subprocess.STDOUT)
+        os.rename(dl.replace('.mp4','') + ".jpg", match.group(1) + '.jpg')
+
+
+# cleanup
+for file in os.listdir('.'):
+    if '[' in file:
+         print('Cleaning up ' + file)
+         os.remove(file)
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..df75fc6
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,7 @@
+certifi==2023.5.7
+charset-normalizer==3.1.0
+idna==3.4
+requests==2.31.0
+scrapetube==2.4.0
+typing_extensions==4.7.0
+urllib3==2.0.3