All Projects → crhenr → youtube-video-maker

crhenr / youtube-video-maker

Licence: GPL-3.0 license
📹 A tool for automatic video creation and uploading on YouTube

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to youtube-video-maker

Wikiquiz
Generates a quiz for a Wikipedia page using parts of speech and text chunking.
Stars: ✭ 778 (+480.6%)
Mutual labels:  wikipedia, nltk
speech-to-text-code-pattern
React app using the Watson Speech to Text service to transform voice audio into written text.
Stars: ✭ 37 (-72.39%)
Mutual labels:  watson, ibm-watson
ruby-sdk
♦️ Ruby SDK to use the IBM Watson services.
Stars: ✭ 45 (-66.42%)
Mutual labels:  watson, ibm-watson
py translator
The end goal is a simple application for translating text in the terminal. Text can be generated interactively or programmatically in the shell environment.
Stars: ✭ 45 (-66.42%)
Mutual labels:  google-api
wikitable2csv
A web tool to convert Wiki tables to CSV 📈
Stars: ✭ 112 (-16.42%)
Mutual labels:  wikipedia
TikTok
Download public videos on TikTok using Python with Selenium
Stars: ✭ 37 (-72.39%)
Mutual labels:  robots
aws-content-analysis
This project is a fully automated video search engine which uses AWS AI services for computer vision and speech recognition to catalog video archives.
Stars: ✭ 67 (-50%)
Mutual labels:  video-processing
Chatagram
Winning ChatBot in the IBM ChatBot competition. A ChatBot for a bank
Stars: ✭ 13 (-90.3%)
Mutual labels:  watson
RFDA-PyTorch
Official Code for 'Recursive Fusion and Deformable Spatiotemporal Attention for Video Compression Artifact Reduction' - ACM Multimedia2021 (ACMMM2021) Accepted Paper Task: Video Quality Enhancement / Video Compression Artifact Reduction
Stars: ✭ 44 (-67.16%)
Mutual labels:  video-processing
openroberta-lab
The programming environment »Open Roberta Lab« by Fraunhofer IAIS enables children and adolescents to program robots. A variety of different programming blocks are provided to program motors and sensors of the robot. Open Roberta Lab uses an approach of graphical programming so that beginners can seamlessly start coding. As a cloud-based applica…
Stars: ✭ 98 (-26.87%)
Mutual labels:  robots
IBM Covid19 Watson FR
Contenu d'entrainement d'un Bot Covid19 pour Watson Assistant en français et allemand.
Stars: ✭ 15 (-88.81%)
Mutual labels:  watson
DrawingBotV3
DrawingBotV3 is a software for creating line drawings from Images
Stars: ✭ 161 (+20.15%)
Mutual labels:  video-processing
FunVideo
A series of embeddable theme into video, include animation and voice.
Stars: ✭ 19 (-85.82%)
Mutual labels:  video-processing
infobox-parser
Parse Wikipedia Infoboxes
Stars: ✭ 35 (-73.88%)
Mutual labels:  wikipedia
stack-chan
A JavaScript-driven M5Stack-embedded super-kawaii robot.
Stars: ✭ 242 (+80.6%)
Mutual labels:  robots
fetch
wik is use to get information about anything on the shell using Wikipedia.
Stars: ✭ 335 (+150%)
Mutual labels:  wikipedia
RedBot
Design files and firmware files for the RedBot robotics board.
Stars: ✭ 22 (-83.58%)
Mutual labels:  robots
node-social-feed-api
Aggregates social media feeds and outputs them to use in an API
Stars: ✭ 20 (-85.07%)
Mutual labels:  google-api
character-extraction
Extracts character names from a text file and performs analysis of text sentences containing the names.
Stars: ✭ 40 (-70.15%)
Mutual labels:  nltk
SSffmpegVideoOperation
This is a library of FFmpeg for android... 📸 🎞 🚑
Stars: ✭ 261 (+94.78%)
Mutual labels:  video-processing

YouTube Video Maker

A tool for automatic video creation and uploading on YouTube.

Result:

Getting Started

These instructions will show you how this tool works and how to have the project up and running on your local machine.

Prerequisites

FFmpeg (version used to build this tool: 4.1.1-1)

$ sudo apt-get install ffmpeg   # on Debian based systems
$ sudo yum install ffmpeg       # on Red Hat based systems

Python libraries:

$ sudo pip3 install google_images_download==2.5.0
$ sudo pip3 install wikipedia==1.4.0
$ sudo pip3 install nltk==3.4.5
$ sudo pip3 install watson_developer_cloud==2.8.0
$ sudo pip3 install google-api-python-client==1.7.8
$ sudo pip3 install oauth2client==4.1.3

You will need to use the NLTK Downloader to obtain punkt:

$ python3
>>> import nltk
>>> nltk.download("punkt")
>>> exit()

Download this repository:

$ git clone https://github.com/crhenr/youtube-video-maker.git

Add your API keys

You will need to put your Watson API keys in the searchrobot.py file:

...
iam_apikey = "YOUR_API_KEY_HERE",
url = "YOUR_URL_HERE"
...

And your Google API keys in the clients_secret.json file:

...
"client_id": "YOUR_CLIENT_ID_HERE",
"client_secret": "YOUR_CLIENT_SECRET_HERE",
...

Run the main file

After completing all the settings, just run the main file:

$ cd youtube-video-maker/src
$ python3 yvm.py

How it works?

The program behaves as follows:

    1. Get the Wikipedia search term and the prefix;
    1. Get the first sentences from the Wikipedia summary which corresponds to the search term;
    1. Remove unnecessary information;
    1. Send each sentence to Watson to get the corresponding keywords;
    1. Download some images from Google Images based on the keywords;
    1. Rename and convert the images to JPG;
    1. Make the video, add the sentences as subtitles and add a music;
    1. Send the final video to YouTube with title, description and tags.

NOTE: All the files (images, videos and subtitles) are saved in the user's folder, in a directory with the search term name.

Example: final_video.mp4

Bugs to fix:

  • Get better images;
  • Correct the error that causes the fifth subtitle to be skipped.

Other information

Project inspired by video-maker, by filipedeschamps

Music extracted from: https://www.youtube.com/watch?v=LeV4u5Y-3ac

Original video upload code: https://developers.google.com/youtube/v3/guides/uploading_a_video?hl=en

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].