Created
February 17, 2021 21:20
-
-
Save tomislacker/1cd13a420682bbf4933884c9a6752416 to your computer and use it in GitHub Desktop.
Quick hack to download and extract all dictionaries from huzheng.org for `sdcv`
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/bash | |
set -exo pipefail | |
HOST=http://download.huzheng.org/dict.org/ | |
if [ -z "$STARDICT_DATA_DIR" ] | |
then | |
echo >&2 "Error: STARDICT_DATA_DIR not set!" | |
exit 1 | |
fi | |
curl -s ${HOST} \ | |
| grep -Eo 'href="[^\"]+"' \ | |
| sed 's/href="\?//g; s/"\?$//g' \ | |
| egrep '\.bz2$' \ | |
| while read this_file; | |
do | |
echo "- $this_file" | |
dst_tarball=${STARDICT_DATA_DIR}/${this_file} | |
if [ -e "$dst_tarball" ] | |
then | |
echo >&2 "Skipping: ${this_file}" | |
continue | |
fi | |
# Download the file to a temporary location | |
wget \ | |
-O ${dst_tarball} \ | |
${HOST}${this_file} | |
# Extract the file | |
tar \ | |
-xvj \ | |
-f ${dst_tarball} \ | |
-C ${STARDICT_DATA_DIR} | |
done | |
# vim:expandtab:ft=bash:sw=4:ts=4 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment