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

woo

master
bel 2022-07-04 11:51:58 -06:00
parent 882de95140
commit 04acc7ff4f
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

@ -258,6 +258,7 @@ html_to_markdown() {
| perl -pe 's|<t(.)><p>(.*?)</p></t.>|<t\1>\2</t\1>|g' \ | perl -pe 's|<t(.)><p>(.*?)</p></t.>|<t\1>\2</t\1>|g' \
| perl -pe 's|<thead>\r*<tr>(?:(?!</tr>).)+</tr>\r*<tr>|<thead><tr>|g' \ | perl -pe 's|<thead>\r*<tr>(?:(?!</tr>).)+</tr>\r*<tr>|<thead><tr>|g' \
| tr '\r' '\n' \ | tr '\r' '\n' \
| sed 's/<a[^>]*>\([^<]*\)<\/a>/\1/g' \
| pandoc \ | pandoc \
-f html \ -f html \
-t markdown+pipe_tables-simple_tables-multiline_tables \ -t markdown+pipe_tables-simple_tables-multiline_tables \