This project uses machine learning (AI) to automate the management of your Youtube clips channel by clipping, editing, creating of thumbnails and uploading to your YT channel

• Demo: https://www.youtube.com/channel/UCzwLEvNi0__N9BHbgTqJKeQ

• Python 3
• Youtube uploader
• OpenCV
• ffmpeg
• Youtube API v3
• ~50GB of free storage (depending of the size of the videos and cuts)

1. Download the latest version of youtubeuploader and extract the executable go file in the project's ./ folder
2. Configure Youtube API v3 accordingly Youtube Uploader instructions and save client_secrets.json in the repo root.
3. Install python requirements

$ pip install -r requirements.txt

4. Populate the folder ./backgrounds with images .png to be randomly selected to your thumbnail
5. Leave a default_face.png on ./assets folder just in case the bot is not able to find a smiling face on your video. It will be used as a default face.
6. Update description and metadata on marcelo.py:upload_video to fit your channel info
7. [Optional] Leave a opening.mp4 and ending.mp4 videos (MP4 encoded, 1920x1080) on assets/ dir to automatically insert an intro and ending sessions on your edited video

1. Prepare a spreadsheet with the following fields (example ./list-sample.csv):

• URL: Youtube url
• time_from: Clip start time (leave it blank for the entire video)
• time_to: Clip end time (leave it blank for the entire video)
• podcast: it will extract the edited audio for a podcast (NOT IMPLEMENTED YET - leave it 0)
• title: Video clip title (don't use comma)
• description: Video clip description (don't use comma)
• tags: Video tags splitted by spaces (don't use comma)

1. Save the spreadsheet as a csv and place the lists/list.csv file in the project folder

2. Run marcelo.py

$ python marcelo.py

3. [On first run only] it will open a page asking for authorization on Youtube

It is recommended to run youtubeuploader mannually and upload at least one video, to generate and store the authorisation file before building the container.

$ docker build -t marcelo .
$ docker run [-it] marcelo

Docker will copy all files to docker root, patch pytube bug and execute from there

• Remember to have your lists/list.csv (clips and cuts list) and client_secrets.json (Youtube API v3 access) ready in the repo root

You can run Marcelo without building the entire image after updating lists/list.csv:

$ docker run [-it] -v "$(pwd)/lists:/app/lists" marcelo

PS: running from a container is slower than running on your physical machine. Video editing and machine learning does not perform well inside virtual environments.

This project execute is executed in 4 phases:

1. Download and cut: Download and cut the video if needed
2. Editing: A bot will scan the entire video to find audio silences, to cut and edit the video automatically
3. Thumbnail: A bot will use machine learning through Computer Vision to find smiling faces in the video, to extract samples and build an unique thumbnail for your channel
4. Upload: Prepare the metadata and Upload the video to your Youtube channel
5. Marcelo: is a tribute to Marcelo Rezende, a Brazilian journalist and television presenter who used to say 'Corta pra mim'

This bot is live, producing the clips channel of the Morning Crypto show.

• Clips: https://www.youtube.com/channel/UCzwLEvNi0__N9BHbgTqJKeQ
• Full videos: https://youtube.com/eddieoz
• Live show on Twitch (every day, 8am BRT): https://twitch.tv/eddieoztv

• jumpcutter
• Awesome Thumbnail Youtube Generator

This project can be found on Radicle

• Issue on cypher.py
  • Youtube changed some internal APIs, not fixed on pytube yet. Solution found on: https://stackoverflow.com/a/71922554
    • Line 264:

    r'a\.[a-zA-Z]\s*&&\s*\([a-z]\s*=\s*a\.get\("n"\)\)\s*&&\s*'
    r'\([a-z]\s*=\s*([a-zA-Z0-9$]{2,3})(\[\d+\])?\([a-z]\)'
    

    • Line 288: nfunc=re.escape(function_match.group(1))),

• Automate the podcast creation
• Use ffmpeg GPU
• Select backgrounds based on title and description
• Indexing captions for searching specific spoken phrase on the video
• Automate the creation of the keywords (by using Watson or another NLP)

Did you like it? Buy me a coffee

Or drop me a tip through Lightning Network: ⚡ zbd.gg/eddieoz