Created
January 26, 2015 04:59
Star
You must be signed in to star a gist
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/bin/sh | |
# Pull manifest of overview metadata and output summary info. | |
TMPFILE=`mktemp /tmp/data_kcmo_org.data.XXXX.json` | |
curl http://data.kcmo.org/data.json | python -mjson.tool > $TMPFILE | |
date | |
echo -n 'Total entries: ' | |
grep -c "\"identifier\":" $TMPFILE | |
echo -n 'Number of uploaders: ' | |
grep -c "\"mbox\":" $TMPFILE | |
echo 'License info:' | |
grep "\"license\":" $TMPFILE | awk -F\" '{print $4}' | sort | uniq -c | |
echo 'Number of updates over the last 5 days:' | |
grep "\"modified\":" $TMPFILE | awk -F\" '{print $4}' | sort | uniq -c | tail -5 | |
echo 'Top 5 days with the largest number of updates:' | |
grep "\"modified\":" $TMPFILE | awk -F\" '{print $4}' | sort | uniq -c | sort -rn | head -5 | |
echo 'Top 5 datasets with duplicate titles:' | |
grep "\"title\"" $TMPFILE | awk -F\" '{print $4}' | sort | uniq -c | sort -rn | awk '$1>1' | head -5 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
xref: https://groups.google.com/d/topic/kc-challenge-cabinet-opendata/JlBkLV4CrVo/discussion