Skip to content
Finding YouTube's top recommendations from any query
CSS Python JavaScript HTML Shell
Branch: master
Clone or download

Latest commit

Guillaume Chaslot
Latest commit 2198471 Mar 27, 2019

Files

Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
data New result files Nov 7, 2016
graph-viz Adding graph visualization in d3js. Jan 9, 2017
results - Enable multiple queries separated by quotes Mar 22, 2017
.gitignore Adding a .gitignore file May 29, 2017
README.md Update README. Jan 17, 2018
follow-youtube-recommendations.py Update and add an option to sort the results by views. Mar 27, 2019
launch.sh New result files Nov 7, 2016
requirements.txt Adding dep requirements May 29, 2017

README.md

Exploring YouTube recommendations

Where does YouTube's recommendation algorithm bring the user if he follows the recommendations? This robot follows the recommendations on YouTube from a given search query to find out where they bring you. After searching on YouTube and following the recommendations, it prints the 50 most recommended videos.

Installation

To install the project's python dependencies, you can use pip:

pip install -r requirements

Used dependencies:

Example of usage:

python2.7 follow-youtube-recommendations.py --query="global warming,vaccines,nasa" --searches=4 --branch=4 --depth=4 --name="science"

  • --query: query that is made on youtube
  • --searches: number of search results from the query to start with
  • --branch: branching factor = number of recommendations that are followed
  • --name: name under which it will be saved
  • --alltime: add this option if you want to start from the most viewed videos for the query (using the option filter by viewcount on youtube)
You can’t perform that action at this time.