Generates a wordcloud from the most recent version of the Italian National recovery and resilience plan

pnrr2wordcloud

#!/bin/sh

# pnrr2wordcloud
#
# Generates a wordcloud from the most recent version of the Italian National
# recovery and resilience plan (Piano Nazionale di Ripresa e Resilienza - PNRR)
#
# Author: Roberto Reale <roberto@reale.me>
# Last updated: 2021-02-11

PNRR=http://www.governo.it/sites/new.governo.it/files/PNRR_2021.pdf

STOPWORDS=https://raw.githubusercontent.com/stopwords-iso/stopwords-it/master/stopwords-it.txt

# Download stopwords for Italian
curl -s -o stopwords $STOPWORDS

# 1) Download the PNRR
# 2) PDF -> text
# 3) Generate the wordcloud
curl -so - $PNRR                                    \
    | pdftotext - -                                 \
    | wordcloud_cli --stopwords  stopwords          \
                    --imagefile  pnrr-wordcloud.jpg \
                    --background black              \
                    --width 1080 --height 1350