78 lines
2.1 KiB
Bash
78 lines
2.1 KiB
Bash
|
#!/bin/sh
|
|||
|
|
|
|||
|
|
# original data
|
|||
|
|
QUALITY_URL="http://www.gary68.de/osm/qa/unmapped/mecklenburg-vorpommern.htm"
|
|||
|
|
# where to get the number of inhabitants
|
|||
|
|
WIKIPEDIA_URL="http://de.wikipedia.org/wiki"
|
|||
|
|
PLACE_TYPE="(town|city)"
|
|||
|
|
# some wikipedia pages have different names
|
|||
|
|
# remove ALL non-letters (7-bit) characters from the _first_ column
|
|||
|
|
PLACE_NAME_MAPPING="Feldberg Feldberger_Seenlandschaft
|
|||
|
|
BoizenburgElbe Boizenburg
|
|||
|
|
FrstenbergHavel F%C3%BCrstenberg/Havel
|
|||
|
|
Goldberg Goldberg_(Mecklenburg)
|
|||
|
|
Malchow Malchow_(Mecklenburg)
|
|||
|
|
OstseebadRerik Rerik
|
|||
|
|
RbelMritz R<>bel
|
|||
|
|
Strasburg Strasburg_(Uckermark)
|
|||
|
|
Tessin Tessin_(bei_Rostock)
|
|||
|
|
Wesenberg Wesenberg_(Mecklenburg)
|
|||
|
|
Zarrentin Amt_Zarrentin"
|
|||
|
|
|
|||
|
|
|
|||
|
|
get_place_data() {
|
|||
|
|
echo '<html><body><table border="1">'
|
|||
|
|
wget --quiet --output-document - "$QUALITY_URL" \
|
|||
|
|
| sed -n "1,/Details all information/p" \
|
|||
|
|
| grep -E -A 4 -B 2 "^<td>$PLACE_TYPE</td>$" \
|
|||
|
|
| grep -v "^--$"
|
|||
|
|
echo '</table></body></html>'
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
|
|||
|
|
get_place_size() {
|
|||
|
|
wget --quiet --output-document - "$WIKIPEDIA_URL/$1" \
|
|||
|
|
| grep -A 1 "^<td>Einwohner:</td>$" \
|
|||
|
|
| tail -1 | cut -d ">" -f 2 | cut -d "<" -f 1 \
|
|||
|
|
| sed s/[^0-9]//g
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
|
|||
|
|
normalize_place_name() {
|
|||
|
|
local simple_name="$(echo "$1" | sed s/[^a-zA-Z]//g)"
|
|||
|
|
local new_name="$(echo "$PLACE_NAME_MAPPING" | grep "^$simple_name" | cut -f 2)"
|
|||
|
|
if test -z "$new_name"
|
|||
|
|
then echo "$1"
|
|||
|
|
else echo "$new_name"
|
|||
|
|
fi
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
|
|||
|
|
get_place_inhabitants() {
|
|||
|
|
local previous_line
|
|||
|
|
local place_name
|
|||
|
|
local place_size
|
|||
|
|
local place_nodes
|
|||
|
|
while read line
|
|||
|
|
do if echo "$line" | grep -q -E "<td>$PLACE_TYPE</td>"
|
|||
|
|
then place_name="$(echo "$previous_line" | cut -d ">" -f 2 | cut -d "<" -f 1)"
|
|||
|
|
place_name="$(normalize_place_name "$place_name")"
|
|||
|
|
place_size="$(get_place_size "$place_name")"
|
|||
|
|
else if echo "$line" | grep -q "^</tr>$"
|
|||
|
|
then echo "<td>$place_size</td>"
|
|||
|
|
place_nodes="$(echo "$previous_line" | cut -d ">" -f 2 | cut -d "<" -f 1)"
|
|||
|
|
echo "<td>$(echo "scale=2;$place_size/$place_nodes" | bc)</td>"
|
|||
|
|
fi
|
|||
|
|
fi
|
|||
|
|
echo "$line"
|
|||
|
|
previous_line="$line"
|
|||
|
|
done
|
|||
|
|
}
|
|||
|
|
|
|||
|
|
|
|||
|
|
# we need the default locales - otherwise 'sed' will not filter umlauts
|
|||
|
|
export LANG=
|
|||
|
|
|
|||
|
|
get_place_data | get_place_inhabitants
|
|||
|
|
|