pacnpal/greptweet
1
0
Fork 0
mirror of https://github.com/thewesker/greptweet.git synced 2025-12-20 12:11:05 -05:00
Code Issues Packages Projects Releases Wiki Activity

Resolve shortened urls

Browse Source
This commit is contained in:
Jamie Kitson
2012-03-14 14:39:10 +00:00
parent dcaca4dff7
commit a1c536a967
1 changed files with 12 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
fetch-tweets.sh
View File

@@ -77,13 +77,24 @@ then
exit exit
fi fi
shortDomains="t.co bit.ly tinyurl.com goo.gl"
xmlstarlet sel -t -m "statuses/status" -n -o "text " -v "id" -o "|" -v "created_at" -o "|" -v "normalize-space(text)" \ xmlstarlet sel -t -m "statuses/status" -n -o "text " -v "id" -o "|" -v "created_at" -o "|" -v "normalize-space(text)" \
-m "entities/urls/url" -i "expanded_url != ''" -n -o "url " -v "url" -o " " -v "expanded_url" $temp | { -m "entities/urls/url" -i "expanded_url != ''" -n -o "url " -v "url" -o " " -v "expanded_url" $temp | {
while read -r first rest while read -r first rest
do do
case $first in case $first in
"text") echo $text; text=$rest ;; "text") echo $text; text=$rest ;;
"url") set -- $(echo $rest); text=$(echo $text | sed s,$1,$2,g) ;; "url")
set -- $(echo $rest)
finUrl=$2
domain=$(echo $finUrl | cut -d'/' -f3)
if [[ "$shortDomains" = *$domain* ]]
then
finUrl=$(curl "$finUrl" -s -L -I -o /dev/null -w '%{url_effective}')
fi
text=$(echo $text | sed s,$1,$finUrl,g)
;;
esac esac
done done
echo $text echo $text