Χρήστης:ArielGlenn/getsearch.sh

#!/bin/bash

usage() {
  echo "Usage: $0 string"
  echo "where string is the search string for which to retrieve titles"
  echo 
  echo "For example:"
  echo "$0 'noentry'";
  exit 1
}

if [ -z "$1"  ]; then
  usage
fi
search=`echo "$1" | sed -e 's/ /_/g;'`
tmp="./search_tmp"
today=`date +"%B-%e-%Y"`
ext="$today"
mkdir -p $tmp
titles="$tmp/titles.$ext"
srcontinue=""

rm -f  $titles.*  

count=1
while [ 1 ]; do

    echo getting search titles $count to $count+500

    # επόμενοι 500

    if [ -z "$sroffset" ];  then
        curl --retry 10 -H 'Expect:' -f "http://el.wiktionary.org/w/api.php?action=query&list=search&srsearch=$search&srprop=title&srlimit=500&format=xml&srwhat=text" | sed -e 's/>/>\n/g;' > $titles.xml.temp
    else
        curl --retry 10 -H 'Expect:' -f "http://el.wiktionary.org/w/api.php?action=query&list=search&srsearch=$search&srprop=title&sroffset=$sroffset&srlimit=500&format=xml&srwhat=text" | sed -e 's/>/>\n/g;' > $titles.xml.temp
    fi
    if [ $? -ne 0 ]; then
        echo "Error $? from curl, unable to get xml pages, bailing"
        exit 1
    fi
    cat $titles.xml.temp >> $titles.xml
    # get continue param
    # format: <search sroffset="500" />
    sroffset=`grep sroffset $titles.xml.temp`
    if [ -z "$sroffset" ]; then
	break;
    else
        sroffset=`echo $sroffset | awk -F'"' '{ print $2 }'`
    fi
    sleep 6
    count=$(( $count+500 ))
done

# format <p ns="0" title="μερικοί" />
cat $titles.xml | grep '<p ns' | awk -F'"' '{ print $4 }'  | sed -e 's/^/[[/g; s/$/]]/g;' > $titles.txt
# done!
echo "done!"
exit 0