You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
bitter/bin/extract_text.sh

17 lines
350 B
Bash

if [ "$#" -lt 1 ]
then
echo "Usage: $0 <files to convert>"
exit 1
fi
QUERY='(.full_text // .retweeted_status.full_text) as $text | [ .id_str,$text ] | @csv'
HEADER='id,text'
for i in "$@"
do
OUTPUT=$i.text.csv
echo $HEADER > $OUTPUT
pv -l -N "$i" $i | jq -r "$QUERY" >> $OUTPUT
# sed -ri s/^"([0-9]+),\\"(.*)\\""$/"\1","\2"/g $OUTPUT
done