massively reduced unnecessary html in fields
This commit is contained in:
parent
bd07776710
commit
fddb390d49
404
script/cards.csv
404
script/cards.csv
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@ -63,7 +63,7 @@ handle_cleaned_html(){
|
|||||||
#echo "$line"
|
#echo "$line"
|
||||||
echo "$line" | grep "<P> <U> " | perl -pe "s|<P> <U> (.*?) </U>(.*?)$|<P> <U> \1 </U> </P>|" >> categoriestmp
|
echo "$line" | grep "<P> <U> " | perl -pe "s|<P> <U> (.*?) </U>(.*?)$|<P> <U> \1 </U> </P>|" >> categoriestmp
|
||||||
done <<< $(echo "$meaning_clean")
|
done <<< $(echo "$meaning_clean")
|
||||||
backside="$( echo "$meaning_clean_func" | tr '\n' ' ')"
|
backside="$( echo "$meaning_clean_func" | grep "<P> <U> " | grep -vF '<DIV class="item"><P class="word"><B>'| tr '\n' ' ')"
|
||||||
#cat categoriestmp
|
#cat categoriestmp
|
||||||
categories="$(cat categoriestmp | tr '\n' ' ' )"
|
categories="$(cat categoriestmp | tr '\n' ' ' )"
|
||||||
printf "%s;\"%s\";\"%s\";\"%s\";\"%s\";\"%s\"\n" "$no_func" "$word_func" "$meaning" "$categories" "$backside" "$pof_func" >> cards.csv
|
printf "%s;\"%s\";\"%s\";\"%s\";\"%s\";\"%s\"\n" "$no_func" "$word_func" "$meaning" "$categories" "$backside" "$pof_func" >> cards.csv
|
||||||
|
Loading…
Reference in New Issue
Block a user