dybr2fedi/dybr2fedi.sh

60 lines
2.6 KiB
Bash
Raw Normal View History

2022-08-14 05:40:14 +00:00
#!/bin/sh
2023-01-08 00:19:10 +00:00
#Пробный образец "моста" Дыбра в gemini
2022-08-14 05:40:14 +00:00
#На данный момент только для аккаунта Лиэс
#Односторонний, без возможности взаимодействия с Дыбром
#Пассивная переодическая проверка на новые статьи с записью id уже отправленных, нужен cron или обернуть в бесконечный цикл
blog_id=1045 # liesliasau Dybr blog id
basedir=$(dirname $0)
2023-01-08 00:19:10 +00:00
baseblogdir=$basedir/blog
mkdir -p $baseblogdir
2023-01-08 00:52:29 +00:00
touch $baseblogdir/index.gmi
2022-08-14 05:40:14 +00:00
#[Dybr section]
get_Lies_pages()
{
curl --compressed --get --url 'https://dybr.ru/v2/entries' \
-H 'accept: application/json' \
2023-01-08 00:52:29 +00:00
-H 'user-agent: Dybr2Fedi,Dybr2Gemini,RSS Bridge' \
2022-08-14 05:40:14 +00:00
--data-urlencode "filters[blog-id]=$blog_id" \
--data-urlencode 'filters[state]=published' \
--data-urlencode 'include=profile,community' \
--data-urlencode 'page[number]=1' \
--data-urlencode 'page[size]=10' \
--data-urlencode 'sort=-published-at'
}
2022-08-14 12:30:41 +00:00
get_Lies_pages > "$basedir"/response.json
2022-08-14 05:40:14 +00:00
2023-01-08 00:19:10 +00:00
for i in $(jj -l -i "$basedir"/response.json 'data.#.id'); do
raw_id=$(echo $i | tr -d '"')
2023-01-08 00:52:29 +00:00
if [ ! -f $baseblogdir/$raw_id.gmi ]; then
orig=$(echo $i | sed -e 's/"//g; s|^|https://dybr.ru/blog/liesliasau/|g')
title=$(jj -i "$basedir"/response.json "data.#[id=$i].attributes.title")
published=$(jq -r ".[] | .[] | select(.id==$i) | .attributes[\"created-at\"]" "$basedir"/response.json)
tags=$(jj -l -i "$basedir"/response.json "data.#[id=$i].attributes.tags" | sed -e 's/"//g' | tr '\n' ',')
content=$(jj -i "$basedir"/response.json "data.#[id=$i].attributes.content")
links_img=$(echo "$content" | pup 'img attr{src}' | sed 's|^|https://dybr.ru|g')
plain_content=$(echo "$content" | w3m -T text/html -cols 65535 -dump -o display_link_number=1 | sed -e 's|\[MORE=.*\]||g ; s|\[/MORE\]||g ; s|\[S:|~~|g ; s|:S\]|~~|g')
# Unpack inline images...
placeholders_img=$(echo "$plain_content" | grep -oP '\[\d{10}\]')
pseudo_index=$(echo "$links_img" | wc -l)
index=1
while [ $index -le $pseudo_index ]; do
placeholder=$(echo "$placeholders_img" | sed $index!d | tr -d '[]')
img=$(echo "$links_img" | sed $index!d)
plain_content=$(echo "$plain_content" | sed "s|\[$placeholder\]|=> $img |g")
index=$(expr $index + 1)
done
echo "# $title\n$plain_content\n\ntags: $tags\n=> $orig orig" > $baseblogdir/$raw_id.gmi
touch -d "$published" $baseblogdir/$raw_id.gmi
2023-01-08 01:05:24 +00:00
echo "=> $raw_id.gmi $title ($published)" | cat - $baseblogdir/index.gmi > $basedir/tmp && mv tmp $baseblogdir/index.gmi
2022-08-14 05:40:14 +00:00
fi
done
2023-01-08 15:05:37 +00:00
$basedir/rss_atom_gen.sh $baseblogdir > $baseblogdir/atom.xml
2023-01-08 00:19:10 +00:00