rc-recent

#!/bin/zsh
## temporary, hopefully
#  2022-09-02 initial version
#  2023-07-15 [XXX skip Trizen for right now (mass update of 'sidef' tasks) XXX]
#  2023-08-17 new hosting for RC, new URL
#  2023-10-26 drop 'www' prefix again
#  nb: trying to catch both Raku and Perl tasks

cd ~/perl6/Rosetta-Code
#curl -s --netrc 'https://rosettacode.org/w/index.php?title=Special:RecentChanges&days=7&from=&limit=100&namespace=0' > recent.html
curl -s -o - 'https://rosettacode.org/wiki/Special:RecentChanges?hidebots=1&limit=100&days=7&enhanced=1&urlversion=2' > recent.html

pcregrep -v --buffer-size=22K footer recent.html  | \
pcregrep 'data-mw-revid.*data-target-page' | \
strip-html - | \
#pcregrep -i 'Thunder|SqrtNegInf|Grondilu|Hkdtam|Raku|Perl\b' | \
pcregrep -i 'Thunder|SqrtNegInf|Trizen|Hkdtam|Tybalt|Rcmlz|Util|Raku|Perl\b' | \
pcregrep -v 'Fth|markup|bizarre|full.list' | \
perl -npe 's/\Q‎\E.*?\Q‎\E//' | \
perl -npe 's/\Q→‎\E{{header.(.*?)}}/$1/' | \
perl -npe 's/talk contribs//' | 
perl -npe "s/'/'/g" 

echo ' '

pcregrep 'mw-enhanced-rc-nested" data-target-page' recent.html | \
pcregrep -i 'Thunder|SqrtNegInf|Trizen|Hkdtam|Raku|Perl\b' | \
cut -c 1-100 - | \
perl -npe 's/^.*?data-target-page="(.*?)".*$/$1/' | \
sort -u