local-sandbox
/
dnd-beyond-scrape
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

cush

master
bel 2022-06-26 23:23:36 -06:00
parent df46dcdd9d
commit 28b9a82004
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
scrape.sh
View File

@ -222,6 +222,7 @@ html_to_markdown() {
local f="$(mktemp)" local f="$(mktemp)"
log url=$1 log url=$1
cat > "$f" cat > "$f"
grep '<title>' "$f" | sed 's/.*>\([^<]*\)<.title>.*/\1/g' >&2
cat "$f" \ cat "$f" \
| readability "file://$(realpath $f)" \ | readability "file://$(realpath $f)" \
| pandoc -f html -t markdown --ascii --toc --wrap=none --strip-comments -o - \ | pandoc -f html -t markdown --ascii --toc --wrap=none --strip-comments -o - \