Newsgathering with own inteligence categorizing [Ongoing]

Knowlegde…

Nowadays it’s hard to keep up on the recent news. Sources aren’t trustworthy, unreliable or just hard to find. I started a piece of software which is querying various newssources and tagging the content to fit into a category. Yeah, there are a lot of projects already out there who’s doing that, but I prefer to have it on my own infrastructure.

The project is still in development, modules getting added step by step.

Right now the downloading of RSS feeds is implemented. Downloaded messages getting tagged after an training phase. The workload can be spanned over different servers, thanks for using Celery as task manager.

Still planned functions:

  • Notification via Mail and Messenger
  • Crosslinking news with different categories

Screenshots:

Header

Statistic

More Statistic

Detailsearch

bottom Link to heading

tool recipes
Django
Django RestFramework
Daphne
Pandas
nltk
scikit
Celery
Quasar (vue)
MariaDB
InfluxDB
Zulip
tl;dr

Statistics per 22.11.2024:

News: 1.398.237 Tagged: 374.152

Sources: 56 Tags: 639