WikiCommons Chinese characters decomposition data downloader (tsv)

get_wikicommons_decomposition.sh

#!/bin/bash
# Download the raw Chinese characters decomposition data
# from WikiCommons as a tsv.
# Usage:
# ./get_wikicommons_decomposition.sh > data.tsv
# awk -F'\t' '{ print $2 }' data.tsv # print the first field
# Depends on:
# - curl
# - jq
# - awk

raw_url="https://api.wikimedia.org/core/v1/commons/page/Commons:Chinese_characters_decomposition" 

curl -s "$raw_url" |
jq -r '.source' |
awk '
  /<pre>/ { flag=1; next }
  /<\/pre>/ { flag=0 }
  flag
'