1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
|
#
# == About ==
#
# Every page has a description and og:description meta tags. These descriptions are
# generated from the text inside paragraphs of the current page.
# The value for those meta tags is "[DESCRIPTION]" and it gets replaced with
# either all of the text on the page, or only the first 200 characters.
function appToDesc(l) {
l = substr(l, parstar, length(l) - parstar + 1 - parend);
gsub("<[^>]*>", "", l); gsub("’", "'", l); gsub(/&[^;]*;/, "", l);
if (desc == "") desc = l;
else desc = desc " " l;
if (length(desc) >= 200) {
desc = substr(desc, 1, 197) "...";
return 1;
}
return 0;
}
BEGIN {
parcont = 0; # continue, we have found a <p> but not a </p>
parstar = 1; # we found a <p>
parends = 0; # we found a </p>
# Loop over the whole file, extract all text in first couple of paragraphs,
# store it in desc (but no more than 200 characters will be saved)
while(getline < ARGV[1]) {
start = index($0, "<h2")
if (start && substr($0, start, 16) != "<h2 id=\"contents")
break;
if (index($0, "<p>"))
parstar = 4;
if (index($0, "</p>"))
parends = 3;
if (parcont || parstar == 4) {
if (appToDesc($0)) break;
parcont = parends == 0;
parstar = 1;
parends = 0;
}
}
close(ARGV[1]); # FILENAME isn't set during BEGIN
}
/\[DESCRIPTION\]/ {
sub(/\[DESCRIPTION\]/, desc);
}
|
