kfm/to-hen
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

hesychius: fix long entries upstream and handle them here

Browse Source
This commit is contained in:
Kierán Meinhardt
2022-10-06 08:16:35 +02:00
parent 543f04b3f0
commit 78037cf36a
2 changed files with 6776 additions and 6990 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
hesychius/download.sh
View File

@@ -5,5 +5,5 @@ root=https://el.wikisource.org
curl -sSL "$root/wiki/%CE%93%CE%BB%CF%8E%CF%83%CF%83%CE%B1%CE%B9" \ curl -sSL "$root/wiki/%CE%93%CE%BB%CF%8E%CF%83%CF%83%CE%B1%CE%B9" \
| htmlq --attribute href 'ol li a[title^="Γλ"]' \ | htmlq --attribute href 'ol li a[title^="Γλ"]' \
| while read -r slug; do | while read -r slug; do
curl -sSL "$root$slug" | htmlq dd | sed 's#</\?dd>##g;s#&lt;#<#g;s#&gt;#>#g' curl -sSL "$root$slug" | htmlq dt,dd | tr -d '\n' | sed 's#\(<dt>\)#\n\1#g;s#<dt>\|</dd>##g;s#</dt><dd>#· #g;s#&lt;#<#g;s#&gt;#>#g'
done done

13736
hesychius/hesychius.txt
View File

File diff suppressed because it is too large Load Diff